Sihem Bakri
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Sihem Bakri has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
Adlen Ksentini
Communication systems EURECOM Biot France
1 shared publication- Adlen Ksentini
Eurecom, France
1 shared publication - Bouziane Brik
Computer Science Department, College of Computing and Informatics, University of Sharjah, Sharjah, UAE
1 shared publication - Charalampos Kalalas
Sustainable AI Research Unit, Centre Tecnolgic de Telecomunicacions de Catalunya (CTTC/CERCA), Barcelona, Spain
1 shared publication - Constantinos B. Papadias
Smart Wireless Future Technologies (SWiFT) Lab, Research, Technology and Innovation Network (RTIN), The American College of Greece, Athens, Greece
1 shared publication - Daniel Gutierrez-Rojas
Department of Electrical Engineering, LappeenrantaLahti University of Technology, Lappeenranta, Finland
1 shared publication
Latest Publications
- 6 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Towards enforcing network slicing in 5G networks
Vers l'application du découpage du réseau dans les réseaux 5G: Les architectures de réseaux sans fil actuelles, de type « une taille pour tous », ne peuvent pas prendre en charge ces critères de services hétérogènes de nouvelle génération 5G. Par conséquent, la recherche autour de la 5G vise à fournir des architectures et des mécanismes plus adéquats pour répondre à ce besoin. L'architecture 5G est conçue pour répondre aux exigences variées et contradictoires des services, en termes de latence, de bande passante et de fiabilité, qui ne peuvent être assurées par la même infrastructure du réseau. Dans ce contexte, le découpage du réseau fourni par la virtualisation du réseau permet de diviser l'infrastructure en différentes tranches, chaque tranche est adaptée aux besoins spécifiques des services, où elle permet à différents services (comme l'automobile, l'Internet des objets...) d'être fournis par différentes instances de la tranche du réseau. Les chercheurs ont défini trois grandes classes de services de découpage en réseau, qui sont: enhanced Mobile BroadBand (eMBB), massive Machine Type Communication (mMTC), and ultra-Reliable and Low-Latency Communication (uRLLC). L'un des principaux défis du déploiement des tranches de réseau est le découpage du réseau d'accès radio (RAN). En effet, la gestion des ressources RAN et leur partage entre les tranches de réseau est une tâche particulièrement difficile. Cette thèse propose des solutions qui visent à améliorer les performances du réseau et d'introduire de la flexibilité et une plus grande utilisation des ressources du réseau, en fournissant de manière précise et dynamique aux tranches de réseau activées les quantités de ressources appropriées pour répondre à leurs divers besoins.
- 6 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Towards enforcing network slicing in 5G networks
Vers l'application du découpage du réseau dans les réseaux 5G: Les architectures de réseaux sans fil actuelles, de type « une taille pour tous », ne peuvent pas prendre en charge ces critères de services hétérogènes de nouvelle génération 5G. Par conséquent, la recherche autour de la 5G vise à fournir des architectures et des mécanismes plus adéquats pour répondre à ce besoin. L'architecture 5G est conçue pour répondre aux exigences variées et contradictoires des services, en termes de latence, de bande passante et de fiabilité, qui ne peuvent être assurées par la même infrastructure du réseau. Dans ce contexte, le découpage du réseau fourni par la virtualisation du réseau permet de diviser l'infrastructure en différentes tranches, chaque tranche est adaptée aux besoins spécifiques des services, où elle permet à différents services (comme l'automobile, l'Internet des objets...) d'être fournis par différentes instances de la tranche du réseau. Les chercheurs ont défini trois grandes classes de services de découpage en réseau, qui sont: enhanced Mobile BroadBand (eMBB), massive Machine Type Communication (mMTC), and ultra-Reliable and Low-Latency Communication (uRLLC). L'un des principaux défis du déploiement des tranches de réseau est le découpage du réseau d'accès radio (RAN). En effet, la gestion des ressources RAN et leur partage entre les tranches de réseau est une tâche particulièrement difficile. Cette thèse propose des solutions qui visent à améliorer les performances du réseau et d'introduire de la flexibilité et une plus grande utilisation des ressources du réseau, en fournissant de manière précise et dynamique aux tranches de réseau activées les quantités de ressources appropriées pour répondre à leurs divers besoins.
- Open Access
- 30 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (4) , 7193-7204
Detection and Classification of Anomalies in WSN-Enabled Cyber-Physical Systems
Detection and classification of anomalies in industrial applications has long been a focus of interest in the research community. The integration of computational and physical systems has increased the complexity of interactions between processes, leading to vulnerabilities in both the physical and cyber layers. This work presents a model structure for anomaly detection in Internet of Things (IoT)-enabled industrial Cyber-Physical Systems (CPSs), enabled by Wireless Sensor Networks (WSNs). The model comprises three primary data blocks in the cyber layer: sensor-based data acquisition, data fusion to convert raw data into useful information, and analytics for decision-making. The rationale behind these blocks highlights the critical role of anomaly detection and is demonstrated through three use cases, namely fault selection in power grids, anomaly detection in an industrial chemical process, and prediction of the CO 2 level in a room. Furthermore, we integrate Explainable AI (XAI) algorithms into an IoT-based system to enhance error detection and correction, while fostering user engagement by offering useful insights into the decision-making process. Our numerical results demonstrate high accuracy in anomaly detection across these scenarios, significantly improving system reliability and enabling timely interventions, which could ultimately reduce operational risks.
- 30 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (4) , 7193-7204
Open AccessDetection and Classification of Anomalies in WSN-Enabled Cyber-Physical Systems
Detection and classification of anomalies in industrial applications has long been a focus of interest in the research community. The integration of computational and physical systems has increased the complexity of interactions between processes, leading to vulnerabilities in both the physical and cyber layers. This work presents a model structure for anomaly detection in Internet of Things (IoT)-enabled industrial Cyber-Physical Systems (CPSs), enabled by Wireless Sensor Networks (WSNs). The model comprises three primary data blocks in the cyber layer: sensor-based data acquisition, data fusion to convert raw data into useful information, and analytics for decision-making. The rationale behind these blocks highlights the critical role of anomaly detection and is demonstrated through three use cases, namely fault selection in power grids, anomaly detection in an industrial chemical process, and prediction of the CO 2 level in a room. Furthermore, we integrate Explainable AI (XAI) algorithms into an IoT-based system to enhance error detection and correction, while fostering user engagement by offering useful insights into the decision-making process. Our numerical results demonstrate high accuracy in anomaly detection across these scenarios, significantly improving system reliability and enabling timely interventions, which could ultimately reduce operational risks.
- 19 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 18 (4) , 4654-4668
Data-Driven RAN Slicing Mechanisms for 5G and Beyond
One of the main challenges when it comes to deploying Network Slices is slicing the Radio Access Network (RAN). Indeed, managing RAN resources and sharing them among network slices is an increasingly difficult task, which needs to be properly designed. The goal is to improve network performance and introduce flexibility and greater utilization of network resources by accurately and dynamically provisioning the activated network slices with the appropriate amounts of resources to meet their diverse requirements. In this paper, we propose a data-driven RAN slicing mechanism based on a resource sharing algorithm running at the Slice Orchestrator (SO) level. This algorithm computes the necessary radio resources to be used by each deployed network slice. These resources are adjusted periodically based on current estimates of achievable throughput performance derived from channel quality information, and in particular from the Channel Quality Indicator (CQI) values of the users of each network slice retrieved from the RAN. CQI information is reported to base stations by the User Equipment (UE) following standard procedures, but extracting and frequently reporting it from base stations to the SO may result in significant communication overhead. To mitigate this overhead while maintaining at the SO level an accurate view of UE channel qualities, we propose a machine learning approach to infer the stability of UE channel conditions, as well as predictive schemes to reduce the CQI reporting intensity based on the inferred channel status. Through extensive simulations, we demonstrate the efficiency of our data-driven RAN slicing framework, which allows to meet the stringent requirements of two main classes of network slices in 5G, i.e., enhanced Mobile Broadband (eMBB) and Ultra-Reliable and Low-Latency Communication (URLLC).
- 19 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 18 (4) , 4654-4668
Data-Driven RAN Slicing Mechanisms for 5G and Beyond
One of the main challenges when it comes to deploying Network Slices is slicing the Radio Access Network (RAN). Indeed, managing RAN resources and sharing them among network slices is an increasingly difficult task, which needs to be properly designed. The goal is to improve network performance and introduce flexibility and greater utilization of network resources by accurately and dynamically provisioning the activated network slices with the appropriate amounts of resources to meet their diverse requirements. In this paper, we propose a data-driven RAN slicing mechanism based on a resource sharing algorithm running at the Slice Orchestrator (SO) level. This algorithm computes the necessary radio resources to be used by each deployed network slice. These resources are adjusted periodically based on current estimates of achievable throughput performance derived from channel quality information, and in particular from the Channel Quality Indicator (CQI) values of the users of each network slice retrieved from the RAN. CQI information is reported to base stations by the User Equipment (UE) following standard procedures, but extracting and frequently reporting it from base stations to the SO may result in significant communication overhead. To mitigate this overhead while maintaining at the SO level an accurate view of UE channel qualities, we propose a machine learning approach to infer the stability of UE channel conditions, as well as predictive schemes to reduce the CQI reporting intensity based on the inferred channel status. Through extensive simulations, we demonstrate the efficiency of our data-driven RAN slicing framework, which allows to meet the stringent requirements of two main classes of network slices in 5G, i.e., enhanced Mobile Broadband (eMBB) and Ultra-Reliable and Low-Latency Communication (URLLC).
- 21 February 2021
- Published by Wiley in International Journal of Communication Systems
- Vol. 34 (7) , e4757
On using reinforcement learning for network slice admission control in 5G: Offline vs. online
Summary: Achieving a fair usage of network resources is of vital importance in Slice‐ready 5G network. The dilemma of which network slice to accept or to reject is very challenging for the Infrastructure Provider (InfProv). On one hand, InfProv aims to maximize the network resources usage by accepting as many network slices as possible; on the other hand, the network resources are limited, and the network slice requirements regarding Quality of Service (QoS) need to be fulfilled. In this paper, we devise three admission control mechanisms based on Reinforcement Learning, namely, Q‐Learning, Deep Q‐Learning, and Regret Matching, which allow deriving admission control decisions (policy) to be applied by InfProv to admit or reject network slice requests. We evaluated the three algorithms using computer simulation, showing results on each mechanism's performance in terms of maximizing the InfProv revenue and their ability to learn offline or online.
- 21 February 2021
- Published by Wiley in International Journal of Communication Systems
- Vol. 34 (7) , e4757
On using reinforcement learning for network slice admission control in 5G: Offline vs. online
Summary: Achieving a fair usage of network resources is of vital importance in Slice‐ready 5G network. The dilemma of which network slice to accept or to reject is very challenging for the Infrastructure Provider (InfProv). On one hand, InfProv aims to maximize the network resources usage by accepting as many network slices as possible; on the other hand, the network resources are limited, and the network slice requirements regarding Quality of Service (QoS) need to be fulfilled. In this paper, we devise three admission control mechanisms based on Reinforcement Learning, namely, Q‐Learning, Deep Q‐Learning, and Regret Matching, which allow deriving admission control decisions (policy) to be applied by InfProv to admit or reject network slice requests. We evaluated the three algorithms using computer simulation, showing results on each mechanism's performance in terms of maximizing the InfProv revenue and their ability to learn offline or online.