Hybrid Heuristic for Solving the Euclidean Travelling Salesman Problem

Abstract

This study introduces a hybrid methodology that integrates the ant colony optimization (ACO) with genetic algorithm (GA) techniques. ACO is employed first to create an initial population and to derive a sub-optimal solution for the TSP using a newly designed inver-over (IO) operator. The Proposed IO operator is utilized to improve the solution derived from the ACO. This refined solution is then employed in the GA, where a genetic operator is applied alongside other randomly selected members from the initial population during the second phase. GA is used with the proposed crossover operator and the 2-opt heuristic in this phase to achieve optimal solution refinement towards a global optimum. Our evaluation of the algorithm’s efficacy uses benchmark datasets from TSPLIB. The proposed approach gives superior solution quality, both the average and the best solution metrics, demonstrating enhanced performance with a lower percentage of best error and percentage of average error. Experimental results indicate that the hybrid approach outperforms the efficiency of other state-of-the-art techniques. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.