Intelligent Traffic Signal Control Based on Reinforcement Learning with Edge Computing and Intelligent Reflecting Surface

With increasing traffic demand and growing environmental complexity, traditional signal control methods struggle with low efficiency and poor adaptability. This study proposes a reinforcement learning-based framework integrating edge computing and intelligent reflecting surfaces (IRS) to enhance traffic signal control. The framework is validated through simulation and optimized via an improved Proximal Policy Optimization (PPO) algorithm with multi-step returns and entropy-based adaptive regularization, ensuring better convergence and stability. Experiments on a 5×5 intersection network in SUMO, under varying traffic scenarios, including ablation and comparative studies, show that the proposed method significantly reduces average delay and improves throughput, demonstrating its effectiveness and reliability.