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

2025-11-30

AI Summary

Resource allocation in multi-cell cellular networks faces challenges due to complex, conflicting utility functions that are only accessible via costly black-box evaluations. Method: We formulate inter-base-station power allocation under spectrum sharing as a non-cooperative game and propose PPR-UCB—a novel algorithm integrating Gaussian process regression with martingale theory to construct tight confidence upper bounds for efficient black-box utility approximation and uncertainty quantification. Contribution/Results: Compared to standard Bayesian optimization, PPR-UCB drastically reduces sample complexity, achieving stable convergence to high-quality pure Nash equilibria with only a few utility evaluations in multi-cell, multi-antenna systems. It simultaneously ensures optimization efficiency and system stability, establishing a new paradigm for black-box game-theoretic optimization.

Technology Category

• Reasoning under Uncertainty: Stochastic Optimization
• Search and Optimization: Sampling/Simulation-based Search
• Game Theory and Economic Paradigms: Cooperative Game Theory

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

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.

Problem

• Optimizing conflicting utility functions in cellular networks
• Finding stable Nash equilibrium via black-box evaluations
• Efficiently allocating radio resources with limited data samples

Innovation

• Bayesian optimization learns sequential decisions for Nash equilibrium
• Martingale techniques enhance Gaussian process surrogate confidence bounds
• Algorithm identifies equilibrium solutions with few data samples