Analysis of Machine Learning Methods for Solving Cumulative Vehicle Routing Problem

Cumulative Vehicle Routing Problem (CVRP) is an important challenge in logistics that involves optimizing vehicle routes by considering cumulative time or distance. This research aims to evaluate the effectiveness of machine learning methods in solving CVRP and compare them with conventional methods. Using machine learning techniques such as deep learning and reinforcement learning algorithms, this study tests the ability of the model to provide a more efficient solution. The results show that machine learning methods can produce better and faster solutions than traditional methods, despite challenges related to data and model complexity. This study concludes that machine learning has significant potential to improve efficiency in solving CVRP, but still requires further development to overcome some of the obstacles.