Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Cooperative Deep Reinforcement Learning for Fair RIS Allocation

Martin Mark Zan, Stefan Schwarz

Abstract

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.

Cooperative Deep Reinforcement Learning for Fair RIS Allocation

Abstract

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.

Paper Structure

This paper contains 27 sections, 38 equations, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. System Model
  3. Channel Model
  4. Beamforming Model
  5. Signal Model
  6. SINR Model
  7. SINR and Utility Estimation
  8. Macroscopic SINR Estimation
  9. Signal Power Estimation
  10. Interference Power Estimation
  11. Utility Function
  12. Auction Format
  13. Bidding Strategies
  14. Marginal Utility Value Estimation
  15. Normalization and Standardization
  16. ...and 12 more sections

Figures (5)

  • Figure 1: Convergence of the episodic reward (left axis) and total auction cost (right axis) during training. Solid lines represent moving-average smoothed curves (window size=5), while semi-transparent lines show the raw data.
  • Figure 2: Representative network realization for $\gamma = 0.2$, showing the locations of the two base stations, users, allocated RISs, and unassigned RISs.
  • Figure 3: Trade-off between sum rate and the minimum user rate of the overloaded base station (BS0). Each point corresponds to a model with a different value of the fairness strength $\gamma$.
  • Figure 4: Atkinson inequality index as a function of the fairness strength $\gamma$ for different values of the sensitivity parameter $\epsilon$, which controls the emphasis on low-rate users.
  • Figure 5: Increasing $\gamma$ shifts RIS resources from BS1 to the overloaded BS0, while also decreasing the number of unallocated RISs due to more aggressive bidding behavior.