基于差分和状态空间遗传混合算法的信号配时优化
投稿时间:2020-08-22  修订日期:2020-09-16  点此下载全文
引用本文:
摘要点击次数: 13
全文下载次数: 0
作者单位E-mail
陈小静 长沙理工大学 电气与信息工程学院 979618333@qq.com 
李茂军 长沙理工大学 电气与信息工程学院  
张辉 湖南大学 机器人学院  
基金项目:国家自然科学基金(61971071);国家重点研发计划(2018YFB1308200);湖南省自然科学基金(2018JJ3079);湖南省重点研发计划(2018GK2022);
中文摘要:为了最大限度地挖掘现有道路的承载能力,提出了一种基于差分进化算法和状态空间模型遗传算法的两阶段混合优化算法,建立以车辆平均等待时间最小为目标的数学模型进行优化。为了解决差分进化算法在后期收敛速度变慢,容易陷入局部最优的缺点,引入改进后的状态空间模型遗传算法形成一种混合算法。然后,用所提出的混合算法对5个经典测试函数进行寻优测试,并与定时控制、差分进化算法以及状态空间模型遗传算法进行对比,实验结果表明该混合算法不仅提高了收敛速度,并且在保证了算法收敛精度的前提下缩短了迭代次数。最后,以单交叉路口为例,验证该混合算法在求解信号灯配时问题时的优化效果。
中文关键词:差分进化算法  状态空间模型遗传算法  信号配时  混合算法  平均等待时间
 
Signal timing optimization based on differential and state-space genetic hybrid algorithm
Abstract:In order to maximize the capacity of existing roads, a two-stage hybrid optimization algorithm based on differential evolution algorithm and state-space model genetic algorithm is proposed, and a mathematical model with the goal of minimizing the average waiting time of vehicles is established for optimization. In order to overcome the slower convergence speed in the later stage of the differential evolution algorithm and easy to fall into local optimum, the improved state-space model genetic algorithm is introduced to form a hybrid algorithm. Then, 5 classical test functions are used to test the performance of the algorithm. The algorithm was compared with timing control, differential evolution algorithm, and state-space model genetic algorithm based on state-space model. Experimental results show that the algorithm not only improves the convergence speed, but also shortens the number of iterations while ensuring the accuracy of the algorithm's convergence. Finally, taking a single intersection as an example, verify the optimization effect of this algorithm in solving the signal timing problem.
keywords:differential evolution algorithm  genetic algorithm based on state-space model  signal timing  hybrid algorithm  average waiting time
查看全文   查看/发表评论   下载pdf阅读器