Traffic Light Signal Parameters Optimization using Modification of Multielement Genetic Algorithm

I Gede Pasek Suta Wijaya, Keeichi Uchimura, Gou Koutaki
2018 International Journal of Electrical and Computer Engineering (IJECE)  
In this research, a traffic light signal optimization is presented for solving the traffic congestion problem using modification of the Multielement Genetic Algorithm. The aim of this method is to improve the lack of vehicle throughput ($F_{F}$) of previous works called as traffic light signal optimization using the Multielement Genetic Algorithm (MEGA) and Particle Swarm Optimization (PSO). In this case, the modification of MEGA is done by adding hash table for saving some best populations and
more » ... est populations and accelerating the recombination process of MEGA. Therefore, the modification of MEGA (the MEGA is equipped by hash table)is called as H-MEGA. It means the H-MEGA is forced to work as PSO like which search the solution in entire particle (based on some best populations). The H-MEGA is employed to find the best signal parameters of real Ooe Toroku Road Network in Kumamoto City, Japan. The experimental results confirm that the H-MEGA based optimization method provides better performance than MEGA and PSO based methods. In detail, the H-MEGA improves both (F_{F}$ of MEGA and PSO based optimization methods by about 10.01\% (from 82,63% to 92.64%) and 6.88% (from 85.76% to 92.64%), respectively. In addition, the proposed method significantly improve the real (F_{F}) of Ooe Toroku road network of Kumamoto City, Japan about 21.62%.
doi:10.11591/ijece.v8i1.pp246-253 fatcat:vinr4cr345ab7cyjf7ypjx4hqi