Bayesian Optimization for Non-Cooperative Game-Based Radio Resource Management

TL;DR

This paper introduces PPR-UCB, a Bayesian optimization method that efficiently finds stable resource allocation strategies in complex, black-box, multi-cell wireless networks modeled as non-cooperative games.

Contribution

It proposes a novel Bayesian optimization approach using Gaussian processes to approximate pure Nash equilibria in resource management games.

Findings

PPR-UCB effectively identifies equilibrium solutions with few samples.

The method outperforms baseline approaches in multi-cell power allocation.

Experiments validate the efficiency and accuracy of the proposed approach.

Abstract

Radio resource management in modern cellular networks often calls for the optimization of complex utility functions that are potentially conflicting between different base stations (BSs). Coordinating the resource allocation strategies efficiently across BSs to ensure stable network service poses significant challenges, especially when each utility is accessible only via costly, black-box evaluations. This paper considers formulating the resource allocation among spectrum sharing BSs as a non-cooperative game, with the goal of aligning their allocation incentives toward a stable outcome. To address this challenge, we propose PPR-UCB, a novel Bayesian optimization (BO) strategy that learns from sequential decision-evaluation pairs to approximate pure Nash equilibrium (PNE) solutions. PPR-UCB applies martingale techniques to Gaussian process (GP) surrogates and constructs high probability confidence bounds for utilities uncertainty quantification. Experiments on downlink transmission power allocation in a multi-cell multi-antenna system demonstrate the efficiency of PPR-UCB in identifying effective equilibrium solutions within a few data samples.