Multi-Objective ptimization of the New Energy Vehicle Supply Chain Considering Risk Losses and Carbon Emissions

Compared to the traditional supply chain, regarding that of new energy vehicles (NEVs), factors such as transportation status, distribution distance, vehicle load, and whether recycled or not, are related to carbon emissions. This study investigates the multi-objective optimization problem of the supply chain of NEVs, considering the risk loss and carbon emissions. A multi-objective mixed-integer linear programming model was developed for this problem, aiming at the occurrence of transportation accidents and their accident rates under different scenarios as the quantitative factors of the risk loss, and simultaneously minimizing the risk loss, carbon emissions, and economic cost. A deep reinforcement learning-based multi-objective optimization framework was designed to effectively solve the problem. Finally, a supply chain network is constructed using Guangdong, China, as an arithmetic example to verify the effectiveness and feasibility of the model and algorithm. The experimental results show that the proposed model and algorithm can effectively solve the multi-objective optimization problem of NEV supply chain, considering risk loss and carbon emissions, and provide a reference for decision makers when making decisions on risk loss and total carbon emissions.