论文部分内容阅读
针对城市过饱和路网的交通信号控制问题,将总延误分为主线路段延误和次线路段延误,将控制问题描述为冲突的多目标控制问题.针对这一问题,提出一种新的非均匀自适应多目标相容优化控制算法,对多目标进化算法NSGA-II算法进行改进,作为多目标相容控制算法的优化工具,提出非均匀Pareto前沿扩张机制来获得Pareto前沿上的一些特殊区域.改进的NSGA-II算法采用自适应种群机制和迭代控制算法机制来提高实时控制算法的计算速度,提出稳定性偏好选择策略来获得稳定的控制器.将提出的改进的多目标相容控制算法在仿真环境中对一个7个交叉口的城市过饱和路网进行实时控制,结果表明,本文提出的相容优化控制算法的效果优于定时控制方案.
Aimed at the problem of traffic signal control in urban supersaturated road network, the total delay is divided into the main line delay and the secondary line delay, and the control problem is described as the conflicting multi-objective control problem. In response to this problem, a new non-uniform The adaptive multi-objective compatible optimization control algorithm is used to improve the multi-objective evolutionary algorithm (NSGA-II). As an optimization tool for the multi-objective compatible control algorithm, a non-uniform Pareto frontier expansion mechanism is proposed to obtain some special regions on the Pareto frontier. The improved NSGA-II algorithm uses adaptive population mechanism and iterative control algorithm to improve the computational speed of real-time control algorithm, and proposes a stability preference selection strategy to obtain a stable controller.The improved multi-objective compatible control algorithm proposed in The real-time control of a city supersaturated road network with seven intersections in the simulation environment shows that the proposed algorithm is better than the timing control scheme.