Federated reinforcement learning for scheduling-offloading policies in multi-cluster NOMA systems

Guardado en:
Detalles Bibliográficos
Publicado en:EURASIP Journal on Advances in Signal Processing vol. 2025, no. 1 (Dec 2025), p. 37
Autor principal: Djemai, Ibrahim
Otros Autores: Sarkiss, Mireille, Ciblat, Philippe
Publicado:
Springer Nature B.V.
Materias:
Acceso en línea:Citation/Abstract
Full Text
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!

MARC

LEADER 00000nab a2200000uu 4500
001 3244968086
003 UK-CbPIL
022 |a 1687-6172 
022 |a 1687-6180 
024 7 |a 10.1186/s13634-025-01242-7  |2 doi 
035 |a 3244968086 
045 2 |b d20251201  |b d20251231 
084 |a 130316  |2 nlm 
100 1 |a Djemai, Ibrahim  |u Télécom SudParis, Institut Polytechnique de Paris, SAMOVAR, Palaiseau, France (GRID:grid.508893.f) 
245 1 |a Federated reinforcement learning for scheduling-offloading policies in multi-cluster NOMA systems 
260 |b Springer Nature B.V.  |c Dec 2025 
513 |a Journal Article 
520 3 |a Intelligent scheduling and resource allocation of user equipments (UEs) in wireless networks has been an ongoing topic of research. The innovation in this field focuses mostly on generalizing the system to include more components, as well as deriving new ways to solve the problem. We address in this paper an unexplored case of the scheduling-offloading problem for a wireless network with mobile edge computing (MEC). In this network, the UEs have mobility models and are transmitting using non-orthogonal multiple access (NOMA). They are also equipped with data buffers and batteries with energy harvesting (EH) capabilities. We propose a novel UEs clustering approach to account for the growing NOMA inter-user interference, which can lead to performance issues especially in the downlink decoding phase. In addition, clustering can help reduce the problem complexity by distributing it among the clusters that operate independently. We investigate deep reinforcement learning (DRL) to devise efficient policies that minimize the packet loss due to delay infringements. Moreover, we use federated learning (FL) to learn a unified policy accounting for the dynamic nature of clusters. Our simulation results based on DRL method, namely the proximal policy optimization (PPO), and standard methods, show the effectiveness of using learning-based algorithms in terms of minimizing the packet loss and the energy consumption. 
653 |a Energy harvesting 
653 |a Wireless networks 
653 |a Deep learning 
653 |a Decoding 
653 |a Bandwidths 
653 |a Optimization 
653 |a Edge computing 
653 |a Resource allocation 
653 |a Mobile computing 
653 |a Energy 
653 |a Spectrum allocation 
653 |a Machine learning 
653 |a Internet of Things 
653 |a Policies 
653 |a Scheduling 
653 |a Digital twins 
653 |a Clustering 
653 |a Decision making 
653 |a Computation offloading 
653 |a Medical equipment 
653 |a Algorithms 
653 |a Federated learning 
653 |a Energy consumption 
653 |a Markov analysis 
653 |a Nonorthogonal multiple access 
700 1 |a Sarkiss, Mireille  |u Télécom SudParis, Institut Polytechnique de Paris, SAMOVAR, Palaiseau, France (GRID:grid.508893.f) 
700 1 |a Ciblat, Philippe  |u Télécom Paris, Institut Polytechnique de Paris, LTCI, Palaiseau, France (GRID:grid.508893.f) 
773 0 |t EURASIP Journal on Advances in Signal Processing  |g vol. 2025, no. 1 (Dec 2025), p. 37 
786 0 |d ProQuest  |t Advanced Technologies & Aerospace Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3244968086/abstract/embedded/ZKJTFFSVAI7CB62C?source=fedsrch 
856 4 0 |3 Full Text  |u https://www.proquest.com/docview/3244968086/fulltext/embedded/ZKJTFFSVAI7CB62C?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3244968086/fulltextPDF/embedded/ZKJTFFSVAI7CB62C?source=fedsrch