Medium-Term Load Forecasting Based on Industry Clustering Electricity Curve Decomposition

doi:10.12204/j.issn.1000-7229.2022.02.010

Abstract

Abstract:

The traditional decomposition method of power consumption sequence is difficult to effectively combine with the analysis of regional industry development trend. Therefore, this paper proposes a medium-term load forecasting model based on the decomposition of the clustering industry electricity curve which combines with the industry development trend. Firstly, the dynamic time warping algorithm is used to calculate the periodicity of the industrial power consumption, to classify the industry which has changed development trend. Secondly, the k-means algorithm is used to cluster pre-classified industries according to similar electricity consumption characteristics, and the seasonal decomposition algorithm is used to decompose the power consumption sequence of the clustering industries. Finally, the support vector regression model is established for each power consumption sub-sequence, and the electricity data of a city in Jiangxi province is taken as an example. The results show that the proposed method can separate the industry power consumption with different electricity consumption characteristics, help to analyze the local industry economic development, and improve the accuracy of regional medium-term load forecasting.

Key words: medium-term load forecasting, industry classification, dynamic time warping, decomposition forecast

CLC Number:

TM715

ZHONG Shiyuan, ZHANG Wenjin, LUO Luping, WANG Wei, XIAO Yiyao, LIAO Zhiwei. Medium-Term Load Forecasting Based on Industry Clustering Electricity Curve Decomposition[J]. ELECTRIC POWER CONSTRUCTION, 2022, 43(2): 81-88.

Figures/Tables 9

Fig.1 Comparison of electricity consumption curves of some representative industries

Table 1 Comparison of different cyclical indicators for selected industries

Fig.2 Representative industries of different periodicity

Table 2 Industry cyclical indicators

Fig.3 Medium-term load forecasting

Fig.4 Cluster centers of strong periodic industrial power consumption

Fig.5 Electricity consumption curve of some industries in weak periodic industry classification

Fig.6 Forecasting results of monthly electricity consumption

Table 3 Forecasting error of monthly electricity consumption

References 20

[1]	康重庆, 夏清, 刘梅. 电力系统负荷预测[M]. 北京: 中国电力出版社, 2007.
[2]	王大鹏, 汪秉文. 基于变权缓冲灰色模型的中长期负荷预测[J]. 电网技术, 2013, 37(1):167-171.
	WANG Dapeng, WANG Bingwen. Medium- and long-term load forecasting based on variable weights buffer grey model[J]. Power System Technology, 2013, 37(1):167-171.
[3]	张士强, 王雯, 王健. ARIMA模型在城市年用电量预测中的应用[J]. 电力需求侧管理, 2010, 12(6):31-34.
	ZHANG Shiqiang, WANG Wen, WANG Jian. Application of ARIMA model in forecasting annual city electricity consumptions[J]. Power Demand Side Management, 2010, 12(6):31-34.
[4]	张永凯, 马欢. 基于TRAMO-SEATS的月售电量预测方法及应用[J]. 电网与清洁能源, 2018, 34(2):72-78.
	ZHANG Yongkai, MA Huan. A monthly electricity sales forecasting method and its application based on TRAMO-SEATS[J]. Power System and Clean Energy, 2018, 34(2):72-78.
[5]	郭鸿业, 陈启鑫, 夏清, 等. 考虑经济因素时滞效应的月度负荷预测方法[J]. 电网技术, 2016, 40(2):514-520.
	GUO Hongye, CHEN Qixin, XIA Qing, et al. Study on mid-term electricity load forecast considering time lag effects of economic factors[J]. Power System Technology, 2016, 40(2):514-520.
[6]	王飞, 李正辉, 李渝, 等. 基于数据序列分辨率压缩尺度优化的月度电量预测方法[J]. 电力系统保护与控制, 2020, 48(11):62-68.
	WANG Fei, LI Zhenghui, LI Yu, et al. Data series resolution compression scale optimization based monthly electricity consumption forecasting[J]. Power System Protection and Control, 2020, 48(11):62-68.
[7]	吴云, 雷建文, 鲍丽山, 等. 基于改进灰色关联分析与蝙蝠优化神经网络的短期负荷预测[J]. 电力系统自动化, 2018, 42(20):67-72.
	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[J]. Automation of Electric Power Systems, 2018, 42(20):67-72.
[8]	杨楠, 李宏圣, 袁景颜, 等. 计及灰色关联度分析的中长期负荷灰色预测方法[J]. 电力系统及其自动化学报, 2018, 30(6):108-114.
	YANG Nan, LI Hongsheng, YUAN Jingyan, et al. Medium-and long-term load forecasting method considering grey correlation degree analysis[J]. Proceedings of the CSU-EPSA, 2018, 30(6):108-114.
[9]	李冬辉, 尹海燕, 郑博文. 基于MFOA-GRNN模型的年电力负荷预测[J]. 电网技术, 2018, 42(2):585-590.
	LI Donghui, YIN Haiyan, ZHENG Bowen. An annual load forecasting model based on generalized regression neural network with multi-swarm fruit fly optimization algorithm[J]. Power System Technology, 2018, 42(2):585-590.
[10]	罗澍忻, 麻敏华, 蒋林, 等. 考虑多时间尺度数据的中长期负荷预测方法[J]. 中国电机工程学报, 2020, 40(S1):11-19.
	LUO Shuxin, MA Minhua, JIANG Lin, et al. Medium and long-term load forecasting method considering multi-time scale data[J]. Proceedings of the CSEE, 2020, 40(S1):11-19.
[11]	宋建, 束洪春, 董俊, 等. 基于GM(1, 1)与BP神经网络的综合负荷预测[J]. 电力建设, 2020, 41(5):75-80.
	SONG Jian, SHU Hongchun, DONG Jun, et al. Comprehensive load forecast based on GM(1, 1) and BP neural network[J]. Electric Power Construction, 2020, 41(5):75-80.
[12]	GONZALEZ-ROMERA E, JARAMILLO-MORAN M A, CARMONA-FERNANDEZ D. Monthly electric energy demand forecasting based on trend extraction[J]. IEEE Transactions on Power Systems, 2006, 21(4):1946-1953. doi: 10.1109/TPWRS.2006.883666 URL
[13]	林女贵. 基于经验模态分解和ARIMA模型的地区售电量预测[J]. 电器与能效管理技术, 2018(7):73-77.
	LIN Nügui. Regional electricity sales forcasting based on empirical mode decomposition and ARIMA model[J]. Electrical & Energy Management Technology, 2018(7):73-77.
[14]	刘俊, 赵宏炎, 刘嘉诚, 等. 基于协整-格兰杰因果检验和季节分解的中期负荷预测[J]. 电力系统自动化, 2019, 43(1):73-80.
	LIU Jun, ZHAO Hongyan, LIU Jiacheng, et al. Medium-term load forecasting based on cointegration-granger causality test and seasonal decomposition[J]. Automation of Electric Power Systems, 2019, 43(1):73-80.
[15]	陈浩文, 刘文霞, 李月乔. 基于奇异谱分析与神经网络的中期负荷预测[J]. 电网技术, 2020, 44(4):1333-1347.
	CHEN Haowen, LIU Wenxia, LI Yueqiao. Medium-term load forecast based on singular spectrum analysis and neural network[J]. Power System Technology, 2020, 44(4):1333-1347.
[16]	徐源, 程潜善, 李阳, 等. 基于大数据聚类的电力系统中长期负荷预测[J]. 电力系统及其自动化学报, 2017, 29(8):43-48.
	XU Yuan, CHENG Qianshan, LI Yang, et al. Mid-long term load forecasting of power system based on big data clustering[J]. Proceedings of the CSU-EPSA, 2017, 29(8):43-48.
[17]	程熙. 基于行业特性的阜宁地区月度电量预测研究[D]. 镇江: 江苏大学, 2018.
	CHENG Xi. Monthly electricity forecast of funning based on industry characteristics[D]. Zhenjiang, China: Jiangsu University, 2018.
[18]	张籍, 薛儒涛, 刘慧, 等. 基于深度信念网络的不同行业中长期负荷预测[J]. 电力系统及其自动化学报, 2019, 31(9):12-19, 27.
	ZHANG Ji, XUE Rutao, LIU Hui, et al. Medium-and long-term load forecasting for different industries based on deep belief network[J]. Proceedings of the CSU-EPSA, 2019, 31(9):12-19, 27.
[19]	潘良军, 王楷, 赵宏炎, 等. 基于春节影响时期分析的中期负荷智能预测[J]. 智慧电力, 2020, 48(9):75-80, 117.
	PAN Liangjun, WANG Kai, ZHAO Hongyan, et al. Mid-term load intelligent prediction based on the analysis of influence period of spring festival[J]. Smart Power, 2020, 48(9):75-80, 117.
[20]	CLEVELAND R B, CLEVELAND W S, MCRAE J E, et al. STL: A seasonal-trend decomposition procedure based on loess[J]. Journal of Official Statistics, 1990, 6(1):3-33.