Fig 1 - uploaded by Robert Caddell Atkinson
Content may be subject to copyright.
Source publication
A novel approach to enhance the robustness of handovers in LTE femtocells is presented. A modified Self Organizing Map is used to allow femtocells to learn about their specific indoor environment including the locations that have prompted handover requests. Optimized handover parameter values are then used that are specific to these locations. This...
Context in source publication
Context 1
... location of the user at the point of a handover trigger is detected by the Monitor stage of the autonomic system. A snapshot of the locations of 100 handover triggers is shown in Figure 1. As can be seen there are 2 clusters of neurons: a single prohibition zone on the right and a single permissive zone on the left. ...
Similar publications
![Figure 3: A letter from the MacGreevy Archive [7, 8]](profile/Ronan-Reilly/publication/266095953/figure/fig3/AS:667619585712138@1536184321381/A-letter-from-the-MacGreevy-Archive-7-8_Q320.jpg)
![Figure 6: A letter taken from the MacGreevy Archive [7, 8]](profile/Ronan-Reilly/publication/266095953/figure/fig5/AS:667619585716232@1536184321410/A-letter-taken-from-the-MacGreevy-Archive-7-8_Q320.jpg)
In this paper we present a novel system for automatically marking up text documents into XML. The system uses the techniques of the Self-Organising Map (SOM) algorithm in conjunction with an inductive learning algorithm, C5.0. The SOM algorithm clusters the XML marked-up documents on a two-dimensional map such that documents having similar content...
In this paper we discuss use of machine learning methods such as self organizing maps, k-means and Ward's clustering to perform classification of universities based on their income. This classification will allow us to quantitate classification of universities as teaching, research, entrepreneur, etc. which is important tool for government, corpora...
The purpose of this study was to review various machine learning techniques for Botnet detection system by looking at their advantage and limitation, and propose our Botnet detection system. In this paper, we summarized different machine learning techniques used in previous research. Recently, machine learning has become prominent in developing Bot...
Citations
... However, the researchers focus on high mobility users only the signaling overhead on lower mobility users degrades the performance parameters as well as energy consumption. [32] In this paper, we have proposed a HO decision algorithm for the LTE-A Femtocell network, which jointly considers the impact of user mobility, interference, and energy efficiency. The proposed algorithm utilizes standard signaling quality measurements to sustain service continuity and reduce the mean UE transmit power. ...
... The proposed algorithm utilizes standard signaling quality measurements to sustain service continuity and reduce the mean UE transmit power. System-level simulations showed that compared to existing algorithms, the proposed algorithm significantly reduces the interference and energy expenditure [32]. However, the algorithm increases the network's core network signaling, degrading the network performance of delay and throughput. ...
The rapid growth of mobile devices and demand for mobile data have made maintaining capacity, high coverage, and data speed challenging. With the emergence of small cell networks, the Long-Term Evolution (LTE) system helped to address these issues, Femtocell technology is being deployed to provide improved indoor coverage. However, a major challenge is the frequent handover and unequal distribution of cell loads, which lead to a reduction in call and data rates. Small cells have changing and unplanned load distribution over time, resulting in certain cells suffering high user density and strong resource competition, while others have low user density and wasteful resources due to low consumption. This imbalance in cell load distribution greatly influences overall network performance and prevents Femtocells from realizing their full potential. Despite several efforts by researchers to enhance network communication, handover is still a challenging issue, many related works have been done in the field but still it needs improvement. This research proposes an Optimized Q-learning-based Handover Decision Algorithm for Femtocells using Load Balancing in LTE-A Networks to improve overall network performance. The algorithm learns to prioritize and select cells with low load during target cell selection and not only provides good Quality of Service (QoS) but also has a low load, resulting in better traffic distribution across the cells. Several simulations were performed using LTE-Sim. Results proved the outperformance of the proposed algorithm over the existing algorithm in terms of QoS with a packet loss ratio for CBR packet transmission of 512 bytes with a rate of 8 packets/second intervals, 88.53%, and VoIP packet transmission of 32 bytes per 20 ms/time interval, 89.24% respectively.
... One example is the incorrect setting of handover hysteresis, which may results in ping-pongs or excessively delayed handovers to a target cell. Therefore, we need to optimize the handover mechanism to curtail unnecessary or missed handovers [48,53]. ...
... In [3], [4], the authors discuss fuzzy logic capabilities. Likewise, a number of papers address the problem by identifying successful handover events through unsupervised learning [5], [6]. In particular, these works propose an approach to handover management based on self-organizing map analysis. ...
We propose an unsupervised learning based anomaly detection framework for identifying cells experiencing performance degradation due to mobility problems, in LTE networks. Handover failure rate is used as a performance metric, whereas the mobility problems considered include too-early and too-late handovers. In order to enable unsupervised learning, the framework leverages existing datasets in commercial LTE networks (e.g. performance management counters, configuration management data, geographical locations, and inventory data etc). To this end, the first step is data pre-processing, followed by feature extraction based on principal component analysis and clustering. For implementation, we use real data from an operational commercial LTE network. Results show that clustering is highly effective in understanding and identifying mobility related anomalous behaviour, and provides actionable insights for automation and self-optimization, paving the way for efficient mobility robustness optimization, which is an important self-optimization use-case for contemporary 4G/5G networks.
... For e.g., eNodeBs can acquire signal strengths along with the angle of arrival of the user to learn specific locations where handover occurred (successfully) and decide whether to allow or disallow certain handover procedures. Although this method is proposed in [37], authors apply this to enhance the network performance by controlling unwanted handovers, which implies that it can be applied to control handovers to rogue eNodeBs. Further, this method does not require any changes to existing LTE standards. ...
Mobile network operators choose Self Organizing Network (SON) concept as a cost-effective method to deploy LTE/4G networks and meet user expectations for high quality of service and bandwidth. The main objective of SON is to introduce automation into network management activities and reduce human intervention. SON enabled LTE networks heavily rely on the information acquired from mobile phones to provide self-configuration, self-optimization, and self-healing features. However, mobile phones can be attacked over-the-air using rogue base stations. In this paper, we carefully study SON related LTE/4G security specifications and reveal several vulnerabilities. Our key idea is to introduce a rogue eNodeB that uses legitimate mobile devices as a covert channel to launch attacks against SON enabled LTE networks.
We demonstrate low-cost, practical, silent and persistent Denial of Service attacks against the network and end-users by injecting fake measurement and configuration information into the SON system. An active attacker can shut down network services in 2 km2 area of a city for a certain period of time and also block network services to a selective set of mobile phones in a targeted area of 200 m to 2 km in radius. With the help of low cost tools, we design an experimental setup and evaluate these attacks on commercial networks. We present strategies to mitigate our attacks and outline possible reasons that may explain why these vulnerabilities exist in the system.
... Differently from [171], [172], in [173], the authors take advantage also of fuzzy logic capabilities. Additionally, in terms of solutions based on unsupervised learning, we can find in the literature the works of [174] and [175]. In these works the authors propose an approach to HO management based on UL and SOM analysis. ...
In this paper, we provide an analysis of self-organized network management, with an end-to-end perspective of the network. Self-organization as applied to cellular networks is usually referred to Self-organizing Networks (SONs), and it is a key driver for improving Operations, Administration, and Maintenance (OAM) activities. SON aims at reducing the cost of installation and management of 4G and future 5G networks, by simplifying operational tasks through the capability to configure, optimize and heal itself. This autonomous management vision has to be extended to the end to end network, to satisfy 5G network management requirements. In literature and also in some instances of products available in the market, Machine Learning (ML) has been identified as the key tool to implement autonomous adaptability and take advantage of experience when making decisions. In this paper we survey how network management can significantly benefit from ML solutions. We review and provide the basic concepts and taxonomy for SON, network management and ML. We analyse the available state of the art in the literature, standardization and in the market. We pay special attention to 3GPP evolution in the area of network management and to the data that can be extracted from 3GPP networks, in order to gain knowledge and experience in how the network is working, and improve network performance in a proactive way. Finally, we go through the main challenges associated with this research line, in both 4G and in what 5G is getting designed, while identifying new directions for research.
... Different approaches in turn, address the problem by identifying successful HO events, through solutions based on unsupervised learning. In particular, the works of [144] and [145] propose an approach to HO management based on UL and SOM analysis. The idea is to exploit the experience gained from the analysis of data of the network based on the angle of arrival and the received signal strength of the user, to learn specific locations where HOs have occurred and decide whether to allow or forbid certain handovers to enhance the network performance. ...
In this paper, we provide an analysis of self-organized network management, with an end-to-end perspective of the network. Self-organization as applied to cellular networks is usually referred to Self-organizing Networks (SONs), and it is a key driver for improving Operations, Administration, and Maintenance (OAM) activities. SON aims at reducing the cost of installation and management of 4G and future 5G networks, by simplifying operational tasks through the capability to configure, optimize and heal itself. To satisfy 5G network management requirements, this autonomous management vision has to be extended to the end to end network. In literature and also in some instances of products available in the market, Machine Learning (ML) has been identified as the key tool to implement autonomous adaptability and take advantage of experience when making decisions. In this paper, we survey how network management can significantly benefit from ML solutions. We review and provide the basic concepts and taxonomy for SON, network management and ML. We analyse the available state of the art in the literature, standardization, and in the market. We pay special attention to 3rd Generation Partnership Project (3GPP) evolution in the area of network management and to the data that can be extracted from 3GPP networks, in order to gain knowledge and experience in how the network is working, and improve network performance in a proactive way. Finally, we go through the main challenges associated with this line of research, in both 4G and in what 5G is getting designed, while identifying new directions for research.
... In [9], A novel approach to enhance the robustness ofhandovers in LTE femtocells is presented. A modified Self Organizing Map is used for allowing femtocells to learn about their specific indoor environment including the locations that have initiated handover requests. ...
