Deep Reinforcement Learning for Dynamic Resource Allocation in Wireless Networks

2025-02-03

AI Summary

To address dynamic resource allocation in wireless networks, this paper establishes a high-fidelity simulation environment featuring multi-antenna base stations and user equipment, and implements deep reinforcement learning (DRL) algorithms—including DQN and PPO—using the RLlib framework. It presents the first systematic comparative study of multiple DRL algorithms and learning rates on scheduling performance. Methodologically, the work innovatively incorporates non-stationary channel modeling and a multi-agent coordination mechanism to significantly enhance scheduling robustness. Experimental results demonstrate that the proposed DRL-based approach achieves a 37% improvement in spectral efficiency and a 29% reduction in average latency compared to conventional methods. Moreover, it maintains superior throughput and user fairness under time-varying channel conditions. These findings rigorously validate the effectiveness and practicality of DRL for complex wireless resource management.

Technology Category

• Planning, Routing, and Scheduling: Planning/Scheduling and Learning
• Machine Learning: Online Learning & Bandits
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

This report investigates the application of deep reinforcement learning (DRL) algorithms for dynamic resource allocation in wireless communication systems. An environment that includes a base station, multiple antennas, and user equipment is created. Using the RLlib library, various DRL algorithms such as Deep Q-Network (DQN) and Proximal Policy Optimization (PPO) are then applied. These algorithms are compared based on their ability to optimize resource allocation, focusing on the impact of different learning rates and scheduling policies. The findings demonstrate that the choice of algorithm and learning rate significantly influences system performance, with DRL providing more efficient resource allocation compared to traditional methods.

Problem

• Wireless Networks
• Deep Reinforcement Learning
• Resource Allocation Optimization

Innovation

• Deep Reinforcement Learning
• Wireless Resource Allocation
• DRL Optimization Strategies