Efficient computation of shortest paths in networks using particle swarm optimization and noising metaheuristics

Abstract

This paper presents a novel hybrid algorithm based on particle swarm optimization (PSO) and noising metaheuristics for solving the single-source shortest-path problem (SPP) commonly encountered in graph theory. This hybrid search process combines PSO for iteratively finding a population of better solutions and noising method for diversifying the search scheme to solve this problem. A new encoding/decoding scheme based on heuristics has been devised for representing the SPP parameters as a particle in PSO. Noising-method-based metaheuristics (noisy local search) have been incorporated in order to enhance the overall search efficiency. In particular, an iteration of the proposed hybrid algorithm consists of a standard PSO iteration and few trials of noising scheme applied to each better/improved particle for local search, where the neighborhood of each such particle is noisily explored with an elementary transformation of the particle so as to escape possible local minima and to diversify the search. Simulation results on several networks with random topologies are used to illustrate the efficiency of the proposed hybrid algorithm for shortest-path computation. The proposed algorithm can be used as a platform for solving other NP-hard SPPs.