Adlen Ksentini’s research while affiliated with EURECOM and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (16)


Cost-efficient slicing in virtual Radio Access Networks
  • Article

July 2023

·

9 Reads

·

1 Citation

Computer Communications

Somreeta Pramanik

·

Adlen Ksentini

·


Machine Learning for Service Migration: A Survey

January 2023

·

64 Reads

·

18 Citations

IEEE Communications Surveys & Tutorials

Future communication networks are envisioned to satisfy increasingly granular and dynamic requirements to accommodate the application and user demands. Indeed, novel immersive and mission-critical services necessitate increased computing and network resources, reduced communication latency, and guaranteed reliability. Thus, efficient and adaptive resource management schemes are required to provide and maintain sufficient levels of Quality of Experience (QoE) during the service life-cycle. Service migration is considered a key enabler of dynamic service orchestration. Indeed, moving services on demand is an efficient mechanism for user mobility support, load balancing in case of fluctuations in service demands, and hardware failure mitigation. However, service migration requires planning, as multiple parameters must be optimized to reduce service disruption to a minimum. Recent breakthroughs in computational capabilities allowed the emergence of Machine Learning as a tool for decision making that is expected to enable seamless automation of network resource management by predicting events and learning optimal decision policies. This paper surveys contributions applying Machine Learning (ML) methods to optimize service migration, providing a detailed literature review on recent advances in the field and establishing a classification of current research efforts with an analysis of their strengths and limitations. Finally, the paper provides insights on the main directions for future research.



Fig. 2: CPU utilization and UDP downlink throughput of the virtual eNB, for different values of the MCS index and a single connected UE.
Fig. 3: CPU utilization and UDP downlink throughput of the virtual eNB vs the number of occupied RBs, for a single connected UE and MCS=27.
Fig. 4: CPU utilization of the virtual eNB vs the MCS index, for a varying number of connected UEs and a total number of occupied RBs equal to 36.
Characterizing the Computational and Memory Requirements of Virtual RANs
  • Preprint
  • File available

January 2022

·

95 Reads

The virtualization of radio access networks (RANs) is emerging as a key component of future wireless systems, as it brings agility to the RAN architecture and offers degrees of design freedom. In this paper, we investigate and characterize the computational and memory requirements of virtual RANs. To this end, we build a virtual RAN test-bed leveraging the srsRAN open-source mobile communication platform and general-purpose processor-based servers. Through extensive experiments, we profile the consumption of computing and memory resources, and we assess the system performance. Further, we build regression models to predict the system behavior as the number of connected users increases, under diverse radio transmission settings. In so doing, we develop a methodology and prediction models that can help designing and optimizing virtual RANs.

Download

Deep Learning for B5G Open Radio Access Network: Evolution, Survey, Case Studies, and Challenges

January 2022

·

2,245 Reads

·

112 Citations

IEEE Open Journal of the Communications Society

Open Radio Access Network (O-RAN) alliance was recently launched to devise a new RAN architecture featuring open, software-driven, virtual, and intelligent radio access architecture. O-RAN architecture is based on (1) disaggregated RAN functions that run as Virtual Network Function (VNF) and Physical Network Function (PNF); (2) the notion of RAN controller that runs centrally RAN applications such as mobility management, users’ scheduling, radio resources allocation, etc. The RAN controller is in charge of enforcing the application decisions by using open interfaces with the RAN functions. One important feature introduced by O-RAN is the heavy usage of Machine Learning (ML) techniques, particularly Deep Learning (DL), to foster innovation and ease the deployment of intelligent RAN applications that are able to fulfill the Quality of Service (QoS) requirements of the envisioned 5G and beyond network services. In this work, we first give an overview of the evolution of RAN architectures toward 5G and beyond, namely C-RAN, vRAN, and O-RAN. We also compare them based on various perspectives, such as edge support, virtualization, control and management, energy consumption, and AI support. Then, we review existing DL-based solutions addressing the RAN part. We also show how they can be integrated/mapped to the O-RAN architecture since these works were not initially adapted to the O-RAN architecture. In addition, we present two case studies for DL techniques deployment in O-RAN. Furthermore, we describe how the main steps of deployed DL models in O-RAN can be automated, to ensure stable performance of these models, introducing ML system operations (MLOps) concept in O-RAN. Finally, we identify key technical challenges, open issues, and future research directions related to the Artificial Intelligence (AI)-enabled O-RAN architecture.


A Formal Approach to Verify Connectivity and Optimize VNF Placement in Industrial Networks

June 2020

·

24 Reads

·

15 Citations

IEEE Transactions on Industrial Informatics

·

·

·

[...]

·

Adlen Ksentini

The increased flexibility and inter-connectivity of modern industrial communication networks, obtained through the use of innovative technologies like Network Function Virtualization (NFV) and Software Defined Networking (SDN), requires a secure and manageable framework to support the new communication and computing needs. To focus on these requirements, this paper proposes a framework for reliable placement of services across physically separated locations, which offers both system optimization, in terms of latency and resource utilization, and connectivity policy enforcement to guarantee service reliability, safety, and security. This is achieved by exploiting a new approach to solve the virtual network embedding problem, using Optimization Modulo Theories (MaxSMT), which allows the use of very expressive constraints.


IEEE TCCN Special Section Editorial: Intelligent Resource Management for 5G and Beyond

June 2020

·

18 Reads

·

2 Citations

IEEE Transactions on Cognitive Communications and Networking

Learning from massive network data to produce cognitive knowledge for efficient resource management in 5G and beyond 5G (B5G) is still challenging. We are delighted to introduce the readers to this special section of the IEEE Transactions on Cognitive Communications and Networking (TCCN), which aims at exploring recent advances and addressing practical challenges in the intelligent resource management in 5G/B5G. We have received a total number of 30 submissions, and after a rigorous review process, 15 articles have been selected for publication, which are briefly discussed as follows.


Named Data Networking in Vehicular Ad Hoc Networks: State-of-the-Art and Challenges

March 2020

·

902 Reads

·

306 Citations

IEEE Communications Surveys & Tutorials

Information-Centric Networking (ICN) has been proposed as one of the future Internet architectures. It is poised to address the challenges faced by today’s Internet that include, but not limited to, scalability, addressing, security, and privacy. Furthermore, it also aims at meeting the requirements for new emerging Internet applications. To realize ICN, Named Data Networking (NDN) is one of the recent implementations of ICN that provides a suitable communication approach due to its clean slate design and simple communication model. There are a plethora of applications realized through ICN in different domains where data is the focal point of communication. One such domain is Intelligent Transportation System (ITS) realized through Vehicular Ad hoc NETwork (VANET) where vehicles exchange information and content with each other and with the infrastructure. To date, excellent research results have been yielded in the VANET domain aiming at safe, reliable, and infotainment-rich driving experience. However, due to the dynamic topologies, host-centric model, and ephemeral nature of vehicular communication, various challenges are faced by VANET that hinder the realization of successful vehicular networks and adversely affect the data dissemination, content delivery, and user experiences. To fill these gaps, NDN has been extensively used as underlying communication paradigm for VANET. Inspired by the extensive research results in NDN-based VANET, in this paper, we provide a detailed and systematic review of NDN-driven VANET. More precisely, we investigate the role of NDN in VANET and discuss the feasibility of NDN architecture in VANET environment. Subsequently, we cover in detail, NDN-based naming, routing and forwarding, caching, mobility, and security mechanism for VANET. Furthermore, we discuss the existing standards, solutions, and simulation tools used in NDN-based VANET. Finally, we also identify open challenges and issues faced by NDN-driven VANET and highlight future research directions that should be addressed by the research community.


FIGURE 1. 5G network slicing.
FIGURE 2. Indicative applications of 5G network slicing.
FIGURE 3. A comparison on related review papers.
FIGURE 4. Network slicing generic architecture.
FIGURE 5. Orchestration architecture across multiple domains.
Algorithmics and Modeling Aspects of Network Slicing in 5G and Beyonds Network: Survey

January 2020

·

406 Reads

·

47 Citations

IEEE Access

One of the key goals of future 5G networks is to incorporate many different services into a single physical network, where each service has its logical network isolated from other networks. Besides, Network Slicing (NS) is considered as the key technology for meeting the service requirements of diverse application domains. Recently, NS faces several algorithmic challenges for 5G networks. This paper provides a review related to NS architecture with a focus on relevant Management and Orchestration (MANO) architecture across multiple domains. In addition, this survey paper delivers a deep analysis and a taxonomy of NS algorithmic aspects. Finally, this paper highlights some of the open issues and future directions.


5G-Slicing-Enabled Scalable SDN Core Network: Toward an Ultra-Low Latency of Autonomous Driving Service

July 2019

·

269 Reads

·

145 Citations

IEEE Journal on Selected Areas in Communications

5G networks are anticipated to support a plethora of innovative and promising network services. These services have heterogeneous performance requirements (e.g., high-rate traffic, low latency and high reliability). To meet them, 5G networks are entailed to endorse flexibility that can be fulfilled through the deployment of new emerging technologies, mainly Software-Defined Networking (SDN), Network Functions Virtualization (NFV) and Network Slicing. In this paper, we focus on an interesting automotive vertical use case: autonomous vehicles. Our aim is to enhance the quality of service of autonomous driving application. To this end, we design a framework that uses the aforementioned technologies to enhance the quality of service of the autonomous driving application. The framework is made of i) a distributed and scalable SDN core network architecture that deploys fog, edge and cloud computing technologies; ii) a network slicing function that maps autonomous driving functionalities into service slices; and iii) a network and service slicing system model that promotes a four-layer logical architecture to improve the transmission efficiency and satisfy the low latency constraint. In addition, we present a theoretical analysis of the propagation delay and the handling latency based on GI/M/1 queuing system. Simulation results show that our framework meets the low-latency requirement of the autonomous driving application as it incurs low propagation delay and handling latency for autonomous driving traffic compared to best-effort traffic.


Citations (13)


... Moreover, recent advancements suggest that a logically centralized yet physically distributed controller offers a promising solution to potential bottlenecks. As for the second issue, Toumi et al. [13] recently demonstrated substantial efforts by the research community to tackle this problem. However, a detailed discussion of this challenge is beyond the scope of our study. ...

Reference:

Empirical Evaluation of QUIC-Based Software-Defined Service Migration in Multi-access Edge Computing Over 5G Networks
Machine Learning for Service Migration: A Survey
  • Citing Article
  • January 2023

IEEE Communications Surveys & Tutorials

... These processing nodes can be either small DCs or processing pool (PP) nodes dedicated to DU/CU processing; in this paper, the term PP represents any of the two options. We assume that the capacities of PPs are limited, and the DU/CU processing at PPs involves some load reflecting the CPU and memory usage [49]. Additionally, joint DU processing at the same PP for a group of RUs (cluster) is considered to effectively implement multi-cell coordination mechanisms [50]. ...

Characterizing the Computational and Memory Requirements of Virtual RANs
  • Citing Conference Paper
  • March 2022

... It is functionally divided into the control plane (O-CU-CP), which handles RRC procedures and the PDCP control segment, and the user plane (O-CU-UP), which manages SDAP and the PDCP user segment. These components interact via the E1 interface, The Near-RT RIC can be deployed either at the edge or within the regional cloud [9], [17], whereas the Non-RT RIC is commonly hosted by the SMO, which manages the configuration and orchestration of RAN components [6], [14]. ...

Deep Learning for B5G Open Radio Access Network: Evolution, Survey, Case Studies, and Challenges

IEEE Open Journal of the Communications Society

... The third group focused on the problem-solving methodologies of NS frameworks. For instance, optimization problems supporting the RA functionality are surveyed in [21], [22], while associated algorithmic aspects of NS orchestration and RA are reviewed in [35], [36]. A growing number of reviews (e.g., [16], [15], and [37]) focus on Machine Learning (ML) approaches and their DRL subset (e.g., [13], [38]- [40]). ...

Algorithmics and Modeling Aspects of Network Slicing in 5G and Beyonds Network: Survey

IEEE Access

... The development of OMT solvers spans a variety of theories, such as linear real / integer arithmetic (Sebastiani and Tomasi 2012;Bjørner, Phan, and Fleckenstein 2015;Sebastiani and Trentin 2015;He et al. 2024), bit vectors (Nadel and Ryvchin 2016;Trentin and Sebastiani 2021), and floating point arithmetic (Trentin and Sebastiani 2019). It has numerous applications such as program verification (Liu et al. 2017;Karpenkov 2017;Ratschan 2017), system safety analysis (Bertolissi, dos Santos, and Ranise 2018;Paoletti et al. 2019;Wang et al. 2021;Erata et al. 2023), software analysis and testing (Zhang 2000;Zhang, Ma, and Zhang 2012;Zhang et al. 2014;Henry et al. 2014;Karpenkov, Friedberger, and Beyer 2016;Jiang et al. 2017;Yao et al. 2021), planning (Roselli, Bengtsson, andÅkesson 2018;Yan et al. 2019;Leofante et al. 2019;Marchetto et al. 2021;Jin et al. 2021;Leofante 2023) and machine learning (Teso, Sebastiani, and Passerini 2017;Sivaraman et al. 2020;Huang et al. 2022Huang et al. , 2024. This paper focuses on OMT(NRA) problems. ...

A Formal Approach to Verify Connectivity and Optimize VNF Placement in Industrial Networks
  • Citing Article
  • June 2020

IEEE Transactions on Industrial Informatics

... The 6TiSCH architecture is crucial for the IIoT, ensuring reliable communication through effective cell allocation to prevent packet loss in high-traffic areas. In factories, field devices and sensors require high reliability and timely information exchange [7]. Efficient cell allocation based on node position directly influences network performance and power consumption [8]. ...

IEEE TCCN Special Section Editorial: Intelligent Resource Management for 5G and Beyond
  • Citing Article
  • June 2020

IEEE Transactions on Cognitive Communications and Networking

... The private network is constructed by defining the combination of network functional components to cater to diverse medical application scenarios [16]. This approach offers enhanced ubiquitous access, increased flexibility in control and forwarding, and greater network openness for medical institutions [15,17]. Considering the various scenarios of intrahospital, interhospital, and out-of-hospital medical services, the 5G network can be categorized into medical-exclusive and preferential channels, as well as ordinary user channels ( Figure 1). ...

5G-Slicing-Enabled Scalable SDN Core Network: Toward an Ultra-Low Latency of Autonomous Driving Service
  • Citing Article
  • July 2019

IEEE Journal on Selected Areas in Communications

... In a VANET setup, vehicles utilize onboard units (OBUs), roadside units (RSUs), and a trusted authority (TA). The TA, an external device, registers RSUs, authenticates vehicles, and monitors the network via RSUs [72,73]. RSUs, stationed along the roadside and utilizing wireless technologies like WiFi, act as intermediaries between the TA and vehicle OBUs, conveying safety instructions to nearby vehicles. ...

Named Data Networking in Vehicular Ad Hoc Networks: State-of-the-Art and Challenges
  • Citing Article
  • March 2020

IEEE Communications Surveys & Tutorials

... In [44], the optimal allocation of radio resources for eMBB and URLLC slices was studied in the network scenario excluding the Xhaul transport domain. In [45], slice-aware optimization of the DU and CU placement was addressed, assuming fixed propagation latencies in the transport network. In [46], a MILP model was proposed for the problem of the joint selection of the optimal functional split and the routing path, between the connected user equipment to the CU while satisfying each service's SLAs. ...

Multi-Objective Function Splitting and Placement of Network Slices in 5G Mobile Networks
  • Citing Conference Paper
  • October 2018

... The main aspect of open-source-MEC is the service-oriented MEC layer (Brik et al., 2020), which contains a uniform south-bound functionality interface and varied network functions, with the south-bound functionality interface connecting different network functions jointly based on the uniform stateless hypertext transmission protocol (HTTP) to ensure that they may interact directly with one another if needed. The work also presented the detached centralized service functionalities into distinct (Huang et al., 2017(Huang et al., , 2022aLv et al., 2018). After that, to improve open-source MEC, the work grabbed numerous more network functions from the 5G core network control plane and constructed several new network functions. ...

Low latency MEC framework for SDN-based LTE/LTE-A networks
  • Citing Conference Paper
  • May 2017