Prediction of spatio-temporal distribution of electric vehicle load based on residential travel simulation

Abstract

Aiming at the randomness and uncertainty in the spatio-temporal distribution prediction of electric vehicle charging load, a method for electric vehicle load prediction that integrates travel chain theory and actual geographic information is proposed. On the basis of road network integration and travel chain theory, a model for the spatio-temporal characteristics of electric vehicle charging demand is established to simulate the user's travel behavior characteristics. At the same time, by modeling the road network in the target area, dividing it by functional area, combining the user behavior characteristics of travel chain theory with target geographic information, and planning and designing the travel path of electric vehicle users through Floyd algorithm, the electric vehicle charging demand load can be predicted. The results of the case study show that the proposed model can predict the variation of electric vehicle charging load based on actual geographic information, and analyze the charging demand and load characteristics of electric vehicles in different functional areas and different administrative regions. The simulation results validate the effectiveness of the proposed model and method.

Keywords

• travel chain
• load forecasting
• geographic information
• charging demand
• floyd algorithm
• markov chain