Intelligent transport route planning using parallel genetic algorithms and MPI in high performance computing cluster

Network analysis in geospatial information system (GIS) provides strong decision support for users in searching optimal route, finding the nearest facility and determining the service area. Searching optimal path is an important advanced analysis function in GIS. In present GIS route finding modules, heuristic algorithms have been used to carry out its search strategy. Due to the lack of global sampling in the feasible solution space, these algorithms have considerable possibility of being trapped into local optima. This paper addresses the problem of selecting route to a given destination on an actual map under a static environment. The proposed solution uses a parallel genetic algorithm (PGA) implemented using High performance Cluster(HPC). A part of an arterial road is regarded as a virus. We generate a population of viruses in addition to a population of routes. A customized method based on a genetic algorithm has been proposed in this paper.