Dynamic Coast Control of Train Movement with Genetic Algorithm

Railway service is now the major transportation means in most of the countries around the world. With the increasing population and expanding commercial and industrial activities, a high quality of railway service is the most desirable. Dwell time control at stations and fixed coasting point in an inter-station run are the current practices to maintain the train service in most metro railway system, however a flexible and efficient train control and operation cannot be accomplished. Coast control is an economical approach to balance run-time and energy consumption in railway operation if time is not an important issue at off-peak hours. Coast control of train operation within inter-station runs offers certain flexibility to manoeuvre between run-time and energy consumption and hence it has become one of the biggest challenges for most metro railway operators around the world. This paper presents an application of genetic algorithms (GA) to search for the appropriate coasting point(s) and investigates the possible improvement on fitness of genes. Single and multiple coasting point control with simple GA are developed to attain the solutions and their corresponding train movement is examined. Further, a hierarchical genetic algorithm is introduced here to integrate the determination of the number of coasting points and a fast mutation scheme, Minimum-Allele-Reserve-Keeper (MARK), is then adopted as a genetic operator to ensure fast convergence.