引用本文: | 彭曙蓉,黄士峻,李彬,等.基于深度学习分位数回归模型的充电桩负荷预测[J].电力系统保护与控制,2020,48(2):44-50.[点击复制] |
PENG Shurong,HUANG Shijun,LI Bin,et al.Charging pile load prediction based on deep learning quantile regression model[J].Power System Protection and Control,2020,48(2):44-50[点击复制] |
|
摘要: |
电动汽车的迅速发展将使充电桩负荷对电网造成影响,为此提出了使用深度学习分位数回归的充电桩负荷预测方法。该方法首先根据历史数据采用Adam随机梯度下降法训练出不同分位数条件下的LSTM神经网络参数估计,然后预测未来96 h内各分位数条件下的结果,再用核密度估计做出同一时刻结果的概率密度函数,最终得到负荷概率密度预测。根据实际充电桩负荷结果表明,提出的概率密度预测方法能较为精准地覆盖真实值,相比于BP神经网络分位数回归有着更高的精确度和参考价值。 |
关键词: LSTM 充电桩 充电负荷 分位数回归 概率密度预测 |
DOI:10.19783/j.cnki.pspc.190289 |
投稿时间:2019-03-18修订日期:2019-08-02 |
基金项目:湖南省教育厅项目创新平台开放基金(17K001) |
|
Charging pile load prediction based on deep learning quantile regression model |
PENG Shurong,HUANG Shijun,LI Bin,ZHENG Guodong,ZHANG Heng |
(School of Electrical & Information Engineering, Changsha University of Science & Technology, Changsha 410114, China) |
Abstract: |
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. This work is supported by Education Innovation Platform Open Fund of Hunan Provincial Department (No. 17K001). |
Key words: LSTM charging pile charging power quantile regression probability density prediction |