Deviation assessment and control method for electricity sales companies based on short-term load bundling forecast

doi:10.3969/j.issn.1674-1951.2021.04.008

Abstract

Abstract:

Assessment on electricity deviation is a crucial transitional link in the electric market reform. For lack of scientific and effective load forecasting analysis on electricity deviation assessment, some power sales companies are of low assessment accuracy. In view of the above situation, a load forecasting method based on the load bundling forecasting and BP neural network model is proposed. The influence of load forecasting on the accuracy of deviation assessment is analyzed. Ten power sales companies in Chongqing executed forecast on their bundled load based on their customers' power consumption data. According to the calculated results of the deviation assessment, this method can alleviate the deviated electricity in the assessment of power sales companies.

Key words: electricity sales company, electricity deviation assessment, load forecasting, load bundling, BP neural network, forecasting accuracy

CLC Number:

F27：TM73

HU Qian, SUN Zhida, JIANG Keteng, LEI Yi, LI Haibo. Deviation assessment and control method for electricity sales companies based on short-term load bundling forecast[J]. Huadian Technology, 2021, 43(4): 47-55.

Figures/Tables 12

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Tab.1

Fig.7

Fig.8

Fig.9

Tab.2

Tab.3

References 26

[1]	电力中长期交易基本规则（暂行）[Z]. 国家发展改革委, 2016.
[2]	江健健, 陈玮, 黄滔, 等. 区域电力市场考核结算新方法[J]. 电力系统自动化, 2008,32(13):40-44.
	JIANG Jianjian, CHEN Wei, HUANG Tao, et al. New settlement methods in regional electricity markets[J]. Automation of Electric Power Systems, 2008,32(13):40-44.
[3]	谢登, 尚超, 杨琦. 跨区电力交易结算中的偏差电量分析[J]. 智慧电力, 2015,43(2):5-8.
	XIE Deng, SHANG Chao, YANG Qi. Analysis of power deviation in settlement of interregional electricity trade[J]. Shaanxi Electric Power, 2015,43(2):5-8.
[4]	郭曼兰, 陈皓勇, 张聪, 等. 偏差电量考核机制下售电公司的最优经营策略[J]. 电力系统自动化, 2017,41(20):17-25.
	GUO Manlan, CHEN Haoyong, ZHANG Cong, et al. Optimal market strategy of retailers under energy deviation penalty[J]. Automation of Electric Power Systems, 2017,41(20):17-25.
[5]	刘敦楠, 汤洪海, 杨沫, 等. 促进新能源消纳的电力交易偏差结算补偿机制[J]. 电力系统自动化, 2017,41(24):105-111.
	LIU Dunnan, TANG Honghai, YANG Mo, et al. Settlement compensation mechanism of power trading deviation with promotion of renewable energy consumption[J]. Automation of Electric Power Systems, 2017,41(24):105-111.
[6]	喻小宝, 谭忠富, 马佳乐, 等. 计及需求响应的售电公司正偏差电量考核优化模型[J]. 电力系统自动化, 2019,43(7):120-128.
	YU Xiaobao, TAN Zhongfu, MA Jiale, et al. Optimal model for positive deviation penalty of power retailers considering demand response[J]. Automation of Electric Power Systems, 2019,43(7):120-128.
[7]	邱煜涵, 邵振国. 调度成本最小化的偏差电量结算方式[J]. 电力与电工, 2012,32(1):13-15.
	QIU Yuhan, SHAO Zhenguo. Settlement mode for deviation electric quantity based on minimizing of cost for dispatch[J]. Electric Power and Electrical Engineering, 2012,32(1):13-15.
[8]	丁坚勇, 张银芽, 杨东俊, 等. 基于频率偏差的跨区电网交易偏差电量责任判定及定价方法[J]. 电力系统自动化, 2017,41(16):105-110.
	DING Jianyong, ZHANG Yinya, YANG Dongjun, et al. Responsibility determination and pricing method of deviation electric quantity based on frequency deviation of cross-regional grid strading[J]. Automation of Electric Power Systems, 2017,41(16):105-110.
[9]	廖旎焕, 胡智宏, 马莹莹, 等. 电力系统短期负荷预测方法综述[J]. 电力系统保护与控制, 2011,39(1):147-152.
	LIAO Nihuan, HU Zhihong, MA Yingying, et al. Review of the short-term load forecasting methods of electric power system[J]. Power System Protection and Control, 2011,39(1):147-152.
[10]	陶莉, 朱小光. 数据预处理对电力负荷预测精度的影响[J]. 华电技术, 2015,37(9):8-10.
	TAO Li, ZHU Xiaoguang. Research on data pre processing to improve the accuracy of load forecasting[J]. Huadian Technology, 2015,37(9):8-10.
[11]	张钦, 王锡凡, 王建学. 需求侧实时电价下供电商购售电风险决策[J]. 电力系统自动化, 2010,34(3):22-27.
	ZHANG Qin, WANG Xifan, WANG Jianxue. Electricity purchasing and selling risk decision for power supplier under real-time pricing[J]. Automation of Electric Power Systems, 2010,34(3):22-27.
[12]	林顺富, 郝朝, 汤晓栋, 等. 基于数据挖掘的楼宇短期负荷预测方法研究[J]. 电力系统保护与控制, 2016,44(7):83-89.
	LIN Shunfu, Hao Chao, TANG Xiaodong, et al. Study of short-term load forecasting method based on data mining for buildings[J]. Power System Protection and Control, 2016,44(7):83-89.
[13]	彭显刚, 胡松峰, 吕大勇. 基于RBF神经网络的短期负荷预测方法综述[J]. 电力系统保护与控制, 2011,39(17):144-148.
	PENG Xiangang, HU Songfeng, LV Dayong. Review on grid short-term load forecasting methods based on RBF neural network[J]. Power System Protection and Control, 2011,39(17):144-148.
[14]	陈丽娜, 张智晟, 于道林. 基于广义需求侧资源聚合的电力系统短期负荷预测模型[J]. 电力系统保护与控制, 2018,46(15):45-51.
	CHEN Lina, ZHANG Zhisheng, YU Daolin. Short-term load forecasting model of power system based on generalized demand side resources aggregation[J]. Power System Protection and Control, 2018,46(15):45-51.
[15]	李伟, 闫宁, 张振刚. 基于粗糙集的混合支持向量机长期电力负荷预测研究[J]. 电力系统保护与控制, 2010,38(13):31-34.
	LI Wei, YAN Ning, ZHANG Zhengang. Study on long-term load forecasting of MIX-SVM based on rough set theory[J]. Power System Protection and Control, 2010,38(13):31-34.
[16]	陈涛, 吕松, 任廷林, 等. 基于最小二乘支持向量机的周用电量预测方法[J]. 华电技术, 2020,42(1):35-40.
	CHEN Tao, LYU Song, REN Tinglin, et al. Prediction method for weekly electricity consumption based on LSSVM algorithm[J]. Huadian Technology, 2020,42(1):35-40.
[17]	李啸骢, 李春涛, 从兰美, 等. 基于动态权值相似日选取算法的短期负荷预测[J]. 电力系统保护与控制, 2017,45(6):1-8.
	LI Xiaocong, LI Chuntao, CONG Lanmei, et al. Short-term load forecasting based on dynamic weight similar day selection algorithm[J]. Power System Protection and Control, 2017,45(6):1-8.
[18]	黎祚, 周步祥, 林楠. 基于模糊聚类与改进BP算法的日负荷特性曲线分类与短期负荷预测[J]. 电力系统保护与控制, 2012,40(3):56-60.
	LI Zuo, ZHOU Buxiang, LIN Nan. Classification of daily load characteristics curve and forecasting of short-term load based on fuzzy clustering and improved BP algorithm[J]. Power System Protection and Control, 2012,40(3):56-60.
[19]	袁铁江, 袁建党, 晁勤, 等. 电力系统中长期负荷预测综合模型研究[J]. 电力系统保护与控制, 2012,40(14):143-146.
	YUAN Tiejiang, YUAN Jiandang, CHAO Qin, et al. Study on the comprehensive model of mid-long term load forecasting[J]. Power System Protection and Control, 2012,40(14):143-146.
[20]	王效. 基于综合模型的电力系统中长期负荷预测方法研究[J]. 华电技术, 2013,35(6):40-41.
	WANG Xiao. Study on power system load prediction method for medium and long term based on comprehensive model[J]. Huadian Technology, 2013,35(6):40-41.
[21]	刘云, 张杭, 张爱民. 需求侧响应下基于负荷特性的改进短期负荷预测方法[J]. 电力系统保护与控制, 2018,46(13):126-133.
	LIU Yun, ZHANG Hang, ZHANG Aimin. Improved load forecasting method based on load characteristics under demand-side response[J]. Power System Protection and Control, 2018,46(13):126-133.
[22]	胡晨, 杜松怀, 苏娟, 等. 新电改背景下我国售电公司的购售电途径与经营模式探讨[J]. 电网技术, 2016,40(11):3293-3299.
	HU Chen, DU Songhuai, SU Juan, et al. Preliminary research of trading approach and management modes of Chinese electricity retail companies under new electricity market reform[J]. Power System Technology, 2016,40(11):3293-3299.
[23]	杨萌, 艾欣, 唐亮, 等. 计及风险规避的售电公司平衡市场优化交易策略研究[J]. 电网技术, 2016,40(11):3300-3308.
	YANG Meng, AI Xin, TANG Liang, et al. Optimal trading strategy in balancing market for electricity retailer considering risk aversion[J]. Power System Technology, 2016,40(11):3300-3308.
[24]	邹鹏, 李春晖, 郭静, 等. 考虑可中断负荷的配售电公司最优购售电策略[J]. 南方电网技术, 2017,11(2):71-77.
	ZOU Peng, LI Chunhui, GUO Jing, et al. Optimal marketing strategy of distribution and retail companies considering interruptible load[J]. Southern Power System Technology, 2017,11(2):71-77.
[25]	舒畅, 钟海旺, 夏清. 基于优化理论市场化的日前电力市场机制设计[J]. 电力系统自动化, 2016,40(2):55-62.
	SHU Chang, ZHONG Haiwang, XIA Qing. Day-ahead electricity market design based in market interpretation of optimization theory[J]. Automation of Electric Power Systems, 2016,40(2):55-62.
[26]	郭乐, 张丹丹. 几种基于可靠性指标的容量支持机制电力市场分析[J]. 华电技术, 2019,41(11):12-17.
	GUO Le, ZHANG Dandan. Analysis on several capacity support mechanisms in electric market based on reliability index[J]. Huadian Technology, 2019,41(11):12-17.

月份	预测值/（kW·h）	期望值/（kW·h）	相对偏差/%
1	3 605 746	3 367 626	-7.070 84
2	2 993 355	2 603 650	-14.967 60
3	4 151 472	4 087 003	-1.577 42
4	4 149 477	3 450 795	-20.247 00
5	4 162 358	2 891 701	-43.941 50
6	4 287 959	3 822 399	-12.179 80
7	4 389 988	3 884 121	-13.024 00
8	4 405 069	4 427 350	0.503 26
9	4 200 764	4 479 331	6.218 94
10	3 499 168	3 128 333	-11.854 10
11	3 576 883	3 655 073	2.139 22
12	3 724 683	3 507 531	-6.191 03

月份	预测值/（kW·h）	期望值/（kW·h）	相对偏差/%
1	3 312 148.405	3 367 626	1.647 38
2	2 783 715.480	2 603 650	-6.915 89
3	3 928 201.186	4 087 003	3.885 53
4	3 544 558.127	3 450 795	-2.717 15
5	2 971 631.086	2 891 701	-2.764 12
6	3 785 150.997	3 822 399	0.974 47
7	3 772 178.220	3 884 121	2.882 06
8	4 216 468.183	4 427 350	4.763 16
9	4 488 805.269	4 479 331	-0.211 51
10	3 032 913.794	3 128 333	3.050 16
11	3 066 103.121	3 655 073	16.113 77
12	3 340 908.740	3 507 531	4.750 41

月份	神经网络预测	多元线性回归预测
1	0	8.295 374
2	6.239 736	15.268 490
3	0.024 353	0.397 925
4	2.029 828	28.082 480
5	1.759 459	53.041 690
6	0	17.826 100
7	0	19.526 100
8	0.614 346	0
9	0	1.608 302
10	0	14.150 450
11	6.785 040	0
12	0.479 945	7.310 930
合计	17.932 700	165.507 80