Application of teaching learning based optimization in traveling salesman problem

• Main Authors: Mulbah, Wonseh, Himanshu, Navneet
• Format: Conference Proceeding
• Language: English
• Subjects: Algorithms; Benchmarks; Global optimization; Heuristic methods; Machine learning; Optimization; Shortest-path problems; Traveling salesman problem; Warehouses
• ISSN: 0094-243X; 1551-7616
• DOI: 10.1063/5.0194178

Over the past three decades, the travelling salesman problem (TSP) has been the most common discrete optimization issue. In TSP, a salesperson leaves the warehouse to distribute the goods to a number of clients before returning to the point of origin, or the warehouse. A constrained global optimization challenge is the identification of the shortest path connected to n consumers. TSP has changed throughout time from laborious manual computations to cutting-edge computational solutions. By offering the best outcomes along the shortest path, the development of meta-heuristic optimization strategies has been successfully shown in TSP. By analyzing thirty different benchmark issues, the effectiveness of metaheuristic algorithms like Teaching Learning (TLBO) is examined in the current study. The individual problem has been analyzed for swarm size 150 and maximum 20 separate runs totaling 1000 iterations. The findings show that Teaching Learning Based optimization is closer to the best outcomes and to other well-known strategies. Comparing the findings from previous publications also shows how well various algorithms perform in locating the ideal path. When the results are compared to the published literature, it is discovered that they are consistent. Furthermore, using particular benchmark issues, deviations from the optimal path indicated by the various methods are demonstrated.