遗传-蚁群算法在智能交通中的应用

随着私家车的增多,城市交通问题越来越严重。为了解决这个问题,人们将计算机技术运用于城市智能交通系统(intelligent transportation systems,ITS)中。行车路径规划是城市智能交通体系中重要的一个环节。目前,有不少路径优化算法被提出用于解决行车路径规划问题,但各有不足。因此,提出了一种混合遗传蚁群算法(GACHA)。从基本蚁群算法入手,结合遗传和蚁群算法的各自优点,将两种算法的寻优过程循环多次结合。在蚁群算法的一次迭代循环后,将蚁群算法产生的较优解代替遗传算法中的部分个体,用以加快遗传算法的迭代速度。同时,将遗传算法算出的解设为较优路径来更新蚁群算法中的信息素分配,实现参数调整。多次相互指导能有效解决蚁群算法前期效率低和遗传算法后期冗余迭代的问题。实验结果表明,遗传-蚁群混合算法可以有效地避免陷入局部最优解,提高计算效率。它具有良好的优化和收敛性,能够准确地找到满足路网综合要求的最优路径。

Application of Genetic-ant Colony Algorithm in Intelligent Transportation

With the increase of private cars,urban traffic problems are getting worse.To solve this problem,people use computer technology in the intelligent transportation systems(ITS).Driving route planning is an important part of urban ITS.At present,many path optimization algorithms have been proposed to solve the problem of driving route planning,but each has its own shortcomings.Therefore,we propose a hybrid genetic ant colony algorithm(GACHA).Starting from the basic ant colony algorithm,combined with the respective advantages of genetic and ant colony algorithms,the optimization of the two algorithms is cycled and combined many times.After an iteration cycle of the ant colony algorithm,the optimal solution generated by the ant colony algorithm is used to replace some individuals in the genetic algorithm to speed up the iteration of the genetic algorithm.At the same time,the solution calculated by the genetic algorithm is set as a better path to update the pheromone allocation in the ant colony algorithm and achieve parameter adjustment.Multiple mutual guidance can effectively solve the problem of low efficiency of the early ant colony algorithm and redundant iteration of the genetic algorithm.The experiment shows that the genetic-ant colony hybrid algorithm can effectively avoid falling into local optimal solutions and improve computational efficiency.It has better optimization and convergence,and can accurately find the optimal path that meets the comprehensive requirements of the road network.