@ARTICLE{Caio_Yongxiang_Forecasting_2024,
 author={Caio, Yongxiang and Chen, Qing and Wang, Yang and Li, Wie and Ren, Jiakuan and Qu, Yangquan},
 volume={vol. 73},
 number={No 2},
 journal={Archives of Electrical Engineering},
 pages={355-372},
 howpublished={online},
 year={2024},
 publisher={Polish Academy of Sciences},
 abstract={In order to deal with the threat of the randomness of large-scale electric vehicle (EV) loads to the safe and economic operation of the distribution network effectively, a forecasting method of EV loads based upon virtual prediction parameter estimation strategy is proposed. Firstly, an in-depth analysis is conducted to thoroughly examine the applicability and target audience of various existing power user load forecasting methods. This initial phase provided a solid foundation for the introduction of the new methods. Secondly, utilizing the Monte Carlo simulation method, a charging load forecasting approach that considers both spatial and temporal distribution is developed. This method effectively captures the diversity of EV charging behaviors by leveraging virtual parameter estimation, integrating insights from historical data into future load predictions, thereby enhancing forecasting accuracy. Finally, to validate the effectiveness of this groundbreaking approach, comprehensive testing was conducted on the MATLAB R2017a simulation platform. This verification phase not only serves to demonstrate the method’s accuracy, but also underscores its practicality and reliability in real-world applications.},
 type={Article},
 title={Forecasting method of electric vehicle charging load based on virtual prediction parameter estimation strategy},
 URL={http://czasopisma.pan.pl/Content/131500/06.pdf},
 doi={10.24425/aee.2024.149921},
 keywords={distribution network, electrical vehicles, forecasting method, Monte Carlo simulation},
}