Cooperative Deep Reinforcement Learning for Fair RIS Allocation
This addresses fairness in resource allocation for future wireless networks, but it is incremental as it builds on existing auction and reinforcement learning methods.
The paper tackles the problem of dynamically allocating reconfigurable intelligent surfaces (RISs) among base stations in multi-cell wireless networks to address performance imbalances, using a fairness-aware collaborative multi-agent reinforcement learning approach that improves the rates of the worst-served users while preserving overall throughput.
The deployment of reconfigurable intelligent surfaces (RISs) introduces new challenges for resource allocation in multi-cell wireless networks, particularly when user loads are uneven across base stations. In this work, we consider RISs as shared infrastructure that must be dynamically assigned among competing base stations, and we address this problem using a simultaneous ascending auction mechanism. To mitigate performance imbalances between cells, we propose a fairness-aware collaborative multi-agent reinforcement learning approach in which base stations adapt their bidding strategies based on both expected utility gains and relative service quality. A centrally computed performance-dependent fairness indicator is incorporated into the agents' observations, enabling implicit coordination without direct inter-base-station communication. Simulation results show that the proposed framework effectively redistributes RIS resources toward weaker-performing cells, substantially improving the rates of the worst-served users while preserving overall throughput. The results demonstrate that fairness-oriented RIS allocation can be achieved through cooperative learning, providing a flexible tool for balancing efficiency and equity in future wireless networks.