Charging pile load prediction based on deep learning quantile regression model

被引：0
|
作者：
Peng S. [1 ]
Huang S. [1 ]
Li B. [1 ]
Zheng G. [1 ]
Zhang H. [1 ]
机构：
[1] School of Electrical & Information Engineering, Changsha University of Science & Technology, Changsha
来源：
Huang, Shijun (610429401@qq.com) | 1600年 / Power System Protection and Control Press卷 / 48期
关键词：
Charging pile; Charging power; LSTM; Probability density prediction; Quantile regression;
D O I：
10.19783/j.cnki.pspc.190289
中图分类号：
学科分类号：
摘要：
The rapid development of electric vehicles will affect the charging pile load on the power grid. Therefore, a charging pile load prediction method is proposed by using deep learning quantile regression. In this method, based on historical data, the Adam stochastic gradient descent method is used firstly to train the LSTM neural network parameter estimation in different quantile conditions. Then the results in each quantile condition of the next 96 hours are predicted. After that, the probability density function of results at the same time is built by using the kernel density estimation. Finally, the load probability density prediction is obtained. According to the actual charging pile load results, the proposed probability density prediction method can predict the real value more accurately. Furthermore, it has higher accuracy and reference value than the BP neural network quantile regression method. ©2020, Power System Protection and Control Press. All right reserved.
引用
收藏
页码：44 / 50
页数：6
相关论文
共 22 条
  • [1] Liu W., Xu X., Zhou X., Daily load forecasting based on SVM for electric bus charging station, Electric Power Automation Equipment, 34, 11, pp. 41-47, (2014)
  • [2] Sun Q., Liu J., Rong X., Et al., Charging load forecasting of electric vehicle charging station based on sup-port vector regression, IEEE PES APPEEC 2016-2016 IEEE PES Asia Pacific Power and Energy Engineering Conference, pp. 777-781, (2016)
  • [3] Wang J., Li W., Ultra-short-term forecasting of wind speed based on CEEMD and GWO, Power System Protection and Control, 46, 9, pp. 69-74, (2018)
  • [4] Zhang L., Huang C., Yu H., Study of charging station short-term load forecast based on wavelet neural networks for electric buses, Communications in Computer and Information Science, 484, pp. 555-564, (2014)
  • [5] Yang J., Huo Z., He Y., Et al., Ultra-short-term wind power prediction based on wavelet and minimum resource allocation network, Power System Protection and Control, 46, 9, pp. 55-61, (2018)
  • [6] Joakim M., Mahmoud S., Autonomous electric vehicle fleet charging in cities: optimal utility estimates and Monte Carlo simulations, 2017 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe), pp. 1-6, (2017)
  • [7] Lu K., Sun W., Ma C., Et al., Load forecast method of electric vehicle charging station using SVR based on GA-PSO, 3rd International Conference on Advances in Energy, Environment and Chemical Engineering, IOP Conference Series: Earth and Environmental Science, (2017)
  • [8] Zhang Y., Yang L., Ge S., Et al., Short-term photovoltaic power forecasting based on Kmeans algorithm and support vector machine, Power System Protection and Control, 46, 21, pp. 118-124, (2018)
  • [9] Xie F., Huang M., Zhang W., Et al., Research on electric vehicle charging station load forecasting, APAP 2011-Proceedings: 2011 International Conference on Advanced Power System Automation and Protection, pp. 2055-2060, (2011)
  • [10] Roger K., Comment on "Local quantile regression, Journal of statistical planning and inference, 143, (2013)
123