Research on Electric Vehicle Route Planning and Energy Consumption Prediction Based on CNN-LSTM Model

In the field of logistics and transportation, balancing high-quality demand with economic benefits is a crucial issue. The introduction of electric vehicles offers new solutions to this challenge. However, the limited range of electric vehicles poses a significant challenge for logistics operations. To effectively address this problem, this paper proposes an electric vehicle path planning method based on convolutional neural networks and long-short-term memory (CNN-LSTM-EVPP). Specifically, the CNN-LSTM model is employed to predict the driving energy consumption for each route by combining traffic data and road data. Finally, the NSGA-II algorithm is used to optimize the predicted energy consumption values and find the optimal path. Experiments show that the method is effective. The algorithm has the potential to enhance distribution efficiency and reduce costs. The optimized path length is reduced by 8.87% and the driving energy consumption is reduced by 8.31%.