Author(s)

SaiNan Wang^*, Zhi Bo

Affiliation(s)

College of Elevator Engineering, Hunan Electrical College Of Technology, Xiangtan 411101, Hunan, China.

Corresponding Author

SaiNan Wang

ABSTRACT

Electric vehicles have strong spatiotemporal randomness during the charging process, which increases the difficulty of power grid control and affects the quality of electric energy. This article proposes a deep learning based spatiotemporal dynamic load prediction method for electric vehicles to address this challenge. A quantile regression model based on air dynamic causal convolutional neural network is established to accurately predict the charging load. This model uses neural network algorithms to enhance network learning ability, preprocesses data based on factors such as changes in peak morning and evening passenger flow, holidays, and unexpected situations during the charging process of electric vehicles, and improves prediction accuracy. And compared with the QRLSTM and QRNN models through experiments, the experimental results show the scientificity of the model.

KEYWORDS

Deep learning; Load forecasting; Smart grid

CITE THIS PAPER

SaiNan Wang, Zhi Bo. Research on spatiotemporal dynamic load prediction of smart grid electric vehicles based on deep learning. World Journal of Educational Studies. 2024, 2(2): 1-7. DOI: 10.61784/wjesv2n257.

REFERENCES

[1] Xiao Bai, Zhu JiaXun, Jiang Zhuo, et al. Electric bus charging station planning considering vehicle charging scheduling mechanism. Electric Power Automation Equipment, 2022, 42(1): 148-155.

[2] Zhang Meixia, Xu Licheng, Yang Xiu, et al. Research on Charging station planning based on spatial-temporal Distribution Characteristics of electric vehicle Charging Demand.Power Grid Technology, 2023, 47(1): 256-268.

[3] Jiang T, Yang L, Qi Z, et al. Electric vehicle charging load prediction considering the orderly charging. Energy Reports, 2022, 8(S14): 124-134.

[4] Yu XiaoXiao, Song Fulong, Zhou Yuanbing, et al. Investigations on the impact of new infrastructure on electricity forecast and power system planning during the 14th five-year plan period. Electric Power, 2021, 54(7): 11-17.

[5] Zhang Linjuan, Xu Changqing, WANG Lili, et al. OD matrix based spatiotemporal distribution of EV charging load prediction. Power System Protection and Control, 2021, 49(20): 82-91..

[6] Hua Yuanpeng, Wang YuanYuan, Han Ding, et al. Mid- and long-term charging load forecasting for electric vehicles in residential areas considering orderly charging . Proceedings of the CSU-EPSA, 2022, 34(6) : 142-150.

[7] Liang H, Sharma I, Zhuang W, Bhattacharya K. Plug-in electric vehicle charging demand estimation based on queueing network analysis// Proc IEEE power and energy soc general meeting, National Harbor, MD: 1–5.

[8] Luo Z, Song Y, Hu Z, Xu Z, Yang X, Zhan K. Forecasting charging load of plug-in electric vehicles in China// Proc IEEE power and energy soc general meeting, San Diego, CA: 1–8.

[9] Yao Chengwen, Yang Ping, Liu Zejian, et al. Load forecasting method based on CNN-GRU hybrid neural network.Power System Technology, 2020, 44(9): 3416-3424.

[10] Majidpour , Mostafa. Time series prediction for Electric Vehicle Charging Load and Solar Power Generation in the context of Smart Grid. UCLA Electronic Theses and Dissertations 2016-01-01: 1-119.

[11]  Dong X, Mu Y, Jia H, Wu J, Yu X. Planning of fast EV charging stations on a round freeway. IEEE Trans Sustain Energy 2016: 1–10.

[12] Mariz B. Ariasab , Sungwoo Baea, Electric vehicle charging demand forecasting model based on big data technologies. Applied Energy , 2016, 183 : 327–339

[13] Liu Wenxia, Xu Xiaobo, Zhou Xi. Daily load forecasting based on SVM for electric bus charging station. Electric Power Automation Equipment, v 34, n 11, p 41-47, No-vember 10, 2014.

[14] Xydas E, Marmaras C, Cipcigan L, Hassan A, Jenkins N. Forecasting electric vehicle charging demand using support vector machines // Power engineering conference (UPEC), Dublin, Ireland: 1–6.

[15] Sun Qiming, Liu Jihong, Rong XiaoXue, et al. Charging load forecasting of electric vehicle charging station based on sup-port vector regression. Asia-Pacific Power and Energy En-gineering Conference, APPEEC, v 2016-December, p 1777-1781, December 9, 2016, IEEE PES APPEEC 2016 – 2016 IEEE PES Asia Pacific Power and Energy Engineering Conference.

[16] Lei Zhang, Chun Huang, et al. Study of charging station short-term load forecast based on wavelet neural networks for electric buses. Communications in Computer and Information Science, v 484, p 555-564, 2014.

[17] Munkhammar Joakim, Shepero Mahmoud. Autonomous electric vehicle fleet charging in cities: Optimal utility esti-mates and Monte Carlo simulations. 2017 IEEE PES Inno-vative Smart Grid Technologies Conference Europe, ISGT-Europe 2017- Proceedings, v 2018-January, Pp1-6, January 16, 2018.

[18]  Lu, Kuan, Sun WenXue, Ma Changhui, et al. Load forecast method of electric vehicle charging station using SVR based on GA-PSO. IOP Conference Series: Earth and Environ-mental Science, v 69, n 1, June 13, 2017, 3rd Interna-tional Conference on Advances in Energy, Environment and Chemical Engineering.

[19] Xie FeiXiang, Huang Mei, Zhang WeiGe, et al. Research on electric vehicle charging station load forecasting. APAP 2011- Proceedings: 2011 International Conference on Advanced Power System Automation and Protection, v 3, p 2055-2060, 2011.

[20] Shi Xin, Qiu Lei, Tian Li, et al. Short-term load forecasting for electric vehicle charging stations based on time series distance measuring // 2017 IEEE 13th International Conference on Electronic Measurement & Instruments: 417-423.