基于流量预测的信号灯配时优化强化学习方法  

Signal Timing Optimization via Reinforcement Learning with Traffic Flow Prediction

作　　者：许明 李金烨 左东宇 张晶 Xu Ming;Li Jinye;Zuo Dongyu;Zhang Jing(College of Software,Liaoning Technical University,Huludao 125105,China)

机构地区：[1]辽宁工程技术大学软件学院,辽宁葫芦岛125105

出　　处：《系统仿真学报》2025年第4期1051-1062,共12页Journal of System Simulation

基　　金：辽宁工程技术大学博士科研基金(21-1027);辽宁省高等学校基本科研项目(LJKMZ20220699)。

摘　　要：针对现有基于强化学习的交通信号控制方法未考虑交通流量变化趋势,无法适应复杂多变路况而造成拥堵的问题,提出了基于流量预测的信号灯配时优化强化学习方法。提出相位配时幅度控制模型,分析历史流量数据的时空特性,对下一时间片的流量进行预测,并根据预测结果计算相位配时的合理范围;使用H-PPO算法在控制信号相位同时增加其配时控制,并设计压力阀奖励函数,避免算法在控制信号时频繁的相位变换影响驾驶员驾驶体验。仿真结果表明:所提方法在提高路口通行效率和减小相位切换频次均有良好表现,优于对比方法。In response to the existing reinforcement learning-based traffic signal control methods that do not consider the changing trends in traffic flow,leading to congestion and inability to adapt to complex and variable road conditions,we propose a traffic signal timing optimization reinforcement learning method based on flow prediction.A phase timing amplitude control model is introduced.This model analyzes the spatiotemporal characteristics of historical traffic data to predict the flow for the next time slot and calculates a reasonable range for phase timing based on the prediction results.The H-PPO algorithm is employed to control the signal phase while simultaneously increasing its timing control.We design a pressure valve reward function to avoid frequent phase changes in controlling signals,thereby affecting the driving experience of motorists.The simulation results demonstrate that the proposed method performs well in enhancing the intersection traffic efficiency and reducing the frequency of phase switching,outperforming the comparison methods.

关 键 词：交通信号控制 智能交通 强化学习 卷积门控循环单元 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]