Hybrid Algorithms for Energy Minimizing Vehicle Routing Problem: Integrating Clusterization and Ant Colony Optimization

This project tackles the Energy‑Minimizing Vehicle Routing Problem (EMVRP), a version of the classic Vehicle Routing Problem (VRP) that focuses on lowering the total energy used by a fleet of vehicles. To deal with the hard computations EMVRP creates, we built a hybrid optimization framework that mixes machine‑learning clustering with metaheuristic search. The approach uses two clustering methods—K‑Means and K‑Medoids—to split the delivery points into small, local zones. This reduces the number of possibilities the algorithm has to examine. After clustering, we apply Ant Colony Optimization (ACO) to find the best routes. Two ACO variants are used: the Free Ant formulation and the Restricted Ant formulation. These guide the search

for low‑energy paths both inside each cluster and between clusters. The project also offers code, step‑by‑step instructions, and tips for running simulations of the hybrid algorithms. You can compare their results to standard benchmark data and see how computation time trades off against energy savings. Overall, the work shows how machine learning and metaheuristics can be combined to create greener logistics, more efficient hybrid fleets, and sustainable transportation systems.

Message: Hi FE, I need help with “Hybrid Algorithms for Energy Minimizing Vehicle Routing Problem: Integrating Clusterization and Ant Colony Optimization” in “Automobile Engineering”