No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
ABRAHAM: Machine Learning Backed Proactive Handover Algorithm using SDN
Abstract
An important aspect of managing multi access point (AP) IEEE 802.11 networks is the support for mobility management by controlling the handover process. Most handover algorithms, residing on the client station (STA), are reactive and take a long time to converge, and thus severely impact Quality of Service (QoS) and Quality of Experience (QoE). Centralized approaches to mobility and handover management are mostly proprietary, reactive and require changes to the client STA. In this paper, we first created an Software-Defined Networking (SDN) modular handover management framework called HuMOR, which can create, validate and evaluate handover algorithms that preserve QoS. Relying on the capabilities of HuMOR, we introduce ABRAHAM, a machine learning backed, proactive, handover algorithm that uses multiple metrics to predict the future state of the network and optimize the AP load to ensure the preservation of QoS. We compare ABRAHAM to a number of alternative handover algorithms in a comprehensive QoS study, and demonstrate that it outperforms them with an average throughput improvement of up to 139%, while statistical analysis shows that there is significant statistical difference between ABRAHAM and the rest of the algorithms.
... Although the mobility management protocols have been applied in the SDN-based access networks, such as the distributed mobility management [14] and proxy mobile IPv6 [15], to preserve the IP address during mobility, the response delay issue is unavoidable because such protocols are operated in the control plane after the forwarding plane delivers the packet-in messages to the controller [16,17]. To handle the response delay issue, several works on proactive flow rule caching considering the mobility features have been conducted [6,11,12,[18][19][20][21][22][23][24]. These works proactively cache the flow rules to the predicted target forwarding nodes, utilizing mobility prediction models such as the Markov predictor [12,18,19,21] and machine learning [20]. ...
... To handle the response delay issue, several works on proactive flow rule caching considering the mobility features have been conducted [6,11,12,[18][19][20][21][22][23][24]. These works proactively cache the flow rules to the predicted target forwarding nodes, utilizing mobility prediction models such as the Markov predictor [12,18,19,21] and machine learning [20]. Since these models naturally have a prediction error according to variable factors, some of the proactively cached rules can be a waste of resources, being repetitively cached with multiple forwarding nodes, and are not utilized at all. ...
... Compared with these works, which focused on the static scenarios in the core networks, there have been several works which considered mobile scenarios in access networks [6,11,12,[18][19][20][21][22][23][24]. Since there can be numerous mobile flows (i.e., handover events), they may generate multitudinous flow rule requests and necessitate a fast response for flow rule installation. ...
Due to the dynamic mobility feature, the proactive flow rule cache method has become one promising solution in software-defined networking (SDN)-based access networks to reduce the number of flow rule installation procedures between the forwarding nodes and SDN controller. However, since there is a flow rule cache limit for the forwarding node, an efficient flow rule cache strategy is required. To address this challenge, this paper proposes the mobility-aware hybrid flow rule cache scheme. Based on the comparison between the delay requirement of the incoming flow and the response delay of the controller, the proposed scheme decides to install the flow rule either proactively or reactively for the target candidate forwarding nodes. To find the optimal number of proactive flow rules considering the flow rule cache limits, an integer linear programming (ILP) problem is formulated and solved using the heuristic method. Extensive simulation results demonstrate that the proposed scheme outperforms the existing schemes in terms of the flow table utilization ratio, flow rule installation delay, and flow rules hit ratio under various settings.
... Extensive research has been conducted on user association and load balancing in IEEE 802.11 networks. Although there are several distributed approaches, most recent efforts concentrated on centralized network management solutions [3,5,[44][45][46][47][48][49][50][51][52][53][54][55]. The SDN paradigm allows for researchers to introduce new mechanisms without having to modify the IEEE 802.11 standard. ...
... Consequently, the authors presented significant performance enhancements over the default STA-driven approaches. The AP selection problem has been addressed in both proactive [54,55] and reactive [49,53] manners. In [54], enhanced mobility support and throughput enhancements were targeted through a supervised learning model with a wider range of input parameters, including the predicted location of STAs, RSSIs, and load of the APs. ...
... The AP selection problem has been addressed in both proactive [54,55] and reactive [49,53] manners. In [54], enhanced mobility support and throughput enhancements were targeted through a supervised learning model with a wider range of input parameters, including the predicted location of STAs, RSSIs, and load of the APs. Moreover, to ensure the preservation of the QoS, the negative impact of STA re-association, i.e., the handover cost, was considered. ...
With the emergence of 5G networks and the stringent Quality of Service (QoS) requirements of Mission-Critical Applications (MCAs), co-existing networks are expected to deliver higher-speed connections, enhanced reliability, and lower latency. IEEE 802.11 networks, which co-exist with 5G, continue to be the access choice for indoor networks. However, traditional IEEE 802.11 networks lack sufficient reliability and they have non-deterministic latency. To dynamically control resources in IEEE 802.11 networks, in this paper we propose a delay-aware approach for Medium Access Control (MAC) management via airtime-based network slicing and traffic shaping, as well as user association while using Multi-Criteria Decision Analysis (MCDA). To fulfill the QoS requirements, we use Software-Defined Networking (SDN) for airtime-based network slicing and seamless handovers at the Software-Defined Radio Access Network (SD-RAN), while traffic shaping is done at the Stations (STAs). In addition to throughput, channel utilization, and signal strength, our approach monitors the queueing delay at the Access Points (APs) and uses it for centralized network management. We evaluate our approach in a testbed composed of APs controlled by SD-RAN and SDN controllers, with STAs under different workload combinations. Our results show that, in addition to load balancing flows across APs, our approach avoids the ping-pong effect while enhancing the QoS delivery at runtime. Under varying traffic demands, our approach maintains the queueing delay requirements of 5 ms for most of the experiment run, hence drawing closer to MCA requirements.
... The designed scheme minimizes the delay but it has high packet loss during data communication. A Machine Learning Backed Multimetric Proactive Handover Algorithm (ABRAHAM) was introduced in [2] for mobility and handover management. The designed algorithm reduces the packet delay but data delivery was not improved at the required level. ...
... The proposed SVRDO-SIDNL technique and the conventional [1], [2], and [21] are implemented in the NS2 network simulator. IP Network Traffic Flows Labeled with 75 Apps dataset [https://www.kaggle.com/jsrojas/ip-networktraffic-flows-labeled-with-87-apps] is used to handle the simulation. ...
... In this section, the proposed SVRDO-SIDNL technique and existing [1], [2], and [21] are discussed with four metrics. Table 2 shows the average data delivery rate versus a number of data packets in the range of 25 to 250. ...
... Depending on the entity responsible for the association decision, schemes can be centralized or distributed. Centralized solutions, e.g., [2], [10], [14], [23], [27], [33], have gained popularity with the increasing adoption of SDN in WLANs [5]. Moreover, centralization brings ease-of-management and improved security and control [34]. ...
... Such an SDN-based solution is Wi-Balance [18], which jointly manages user association and channel assignment. AP selection can be proactive [27] or reactive [8], [19], [20], [36]. Machine learning techniques are of great help for proactive approaches such as ABRA-HAM [27] where a supervised learning model takes various performance indicators to find an efficient user-AP mapping. ...
... AP selection can be proactive [27] or reactive [8], [19], [20], [36]. Machine learning techniques are of great help for proactive approaches such as ABRA-HAM [27] where a supervised learning model takes various performance indicators to find an efficient user-AP mapping. ...
... This is attributed to the difficulties involved in the selection of handoff parameters as well as the optimal setting of these parameters [6]. Unfortunately, most of the conventional handoff strategies are reactive and hence experience considerable latencies which severely degrade both QoS and Quality of Experience (QoE) [10]. Since the 5G networks serve as the backbone for the Internet of Things (IoT) communications, the energy consumption and signaling overheads must be reduced during the handoff process so as to support resource-constrained devices [11]. ...
... To optimize the access point load and enhance QoS, a proactive machine learningbased multiple metrics prediction scheme is developed in [10]. On the other hand, fuzzy logic-based handover optimization algorithms are introduced in [35,36]. ...
The 3rd Generation Partnership Project (3GPP) has specified the 5G Authentication and Key Agreement (5G AKA) protocol for handover authentication. However, this protocol is susceptible to a myriad of attacks such as man-in-the-middle, denial of service, impersonation, jamming and packet replays. In addition, it fails to offer perfect forward key secrecy. Therefore, other schemes have been developed to address these challenges. However, the attainment of perfect security and privacy at low complexities still remain a mirage. This is due to the numerous security, performance and privacy issues in these schemes. In this paper, a Self Organizing Map (SOM) based target tracking area selection algorithm is developed. Additionally, a scheme based on elliptic curve cryptography is deployed to authenticate the handoff entities. The obtained results indicate that this approach has reduced number of ping-pong and failed handoffs. In terms of security, it is resilient against attacks such as packet replays, spoofing and privileged insiders. It also offers perfect forward key secrecy, strong user anonymity and untraceability at the lowest communication and computation complexities.
... Кроме того, будущее высшей школы немыслимо без специальностей и направлений подготовки студентов в области нанотехнологий [4,5,16] и smart-технологий [10,13,14]. И здесь речь не должна идти об общей их подготовке. ...
... В средах vMN контроллер SDN использует эту информацию для улучшения оптимизированных решений о передаче обслуживания, которые влияют на технологически независимый механизм управления мобильностью потока для гетерогенных сетей [15]. Согласно [16], мобильные SDN (M-SDN) сокращают время паузы трафика, вызванное инициированной хостом передачей обслуживания уровня 2, рассматриваемой в корпоративной сети на основе SDN. ...
... Closely related to user association approaches are the solutions that employ ML to predict and optimize handover processes [152], [153]. The work in [152] builds a stacked residual NN to predict traffic demands in cellular base stations and cells, and incorporates fine-grained handover information. ...
... Different from the rest, LSTM is exploited in [154] for multi-task learning (also covering incremental learning) pursuing handover management, and initial Modulation Coding Scheme (MCS) selection in 5G networks with the ultimate aim of optimizing operational efficiency and autonomy in the RAN management. Similar works, such as ABRAHAM [153], can also be found in Wi-Fi networks. This paper presents a proactive ML-based handover algorithm building on [80] aiming to introduce zero-touch approaches able to optimize network-wide load while preserving QoS. ...
Mobile networks are facing an unprecedented demand for high-speed connectivity originating from novel mobile applications and services and, in general, from the adoption curve of mobile devices. However, coping with the service requirements imposed by current and future applications and services is very difficult since mobile networks are becoming progressively more heterogeneous and more complex. In this context, a promising approach is the adoption of novel network automation solutions and, in particular, of zero-touch management techniques. In this work, we refer to zero-touch management as a fully autonomous network management solution with human oversight. This survey sits at the crossroad between zero-touch management and mobile and wireless network research, effectively bridging a gap in terms of literature review between the two domains. In this paper, we first provide a taxonomy of network management solutions. We then discuss the relevant state-of-the-art on autonomous mobile networks. The concept of zero-touch management and the associated standardization efforts are then introduced. The survey continues with a review of the most important technological enablers for zero-touch management. The network automation solutions from the RAN to the core network, including end-toend aspects such as security, are then surveyed. Finally, we close this article with the current challenges and research directions.
... On the other hand, overlapping coverage areas in Light Fidelity (Li-Fi) and Wireless Fidelity (Wi-Fi) networks has been highlighted in [6] as being detrimental in the design of handovers between these networks. Similarly, the reactive nature of most of the handoff algorithms has been noted to be taking too long to converge and hence reducing QoS and Quality of Experience (QoE) [7]. In light of these challenges, artificial intelligence (AI) based techniques have been adopted in automatic decision making process. ...
... To enhance QoS, a machine learning based algorithm is presented in [7]. This algorithm is proactive and is able to optimize the access point load using a number of metrics for network future state predictions. ...
The deployment of many base stations within a small network coverage area can potentially increase network capacities. However, this implies frequent handoffs as the users move within the small tracking areas. An effective handoff strategy is therefore required to boost quality of service and quality of experience during the handoff process. Unfortunately, most of the conventional handoff strategies are reactive and tend to deploy single or few parameters as inputs to the decision-making process. As such, handoffs are executed without fully considering user satisfaction as well as application, device and service requirements. This results in deterioration of both quality of service and quality of experience after the handoff procedures. In this paper, extreme gradient boosting based algorithm is presented. The results show that it has minimal handoff failure and ping pong rates, while exhibiting very high handoff success rates. In addition, its receiver operating characteristic-area under curve value of 0.97627 exceeds the 0.7 threshold. Consequently, it is capable of predicting the success of the inter-radio access technology handoff with high probability.
... However, handovers produce a reassociation process that may involve a period when the station has no connection. Many works in the literature have proposed solutions to deal with this problem [24][25][26][27][28]. The authors in [24] propose a solution that requires that the APs operate on non-overlapping channels. ...
... As the stations are not aware of the existence of the real AP, they remain connected to the same LVAP as if no change had been performed. LVAPs are also applied in [26][27][28]. ...
In a world with increasing traffic demands, wireless technologies aim to meet them by means of new Radio Access Technologies that provide faster connectivity. Such is the case of 4G and 5G. However, in indoor scenarios, where the capabilities of these technologies are significantly affected by the distance to the base station and the materials used in the construction of buildings, Wi-Fi is still the technology of reference thanks to its low cost and easy deployment. In this context, it is usual to find multi-AP Wi-Fi networks whose deployment has been carefully planned. However, the user-AP association decision procedure is not defined by the IEEE 802.11 standard. As a result, vendors choose selfish approaches based on signal strength. This leads to uneven user distributions and nonoptimal resource utilization. To deal with this, densification has been used over the years, but this is expensive as it needs more infrastructure. Moreover, this results in more APs in the same collision domain. To avoid the need for densification, in this paper we introduce WiMCA, a joint SDN-based user association and channel assignment solution for Wi-Fi networks that considers signal strength, channel occupancy and AP load to make better association decisions. Experimental results have demonstrated that, in terms of aggregated goodput, WiMCA outperforms approaches based on signal strength by 55%, providing better user level fairness and accommodating more users and traffic before reaching the point at which densification is needed.
... Ensar Zeljkovi ́ vd. [15] çalışmalarında MÖ destekli bir HO algoritması (ABRAHAM) geliştirmişlerdir. Bu çalışmada MK ile ağ geçidi arasındaki bağlantı kalitesini tahmin edebilen LSTM ağı modellemişlerdir. ...
... Son katman ise sistemin çıktısı olarak görev görür. Sinir ağlarının performansı gizli katman sayılarının ve her bir katmandaki düğüm sayılarının arttırılıp azaltılması (deneme yanılma) ile iyileştirilir [12,15,[19][20][21]. ...
Bu çalışmada, Uzun Kısa-Vadeli Hafıza (LSTM) tabanlı derin sinir ağı ile beşinci nesil küçük hücre ağlarında el değiştirme (handover, HO) tahminlerini gerçekleştiren yeni bir model geliştirilmiştir. İlk olarak HO tahmininde eğitim için kullanılacak olan veri seti Riverbed Modeler benzetim yazılımında tasarlanan benzetim senaryoları ile oluşturulmuştur. Bu senaryolar aracılığıyla sinir ağının veri kümesinde kullanılacak üç adet giriş (RSSI, SNR ve Jitter) parametresi ve bir adet çıkış parametresi (adaylık değeri) elde edilmiştir. Bu veri seti makine öğrenmesi algoritmalarından LSTM, SVM, Tree ve Lineer Regresyon teknikleri ile eğitilmiştir. LSTM tabanlı derin sinir ağı diğer regresyon algoritmaları ile karşılaştırılmış ve daha yüksek performansa sahip olduğu tespit edilmiştir. LSTM için eğitilen modelin sonuçları incelendiğinde; R2 0.997886801, MAE 0.0036, MSE 0.000043153, MAPE 0.000578808 ve RMSE değeri 0.006569115 olarak bulunmuştur. LSTM tabanlı derin sinir ağlarının, regresyon işlemlerinde yüksek başarım gösterdiği görülmüştür. Sonuç olarak önerilen regresyon modeli ile 5G küçük hücre ağlarında HO kararlarının tahmin edilebildiği gösterilmiştir.
... To this end, the station stores the set of channels each neighbor is operating and the set of neighboring access points on each channel. Zeljković et al. introduce a SDN modular handover management framework, which creates, validates and evaluates handover algorithms that preserve Quality of Service (QoS) [25]. They also propose a proactive handover algorithm based on machine learning, which relies on multiple metrics to predict the future state of the network and to optimize the AP load, while preserving QoS. ...
... Stores the set of channels each neighbor is operating and the set of neighboring APs on each channel [25] Evaluates Handover Algorithms for QoS SDN + Machine Learning [26] Monitor wireless AP MBD platforms, data analysis, and distributed acquisition tools [28] Optimize use of the wireless spectrum Cooperation between access points to perform beamforming [29][30][31][32][33][34] Positioning Analysis Machine Learning [35] 100.000 Traces of cellphones Dataset - [36] People's Movement Dataset - [37] Classify user mobility applications Clusters Similar Profiles and their future trajectory [41] Characterization and spectrum analysis in next-generation wireless networks Survey ...
In this paper we focus on knowledge extraction from large-scale wireless networks through stream processing. We present the primary methods for sampling, data collection, and monitoring of wireless networks and we characterize knowledge extraction as a machine learning problem on big data stream processing. We show the main trends in big data stream processing frameworks. Additionally, we explore the data preprocessing, feature engineering, and the machine learning algorithms applied to the scenario of wireless network analytics. We address challenges and present research projects in wireless network monitoring and stream processing. Finally, future perspectives, such as deep learning and reinforcement learning in stream processing, are anticipated.
... Other works, such as the one discussed in [24], delve into integrating machine learning into the handover decision algorithm known as ABRAHAM. This algorithm incorporates various decision criteria, including load, RSSI, and location. ...
Time-Sensitive Networking (TSN) plays a crucial role in ensuring determinism and low latency, vital for the demands of industrial applications. Integrating the benefits of wire-less networks, including mobility, presents a significant challenge in such environments. In this study, we propose a novel solution to address this challenge by introducing handover capabilities into wireless Time-Sensitive Networking (W-TSN). Through real-world development and testing, we present an optimized approach for minimizing handover delay and leveraging machine learning to select the optimal handover time and space moment in a two-dimensional environment, with low effect on time-sensitive traffic. Our findings demonstrate that our mechanism reduces handover delay below 10 milliseconds and optimizes the handover moment selection, leading to improvements in critical network parameters such as bandwidth and jitter.
... The issues mentioned above may hinder the deployment of the PBFT over cellular networks, but they can be mitigated by embracing some techniques. For example, encryption and cryptography can be incorporated to mitigate security and privacy issues [45], and predictive handover facilitated by machine learning can address the mobility issue [46]. ...
Blockchain has shown significant potential as a key enabler in privacy and security in the forthcoming 6G wireless network, due to its distributed and decentralized characteristics. Practical byzantine fault tolerance (PBFT) emerges as a prominent technology for deployment in wireless networks due to its attributes of low latency, high throughput, and minimal computational requirements. However, the high complexity of communication is the bottleneck of PBFT for achieving high scalability. To tackle this problem, this paper proposes a novel framework of PBFT, where the inter-node communication during the normal case operation is completed through base stations. The uplink and downlink communication between the base station and nodes are modelled based on the signal-to-interference-plus-noise ratio (SINR) threshold. A novel ‘timeout’ mechanism is incorporated to reduce the communication complexity. The performance is evaluated by metrics including consensus success probability, communication complexity, view change delay, view change occurrence probability, consensus delay, consensus throughput and energy consumption. The numerical results show that the proposed scheme achieves higher consensus success probability and throughput, lower communication complexity and consensus delay compared to the conventional PBFT. The results of view change delay and view change occurrence probability and the optimal configuration provide analytical guidance for the deployment of wireless PBFT networks.
... The two surveys [27], [28] identify many challenges intrinsic to the use of ML and AI techniques to improve key performance indicators related to wireless networks. In [29], [30] ML techniques are used for the selection of the best AP, whereas in [31], [32] they are exploited to drive the handover decision between APs. Other works are based on traffic prediction [33], [34]. ...
One of the aspects that mainly characterize wireless networks is their apparent unpredictability. Although several attempts were made in the past years to define for them deterministic medium access techniques, for instance by having data exchanges scheduled by an access point, as a matter of fact they remain a partial solution and are unable to ensure the same behavior as wired infrastructures, since interference may also come from devices outside the network, which obey different rules. A possible way to cope with disturbance on air, both internal and external to the network, is to obtain some knowledge about it by analyzing what happened in the recent past. This information, usually expressed in terms of suitable metrics, is then employed to optimize network operation, for example by prioritizing time-sensitive traffic when needed. In the simplest approaches such metrics coincide with statistical indices evaluated on transmission outcomes, like the failure rate. In this paper we analyze a more sophisticated solution that relies on machine learning, and in particular on artificial neural networks, to predict the behavior of a Wi-Fi link in terms of its frame delivery ratio. Results confirm that more accurate predictions than simpler methods (e.g., moving average) are possible, even when training is partially independent from the specific conditions experienced on the different channels.
... In [65], a framework called HuMOR has been proposed, which is a software-defined network (SDN) modular transport management framework, to create and evaluate and verify QoS-preserving transmission algorithms. In addition, they have introduced ABRAHAM based on the capabilities of HuMOR, which is a machine learning-supported proactive and proactive forwarding algorithm that uses many metrics to predict future network conditions and improve AP load to ensure QoS is maintained. ...
These days, Internet coverage and technologies are growing rapidly, hence, it makes the network more complex and heterogeneous. Software defined network (SDN) revolutionized the network architecture and simplified the network by separating the control and data plane. On the other hand, machine learning (ML) and its derivations have made the systems more intelligent. Many pieces of research papers have addressed ML and SDN. In this survey, we collected the papers published in Springer, Elsevier, IEEE, and ACM and addressed SDN and ML between 2016-2023. The research papers are organized based on the solutions, evaluation parameters, and evaluation environments to help those working on SDN and ML for improving the target functional or non-functional parameters. The research papers will be analyzed to extract the solutions, evaluation parameters and environments. The extracted solutions, evaluation parameters and environments will be clustered in this review paper. The research gap and future research directions will be stated in this work. This survey is completely useful for those who working on SDN and want to improve the functional and non-functional parameters using machine learning.
... В средах vMN контроллер SDN использует эту информацию для улучшения оптимизированных решений о передаче обслуживания, которые влияют на технологически независимый механизм управления мобильностью потока для гетерогенных сетей [15]. Согласно [16], мобильные SDN (M-SDN) сокращают время паузы трафика, вызванное инициированной хостом передачей обслуживания уровня 2, рассматриваемой в корпоративной сети на основе SDN. ...
Мобильность пользовательского оборудования (UE) в сотовой сети является сложной задачей с точки зрения контроля и управления. Текущая традиционная передача обслуживания в сети Long-Term Evolution (LTE) управляется усовершенствованным узлом B или eNodeB (eNB), который представляет собой децентрализованное решение. В отличие от существующей технологии, программно-определяемая сеть (SDN) имеет возможность обслуживать пакеты коммутационного оборудования без участия контроллера SDN, за исключением первого. В соответствии с нашим решением «бесшовный» переход активного мобильного устройства из зоны действия одной базовой станции в зону действия другой без разрыва соединения - так называемый «хэндовер» (handover) управляется контроллером SDN, который отслеживает общее управление сетью и диктует записи потоков для коммутаторов OpenFlow в сети. Из результатов исследования будет видно, что наш подход отслеживает всю сеть на централизованном контроллере с улучшенной производительностью.
User equipment (UE) mobility in a cellular network is a complex task in terms of control and management. The current legacy Long-Term Evolution (LTE) network handoff is managed by an evolved Node B or eNodeB (eNB), which is a decentralized solution. Unlike existing technology, software-defined network (SDN) has the ability to serve packets of switching equipment without the participation of the SDN controller, except for the first one. In accordance with our solution, a "seamless" transition of an active mobile device from the coverage of one base station to the coverage of another without breaking the connection - the so-called "handover" (handover) is controlled by the SDN controller, which monitors the overall management of the network and dictates flow records for OpenFlow switches online. From the results of the study, it will be seen that our approach monitors the entire network on a centralized controller with improved performance.
... Even though virtual AP management has recently been introduced for mobility support in enterprise WLANs, virtual AP management aims to remove authentication and reassociation (i. e., not to improve the channel scanning procedure) during handover through virtual AP migration between APs [12][13][14]. ...
... Different network problems like channel access [34], link configurations [35], frame aggregation [36], traffic and channel predictions [37], adaptive beamforming [38] etc. have been addressed through AI & ML algorithms. From the network management perspective, user mobility prediction, handovers management [39], user associations [40] and network deployment problems have also been tackled efficiently through AI & ML. However, research efforts to employ AI & ML to understand complex relationships and dependencies between OSI layer parameters, crosslayer optimization and developing distributed intelligence in network edge devices to improve network scalability and IoT user's/application's QoS/QoE is somewhat unexplored. ...
Wireless IoT networks have seen an unprecedented rise in number of devices, heterogeneity and emerging use cases which led to diverse throughput, reliability and latency (Quality of Service) requirements. Fulfilling these diverse requirements in a rapidly changing and dynamic wireless environment is a complex and challenging task. On top of including new technologies and wireless standards, one solution is to deploy cross-layer Design (CLD) and multiple Radio Access Technologies (Multi-RAT) to develop scalable QoS-aware IoT networks. However, the complexity of such solutions is high as it involves complex inter-layer interactions and dependencies and inter-application dependencies in multi-RAT networks. Moreover, the wireless environment is very dynamic, so having an optimal constellation of parameters is a challenging task. In this paper, we address the possibilities of using Artificial Intelligence (AI) and Machine Learning (ML) to address these high dimensional and dynamic problems. Based on our findings, we have proposed a distributed network management framework employing AI & ML for studying inter-layer dependencies and developing cross-layer design, traffic classification and traffic prediction at the edge devices for reliable QoS in multi-RAT IoT networks. A thorough discussion on future directions and emerging challenges related to our proposed framework has also been provided for further research in this field.
... ABRAHAM (mAchine learning Backed multi-metRic Handover AlgorithM) [194] is an ML-based proactive handover algorithm that uses multiple metrics to predict the future location of stations and the future AP load. Additionally, using long short-term memory (LSTM), it predicts the future RSSI values. ...
Wireless local area networks (WLANs) empowered by IEEE 802.11 (Wi-Fi) hold a dominant position in providing Internet access thanks to their freedom of deployment and configuration as well as the existence of affordable and highly interoperable devices. The Wi-Fi community is currently deploying Wi-Fi 6 and developing Wi-Fi 7, which will bring higher
data rates, better multi-user and multi-AP support, and, most importantly, improved configuration flexibility. These technical innovations, including the plethora of configuration parameters, are making next-generation WLANs exceedingly complex as the dependencies between parameters and their joint optimization usually have a non-linear impact on network performance. The complexity is further increased in the case of dense deployments and coexistence in shared bands. While classical optimization approaches fail in such conditions, machine learning (ML) is
able to handle complexity. Much research has been published on using ML to improve Wi-Fi performance and solutions are slowly being adopted in existing deployments. In this survey, we adopt a structured approach to describe the various Wi-Fi areas where ML is applied. To this end, we analyze over 250 papers in the field, providing readers with an overview of the main trends. Based on this review, we identify specific open challenges and provide general future research directions.
... The handover management framework given in [17] is known as a HuMOR, which can create, validate, and evaluate handover algorithms that preserve QoS. The authors proposed ABRAHAM, a mAchine learning Backed multi-metRic proActive Handover AlgorithM. ...
The mobility of user equipment (UE) in cellular network is a challenging issue in terms of its management. Current traditional handover in Long-Term Evolution (LTE) network is managed by evolved Node B or eNodeB (eNB) which is a decentralized solution. In contrast to existing technology, software defined network (SDN) has the capability of serving the packets of the switching equipment without involving the SDN controller except for the first one. We have proposed an SDN-based centralized solution for handover management in LTE network. Based on our solution, the handover is being managed by SDN controller which keeps track of the overall network management and dictates the flow entries to the OpenFlow switches in the network. In our testbed, two UEs are connected to two eNBs, and one of the UE performs a handover from one eNB to other eNB. It enhances the performance of the network in terms of reducing the delay while performing the handover and increasing the data rate of the running application. The initial delay will be bit higher due to the initial flow entry absence in the flow tables of the switches; later, the delay will be reduced. It is evident from the results that our approach keeps track of the overall network at centralized controller with improved performance.
... Most of the current 5G handover schemes are reactive and hence incurs long latencies which reduce QoS and Quality of Experience (QoE) [12]. The handover completion time ranges from several hundred milliseconds [13] to 4 s [14]. ...
The fifth generation (5G) networks are characterized with ultra-dense deployment of base stations with limited footprint. Consequently, user equipment’s handover frequently as they move within 5G networks. In addition, 5G requirements of ultra-low latencies imply that handovers should be executed swiftly to minimize service disruptions. To preserve security and privacy while at the same time maintaining optimal performance during handovers, numerous schemes have been developed. However, majority of these techniques are either limited to security and privacy or address only performance aspect of the handover mechanism. As such, there is need for a novel handover authentication protocol that addresses security, privacy and performance simultaneously. This paper presents a machine learning protocol that not only facilitates optimal selection of target cell but also upholds both security and privacy during handovers. Formal security analysis using the widely adopted Burrows–Abadi–Needham (BAN) logic shows that the proposed protocol achieves all the six formulated under this proof. As such, the proposed protocol facilitates strong and secure mutual authentication among the communicating entities before generating the shares session key. The derived session key protected the exchanged packets to avert attacks such as forgery. In addition, informal security evaluation of the proposed protocol shows that it offers perfect forward key secrecy, mutual authentication any user anonymity. It is also demonstrated to be robust against attacks such as denial of service (DoS), man-in-the-middle (MitM), masquerade, packet replays and forgery. In terms of performance, simulation results shows that it has lower packets drop rate and ping–pong rate, with higher ratio of packets received compared with improved 5G authentication and key agreement (5G AKA’) protocol. Specifically, using 5G AKA’ as the basis, the proposed protocol reduces the handover rate by 94.4%, hence the resulting handover signaling is greatly minimized.
... ABRAHAM (mAchine learning Backed multi-metRic Handover AlgorithM) [194] is an ML-based proactive handover algorithm that uses multiple metrics to predict the future location of stations and the future AP load. Additionally, using long short-term memory (LSTM), it predicts the future RSSI values. ...
Wireless local area networks (WLANs) empowered by IEEE 802.11 (Wi-Fi) hold a dominant position in providing Internet access thanks to their freedom of deployment and configuration as well as the existence of affordable and highly interoperable devices. The Wi-Fi community is currently deploying Wi-Fi~6 and developing Wi-Fi~7, which will bring higher data rates, better multi-user and multi-AP support, and, most importantly, improved configuration flexibility. These technical innovations, including the plethora of configuration parameters, are making next-generation WLANs exceedingly complex as the dependencies between parameters and their joint optimization usually have a non-linear impact on network performance. The complexity is further increased in the case of dense deployments and coexistence in shared bands. While classical optimization approaches fail in such conditions, machine learning (ML) is well known for being able to handle complexity. Much research has been published on using ML to improve Wi-Fi performance and solutions are slowly being adopted in existing deployments. In this survey, we adopt a structured approach to describing the various areas where Wi-Fi can be enhanced using ML. To this end, we analyze over 200 papers in the field, providing readers with an overview of the main trends. Based on this review, we identify both open challenges in each Wi-Fi performance area as well as general future research directions.
... However, all these algorithms are MG dependent, and there is no novelty where an unwanted MG can be avoided through prior prediction of mmWaves' signal strength by exploiting out-of-band information that is already available. With the advancement of computing power, ML-driven algorithms are mostly proposed to overcome limitations in classical techniques [31][32][33][34][35][36][37][38][39] in such scenarios. However, the ML-based technique is only effective if it is efficiently exploited. ...
The future high-speed cellular networks require efficient and high-speed handover mechanisms. However, the traditional cellular handovers are based upon measurements of target cell radio strength which requires frequent measurement gaps. During these measurement windows, data transmission ceases each time, while target bearings are measured causing serious performance degradation. Therefore, prediction-based handover techniques are preferred in order to eliminate frequent measurement windows. Thus, this work proposes an ultrafast and efficient XGBoost-based predictive handover technique for next generation mobile communications. The ML algorithm in general prefers 70–30% of training and test data, respectively. However, always obtaining 70% of training samples in mobile communications is challenging because the channel remains correlated within coherence time only. Therefore, collecting training samples beyond coherence time limits performance and adds delay; thus, the proposed work trains the model within coherence time where this fixed data split of 70–30% makes the model exceed coherence time. Despite the fact that the proposed model gets starved of required training samples, still there is no loss in predication accuracy. The test results show a maximum delay improvement of up to 596 ms with enhanced performance efficiency of 68.70% depending upon the scenario. The proposed model reduces delay and improves efficiency by having an appropriate training period; thus, the intelligent technique activates faster with improved accuracy and eliminates delay in the algorithm to predict mmWaves’ signal strength in contrast to actually measuring them.
... Bi et al. [20] proposed a fog computing architecture, which improves the handoff performance and data communication efficiency in mobile fog computing. Zeljković et al. [21] proposed a modular handover management framework based on SDN, which reduce the delay in the handover process and the signaling overhead of handover. Yin et al. [22] proposed a new fast switching scheme for SDNbased vehicle network to improve the switching performance. ...
With the access devices that are densely deployed in multi-access edge computing environments, users frequently switch access devices when moving, which causes the imbalance of network load and the decline of service quality. To solve the problems above, a seamless handover scheme for wireless access points based on perception is proposed. First, a seamless handover model based on load perception is proposed to solve the unbalanced network load, in which a seamless handover algorithm for wireless access points is used to calculate the access point with the highest weight, and a software-defined network controller controls the switching process. A joint allocation method of communication and computing resources based on deep reinforcement learning is proposed to minimize the terminal energy consumption and the system delay. A resource allocation model is based on minimizing terminal energy consumption, and system delay is built. The optimal value of task offloading decision and resource allocation vector are calculated with deep reinforcement learning. Experimental results show that the proposed method can reduce the network load and the task execution cost.
... Similarly, in [131], a Bayesian regression based policy was introduced for low-frequency high-speed railway systems. Meanwhile, in [92], a machine learning (ML) based proactive, handover algorithm that employed multiple metrics to predict the future state of the network and optimize the load in order to ensure preservation of the quality of service (QoS) and experience (QoE) was proposed, whereas, in [260], linear regression, long-short term memory, and recursive neural networks methodologies were examined as possible approaches for network load prediction and a proactive hand-over policy was presented. Finally, in [301], the authors presented a deep reinforcement learning (DRL)-based hand-over management algorithm to address the large-scale load balancing problem for ultra-dense networks. ...
This white paper on AI and ML as enablers of beyond 5G (B5G) networks is based on contributions from 5G PPP projects that research, implement and validate 5G and B5G network systems.
The white paper introduces the main relevant mechanisms in Artificial Intelligence (AI) and Machine Learning (ML), currently investigated and exploited for 5G and B5G networks. A family of neural networks is presented which are, generally speaking, non-linear statistical data modeling and decision-making tools. They are typically used to model complex relationships between input and output parameters of a system or to find patterns in data. Feed-forward neural networks, deep neural networks, recurrent neural networks, and convolutional neural networks belong to this family. Reinforcement learning is concerned with how intelligent agents must take actions in order to maximize a collective reward, e.g., to improve a property of the system. Deep reinforcement learning combines deep neural networks and has the benefit that is can operate on non-structured data. Hybrid solutions are presented such as combined analytical and machine learning modeling as well as expert knowledge aided machine learning. Finally, other specific methods are presented, such as generative adversarial networks and unsupervised learning and clustering.
... There are few studies on handover management for SDNbased 5G small cells in the literature. Machine learning techniques [13][14][15], centralized and distributed approaches [16][17][18][19], SDN enabled handover [20,21] have been proposed for handover management. Therefore, the multicriteria entropy-based SAW ranking algorithm running on the controller is used for handover management in SDNbased 5G small cell architecture for the first time in the literature. ...
The high data traffic requirements of the new generation 5G networks will be satisfied with effective and efficient mobility and handover management. However, dense or ultra-dense small cell (eNB) placements in 5G networks may lead to some problems, such as latency, handover failures, frequent handover, ping-pong effect, etc. In this study, we propose an Entropy-based simple additive weighting decision-making method for multi-criteria handover in software-defined networking (SDN) based 5G small cells for the solution of the aforementioned problems. This method provides the connection of the mobile node to the most suitable eNB using bandwidth, user density and SINR parameters. The proposed handover method is compared with conventional LTE handover and distributed approach in terms of delay, block ratio, handover failure and throughput according to the varying number of mobile users. The scalability of handovers for both approaches according to the user number are also analysed. According to the simulation results, the proposed approach achieved 15%, 48% and 22% improvement in handover delay, blocking probability and throughput, respectively, compared to the conventional LTE handover.
... In [93], the HO management framework that allows the use of HO algorithms that can use multiple metrics in decisionmaking processes, centralized, proactive in order to have appropriate mobility management in IEEE 802.11 Wi-Fi networks is presented. ...
With the rapid increase in the number of mobile users, wireless access technologies are evolving to provide mobile users with high data rates and support new applications that include both human and machine-type communications. Heterogeneous networks (HetNets), created by the joint installation of macro cells and a large number of densely deployed small cells, are considered an important solution to deal with the increasing network capacity demands and provide high coverage to wireless users in future fifth generation (5G) wireless networks. Due to the increasing complexity of network topology in 5G HetNets with the integration of many different base station types, in 5G architecture mobility management has many challenges. Intense deployment of small cells, along with many advantages it provides, brings important mobility management problems such as frequent handover (HO), HO failure, HO delays, ping-pong HO and high energy consumption which will result in lower user experience and heavy signal loads. In this paper, we provide a comprehensive study on the mobility management in 5G HetNet in terms of radio resource control, the initial access and registration procedure of the user equipment (UE) to the network, the paging procedure that provides the location of the UE within the network, connected mode mobility management schemes, beam level mobility and beam management. Besides, this paper addresses the challenges and suggest possible solutions for the 5G mobility management. INDEX TERMS Mobility management, handover, heterogeneous networks, 5G network.
... To this end, the station stores the set of channels each neighbor is operating and the set of neighboring access points on each channel. Zeljković et al. introduce an SDN modular handover management framework, which creates, validates and evaluates handover algorithms that preserve Quality of Service (QoS) [25]. They also propose a proactive handover algorithm based on machine learning, which relies on multiple metrics to predict the future state of the network and to optimize the AP load, while preserving QoS. ...
In this paper we focus on knowledge extraction from large-scale wireless networks through stream processing. We present the primary methods for sampling, data collection, and monitoring of wireless networks and we characterize knowledge extraction as a machine learning problem on big data stream processing. We show the main trends in big data stream processing frameworks. Additionally, we explore the data preprocessing, feature engineering, and the machine learning algorithms applied to the scenario of wireless network analytics. We address challenges and present research projects in wireless network monitoring and stream processing. Finally, future perspectives, such as deep learning and reinforcement learning in stream processing, are anticipated.
... One of the most widely studied features is the Received Signal Strength Indicator (RSSI). In [58] this is used by a Recurrent Neural Network (RNN) to perform seamless user-AP association. Similarly, in [59] the authors rely on SL (SVMs and Naive Bayes) to estimate the number of active nodes in a Wi-Fi network. ...
Software-Defined Networking (SDN) is gaining a lot of traction in wireless systems with several practical implementations and numerous proposals being made. Despite instigating a shift from monolithic network architectures towards more modulated operations, automated network management requires the ability to extract, utilise and improve knowledge over time. Beyond simply scrutinizing data, Machine Learning (ML) is evolving from a simple tool applied in networking to an active component in what is known as Knowledge-Defined Networking (KDN). This work discusses the inclusion of ML techniques in the specific case of Software-Defined Wireless Local Area Networks (SD-WLANs), paying particular attention to the frame length optimization problem. With this in mind, we propose an adaptive ML-based approach for frame size selection on a per-user basis by taking into account both specific channel conditions and global performance indicators. By relying on standard frame aggregation mechanisms, the model can be seamlessly embedded into any Enterprise SD-WLAN by obtaining the data needed from the control plane, and then returning the output back to this in order to efficiently adapt the frame size to the needs of each user. Our approach has been gauged by analysing a multitude of scenarios, with the results showing an average improvement of 18.36% in goodput over standard aggregation mechanisms.
Mobile devices’ popularization has brought several new applications to communication networks. As we move into an increasingly denser scenario, problems such as collisions between transmissions and unbalanced load become more pronounced. Moreover, while station-based handoff is inefficient to reduce these issues, network-wide handover decisions might provide better network resource management. This paper proposes LEAF, an access point virtualization solution based on Software Defined Networking to enable station (STA) handover conducted by the network, based on a global scope. Unlike other solutions in the literature, our proposal fully supports multichannel migrations through the IEEE 802.11h Channel Switch Announcement without restricting the channel utilization by the access points. To demonstrate the feasibility of such an approach, we present experimental data regarding the behavior of several different devices in face of this mechanism. We also evaluate our complete virtualization solution, which reveals that the handoff of STAs did not lead to significant packet losses or delays in STAs’ connections, while providing a foundation to improve network’s self-management and flexibility, allowing association control and load balancing tasks to be executed on top of our solution.
SDN’s ability to provide a global view, centralized control, and flexibility in orchestrating network infrastructure are expected to overcome challenges in the dynamic conditions of vehicular communications. We are looking to rely on SDN technologies to achieve Vehicular communications capacity and performance, which increase the safety of vehicles and transportation, save cost & energy, and increase the vehicles’ autonomy level. The usage of SDN in vehicular communications has been the subject of considerable research. Researchers address challenges such as low latency, high throughput, reliability, dense VANET, security, and scalability. Furthermore, this paper surveys the integration of SDN and other enabling technologies with vehicular communications, both for IEEE 802.11 and the C-V2X RAT families. It begins by discussing performance comparisons and coexistence between IEEE 802.11 and C-V2X standards, implementation of SDN in various use cases, integration of SDN with other enabling technologies, the study of particular SDN components to support vehicular communications performance, and SDN usage to support the specific issues vehicular communications. Finally, open directions and challenges of the research are discussed.
Artificial Intelligence (AI) technology is becoming one of the master instruments in the new world for many companies worldwide. The future of learning and the process of development have been bundled with innovations in the coming years. The application of AI helps to enhance the quality of employees through training and development at par with industrial needs. AI involves in the functional areas of the human resource segment such as recruitment, training, performance assessment, and employee retention. AI creates a next-gen technological workplace that succeeds in the seamless association between organisational systems and employees. Hence, human capitals are not obsolescent, but their efficiencies are bolstered by upcoming technology. In reality, AI offers organisations with a good amount of freeing up resources for greater tasks. The AI-enabled advanced software will read the employee based on their documents entered. Moreover, the AI application helps to identify various issues of the employees through staff data related to their stress level, late coming, unnecessary leaves, and so on. It has great market potential and is applicable not only in HR operations but also across the organisation. Therefore, AI helps the HR professional to make the decision-making process easier and smarter.
In this work, we propose two lightweight access point (AP) localization and selection schemes, AP-Cov and improved AP-Cov (IAP-Cov), in IEEE 802.11-enabled IoT networks for reducing handover delay and maintaining uninterrupted connectivity during movement. The proposed scheme AP-Cov consists of two phases—the localization of APs and
a priori
selection of APs in the direction of mobility. In the localization phase, an IoT device exploits the features of neighbor report request (NRR) and beacon report request (BRR) of IEEE 802.11k to get the nearby APs’ information along with their location and uses simple algebra to compute the location of next APs beforehand, instead of using heavyweight processing in resource-constrained IoT networks. In the AP selection phase, a linear optimization model is formulated to select the optimal AP for subsequent association. In IAP-Cov, a broadcast sequence of neighbor IoT is proposed for reducing the number of broadcasts. We implement the schemes in NS-3 and compare performance with the baseline standard, which shows that AP-Cov detects the availability of APs with 98.625% and 96.5% accuracy, improves accuracy over message complexity by 23% and 78% and reduces handover by 36.37% and 67.52% in constant-velocity and random-velocity mobility models, respectively. The evaluation of computational complexity shows that the proposed schemes are lightweight too. IAP-Cov reduces broadcasts and delay by 49%, 77.36% and 6%, 25% compared to AP-Cov using the constant-velocity and random-velocity mobility models, respectively.
5G and beyond communication technologies have started to spread around the world. Higher frequencies lead 5G base stations to have small coverage areas. Besides, the wireless network users have mobility and may move fast among the base stations. Software-Defined Networking (SDN) is a promising network solution for dynamic and dense networks such as 5G networks. The handover process defines the transfer of mobile users’ connections among the base stations and the handover has to happen frequently in ultra-dense networks. In this study, we aim to construct a more robust handover based on Long Short-Term Memory (LSTM) with SDN in terms of the number of handover and handover failures. LSTM, Linear Regression, Support Vector Machine, and Tree algorithms performances have been investigated for handover. According to the R2 values of LSTM, SVM, Tree, Linear Regression results are obtained as 0.998, 0.980, 0.980 and 0.75, respectively. Root Mean Square Error (RMSE), coefficient of determination (R2), Mean Squared Error (MSE), and Mean Absolute Deviation (MAE) statistics prove the improvement of the handover mechanism. In the proposed approach, approximately 30% reduction in the HO failure ratio and 22.22% reduction number of handover have been observed.
Due to its ubiquitous use, WiFi may play an essentialrole in providing indoor connectivity for the new real-timeservices in several 5G verticals. However, there are still pressingissues to be addressed, requiring new mobility managementschemes to guarantee reliable and low latency communications.In this paper, we propose a novel SDN-NFV based architec-ture with a low cost off-the-shelf WiFi that explores a multi-connectivity scheme at the user devices. In order to demonstratethe feasibility of our approach, we developed a prototype andperformed experiments on seamless handover using: i) an SDN-NFV based packet duplication solution; and ii) a source-routingsolution for end-to-end communication. Results show that theproposed architecture can provide an efficient seamless handover,increasing the likelihood of delivering packets with minimaleffects on latency.
The softwarization of networks is enabled by the SDN (Software-Defined Networking), NV (Network Virtualization), and NFV (Network Function Virtualization) paradigms, and offers many advantages for network operators, service providers and datacenter providers. Given the strong interest in both industry and academia in the softwarization of telecommunication networks and cloud computing infrastructures, a series of special issues was established in IEEE Transactions on Network and Service Management, which aims at the timely publication of recent innovative research results on management of softwarized networks.
In large and densely deployed IEEE 802.11 networks, a fast and seamless handover scheme is an important aspect in order to provide reliable connectivity for mobile users. However, IEEE 802.11 only supports decentralized, reactive and mobile node-driven handovers resulting in long handover times, packet loss due to interrupted connectivity and sub-optimal access point selection. Recently, centralized approaches have been developed that try to solve many of the challenges but these are mostly proprietary, reactive and require changes to mobile node stacks. In this paper, we propose a novel handover solution based on the principle of Software Defined Networking, that addresses the aforementioned challenges. Using virtualization and softwarization, we shift the traditional mobile node-driven handovers to the access point, while maintaining compliance with legacy devices. Moreover, we develop a proactive handover algorithm ADNA, which combines network state, traffic load and node mobility information. We evaluate our approach extensively in a testbed, showing that it outperforms existing approaches by improving the overall throughput by 116% while reducing the number of handovers by 44% on average.
The density of Wi-Fi at professional environments, such as offices, is resulting in increased strain on the management of Wi-Fi networks, of which handovers are an essential part of. The centralized approach of SDN allows taking more intelligent decisions, as opposed to per device optimizations. There is thus an increased interest in SDN-based Wi-Fi management, especially for handovers. Several proposals for SDN-based handover algorithms are being investigated and there is a need for actually validating them. In this demo, we will showcase a Wi-Fi SDN framework, on top of which a number of decision-making handover algorithms can be used. This framework is used in a real-life, large scale Wi-Fi testbed. The framework allows for different decision-making handover algorithms to be created and validated on large scale.
Abstract— This paper addresses the issue of the Handover
(HO) decision in Wi-Fi environments. Existing HO methods do not
meet the requirements of modern applications for mobile nodes
due to the lack of intelligence, awareness Quality of Service (QoS)
and the Quality of Experience (QoE) requirements of mobile users.
We therefore introduce a novel architecture that implements a
horizontal HO algorithm for Wi-Fi networks, based on Fuzzy
Logic Control (FLC). This architecture is based on the Software
Defined Networking (SDN) concept, where the Wi-Fi network is
controlled centrally and the wireless Access Points (APs) are
programmable. In this architecture, the proposed HO algorithm
will assist wireless users to find the AP that can best support the
application in terms of its QoS and QoE requirements. The use of
FLC, which can include QoS and QoE in the HO algorithm,
together with the use of SDN, provide promising performance
results with respect to the 802.11 standard and another approach
proposed in the literature.
IEEE 802.11 wireless LAN is proliferating since the increased trend in the wireless network utilization on mobile devices. Accuracy, fast content delivery, and reliable mobility support are essential features of any network to support the changing trend in a wireless network. However, traditional architectures in wireless LAN (WLANs or WiFi) always endured from challenges such as the provision of consistent mobility, real-time packet flow, and seamless handoff. Generally, most of the WLAN only relies on signal strength for handoff which is not sufficient enough for fair selection of an access point (AP) and therefore causes imperfect performance of the network. We present a novel mobility management scheme for WLANs to deal with the mobility management issues, and load balancing by software-defined network (SDN) and network function virtualization (NFV) technologies. The proposed scheme is based on logical AP (LAP) that keeps a connection with the user/mobile terminal (MT) during handoff triggered by either the user or the SDN controller for seamless mobility. It also involves the current state of each AP in addition to traditional parameters of WLAN. We implemented the proposed scheme on a real testbed in a WLAN environment. The evaluation results authenticate that our proposed scheme provides robust handover without throughput degradation and load imbalance among adjacent APs, and allocates the best AP in the neighboring region. Moreover, our proposed scheme is feasible to implement since it did not require any modification at the mobile terminal.
In this demo we present the EmPOWER Mobile Network Operating System. EmPOWER supports both WiFi and LTE networks and can interface with state--the--art SDN controllers using an intent--based interface. A Python--based SDK allows network programmers to write and deploy advanced control tasks as Network Apps. The demo will illustrate three Network Apps: mobility management, multicast, and VNF chaining/migration. We will also stage a speed tutorial allowing attendees to write and test a simple Network App using the EmPOWER SDK.
Chaotic deployment of Wireless Local Area Networks (WLANs) in dense urban areas is one of the common issues of many Internet Service Providers (ISPs) and Wi-Fi users. It results in a substantial reduction of the throughput and impedes the balanced distribution of bandwidth among the users. Most of these networks are managed independently and there is no cooperation among them. Moreover, the conventional association mechanism that selects the Access Points (APs) with the strongest Received Signal Strength Indicator (RSSI) aggravates this situation. In this paper, we present a versatile near-optimal solution for the fair bandwidth distribution over virtualized WLANs through dynamic association control. The proposed scheme is called ACO-PF, which is developed on top of Ant Colony Optimization (ACO) as a meta-heuristic technique to provide Proportional Fairness (PF) among the greedy clients. In fact, it presents a generic and centralized solution for ISPs that are using a common, virtualized or overlapped WLAN infrastructure for serving their customers. We have evaluated the efficacy of ACO-PF through numerical analysis versus popular existing schemes for both downlink and uplink scenarios. Our proposed technique has less complexity in terms of the implementation and running time for large-scale WLANs and it can be easily developed and customized for different objective functions. In addition, it is implemented in a testbed environment to investigate the key challenges of real deployment scenarios.
In this letter, the development and testing of an open enterprise Wi-Fi solution based on virtual access points (APs), managed by a central WLAN controller is presented. It allows seamless handovers between APs in different channels, maintaining the QoS of real-time services. The potential scalability issues associated to the beacon generation and channel assignment have been addressed. A battery of tests has been run in a real environment, and the results are reported in terms of packet loss and delay.
We propose a novel vertical handoff scheme with the support of the software-defined networking technique for heterogeneous wireless networks. The proposed scheme solves two important issues in vertical handoff: network selection and handoff timing. In this paper, the network selection is formulated as a 0-1 integer programming problem, which maximizes the sum of channel capacities that handoff users can obtain from their new access points. After the network selection process is finished, a user will wait for a time period. Only if the new access point is consistently more appropriate than the current access point during this time period, will the user transfer its inter-network connection to the new access point. Our proposed scheme ensures that a user will transfer to the most appropriate access point at the most appropriate time. Comprehensive simulation has been conducted. It is shown that the proposed scheme reduces the number of vertical handoffs, maximizes the total throughput, and user served ratio significantly.
Programming a mobile network requires to account for multiple complex operations, such as allocating radio resources and monitoring interference. Nevertheless, the current Software-Defined Networking ecosystem provides little support for mobile networks in term of radio data-plane abstractions, controllers, and programming primitives. Starting from the consideration that WiFi is becoming an integral part of the 5G architecture, we present a set of programming abstractions modeling three fundamental aspects of a WiFi network, namely state management of wireless clients, resource provisioning, and network state collection. The proposed abstractions hide away the implementation details of the underlying wireless technology providing programmers with expressive tools to control the state of the network. We also describe a proof-of-concept implementation of a Software-Defined Radio Access Network controller for WiFi networks and a Python-based Software Development Kit leveraging the proposed abstractions. The resulting platform can be effectively leveraged in order to implement typical control tasks such as mobility management and traffic engineering as well as applications and services such as multicast video delivery and/or dynamic content caching.
To achieve high performance and reliability in video streaming over wireless local area networks (WLANs), one must jointly consider both optimized association to access points (APs) and handover management based on dynamic scanning of alternate APs. In this article, we propose a new architecture within the software-defined networking (SDN) framework, which allows stations to be connected to several APs simultaneously and to switch fast between them. We evaluate our system in a real-time testbed and demonstrate that our SDN-based handover mechanism significantly reduces the number and duration of video freeze events and allows for smaller playout buffers.
Traditional handover decision algorithms for mobile devices mainly depend on signal strength. In the very near future, these will be obsolete for wireless networks and mobile terminals that are rapidly evolving towards being heterogeneous and multimodal, respectively, in response to the huge market potential. In the given circumstances, more sophisticated and intelligent handover decision algorithm is needed so that terminals can select the best option available from diverse networks and services as per user requirements. The algorithm has to provide user applications the flexibility to switch automatically between active interfaces that best suit them based on application requirements and interface capabilities, as well as to use multiple radio interfaces simultaneously ensuring the optimum usage of the network resources available to the terminal. In order to realize the above requirements, this paper illustrates a novel context-aware vertical handover decision algorithm suitable for multimode mobile devices in heterogeneous wireless networks based on the Analytic Hierarchy Process (AHP) and evaluates its performance through simulation.
Dyson is a new software architecture for building customizable WLANs. While research in wireless networks has made great strides, these advancements have not seen the light of day in real WLAN deployments. One of the key reasons is that today's WLANs are not architected to embrace change. For example, system administrators cannot fine-tune the association policy for their particular environment: an administrator may know certain nodes in certain locations interfere with each other and cause a severe degradation in throughput, and hence, such associations must be avoided in the particular deployment. Dyson defines a set of APIs that allow clients and APs to send pertinent information such as radio channel conditions to a central controller. The central controller processes this information, to form a global view of the network. This global view, combined with historical information about spatial and temporal usage patterns, allows the central controller enact a rich set of policies to control the network's behavior. Dyson provides a Python-based scripting API that allows the central controller's policies to be extended for site-specific customizations and new optimizations that leverage historical knowledge. We have built a prototype implementation of Dyson, which currently runs on a 28-node testbed distributed across one floor of a typical academic building. Using this testbed, we examine various aspects of the architecture in detail, and demonstrate the ease of implementing a wide range of policies. Using Dyson, we demonstrate optimizing associations, handling VoIP clients, reserving airtime for specific users, and optimizing handoffs for mobile clients.
Dense deployments of WLANs suffer from increased interference and, as a result, reduced capacity. There are three main functions used to improve the overall network capacity: 1) intelligent frequency allocation across access points (APs); 2) load-balancing of user affiliations across APs; and 3) adaptive power control for each AP. Several algorithms have been proposed in each category, but so far, their evaluation has been limited to: a) each approach in isolation; and b) simulations or small-scale testbeds. In this paper, we ask the question: What is the best way to combine these different functions? Our focus is to fully explore the interdependencies between the three functions in order to understand when and how to deploy them on a network. We follow a measurement-driven study to quantify the effects of three previously proposed optimization schemes (one for each category) on a relatively large testbed and in many different scenarios. Surprisingly, we find that blindly applying all the three optimization schemes is not always preferable; it can sometimes degrade the performance by as much as 24% compared to using only two of the schemes. We discover that there are explicit conditions that are conducive for applying specific combinations of the optimization schemes. We capture these conditions within a comprehensive framework, which we call measurement-driven guidelines (MDG). While we derive such guidelines based on measurements on one experimental testbed, we test their applicability and efficacy on a second testbed in a different location. We show that our framework improves network capacity consistently across both testbeds, with improvements ranging from 22% to 142% with 802.11a, and 103% to 274% with 802.11g.
Within IEEE 802.11 Wireless Local Area Networks (WLANs), client stations can move freely, but because of the short range of their Access Points (APs), they usually need to reassociate with different APs to continue to communicate. When changing APs, a client station starts a process known as a handoff that can take up to 2 seconds, which is too long for real-time applications such as Voice over IP (VoIP). Various solutions have been proposed to change or improve the client behaviour when doing a handoff. Previously, we proposed the idea of Virtual Access Points (VAP) implemented on APs in which a client station changes APs without disrupting its current communication. Based on this new concept, we have developed a solution called Multichannel Virtual Access Points (mVAP) to take advantage of APs operating on multiple channels. We have implemented mVAP using PACMAP, a tool for packet manipulation, and evaluated its performance. Our results show that mVAP is a new efficient technique for seamless handoffs without performance degradation.
Optimally choosing operating parameters for access points in an enterprise wireless LAN environment is a difficult and well-studied problem. Unlike past work, the SMARTA self-managing wireless LAN architecture dynamically adjusts both access point channel assignments and power levels in response to measured changes in the wireless environment to optimize arbitrary objective func- tions, while taking into account the irregular nature of RF propa- gation, and working with unmodified legacy clients. We evaluate the SMARTA architecture through simulation and show that our solution is not only feasible, but also provides significant improve- ments over existing approaches. For example, in a realistic sce- nario, SMARTA can provide 50% more throughput and 40% lower mean per-packet delay than a hand-optimized configuration. More- over, SMARTA can automatically reconfigure channels and power levels in response to both small and large changes in the RF envi- ronment due to client movement.
Use of mobile computing devices such as laptops, PDAs, and Wi-Fi enabled phones is increasing in the workplace. As the usage of corporate 802.11 wireless networks (WLANs) grows, network performance is becoming a significant concern. We have built DenseAP, a novel system for improving the per- formance of enterprise WLANs using a dense deployment of access points (APs). In sharp contrast with wired networks, one cannot increase the capacity of a WLAN by simply deploying more equipment (APs). To increase capacity, the APs must be assigned appropriate channels and the clients must make intelli- gent decisions about which AP to associate with. Furthermore, the decisions about channel assignment, and associations must be based on a global view of the entire WLAN, rather than the local viewpoint of an individual client or AP. Given the diver- sity of Wi-Fi devices in use today, another constraint on the de- sign of DenseAP is that it must not require any modification to Wi-Fi clients. In this paper, we show how the DenseAP system addresses these challenges, and provides significant improve- ments in performance over existing WLANs.
Learning to store information over extended time intervals by recurrent backpropagation takes a very long time, mostly because of insufficient, decaying error backflow. We briefly review Hochreiter's (1991) analysis of this problem, then address it by introducing a novel, efficient, gradient based method called long short-term memory (LSTM). Truncating the gradient where this does not do harm, LSTM can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units. Multiplicative gate units learn to open and close access to the constant error flow. LSTM is local in space and time; its computational complexity per time step and weight is O. 1. Our experiments with artificial data involve local, distributed, real-valued, and noisy pattern representations. In comparisons with real-time recurrent learning, back propagation through time, recurrent cascade correlation, Elman nets, and neural sequence chunking, LSTM leads to many more successful runs, and learns much faster. LSTM also solves complex, artificial long-time-lag tasks that have never been solved by previous recurrent network algorithms.
Recurrent neural networks can be used to map input sequences to output sequences, such as for recognition, production or prediction problems. However, practical difficulties have been reported in training recurrent neural networks to perform tasks in which the temporal contingencies present in the input/output sequences span long intervals. We show why gradient based learning algorithms face an increasingly difficult problem as the duration of the dependencies to be captured increases. These results expose a trade-off between efficient learning by gradient descent and latching on information for long periods. Based on an understanding of this problem, alternatives to standard gradient descent are considered.
Efficient resource allocation in enterprise wireless local area networks(WLAN) has become more paramount with the shift of traffic toward WLANs and increasing share of the video traffic. Unfortunately, current practise of client-driven association to APs has several shortcomings, e.g., sticky client problem. As a remedy, we propose to move the AP association decision to a periodically-running central controller which aims to maximize the proportionally-fair network throughput. After formulating the optimal mapping problem, we devise several heuristics requiring various degrees of knowledge, e.g., pairwise user-AP link rates, throughput demand of each user. Our analysis via simulations on realistic scenarios (conference, office, and shopping mall) shows the superior performance of our proposals in terms of aggregate logarithmic throughput. While the utility gain over the conventional client-driven approach is modest, up to 18%, the resulting increase in the weakest user's throughput is significant (71-120%) as well as that of AP load balance and fairness of user throughputs. Moreover, our evaluations reveal a very small optimality gap (between 0.1-5%). The highest gain is observed in the conference setting where the users are unevenly distributed in the network and hence there is a huge load imbalance among the APs. While schemes requiring more knowledge, i.e., on handover-cost and traffic demands, perform the best, a naive approach which runs periodically and assigns each user to the AP providing the highest signal level to that user maintains up to 41% gain in the weakest user's throughput over the client-driven handover approach.
In existing wireless systems it’s hard for an operator to implement the services and change the network strategy under heavy load due to its proprietary and inflexible hardware based architectures. This paper explores the concept of SDN in wireless networks. An access point (AP) load balance based handover scheme in SDN WiFi systems is proposed for overlapping wireless LAN cells to take efficient handover based on AP load. We implemented the proposed load balancing handover scheme in Mininet-WiFi emulator which could handle the access points from a centralized controller and helps the test client how and when to connect with the right AP and take efficient handover based on AP load. New interface is added with the station, client’s traffic is tested at different positions and obtained improved throughput for mobile clients. Experimental results show that total network throughput is higher after a successful handover.
Software defined wireless local area network (SDWLAN) has gained significant interest recently from both academic and industrial communities, and initiated a paradigmatic reconsideration on the stereotyped management and control of current WLAN due to its flexibility and programmability. However, with the proliferation of mobile devices, efficient client association with quality of service (QoS) guarantees in high-density SDWLAN is a very challenging issue. In this paper, we study the client association problem in SDWLAN with new features including centralized association, global network state awareness, seamless handoff and flow-level association. We formulate the client association in high-density scenario as an optimization problem aiming to minimize the inter packet delay of individual flows, based on an unsaturated and heterogeneous Markovian analytical model. Further, we interpret the optimization problem as an NP-hard supermodular set function minimization problem, which is solved by two low-complexity heuristic methods, namely the greedy algorithm and the bounded local search algorithm. Through simulations, we demonstrate the effectiveness of our proposed client association solution.
Handover of Mobile Equipment (ME) between different Access Points (APs) is an inevitable problem in the wireless network. Mobility of the mobile equipment can cause degradation of Quality of Service (QoS). How to satisfy the user's QoS and achieve seamless handover becomes a very worth of study in the field of wireless communication network. In this paper, we proposed a handover management scheme in the WLAN based on Software Defined Networking (SDN) architecture. In this scheme, the handover decision making process is processed layered and we proposed a multiple attributes handover algorithm based on fuzzy logic (FLMAHA). The algorithm utilizes Received Signal Strength (RSS), forecasting RSS and available bandwidth as parameters to design of fuzzy logic system, using fuzzy logic method to process the parameters, and then obtain the quantized value of each network parameters membership. At last through calculating network performance evaluation values to make handover decision. Finally, the experimental results showed that our proposed handover scheme can avoid the “ping pong” effect and ensure QoS.
Deep neural nets with a large number of parameters are very powerful machine learning systems. However, overfitting is a serious problem in such networks. Large networks are also slow to use, making it difficult to deal with overfitting by combining the predictions of many different large neural nets at test time. Dropout is a technique for addressing this problem. The key idea is to randomly drop units (along with their connections) from the neural network during training. This prevents units from co-adapting too much. During training, dropout samples from an exponential number of different "thinned" networks. At test time, it is easy to approximate the effect of averaging the predictions of all these thinned networks by simply using a single unthinned network that has smaller weights. This significantly reduces overfitting and gives major improvements over other regularization methods. We show that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets. © 2014 Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever and Ruslan Salakhutdinov.
We propose a novel Quality of Service (QoS) vertical handoff scheme with the support of the Software-Defined Network (SDN) technique for the heterogeneous wireless networks. The proposed scheme solves two important issues of the vertical handoff: network selection and handoff timing. In this paper, the network selection is formulated as an 0-1 integer programming problem, which maximizes the overall QoS and avoids the network congestion. After the network selection process is finished, a mobile will wait for a time period for implementing the vertical handoff. The selected network should be consistently more appropriate than the current network during the time period, the mobile will transfer its inter-network connection to the selected network. Our proposed scheme ensures that, a mobile will transfer to the most appropriate network at the most appropriate time. Comprehensive simulation has been conducted. It is shown that the proposed scheme reduces the number of vertical handoffs, and maximizes the overall QoS significantly comparing with existing schemes.
We introduce Adam, an algorithm for first-order gradient-based optimization
of stochastic objective functions. The method is straightforward to implement
and is based an adaptive estimates of lower-order moments of the gradients. The
method is computationally efficient, has little memory requirements and is well
suited for problems that are large in terms of data and/or parameters. The
method is also ap- propriate for non-stationary objectives and problems with
very noisy and/or sparse gradients. The method exhibits invariance to diagonal
rescaling of the gradients by adapting to the geometry of the objective
function. The hyper-parameters have intuitive interpretations and typically
require little tuning. Some connections to related algorithms, on which Adam
was inspired, are discussed. We also analyze the theoretical convergence
properties of the algorithm and provide a regret bound on the convergence rate
that is comparable to the best known results under the online convex
optimization framework. We demonstrate that Adam works well in practice when
experimentally compared to other stochastic optimization methods.
We present Odin, an SDN framework to introduce programma-bility in enterprise wireless local area networks (WLANs). Enterprise WLANs need to support a wide range of services and functionalities. This includes authentication, authoriza-tion and accounting, policy, mobility and interference man-agement, and load balancing. WLANs also exhibit unique challenges. In particular, access point (AP) association de-cisions are not made by the infrastructure, but by clients. In addition, the association state machine combined with the broadcast nature of the wireless medium requires keep-ing track of a large amount of state changes. To this end, Odin builds on a light virtual AP abstraction that greatly simplifies client management. Odin does not require any client side modifications and its design supports WPA2 En-terprise. With Odin, a network operator can implement enterprise WLAN services as network applications. A pro-totype implementation demonstrates Odin's feasibility.
We present a simple regularization technique for Recurrent Neural Networks
(RNNs) with Long Short-Term Memory (LSTM) units. Dropout, the most successful
technique for regularizing neural networks, does not work well with RNNs and
LSTMs. In this paper, we show how to correctly apply dropout to LSTMs, and show
that it substantially reduces overfitting on a variety of tasks. These tasks
include language modeling, speech recognition, and machine translation.
In this paper, we suggest about MIH (Media Independent Handover) supporting fully distributed handover in heterogeneous network based on Open vSwitch and OpenFlow. Although, personal mobile devices which are released recently have more than 2 mobile network interfaces, there is a small chance to utilize them simultaneously. To do this, MIH is suggested to guarantee the quality of application service when terminals of service users move to the other feature of wireless network in heterogeneous wireless network environment. Also, Open vSwitch of software type of various factors in SDN (Software Defined Network) and OpenFlow which has a control function by interacting with Data Path on network switch have arisen as a proposal to utilize wireless interfaces.
Thus, in this paper, we experimented changes in packet flow of wireless interfaces. Moreover, we suggest a method of MIH based on SDN to guarantee communication quality of devices which uses more than 2 wireless interfaces.
We propose a method for dynamic load balancing in wireless LANs (WLANs), which adapts association topology dynamically based on traffic conditions, while keeping the handoff overhead negligible using virtualized wireless network interfaces (WNICs). In large-scale WLANs, there are many locations that each station (STA) can discover multiple access points (APs). In these locations, the conventional approach to the AP selection in which each station connects to the AP with the strongest Received Signal Strength Indication (RSSI) may suffer from imbalanced load among APs. To address this issue, a number of AP selection schemes have been proposed, which achieve load balancing by changing some STA-AP associations. However, since stations cannot communicate during handoff, frequent changes of STA-AP associations will result in serious deterioration of the communication quality. Therefore, in the existing schemes, we face a problem that it is difficult to decide appropriate timing of association changes. Nevertheless, this problem was not considered as a major concern in the literature. In this paper, we propose a method for trigger-based dynamic load balancing in WLANs. In the proposed method, to minimize the handoff overhead, the WNIC on a station is virtualized and connected to multiple APs simultaneously. Using this approach, we propose a method that continuously monitors changes in traffic conditions and that switches STA-AP associations at appropriate timing based on the monitored results. We evaluate the effectiveness of our method in terms of aggregated throughput and fairness using the ns-3 simulator. Compared with the result in the traditional AP selection method, aggregated throughput is improved by about 11%, while increasing the Jain's fairness index by about 19% in our method.
Conference code: 93298, Export Date: 21 December 2012, Source: Scopus, Art. No.: 6294711, doi: 10.1109/TEMU.2012.6294711, Language of Original Document: English, Correspondence Address: Mumtaz, S.; Institute of Telecommunication, Aveiro, 3810-193, Portugal, References: (2001) Broadband Ratho Access Networks (BRAN); HIPERLAN Tpe 2; Requirements and Architectures for Interworking between HIPERLAN/2 and 3 rd Generation Cellular Systems, , ETSI TR 101 957: V1.1.1 08;
In future wireless communication networks, seamless handoff either by vertical or horizontal is an important issue in radio resource management. For a vertical handoff (VHO), each candidate network is evaluated as a function of multiple attributes such as available bandwidth, delay, data rate, and cost, etc. However, the variations of these parameters and distributed VHO decisions might cause the instability of VHO decisions, which is inefficient in utilizing network resources due to frequent handoffs. In this letter, we propose a service history-based VHO algorithm to reduce unnecessary handoffs and call dropping probability in addition to QoS parameter considerations. Simulation results show that the proposed VHO algorithm outperforms existing algorithms.
Wireless technologies have been widely deployed in the last decade making users demand for continuous connectivity. Users not only demand being attached to a network, but possibly to the one with the highest performance, or at least to a network able to fulfill their requirements. To choose the best network among different candidates, the IEEE 802.21 standard has been developed. In this paper we aim at demonstrating the viability of performing Vertical Handover (VHO) processes based on the IEEE 802.21 protocol. To do so, we have evaluated a VHO strat- egy which considers network availability and maximum data rate in order to choose the best network candidate among the Wireless Fidelity (Wi-Fi), the Worldwide interoperability for Microwave Access (WiMAX), and the Universal Mobile Telecommunications System (UMTS). Moreover, throughout a set of experiments, we have also evaluated the maximum performance of the available networks. Index Terms—Vertical handover, IEEE 802.21, Wi-Fi, WiMAX, UMTS, ns-2.
Wireless technologies, under the “Anywhere, Anytime” paradigm, offer users the promise of being always attached to the network. Mobile devices enabled with multiple wireless technologies make possible to maintain seamless connectivity in highly dynamic scenarios such as vehicular networks (VNs), switching from one wireless network to another by using vertical handover techniques (VHO). In this paper we present an overview of VHO techniques, along with the main algorithms, protocols and tools proposed in the literature. In addition we suggest the most appropriate VHO techniques to efficiently communicate in VN environments considering the particular characteristics of this type of networks.
With the technical advances in ubiquitous computing and wireless networking, there has been an increasing need to capture the context information (such as the location) and to figure it into applications. In this paper, we establish the theoretical base and develop a localization algorithm for building a zero-configuration and robust indoor localization and tracking system to support location-based network services and management. The localization algorithm takes as input the on-line measurements of received signal strengths (RSSs) between 802.11 APs and between a client and its neighboring APs, and estimates the location of the client. The on-line RSS measurements among 802.11 APs are used to capture (in real-time) the effects of RF multi-path fading, temperature and humidity variations, opening and closing of doors, furniture relocation, and human mobility on the RSS measurements, and to create, based on the truncated singular value decomposition (SVD) technique, a mapping between the RSS measure and the actual geographical distance. The proposed system requires zero-configuration because the on-line calibration of the effect of wireless physical characteristics on RSS measurement is automated and no on-site survey or initial training is required to bootstrap the system. It is also quite responsive to environmental dynamics, as the impacts of physical characteristics changes have been explicitly figured in the mapping between the RSS measures and the actual geographical distances. We have implemented the proposed system with inexpensive off-the-shelf Wi-Fi hardware and sensory functions of IEEE 802.11, and carried out a detailed empirical study in our division building. The empirical results show the proposed system is quite robust and gives accurate localization results (i.e., with the localization error within 3 meters).
Her current research is mostly based on sharing models for next generation end-to-end network resources
Nina Slamnik-Kriještorac has recently started her PhD adventure in the
field of Applied Engineering Sciences, as a PhD Student at the University of
Antwerp and the imec research center in Belgium. She obtained Master degree
in telecommunications engineering at Faculty of Electrical Engineering,
University of Sarajevo, Bosnia & Herzegovina, in July 2016. Her current
research is mostly based on sharing models for next generation end-to-end
network resources, based on enabling programmable networks for flexible
smart cities.
Meta-heuristic solution for dynamic association control in virtualized multi-rate WLANs
- torshizi