Optimization of Vehicle Routing Problem in the Context of E-commerce Logistics Distribution.

2E-MDCVRP is a multi-depot, capacity, twoechelon vehicle routing issue. Satellites make it possible to collect and sort orders. In this paper, a 2E-MDCVRP model will be designed to be applied to e-commerce. In the completion stage, the researcher developed a 2E-MDCVRP solution with two stages of completion. The first stage is finding the best route for the satellite to travel to the customer. In the first stage of work, satellites are plotted as centroids in clusters using the k-Means algorithm to obtain k-set clusters. To determine route scheduling using the RNN algorithm in determining travel routes in the second echelon. The second stage uses the trial-anderror method to determine the first echelon's routing schedule. This research aims to minimize the operational application, fuel consumption, vehicle maintenance, vehicle oil change, and handling costs. Moreover, at the end of the paper, the researcher simulate the model that has been built and test the model's effectiveness by comparing it with the classic MDCVRP model, which is similar to the Same-Day Delivery model. The test results show that the 2E-MDCVRP model can make better total distance and cost improvements than the classic MDCVRP model carried out by Same-day Delivery. [ABSTRACT FROM AUTHOR]