Optimization of traffic network signal timing using decentralized genetic algorithm

Abstract

This work aims to minimize average delay for signalized traffic network along Jalan UMS under oversaturated condition using decentralized genetic algorithm (DGA). Relieving traffic network is a key challenge for a nation for improving its socio-economic systems and welfare to society. Control the traffic signal timing becomes a cost effective solution to reduce congestion since the space constraint limits the authority to build more infrastructures in city. Regrettably, most of the current traffic signal control systems are not yet optimized. They are preset based on historical traffic data; thus they are inadequate to cope with the dynamic changes in real traffic scenario. Therefore, this work proposes DGA to optimize the traffic network signal for reducing average delay during the morning peak hour. A comprehensive traffic model based on Public Works Department, Malaysia has been developed as the platform. The average delay experienced by vehicles to traverse the crossed intersection during morning peak hour is used as the performance metric to evaluate performances of the proposed algorithm. Simulation results show developed DGA is able to reduce the average network delay by optimizing the traffic signal.