Improving TSP Solutions Using GA with a New Hybrid Mutation Based on Knowledge and Randomness

TL;DR

This paper introduces a hybrid mutation operator for genetic algorithms, combining knowledge-based and random mutations, to improve solutions for the Traveling Salesman Problem, demonstrating enhanced efficiency on benchmark instances.

Contribution

A novel hybrid mutation operator called IRGIBNNM is proposed, combining knowledge-based and random mutations, along with an improved mutation selection strategy for TSP solutions.

Findings

The proposed mutation improves GA performance on TSP benchmarks.

Combining IRGIBNNM with other mutations yields better results.

Experimental results confirm the effectiveness of the hybrid mutation.

Abstract

Genetic algorithm (GA) is an efficient tool for solving optimization problems by evolving solutions, as it mimics the Darwinian theory of natural evolution. The mutation operator is one of the key success factors in GA, as it is considered the exploration operator of GA. Various mutation operators exist to solve hard combinatorial problems such as the TSP. In this paper, we propose a hybrid mutation operator called "IRGIBNNM", this mutation is a combination of two existing mutations, a knowledge-based mutation, and a random-based mutation. We also improve the existing "select best mutation" strategy using the proposed mutation. We conducted several experiments on twelve benchmark Symmetric traveling salesman problem (STSP) instances. The results of our experiments show the efficiency of the proposed mutation, particularly when we use it with some other mutations. Keyword: Knowledge-based mutation, Inversion mutation, Slide mutation, RGIBNNM, SBM.