Genetic Algorithm Optimization for Solving the Traveling Salesman Problem in the Indonesian Business Environment

Abstract

The Traveling Salesman Problem (TSP) is one of the combinatorial optimization problems that is highly relevant in distribution and logistics route planning. This study aims to optimize the Genetic Algorithm (GA) for solving TSP in the Indonesian business environment, which has complex geographical characteristics and diverse logistics infrastructure. The proposed approach combines dynamic parameter adaptation and regional clustering to improve convergence efficiency and solution quality. Experiments were conducted on the distribution route data of an Indonesian logistics company with three scenarios: conventional GA, adaptive GA, and clustering-based GA. Performance evaluation was based on total travel distance, computation time, solution stability, and convergence rate. The results show that adaptive AG produces the best performance, with a reduction in total travel distance of up to 20% more efficient, faster convergence time (95 iterations compared to 120 iterations in conventional AG), and solution stability reaching 90.6%. These findings indicate that parameter adaptation in AG can significantly improve the effectiveness of TSP optimization in the Indonesian business context. The contribution of this research not only strengthens the development of adaptive metaheuristic algorithms but also provides practical benefits for the logistics industry in designing more efficient, cost-effective, and sustainable distribution routes.