STAR-RISs Assisted NOMA Networks: A Distributed Learning Approach
- 1 January 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 17 (1) , 264-278
Abstract
A novel simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) aided downlink non-orthogonal multiple access (NOMA) communication framework is proposed. Two STAR-RIS protocols are investigated, namely the energy splitting (ES) and the mode switching (MS). However, since the STAR-RIS has a massive number of reconfigurable elements, the passive beamforming problem has enormous action dimensions and extremely high complexity, resulting in an increased training time and performance degradation for the artificial intelligent agent. To resolve this predicament, a partitioning approach is proposed to divide the STAR-RIS into several tiles. A distributed learning approach is conceived for the partitioning and the corresponding tile-based passive beamforming of each STAR-RIS, as well as the power allocation for users to maximize the average throughput achieved by multiple base stations. In particular, the deep reinforcement learning (DRL) agent is employed at each BS, and an access-free federated learning (AFFL) model, which gathers the features of federated learning (FL) and transfer learning (TL) is proposed to accelerate or even exempt the training process for agents. Simulation results indicate that 1) the ES protocol is preferred for being employed in the NOMA networks compared with the MS protocol; 2) the tile-based passive beamforming approach outperforms benchmarks while the STAR-RIS has a large size; 3) the proposed AFFL framework effectively reduces or exempts the training overhead.Keywords
Funding Information
- CHIST-ERA (SUNRISE CHIST-ERA-20-SICT-005)
- Engineering and Physical Sciences Research Council (EP/W035588/1)
- Royal Society (RGS\R1\221050, IEC\NSFC\201112)
- China Scholarship Council (201908610187)
This publication has 38 references indexed in Scilit:
- Capacity Characterization for Intelligent Reflecting Surface Aided MIMO CommunicationIEEE Journal on Selected Areas in Communications, 2020
- Power Control Based on Deep Reinforcement Learning for Spectrum SharingIEEE Transactions on Wireless Communications, 2020
- Reconfigurable Intelligent Surface-Based Index Modulation: A New Beyond MIMO Paradigm for 6GIEEE Transactions on Communications, 2020
- Wireless Communications Through Reconfigurable Intelligent SurfacesIEEE Access, 2019
- IoT Devices Recognition Through Network Traffic Analysis2018
- Energy-Efficient User Scheduling and Power Allocation for NOMA-Based Wireless Networks With Massive IoT DevicesIEEE Internet of Things Journal, 2018
- On the Optimality of Power Allocation for NOMA Downlinks With Individual QoS ConstraintsIEEE Communications Letters, 2017
- Enhancing the Physical Layer Security of Non-Orthogonal Multiple Access in Large-Scale NetworksIEEE Transactions on Wireless Communications, 2017
- Cooperative Non-orthogonal Multiple Access With Simultaneous Wireless Information and Power TransferIEEE Journal on Selected Areas in Communications, 2016
- Dynamic control of electromagnetic wave propagation with the equivalent principle inspired tunable metasurfaceScientific Reports, 2014