The randomness of charging behavior in time and space increases the difficulty of load forecasting of EV charging stations. In this paper, to improve the accuracy of load forecasting, by building a load prediction mode based on stacked auto encoder neural network(SAE) at the edge platform, and in-depth study of the interaction mode of EV and power grid. The model of electric vehicle charging pile load prediction based on SAE is introduced and the key factors affecting the charging station load, such as historical load, temperature, weather type, etc., are also considered. Finally, the short-term load forecasting of a practical charging station is realized and compares with DBN and ELM algorithm. The result shows the proposed approach can provide more accurate forecasting result, which benefits the stable operation pf power grid.
Load Forecasting of Electric Vehicle Charging Station Based on Edge Computing
2020-08-01
4513009 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Electric Vehicle Charging Load Forecasting based on Monte Carlo
VDE-Verlag | 2022
|Electric vehicle charging station load calculation method
Europäisches Patentamt | 2020
|Charging load control method and device for electric vehicle charging station
Europäisches Patentamt | 2023
|Demand Forecasting-Based Layout Planning of Electric Vehicle Charging Station Locations
British Library Conference Proceedings | 2018
|