Short-term Load Prediction Based on Combined Model of Long Short-term Memory Network and Light Gradient Boosting Machine

被引：0
|
作者：
Chen W. [1 ]
Hu Z. [1 ]
Yue J. [2 ]
Du Y. [1 ]
Qi Q. [1 ]
机构：
[1] School of Electrical Engineering and Automation, Wuhan University, Wuhan
[2] Electric Power Research Institute of Guangdong Power Grid Co., Ltd., Guangzhou
来源：
Dianli Xitong Zidonghua/Automation of Electric Power Systems | 2021年 / 45卷 / 04期
基金：
中国国家自然科学基金;
关键词：
Combined model; Light gradient boosting machine (LightGBM); Long short-term memory (LSTM) network; Optimal weighted combination method; Short-term load prediction;
D O I：
10.7500/AEPS20200312005
中图分类号：
学科分类号：
摘要：
Short-term load prediction is the basis for safe dispatch and smooth operation of the power grid. To further improve the accuracy of load prediction, a combined prediction model based on long short-term memory (LSTM) network and light gradient boosting machine (LightGBM) is proposed. Firstly, according to the input structure of the LSTM network and LightGBM model, the pre-processed load data, temperature data, date data and holiday information are input into the two models, and the respective prediction results are obtained after training. Then, the optimal weighted combination method is used to determine the weight coefficients, and the prediction value of the combined model is obtained. Finally, taking actual load data as examples for analysis, the results show that the proposed method can effectively combine the advantages of the two models. It takes the effective information of discontinuous features into account while preserving the overall perception of time-series data. Compared with other models, the proposed method has higher prediction accuracy. © 2021 Automation of Electric Power Systems Press.
引用
收藏
页码：91 / 97
页数：6
相关论文
共 25 条
  • [1] WU Yun, LEI Jianwen, BAO Lishan, Et al., Short-term load forecasting based on improved grey relational analysis and neural network optimized by bat algorithm, Automation of Electric Power Systems, 42, 20, pp. 67-72, (2018)
  • [2] KONG Xiangyu, LI Chuang, ZHENG Feng, Et al., Short-term load forecasting method based on empirical mode decomposition and feature correlation analysis, Automation of Electric Power Systems, 43, 5, pp. 46-52, (2019)
  • [3] YILDIZ B, BILBAO J I, SPROUL A B., A review and analysis of regression and machine learning models on commercial building electricity load forecasting, Renewable and Sustainable Energy Reviews, 73, pp. 1104-1122, (2017)
  • [4] FANG J, XING Y, FU Y, Et al., Rural power system load forecast based on principal component analysis, Journal of Northeast Agricultural University, 22, 2, pp. 67-72, (2015)
  • [5] LIU Ronghui, ZHAO Caitao, Study of the short-term forecasting of the temperature sensitive load based on data mining technology, Power system and clean energy, 33, 11, pp. 32-38, (2017)
  • [6] LIU Xin, TENG Huan, GONG Yubin, Et al., Short-term load forecasting based on the improved Kalman filter algorithm, Electrical Measurement & Instrumentation, 56, 3, pp. 42-46, (2019)
  • [7] JIAO Runhai, SU Chenjun, LIN Biying, Et al., Short-term load forecasting by grey model with weather factor-based correction, Power System Technology, 37, 3, pp. 720-725, (2013)
  • [8] SINGH P, DWIVEDI P., Integration of new evolutionary approach with artificial neural network for solving short term load forecast problem, Applied Energy, 217, pp. 537-549, (2018)
  • [9] LLOYD J R., GEFCom2012 hierarchical load forecasting: gradient boosting machines and gaussian processes, International Journal of Forecasting, 30, 2, pp. 369-374, (2014)
  • [10] ZHAO Yun, GAO Zepu, XIAO Yong, Et al., Short term load forecasting based on multilayer clustering and improved BP neural network, Engineering Journal of Wuhan University, 52, 7, pp. 622-629, (2019)
123