基于改进遗传算法的交通信号双层同步优化控制  

Optimization of Synchronous Bi-level Traffic Signal Control Based on Improved Genetic Algorithm

作　　者：罗濠成 任斌[2] 何春红 LUO Haocheng;REN Bin;HE Chunhong(School of Computer Science and Technology,Dongguan University of Technology,Dongguan 523808,China;International School of Microelectronics,Dongguan University of Technology,Dongguan 523808,China;School of Urban Construction and Environment,Dongguan City University,Dongguan 523109,China)

机构地区：[1]东莞理工学院计算机科学与技术学院,广东东莞523808 [2]东莞理工学院国际微电子学院,广东东莞523808 [3]东莞城市学院城建与环境学院,广东东莞523109

出　　处：《东莞理工学院学报》2025年第1期35-40,共6页Journal of Dongguan University of Technology

基　　金：国家自然科学基金面上项目(62273096);东莞市社会发展科技重点项目(20211800904492,20211800904692);松山湖科技特派员项目(20234379-01KCJ-G);广东省高等学校特色创新项目(2022KTSCX218)。

摘　　要：针对遗传算法对交通信号配时和相位相序同步优化存在求解空间大、收敛困难的问题,本文构建了交通信号双层同步优化控制模型,并改进了遗传算法。在双层模型中,上层根据相应的约束条件优选相位相序,下层根据上层的结果优化交通信号配时。遗传算法采用了精英策略和自适应变异算子,分别用于保留最优交通信号控制方案和提高优化效率。通过SUMO交通仿真实验平台对真实的交通流数据和交通信号控制方案进行对比分析,所提的方法具备自适应能力,收敛效率高,能有效降低车辆平均等待时间和提高车辆分流效率。This papers addresses the challenge of convergence when synchronously optimizing traffic signal timing and phase using genetic algorithms.A bi-level synchronous optimization model for traffic signals control using improved genetic algorithm is proposed.The upper-level optimizes phase based on corresponding constraint conditions,while the lower-level optimizes average vehicle waiting times.The genetic algorithm is designed with an elite strategy and adaptive operators to enhance optimization efficiency.Experimental validation is conducted through the SUMO using real data and traffic signal control scheme.Results show that the proposed method has adaptive capabilities,high convergence efficiency,and can effectively reduce the average waiting time of vehicles and improve the efficiency of vehicle diversion.

关 键 词：智慧交通 城市交通拥堵 交通信号控制 遗传算法 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]