Abstract
Transportation is a key element in any city, connecting the outermost suburbs to the center. Most studies done to elevate the transportation system are through optimizing the schedule of vehicles with respect to company’s benefit. When the focus shifts to the riders, other projects gather ridership data to predict future demand. However, this project considers the rider’s experience by optimizing a bus’s schedule with the objective of minimizing passengers remaining at waiting stations using a hybrid genetic algorithm. The schedule will no longer be static, but dynamic, morphing periodically, to service every passenger possible while considering spaciotemporal factors, fleet size, vehicle capacity and more. Most scheduling problems use the genetic algorithm and its variations to solve scheduling problems, and this study integrates it with simulated annealing, since their combination can avoid poor local search of genetic algorithm and speeding its process. The proposed integrated genetic algorithm and simulated annealing has proven to be the best both genetic algorithm and simulated annealing in finding a solution that minimized the total number of remaining passengers in a day. This technique can be translated into other forms of transportation such as bus rapid transport, subways, trains and more.

This publication has 32 references indexed in Scilit: