Journal articles, conference papers and my Ph.D. thesis on full-duplex wireless, LoRaWAN, machine learning for networks, game theory and edge computing.Articles de revue, communications et thèse de doctorat sur le full-duplex, LoRaWAN, l'apprentissage automatique pour les réseaux, la théorie des jeux et l'edge computing.
Computational offloading is a pivotal solution to several Internet of Things (IoT) issues as it helps subdue the constrained nature of IoT devices. By harnessing the large capacity at the Edge, IoT devices with limited battery and storage can delegate certain tasks, especially those related to Machine Learning. Because of their restricted capacity, such devices can only store a limited amount of data as a training set for their learning, leading to a faulty prediction with high error rate. To tackle that issue, IoT devices can federate the learning process with other devices while the Edge server acts as an aggregator. However, selecting the appropriate Edge is a significant challenge. In fact, although learning collectively can reduce the prediction error,...
@inproceedings{khawam2024edge,
title = {Edge Selection Non-Cooperative Game in IoT Edge Computing},
author = {Kinda Khawam and Hussein Taleb and Hassan Fawaz and Samer Lahoud and Dominique Quadri and Steven Martin},
booktitle = {IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)},
year = {2024},
url = {https://ieeexplore.ieee.org/document/10817426}
}
Computational offloading is an efficient way to help constrained IoT devices by performing heavy tasks on Edge servers, especially tasks related to Machine Learning. Moreover, due to their limited learning capacity and memory size, such devices can only store a limited amount of data as a training set for their learning. Consequently, learning prediction is bound to be smeared with relatively high error. To mend that issue, IoT devices can federate the learning process with their pairs via an Edge server. However, offloading repeatedly the learning model through a wireless access network is time consuming. Hence, although learning collectively can reduce the learned model variance, it inflicts a communication cost depending on the selected Edge server. Therefore, in this paper,...
@inproceedings{khawam2024noncooperative,
title = {Non-Cooperative Edge Server Selection Game for Federated Learning in IoT},
author = {Kinda Khawam and Hussein Taleb and Samer Lahoud and Hassan Fawaz and Dominique Quadri and Steven Martin},
booktitle = {IEEE Network Operations and Management Symposium (NOMS 2024)},
year = {2024},
url = {https://ieeexplore.ieee.org/document/10575406}
}
In this paper, we aim to tackle the challenges of resource block scheduling and power allocation in the context of multi-cell full-duplex wireless networks. This is a more realistic setting than the single cell scenario, and it better envisions how full-duplex wireless communications could eventually be implemented. We propose an optimal queue-aware joint scheduling and power allocation algorithm for full-duplex wireless networks in a multi-cell scenario. Because of its mathematical intractability, we decouple the problem and solve it for scheduling first, and for power allocation second. We consider both indoor and outdoor scenarios and show that the gains of multi-cell full-duplex wireless networks, with respect to their half-duplex counterparts, are not always prevalent. Furthermore, we highlight the importance of inter-cell...
@article{fawaz2023queueaware,
title = {Queue-Aware Resource Allocation in Full-Duplex Multi-Cellular Wireless Networks},
author = {Hassan Fawaz and Samer Lahoud and Melhem El Helou and Kinda Khawam},
journal = {IEEE Journal on Selected Areas in Communications (JSAC)},
year = {2023},
url = {https://ieeexplore.ieee.org/document/10158674}
}
In this paper, we propose a graph convolutional deep reinforcement learning framework for both smart load balancing and queuing agents in a collaborative environment. We aim to balance traffic loads on different paths, and then control how packets belonging to different flow classes are dequeued at network nodes. Our objective is twofold: first to improve general network performance in terms of throughput and end-to-end delay, and second, to ensure meeting stringent service level agreements for a set of classified network flows. Our proposals use attention mechanisms to extract relevant features from local observations and neighborhood policies to limit the overhead of inter-agent communications. We assess our algorithms in a Mininet testbed and show that they outperform classic approaches to load...
@inproceedings{fawaz2023graph,
title = {Graph Convolutional Reinforcement Learning for Load Balancing and Smart Queuing},
author = {Hassan Fawaz and Omar Houidi and Djamal Zeghlache and Julien Lesca and Pham Tran Anh Quang and Jérémie Leguay and Paolo Medagliani},
booktitle = {IFIP Networking Conference (IFIP Networking)},
year = {2023},
url = {https://ieeexplore.ieee.org/document/10186430}
}
This paper explores the use of multi-agent deep learning as well as learning to cooperate principles to meet strict service level agreements, in terms of throughput and end-to- end delay, for a set of classified network flows. We consider agents built on top of a weighted fair queuing algorithm that continuously set weights for three flow groups: gold, silver, and bronze. We rely on a novel graph-convolution based, multi-agent reinforcement learning approach known as DGN. As bench- marks, we propose centralized and distributed deep Q-network algorithms and evaluate their performances in different network, traffic, and routing scenarios, highlighting both the effectiveness of our proposals and the importance of agent cooperation. We show that our DGN-based approach meets stringent throughput and...
@article{fawaz2023graph,
title = {Graph Convolutional Reinforcement Learning for Collaborative Queuing Agents},
author = {Hassan Fawaz and Julien Lesca and Pham Tran Anh Quang and Jérémie Leguay and Djamal Zeghlache and Paolo Medagliani},
journal = {IEEE Transactions on Network and Service Management (IEEE TNSM)},
year = {2023},
doi = {10.1109/TNSM.2022.3226605},
url = {https://ieeexplore.ieee.org/document/9969933}
}
With over 75 billion Internet of Things (IoT) devices expected worldwide by the year 2025, inaugural MAC layer solutions for long-range IoT deployments no longer suffice. LoRaWAN, the principal technology for comprehensive IoT deployments, enables low power and long range communications. However, synchronous transmissions on the same spreading factors and within the same frequency channel, augmented by the necessary clustering of IoT devices, will cause collisions and drops in efficiency. The performance is further impacted by the shortage of radio resources and by multiple operators utilizing the same unlicensed frequency bands. In this paper, we propose a game theoretic based channel selection algorithm for LoRaWAN in a multi-operator deployment scenario. We begin by proposing an optimal formulation for the selection...
@article{khawam2022a,
title = {A channel selection game for multi-operator LoRaWAN deployments},
author = {Kinda Khawam and Hassan Fawaz and Samer Lahoud and Odalric-Ambrym Maillard and Steven Martin},
journal = {Elsevier Computer Networks},
year = {2022},
url = {https://www.sciencedirect.com/science/article/pii/S1389128622002821}
}
With the goal of meeting the stringent throughput and delay requirements of classified network flows, we propose a Deep Q-learning Network (DQN) for optimal weight selection in an active queue management system based on Weighted Fair Queuing (WFQ). Our system schedules flows belonging to different priority classes (Gold, Silver, and Bronze) into separate queues, and learns how and when to dequeue from each queue. The neural network implements deep reinforcement learning tools such as target networks and replay buffers to help learn the best weights depending on the network state. We show, via simulations, that our algorithm converges to an efficient model capable of adapting to the flow demands, producing thus lower delays with respect to traditional WFQ.
@inproceedings{fawaz2021deep,
title = {Deep reinforcement learning for smart queue management},
author = {Hassan Fawaz and Djamal Zeghlache and Pham Tran Anh Quang and Jérémie Leguay and Paolo Medagliani},
booktitle = {NetSys 2021, MaLeNe Workshop},
year = {2021},
url = {https://hal.science/hal-03546621}
}
Full-duplex communications promise to double the throughput of a wireless network, so long as the resulting interferences can be combated. Nonetheless, already dealing with the intricacy of determining base station-to-user radio channels, full duplex wireless networks need additional information on the channels in between all the user equipment. This information is necessary to determine user radio conditions, and thereafter efficiently allocate resources. A signaling overhead is likely to burden the user equipment, which already lack any methods to estimate and convey such user-to-user channel states. In this paper, we aim to circumvent the complexities and requirements of traditional scheduling techniques by introducing a reinforcement learning based scheduling algorithm for full-duplex wireless networks. This scheduling approach does not need to estimate...
@article{fawaz2021a,
title = {A reinforcement learning approach to queue-aware scheduling in full-duplex wireless networks},
author = {Hassan Fawaz and Melhem El Helou and Samer Lahoud and Kinda Khawam},
journal = {Elsevier Computer Networks},
year = {2021},
doi = {10.1016/j.comnet.2021.107893},
url = {https://www.sciencedirect.com/science/article/pii/S1389128621000578}
}
Faced with the limitations of the Aloha random access scheme and spread spectrum techniques, LoRaWAN is yet to realize its potential as the flagship technology for large-scale Internet-of-Things applications. LoRaWAN allows for low power and long range communications. Nonetheless, concurrent transmissions on the same spreading factors (SFs), increased with the inevitable densification of device deployment, will lead to collisions and degradation in performance. The problem is further amplified due to the shortage in radio resources, with multiple operators utilizing the same unlicensed frequency bands. In this article, we investigate different interoperator cooperation schemes and devise multiple algorithms for SF assignment in a multioperator LoRaWAN deployment scenario. We start by proposing a proportional fair optimal formulation for the assignment with the...
@article{fawaz2020cooperation,
title = {Cooperation for Spreading Factor Assignment in a Multioperator LoRaWAN Deployment},
author = {Hassan Fawaz and Kinda Khawam and Samer Lahoud and Steven Martin and Melhem El Helou},
journal = {IEEE Internet of Things Journal},
year = {2020},
doi = {10.1109/JIOT.2020.3031681},
url = {https://ieeexplore.ieee.org/document/9226528}
}
Contemporary progress in telecommunication technologies have made full-duplex wireless communications feasible. The latter promise to double the capacity of wireless networks by allowing devices to concurrently transmit and receive on the same radio resources. In this paper, we devise mathematical optimal formulations for scheduling in full-duplex and hybrid full-duplex/half-duplex orthogonal frequency division multiple access networks. Our optimal models are queue-aware and address the new interferences that arise from working with full-duplex wireless networks: self-interference and intra-cell co-channel interference. We apply these models with different scheduling objectives, tackling issues such as signal-to-interference-plus-noise ratio (SINR) maximization and user fairness. Accordingly, we first propose an optimal full-duplex Max-SINR algorithm and an optimal full-duplex Proportional Fair algorithm. Additionally, and since full-duplex communications may not...
@article{fawaz2020queueaware,
title = {Queue-aware scheduling in full-duplex wireless networks},
author = {Hassan Fawaz and Samer Lahoud and Melhem El Helou},
journal = {Springer Wireless Networks},
year = {2020},
doi = {10.1007/s11276-020-02308-0},
url = {https://link.springer.com/article/10.1007/s11276-020-02308-0}
}
In this paper, we apply a game theoretic approach to power allocation in full-duplex orthogonal frequency division multiple access networks. Such networks exhibit a full-duplex base station, which allocates the same radio resources to a pair of half-duplex user equipment: one on the uplink, and one on the downlink. A theoretical doubling of the capacity is threatened by the interferences generated by full-duplex operation: self-interference and intra-cell co-channel interference. In our work, we propose three non-cooperative games aimed at tackling the intricate task of allocating power to scheduled pairs of user equipment, with objectives varying from improving user equipment performance to reducing power expenditure. The games have two sets of players: the users on the uplink, and the base station...
@article{fawaz2019a,
title = {A Game Theoretic Framework for Power Allocation in Full-Duplex Wireless Networks},
author = {Hassan Fawaz and Kinda Khawam and Samer Lahoud and Melhem El Helou},
journal = {IEEE Access},
year = {2019},
doi = {10.1109/ACCESS.2019.2957316},
url = {https://ieeexplore.ieee.org/document/8920029}
}
This is my Thesis Dissertation. My thesis work revolved around proposing scheduling and power allocation algorithms for full-duplex wireless networks. We utilized multiple tools such as optimization, heuristics, game theory, and machine learning and considered different scenarios from single-cell to multi-cell deployments.
@phdthesis{fawaz2019scheduling,
title = {Scheduling and Power Allocation in Full-Duplex Wireless Networks},
author = {Hassan Fawaz},
school = {Saint Joseph University of Beirut},
year = {2019},
url = {https://hal-usj.archives-ouvertes.fr/tel-03133975v1}
}
The benefits of full-duplex wireless communications, specifically with respect to their half-duplex counterparts, are now well under examination. As a result, research into the corresponding scheduling and power allocation algorithms has thrived. In this paper, we propose a non-cooperative game theoretic algorithm for power allocation in full-duplex orthogonal frequency division multiple access networks. The game is played between user equipment on the uplink, and the base station on the downlink. The objective of the game is two-fold: maximizing the signal-to-noise-plus-interference ratio, while hindering the harmful interferences resulting from full-duplex operation. We prove that our game is super-modular. For such a game, a best response algorithm is capable of attaining a Nash equilibrium. We simulate our proposal along with a fairness...
@inproceedings{fawaz2019a,
title = {A Game Theoretic Approach for Power Allocation in Full Duplex Wireless Networks},
author = {Hassan Fawaz and Kinda Khawam and Samer Lahoud and Melhem El Helou},
booktitle = {2019 IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)},
year = {2019},
url = {https://ieeexplore.ieee.org/document/8904134}
}
With the promise of doubling a wireless network’s capacity, researchers on full-duplex wireless networks need to address multiple issues such as user equipment pairing, power control, and the availability of channel state information. In this paper, we propose a discrete simulator for scheduling and power allocation proposals in full-duplex orthogonal frequency division multiple access networks. Our simulator is queue-aware and adaptable to different scheduling objectives. It enables varying the path-loss model, user distribution, noise conditions, and throughput demands. Additionally, it permits the calculation of packet level performance metrics such as the waiting delay.
@inproceedings{fawaz2018a,
title = {A Queue-Aware Discrete Scheduling Simulator for Full-Duplex OFDMA Wireless Networks},
author = {Hassan Fawaz and Samer Lahoud and Melhem El Helou},
booktitle = {International Conference on Computer and Applications (ICCA)},
year = {2018},
url = {https://ieeexplore.ieee.org/document/8460235}
}
While helping better utilize the system’s resources, full-duplex technologies have the ability to double the efficiency of wireless networks. However, these networks would suffer from added types of interferences, namely self-interference and intra-cell co-channel interference. As such, efficiently addressing scheduling and power allocation in full-duplex networks is vital. In this article, we formulate a queue-aware, fair scheduling and power allocation problem for full duplex orthogonal frequency division multiple access networks. Due to its intractability, we decompose this problem into two: a scheduling problem and a power allocation problem. We compare our proposal to the state-of-the-art, and show that it improves fairness among the user equipment at no cost in the system’s performance. Simulation results show a significant increase in throughput...
@inproceedings{fawaz2018queueaware,
title = {Queue-Aware Priority Based Scheduling and Power Allocation in Full-Duplex OFDMA Cellular Networks},
author = {Hassan Fawaz and Samer Lahoud and Melhem El Helou and Joe Saad},
booktitle = {2018 25th International Conference on Telecommunications (ICT)},
year = {2018},
url = {https://ieeexplore.ieee.org/document/8464919}
}
In this paper, we propose an optimal algorithm for scheduling in a full duplex Orthogonal Frequency Division Multiple Access network. This network exhibits a full-duplex base station that concurrently communicates with a pair of one uplink, and one downlink half duplex user equipment (UE). Our objective is to maximize the system’s sum-SINR i.e., the sum of the SINR values of all the UEs that are allocated resources. We formulate our optimal algorithm as an integer linear optimization problem. Our formulation of the problem has the originality of incorporating a non-full buffer traffic model. In order to deal with such type of traffic, we introduce a resource utilization factor along with additional constraints on the optimization. This factor helps tune the...
@inproceedings{fawaz2018optimal,
title = {Optimal Max-SINR scheduling in full-duplex OFDMA cellular networks with dynamic arrivals},
author = {Hassan Fawaz and Samer Lahoud and Melhem El Helou and Marc Ibrahim},
booktitle = {IFIP Wireless Days},
year = {2018},
url = {https://ieeexplore.ieee.org/document/8361720}
}
Scheduling in full-duplex networks is essential for efficiently managing resources, and for mitigating interference problems. However, this task is hindered by the lack of complete channel state information. Full duplex networks need information on the radio channel in between the user equipment that current wireless networks do not provide. In this paper, we propose two queue-aware optimal algorithms, one greedy and one fair, for scheduling in full duplex orthogonal frequency division multiple access networks. We propose heuristic alternatives for these algorithms, and show that they provide near optimal performance. With two different scheduling objectives at hand, we study the impact of imperfect channel state information on scheduling in full duplex networks.
@inproceedings{fawaz2018queueaware,
title = {Queue-Aware Scheduling in Full Duplex OFDMA Wireless Networks with Imperfect Channel State Information},
author = {Hassan Fawaz and Samer Lahoud and Melhem El Helou and Marc Ibrahim},
booktitle = {European Wireless 2018},
year = {2018},
url = {https://ieeexplore.ieee.org/document/8385522}
}
In Half-Duplex (HD) systems, at a given time instant, a radio resource is exclusively assigned to one User Equipment (UE) either for transmission or for reception. Full-Duplex (FD) networks promise to increase the system’s capacity by allocating resources simultaneously to two UEs: one uplink UE and one downlink UE. In order to enhance the network’s spectral efficiency, the system needs to deal with two major types of interference: self-interference and co-channel interference. This is one of the main challenges of scheduling in FD systems. In this article, we propose two algorithms for scheduling in FD Orthogonal Frequency Division Multiple Access Systems (FD-OFDMA). First, we propose an FD Maximum Signal-to-Interference-plus-Noise ratio (FD Max-SINR) algorithm, which allocates resources in FD depending on...
@inproceedings{fawaz2017maxsinr,
title = {Max-SINR scheduling in Full-Duplex OFDMA cellular networks with dynamic arrivals},
author = {Hassan Fawaz and Samer Lahoud and Melhem El Helou and Marc Ibrahim},
booktitle = {2017 IEEE Symposium on Computers and Communications (ISCC)},
year = {2017},
url = {https://ieeexplore.ieee.org/document/8024577}
}
No publication matches these filters.Aucune publication ne correspond à ces filtres.
Citation counts and the full list are on Google Scholar.Le nombre de citations et la liste complète sont sur Google Scholar.Preprints are provided for timely dissemination; copyright remains with the authors or publishers.Les versions auteur sont fournies pour une diffusion rapide ; les droits restent aux auteurs ou aux éditeurs.
Esc
↑↓ navigate↵ open/ or Ctrl K search
I use Google Analytics to see which pages are useful. No ads, no tracking without your OK.J'utilise Google Analytics pour savoir quelles pages sont utiles. Pas de publicité, aucun suivi sans votre accord.DetailsEn savoir plus