Modified self organizing neural network algorithm for solving the Vehicle Routing Problem
Document Type
Conference Proceeding
Date of Original Version
1-1-2015
Abstract
Although a significant amount of research has focused on the use of Artificial Neural Networks (ANNs) for solving the Traveling Salesman Problem (TSP), there is considerably less attention on the application of ANNs to the Vehicle Routing Problem (VRP). This paper proposes an updated Self Organizing Map approach to solving the Capacitated Vehicle Routing Problem (CVRP). The proposed algorithm extends existing research by strengthening the bias term and introducing a restricted mechanism in order to encourage the network to explore a greater number of feasible solutions. Numerical results from benchmark problems demonstrate that the proposed algorithm is superior to two other well-known construction heuristics, the Sweep algorithm and the Clarke and Wright algorithm, and the proposed algorithm's results surpass the existing SOM approaches on nearly all benchmark problems.
Publication Title, e.g., Journal
Proceedings - IEEE 18th International Conference on Computational Science and Engineering, CSE 2015
Citation/Publisher Attribution
Steinhaus, Meghan, Arash N. Shirazi, and Manbir Sodhi. "Modified self organizing neural network algorithm for solving the Vehicle Routing Problem." Proceedings - IEEE 18th International Conference on Computational Science and Engineering, CSE 2015 (2015): 246-252. doi: 10.1109/CSE.2015.56.