Distributed RIS-Enhanced Cell-Free NOMA Networks
Authors:
- 4 December 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 106-111
Abstract
Cell-free network is recognized as a novel networking architecture that allows multiple access points (APs) to provide collaborative signal processing for distributed user equipments (UEs). An important feature of cell-free networks is that the restriction of cell boundaries is removed to alleviate the coverage issue of cell-edge users. However, an intractable problem is that the line-of-sight (LoS) links between the AP and cell-edge users are likely to be blocked by high-rise buildings in the urban city. To address this issue, one promising solution to combat the unfavorable wireless propagation environment is the use of reconfigurable intelligent surfaces (RISs) for providing virtual LoS links between the AP and UEs. In order to maximize the energy efficiency of cell-free networks, the transmit beamforming should be designed carefully to eliminate inter-user interference and reduce the power consumed by transmitting per bit. In this paper, a long-term energy efficiency maximization problem is formulated by jointly optimizing the transceiver design and RIS deployment. Consider the uncertainty of wireless environments and the requirement of real-time control, a novel hybrid deep deterministic policy gradient (DDPG)-based algorithm is proposed, where a multi-agent DDPG framework is adopted for robustness enhancement. Simulation results verify the effectiveness of the proposed DDPG-based algorithm, and show the performance improvement brought by the deployment of multiple RISs in cell-free networks.Keywords
Funding Information
- Natural Science Foundation of Shandong Province
This publication has 11 references indexed in Scilit:
- STAR-RIS Integrated Nonorthogonal Multiple Access and Over-the-Air Federated Learning: Framework, Analysis, and OptimizationIEEE Internet of Things Journal, 2022
- Integrating Over-the-Air Federated Learning and Non-Orthogonal Multiple Access: What Role Can RIS Play?IEEE Transactions on Wireless Communications, 2022
- Federated Learning in Multi-RIS-Aided SystemsIEEE Internet of Things Journal, 2021
- Deep Reinforcement Learning for Energy-Efficient Beamforming Design in Cell-Free Networks2021
- Beyond Cell-Free MIMO: Energy Efficient Reconfigurable Intelligent Surface Aided Cell-Free MIMO CommunicationsIEEE Transactions on Cognitive Communications and Networking, 2021
- Resource Allocation for Multi-Cell IRS-Aided NOMA NetworksIEEE Transactions on Wireless Communications, 2021
- RIS Enhanced Massive Non-Orthogonal Multiple Access Networks: Deployment and Passive Beamforming DesignIEEE Journal on Selected Areas in Communications, 2020
- Reconfigurable Intelligent Surface Assisted Multiuser MISO Systems Exploiting Deep Reinforcement LearningIEEE Journal on Selected Areas in Communications, 2020
- Max–Min Rate of Cell-Free Massive MIMO Uplink With Optimal Uniform QuantizationIEEE Transactions on Communications, 2019
- Cell-Free Massive MIMO Versus Small CellsIEEE Transactions on Wireless Communications, 2017