Welcome to Francis Academic Press

Academic Journal of Engineering and Technology Science, 2022, 5(13); doi: 10.25236/AJETS.2022.051301.

Electric vehicle charging load forecasting method considering the impact of the emergency

Author(s)

Wenhao Wu1, Zonghuan Chi2

Corresponding Author:
​Wenhao Wu
Affiliation(s)

1Department of Electric Power Engineering, North China Electric Power University, Baoding, Hebei, 071000, China

2College of Electronics and Automation, City Institute Dalian University of Technology, Dalian, Liaoning, 116000, China 

Abstract

The use of electric vehicles not only drives economic growth but also contributes to the goal of "carbon peak and carbon neutrality". However, large-scale electric vehicle charging station access impacts the security and stability of the power grid. To effectively predict electric vehicle charging load, this paper builds LSTM neural network model based on PyTorch. The historical load data of a charging pile in Beijing from December 12, 2019 to February 1, 2020 was selected for analysis and prediction. Firstly, quantificat the epidemic’s impact on charging load, vectorize and normalize the historical load data. Then, the BPTT algorithm was used to train the neural network to predict the data of February 1, 2020, and the error was finally 4.17%. The prediction accuracy is much higher than that of the RNN and the CNN.

Keywords

deep learning; long short-term memory artificial neural network; short term load prediction; K-means clustering algorithm

Cite This Paper

Wenhao Wu, Zonghuan Chi. Electric vehicle charging load forecasting method considering the impact of the emergency. Academic Journal of Engineering and Technology Science (2022) Vol. 5, Issue 13: 1-9. https://doi.org/10.25236/AJETS.2022.051301.

References

[1] Yun Chen, Yun Ruan, Zhijun Pan, et al. Contribution of new power systems to realizing dual carbon targets in coastal cities. Automation of Electric Power Systems, 2022, 46(14):11-18.

[2] C. Camus, T. Farias, J. Esteves. Potential impacts assessment of plug-in electric vehicles on the Portuguese energy market [J]. Energy Policy, 2011, 39(10).

[3] H.S. Das, M.M. Rahman, S. Li, C.W. Tan. Electric vehicles standards, charging infrastructure, and impact on grid integration: A technological review [J]. Renewable and Sustainable Energy Reviews, 2020, 120(C).

[4] Zhang Ruihong, Wang Zengfeng. On the development path of intelligent manufacturing technology for new energy Vehicles [J]. Times Auto, 2021(01):75-76.

[5] Li Bo, Men Deyue, Yan Yaqin, Yang Junfeng, Zhou Jieying, Luo Zhiqiang, Zeng Lili. [5] Bus load prediction based on numerical weather forecast [J]. Automation of electric power systems, 2015, 39(01):137-140.

[6] Li Y R, Han T T, He D, Guo H, Ma Z Q. Application of ARIMA time series analysis model to long term forecast of ozone concentration [J]. And environmental science, 2021, 42(07):3118-3126.DOI:10.13227/j.hjkx.202011237.

[7] Su Xiaolin, Zhang Yanjuan, Wu Zhong, Yan Xiaoxia. Large-scale electric vehicle charging load forecasting and its influence on grid [J]. Journal of modern electric power, 2018, 35(01):45-54.DOI:10.19725/j.cnki.1007-2322.2018.01.008.

[8] Wang Zengping, Zhao Bing, Ji Weijia, Gao Xin, Li Xiaobing. GRE-NN model based short-term load forecasting method [J]. Automation of electric power systems, 2019, 43(05):53-58.

[9] Xun Chao, Chen Bojian, Wu Xiangyu, Xiang Kangli, Lin Keyao, Xiao Fen, Yi Yang. Researchon short-term power load forecasting method based on improved K-means algorithm [J]. Electric power science and technology, 2022, 37(01):90-95.DOI:10.19781/j.issn.1673-9140.2022.01.011.

[10] GE Fuyong, Lei Jingsheng. Based on CNN - GRU helped SA model of short-term power load forecasting research [J]. Journal of modern information technology, 2021, 5(07):150-154.DOI:10.19850/j.cnki.2096-4706.2021.07.039.

[11] YAN Chung-xi, Chen Hao. Optimization of LSSVM short-term power load forecasting methodbased on improved Longniushu search algorithm [J]. Electrical measurement and instrumentation,2020, 57(06):6-11+18.DOI:10.19753/j.issn1001-1390.2020.06.002.

[12] Chao Yan, Yankun Zhang, Weiyi Zhong, Can Zhang, Baogui Xin. A Truncated SVD-Based ARIMA Model for Multiple QoS Prediction in Mobile Edge Computing [J].Tsinghua Science and Technology,2022,27(02):315-324.

[13] Yan Qian-gui, Liu Huanan, Han Ning-hui, Chen Song-song, Yu Dong-min. Location and capacity optimization method of charging station considering the spatial and temporal distribution of electric vehicles [J]. Proceedings of the csee, 2021, 41(18): 6271-6284. DOI:10.13334/j.0258-8013.pcsee.202001.

[14] Zhu Shiqi. Application of deep learning in power load forecasting [J]. Industry & Technology Forum, 2022, 21(14):42-44.

[15] GIBSONA, PATTERSON J. Deep Learning: A Practitioner's Approach [M].Boston: O'Reilly Media, 2017.

[16] Zhang Meina, Liu Meiyan. A model based on neural network drivers of RTRL cruise [J]. Journal of electronic science and technology, 2016, 29(06): 5-7. DOI:10.16180/j.cnki.issn1007-7820.2016.06.002.

[17] Pang Chuan-jun, Zhang Bo, Yu Jian-ming. Short-term power load forecasting based on LSTM recurrent neural network [J]. Electric power engineering technology, 2021, 40(01):175-180+194.