摘要
城市交通工具的合理调度能够有效缓解日益严峻的交通压力,出租车作为公共出行的交通工具满足了大量的出行需求。蚁群算法(ACO)作为仿生算法的代表,根据蚂蚁个体产生的信息素,通过不同策略和信息素更新等操作,逐步接近最优解,适合解决城市交通资源路径规划问题。文章给出一种改进的蚁群算法进行出租车调度,在不同时间段内,对非热点区域向热点区域以及热点区域向非热点区域转移进行研究,根据信息素差异化特征,首先建立了时间区域优化算法和区域调度模型,通过对数据样本的训练得到不同情况下的转移概率和行驶里程,从而确定最优的抑制因子和调节参数,提高出租车转移概率并减少空载行驶距离,实现对出租车资源的合理分配。
The reasonable scheduling of urban transportation can effectively alleviate the increasingly severe traffic pressure.As a means of public transportation,taxis meet a large number of Travel demand.Ant colony algorithm(ACO)is a representative of bio nic algorithm.According to pheromone generated by ants,ACO can update pheromone through different strategies and operations,gradually approaching the optimal solution,it is suitable for solving the problem of urban traffic resource path planning.This paper presents an improved ant colony algorithm for taxi scheduling according to the characteristics of pheromone differentiation,we first establish the time series through the training of data samples,the transfer probability and mileage under different conditions are obtained,so as to determine the optimal suppression by controlling factors and adjusting parameters,the transfer probability of taxi can be improved and the no-load driving distance can be reduced,and the reasonable allocation of taxi resources can be realized.
作者
于霞
杨光
Yu Xia;Yang Guang(School of Information Science and Engineering,Shenyang University of Technology,Shenyang 110870,China)
出处
《长江信息通信》
2021年第3期30-32,35,共4页
Changjiang Information & Communications
关键词
智能交通
出租车
车辆调度
蚁群算法
信息素
Intelligent transportation
taxi
vehicle scheduling
ant colony algorithm
pheromone
inhibition factor
hot area