Water cycle algorithm: implementation and analysis of solutions to the bi-bjective travelling salesman problem

Abstract

This research is an implementation of the Water Cycle Algorithm (WCA) to solve the biobjective Travelling Salesman Problem, based on the kroAB100 problem in the TSPLIB library, and compare its performance to an alternative metaheuristic algorithm (MO Ant Colony BiCriterionAnt). Metrics such as generational distance, inverse generational distance, spacing, dispersion and maximum dispersion were used to compare the two algorithms. Results demonstrate that the Water Cycle Algorithm generates superior solutions to this category of problem according to most of the metrics.