Deep Diffusion Deterministic Policy Gradient based Performance Optimization for Wi-Fi Networks

TL;DR

This work addresses MAC-layer performance in dense Wi‑Fi networks by jointly optimizing contention window and frame aggregation length. It introduces D3PG, a diffusion-model–aided extension of DDPG that uses a forward diffusion to inject noise into candidate solutions and a learned reverse diffusion to denoise toward optimal actions, conditioned on network state. The approach demonstrates substantial throughput gains (up to ~75% over BEB baselines) and improved stability and convergence in NS3 simulations, outperforming PPO and standard DDPG baselines. The results suggest that diffusion-enhanced DRL can effectively model and navigate the complex parameter interdependencies in dense Wi‑Fi environments, offering a practical path to improved real-world performance.

Abstract

Generative Diffusion Models (GDMs), have made significant strides in modeling complex data distributions across diverse domains. Meanwhile, Deep Reinforcement Learning (DRL) has demonstrated substantial improvements in optimizing Wi-Fi network performance. Wi-Fi optimization problems are highly challenging to model mathematically, and DRL methods can bypass complex mathematical modeling, while GDMs excel in handling complex data modeling. Therefore, combining DRL with GDMs can mutually enhance their capabilities. The current MAC layer access mechanism in Wi-Fi networks is the Distributed Coordination Function (DCF), which dramatically decreases in performance with a high number of terminals. In this study, we propose the Deep Diffusion Deterministic Policy Gradient (D3PG) algorithm, which integrates diffusion models with the Deep Deterministic Policy Gradient (DDPG) framework to optimize Wi-Fi network performance. To the best of our knowledge, this is the first work to apply such an integration in Wi-Fi performance optimization. We propose an access mechanism that jointly adjusts the contention window and the aggregation frame length based on the D3PG algorithm. Through simulations, we have demonstrated that this mechanism significantly outperforms existing Wi-Fi standards in dense Wi-Fi scenarios, maintaining performance even as the number of users increases sharply.

Figures (6)

• Figure 1: System Model
• Figure 2: Total Average Throughput Comparison of Different Algorithm
• Figure 3: Average Delay Comparison of Different Algorithm
• Figure 4: Training Process D3PG vs. Baseline 3
• Figure 5: Comparison of Different Denoise Steps