基于LSTM和CatBoost组合模型的短期负荷预测

doi:10.11985/2021.03.009

电气工程学报 ›› 2021, Vol. 16 ›› Issue (3): 62-69.doi: 10.11985/2021.03.009

扫码分享

基于LSTM和CatBoost组合模型的短期负荷预测

党存禄¹^,²^,³(), 杨海兰¹(), 武文成⁴

1.兰州理工大学电气工程与信息工程学院兰州 730050
2.兰州理工大学甘肃省工业过程先进控制重点实验室兰州 730050
3.兰州理工大学电气与控制工程国家级实验教学示范中心兰州 730050
4.甘肃送变电工程有限公司兰州 730070

收稿日期:2020-10-29 修回日期:2021-03-28 出版日期:2021-09-25 发布日期:2021-10-29
通讯作者: 杨海兰 E-mail:dcl_1964@163.com;3104067292@qq.com
作者简介:* 杨海兰,女,1987年生,硕士研究生。主要研究方向为配网自动化。E-mail： 3104067292@qq.com
党存禄,男,1964年生,教授。主要研究方向为新能源发电技术,电力电子与电力传动。E-mail： dcl_1964@163.com

Short-term Load Forecasting Based on LSTM and CatBoost Combined Model

DANG Cunlu¹^,²^,³(), YANG Hailan¹(), WU Wencheng⁴

1. College of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou 730050
2. Key Laboratory of Gansu Advanced Control for Industrial Processes, Lanzhou University of Technology, Lanzhou 730050
3. National Demonstration Center for Experimental Electrical and Control Engineering Education, Lanzhou University of Technology, Lanzhou 730050
4. Gansu Transmission and Transformation Engineering Co., Ltd., Lanzhou 730070

Received:2020-10-29 Revised:2021-03-28 Online:2021-09-25 Published:2021-10-29
Contact: YANG Hailan E-mail:dcl_1964@163.com;3104067292@qq.com

摘要/Abstract

摘要：

针对现有的电力系统短期负荷预测方法存在预测精度较差的问题,提出一种基于长短期记忆神经网络(Long short term memory,LSTM)和CatBoost组合的短期负荷预测方法,针对电力负荷数据具有时序性和非线性的特点,以及长短期记忆网络不能直接处理类别型特征,对处理后的电力负荷数据建立LSTM负荷预测模型和CatBoost负荷预测模型;用方差倒数法确定加权系数,得到LSTM和CatBoost组合模型的预测值;最后使用实际负荷数据对算法有效性进行验证,预测结果表明采用LSTM和CatBoost组合模型的方法在负荷预测精度上有显著的提高。

关键词: 短期负荷预测, 方差倒数法, LSTM, CatBoost, 组合模型

Abstract:

In view of the poor prediction accuracy of existing short-term load forecasting methods for power systems, a short-term load forecasting method based on the combination of long short term memory (LSTM) and CatBoost is proposed. Firstly, in view of the time-series and nonlinear characteristics of the power load data, and the fact that the long-term and short-term memory networks can not directly deal with the categorical features, the LSTM load forecasting model and the CatBoost load forecasting model are established for the processed power load data. Secondly, the weighted coefficients are determined by the inverse variance method, and the predicted values of the LSTM and CatBoost models are obtained. Finally, the validity of the algorithm is verified by the actual load data. The prediction results show that the combined model of LSTM and CatBoost can significantly improve the accuracy of load forecasting.

Key words: Short-term load forecasting, reciprocal variance method, LSTM, CatBoost, combined model

中图分类号:

TM74

党存禄, 杨海兰, 武文成. 基于LSTM和CatBoost组合模型的短期负荷预测[J]. 电气工程学报, 2021, 16(3): 62-69.

DANG Cunlu, YANG Hailan, WU Wencheng. Short-term Load Forecasting Based on LSTM and CatBoost Combined Model[J]. Journal of Electrical Engineering, 2021, 16(3): 62-69.

图/表 10

图1

图2

表1

图3

图4

表2

图5

图6

图7

表3

参考文献 22

[1]	李泽文, 胡让, 刘湘, 等. 基于PCA-DBILSTM的多因素短期负荷预测模型[J]. 电力系统及其自动化学报, 2020:1-9.
	LI Zewen, HU Rang, LIU Xiang, et al. Multi-factor short-term load forecasting model based on PCA-DBILSTM[J]. Journal of Electric Power System and Automation, 2020:1-9.
[2]	陈吕鹏, 殷林飞, 余涛, 等. 基于深度森林算法的电力系统短期负荷预测[J]. 电力建设, 2018, 39(11):42-50.
	CHEN Lüpeng, YIN Linfei, YU Tao, et al. Short-term load forecasting of power system based on deep forestalgorithm[J]. Electric Power Construction, 2018, 39(11):42-50.
[3]	黄南天, 齐斌, 刘座铭, 等. 采用面积灰关联决策的高斯过程回归概率短期负荷预测[J]. 电力系统自动化, 2018, 42(23):64-75.
	HUANG Nantian, QI Bin, LIU Zuoming, et al. Gaussian process regression probabilistic short-term load forecasting using area gray correlation decision[J]. Automation of Electric Power Systems, 2018, 42(23):64-75.
[4]	DUDEK G. Pattern-based local linear regression models for short-term load forecasting[J]. Electric Power Systems Research, 2016, 130:139-147. doi: 10.1016/j.epsr.2015.09.001
[5]	DAGDOUGUI H, BAGHERI F, LE H, et al. Neural network model for short-term and very-short-term load forecasting in district buildings[J]. Energy and Buildings, 2019, 203:109408. doi: 10.1016/j.enbuild.2019.109408
[6]	马静波, 杨洪耕. 自适应卡尔曼滤波在电力系统短期负荷预测中的应用[J]. 电网技术, 2005(1):75-79.
	MA Jingbo, YANG Honggeng. Application of adaptive Kalman filter in short-term load forecasting of power system[J]. Power System Technology, 2005(1):75-79.
[7]	BAHARUDIN Z, KAMEL N. Autoregressive method in short term load forecast[C]// 2008 IEEE 2nd International Power and Energy Conference,Johor Bahru,IEEE, 2008:1603-1608.
[8]	朱陶业, 晏小兵, 李应求. ARIMA模型在广西短期电力负荷预测中的应用[J]. 长沙电力学院学报, 2000(2):20-22.
	ZHU Taoye, YAN Xiaobing, LI Yingqiu. Application of ARIMA model in Guangxi short-term power load forecasting[J]. Journal of Changsha University of Electric Power, 2000(2):20-22.
[9]	ZENG P, JIN M, ELAHE M F. Short-term power load forecasting based on cross multi-model and second decision mechanism[J]. IEEE Access, 2020(8):184061-184072.
[10]	周佃民, 管晓宏, 孙婕, 等. 基于神经网络的电力系统短期负荷预测研究[J]. 电网技术, 2002(2):10-13,18.
	ZHOU Dianmin, GUAN Xiaohong, SUN Jie, et al. Research on power system short-term load forecasting based on neural network[J]. Power System Technology, 2002(2):10-13,18.
[11]	吴潇雨, 和敬涵, 张沛, 等. 基于灰色投影改进随机森林算法的电力系统短期负荷预测[J]. 电力系统自动化, 2015, 39(12):50-55.
	WU Xiaoyu, HE Jinghan, ZHANG Pei, et al. Power system short-term load forecasting based on gray projection improved random forest algorithm[J]. Automation of Electric Power Systems, 2015, 39(12):50-55.
[12]	叶淳铮, 常鲜戎, 顾为国. 基于小波变换和支持向量机的电力系统短期负荷预测[J]. 电力系统保护与控制, 2009, 37(14):41-45.
	YE Chunzheng, CHANG Xianrong, GU Weiguo. Power system short-term load forecasting based on wavelet transform and support vector machine[J]. Power System Protection and Control, 2009, 37(14):41-45.
[13]	孔祥玉, 郑锋, 鄂志君, 等. 基于深度信念网络的短期负荷预测方法[J]. 电力系统自动化, 2018, 42(5):133-139.
	KONG Xiangyu, ZHENG Feng, E Zhijun, et al. Short-term load forecasting based on deep belief network[J]. Automation of Electric Power Systems, 2018, 42(5):133-139.
[14]	陆继翔, 张琪培, 杨志宏, 等. 基于CNN-LSTM混合神经网络模型的短期负荷预测方法[J]. 电力系统自动化, 2019, 43(8):131-137.
	LU Jixiang, ZHANG Qipei, YANG Zhihong, et al. Short-term load forecasting method based on CNN-LSTM hybrid neural network model[J]. Automation of Electric Power Systems, 2019, 43(8):131-137.
[15]	党存禄, 武文成, 李超锋, 等. 基于CatBoost算法的电力短期负荷预测研究[J]. 电气工程学报, 2020, 15(1):76-82.
	DANG Cunlu, WU Wencheng, LI Chaofeng, et al. Power short-term load forecasting based on CatBoost algorithm[J]. Journal of Electrical Engineering, 2020, 15(1):76-82.
[16]	陈鸿琳, 李欣然, 冷华, 等. 运用PSO和GRNN的短期负荷二维组合预测[J]. 电力系统及其自动化学报, 2018, 30(2):85-89.
	CHEN Honglin, LI Xinran, LENG Hua, et al. Two-dimensional combined forecasting of short-term load using PSO and GRNN[J]. Proceedings of the CSU-EPSA, 2018, 30(2):85-89.
[17]	熊图, 赵宏伟, 蔡智洋, 等. 动态组合深度学习模型在短期负荷及光伏功率预测中的应用[J]. 可再生能源, 2020, 38(4):458-463.
	XIONG Tu, ZHAO Hongwei, CAI Zhiyang, et al. Application of dynamic combination deep learning model in short-term load and photovoltaic power forecasting[J]. Renewable Energy, 2020, 38(4):458-463.
[18]	金樑. SVM与神经网络的组合模型在短期电力负荷预测中的应用研究[D]. 长春:吉林大学, 2018.
	JIN Liang. Application of combined model of SVM and neural network in short-term load forecasting[D]. Changchun:Jilin University, 2018.
[19]	王蒙, 张国友, 田丽, 等. 基于最优组合预测模型的电力负荷预测研究[J]. 重庆工商大学学报, 2012, 29(9):65-69.
	WANG Meng, ZHANG Guoyou, TIAN Li, et al. Research on power load forecasting based on the optimal combination forecasting model[J]. Journal of Chongqing Technology and Business University, 2012, 29(9):65-69.
[20]	彭文, 王金睿, 尹山青. 电力市场中基于Attention- LSTM的短期负荷预测模型[J]. 电网技术, 2019, 43(5):1745-1751.
	PENG Wen, WANG Jinrui, YIN Shanqing. Attention- LSTM-based short-term load forecasting model in the power market[J]. Power System Technology, 2019, 43(5):1745-1751.
[21]	詹英. 组合预测方法在我国人均GDP预测中的应用[D]. 武汉:华中师范大学, 2014.
	ZHAN Ying. Application of combined forecasting method in China’s per capita GDP forecast[D]. Wuhan:Central China Normal University, 2014.
[22]	杨红军, 王胜辉, 李潇潇. 基于最优加权组合模型的光伏出力预测[J]. 沈阳工程学院学报, 2019, 15(4):300-305.
	YANG Hongjun, WANG Shenghui, LI Xiaoxiao. PV output forecasting based on optimal weighted combination model[J]. Journal of Shenyang Institute of Engineering, 2019, 15(4):300-305.

算法名称	MAPE(%)
算法名称	工作日	周末
LSTM	3.57	4.26
CatBoost	3.01	3.72
LSTM-CatBoost	2.66	3.31

算法名称	MAPE(%)	RMSE/MW	MAE/MW
GBDT	4.16	393.70	313.37
LSTM	3.57	303.10	237.55
CatBoost	3.01	246.01	258.13
LSTM-GBDT	2.81	243.91	196.12
BP-SVM	3.58	291.32	260.371
LSTM-CatBoost	2.66	229.23	178.61

基于LSTM和CatBoost组合模型的短期负荷预测

Short-term Load Forecasting Based on LSTM and CatBoost Combined Model

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 22

相关文章 1

编辑推荐

Metrics

本文评价