电力市场环境下电力用户电价特征提取和异常识别方法

doi:10.16183/j.cnki.jsjtu.2023.448

上海交通大学学报 ›› 2025, Vol. 59 ›› Issue (7): 995-1006.doi: 10.16183/j.cnki.jsjtu.2023.448

• 新型电力系统与综合能源 • 上一篇下一篇

电力市场环境下电力用户电价特征提取和异常识别方法

朱峰¹, 单超¹, 吴宁¹(), 蔡奇新¹, 祝宇楠¹, 刘云鹏¹, 左强²

1.国网江苏省电力有限公司营销服务中心,南京 210019
2.国网江苏省电力有限公司,南京 210019

收稿日期:2023-09-06 修回日期:2024-03-10 接受日期:2024-03-11 出版日期:2025-07-28 发布日期:2025-07-22
通讯作者: 吴宁 E-mail:wuning@sgcc.com.cn
作者简介:朱峰(1991—),硕士生,工程师,从事电力市场营销研究.
基金资助:
国网江苏省电力有限公司科技项目(J2022070)

Feature Extraction and Anomaly Identification Method for Power Customer Price in Power Market Enviroment

ZHU Feng¹, SHAN Chao¹, WU Ning¹(), CAI Qixin¹, ZHU Yunan¹, LIU Yunpeng¹, ZUO Qiang²

1. Marketing Service Center of State Grid Jiangsu Electric Power Co., Ltd., Nanjing 210019, China
2. State Grid Jiangsu Electric Power Co., Ltd., Nanjing 210019, China

Received:2023-09-06 Revised:2024-03-10 Accepted:2024-03-11 Online:2025-07-28 Published:2025-07-22
Contact: WU Ning E-mail:wuning@sgcc.com.cn

摘要/Abstract

摘要：

在复杂的电力市场环境和数据信息不完全的条件下,快速识别电力用户电价异常,挖掘电价异常的原因,是促进电力市场的平稳有序运行以及保障电力用户合理利益的关键问题之一.提出一种电力市场环境下电力用户电价特征提取及异常识别方法,首先构建电价特征向量,基于谱聚类算法降低特征向量数据维度,并提取典型电价特征,将其作为判定电价异常的基准;然后逐一计算各电力用户与典型电价特征之间的相似程度,对电价异常进行两阶段分步识别:先从用电和交易行为两方面进行初步识别和快速定位,再在此基础上进行深入识别.案例分析显示该方法能够快速有效提取典型电价特征并识别电价异常.进一步从用电和交易行为两方面分析电价异常原因,并提出相应的改进措施.

关键词: 电力市场, 电价, 谱聚类, 特征提取, 异常识别

Abstract:

Identifying electricity price anomalies and exploring the underlying reasons in such a complex market environment, especially with incomplete data, is a key issue for promoting the orderly operation of power market and ensuring the reasonable interests of power customers. Therefore, a method is established for feature extraction and anomaly identification of electricity prices for power customers. First, an electricity price feature vector is constructed, and its dimensionality is reduced using a spectral clustering algorithm. Then, typical electricity price characteristics are extracted as the basic standard for determining price anomalies. Next, the similarity between each power customer and typical electricity price characteristics is calculated. Finally, electricity price anomalies are identified in two stages. The causes of anomalies are initially and rapidly identified based on electricity consumption and trading behavior, and then further identified in-depth. Case analysis shows that this method can quickly and effectively extract typical electricity price features and identify anomalies. The reasons behind these anomalies are further analyzed from both electricity consumption and trading behaviors, and corresponding improvement measures are proposed.

Key words: power market, electricity price, spectral clustering, feature extraction, anomaly identification

中图分类号:

TM721

朱峰, 单超, 吴宁, 蔡奇新, 祝宇楠, 刘云鹏, 左强. 电力市场环境下电力用户电价特征提取和异常识别方法[J]. 上海交通大学学报, 2025, 59(7): 995-1006.

ZHU Feng, SHAN Chao, WU Ning, CAI Qixin, ZHU Yunan, LIU Yunpeng, ZUO Qiang. Feature Extraction and Anomaly Identification Method for Power Customer Price in Power Market Enviroment[J]. Journal of Shanghai Jiao Tong University, 2025, 59(7): 995-1006.

图/表 8

图1

表1

表2

图2

图3

表3

图4

图5

参考文献 34

[1]	国家发展改革委. 关于进一步深化燃煤发电上网电价市场化改革的通知[EB/OL]. (2021-10-11)[2023-04-23]. https://www.ndrc.gov.cn/xxgk/zcfb/tz/202110/t20211012_1299461.html.
	National Development and Reform commission. Notice on further deepening the market reform of coal power generation price[EB/OL]. (2021-10-11)[2023-04-23]. https://www.ndrc.gov.cn/xxgk/zcfb/tz/202110/t20211012_1299461.html.
[2]	国家发展改革委办公厅. 关于组织开展电网企业代理购电工作有关事项的通知[EB/OL]. (2021-10-23)[2023-04-23]. https://www.ndrc.gov.cn/xwdt/tzgg/202110/t20211026_1300893.html.
	National Development and Reform commission. Notice on matters relating to the organization of agent power purchase of power grid enterprises[EB/OL]. (2021-10-23)[2023-04-23]. https://www.ndrc.gov.cn/xwdt/tzgg/202110/t20211026_1300893.html.
[3]	白杨, 李昂, 夏清. 新形势下电力市场营销模式与新型电价体系[J]. 电力系统保护与控制, 2016, 44(5): 10-16.
	BAI Yang, LI Ang, XIA Qing. Electricity business marketing modes in the new environment and new electricity pricing systems[J]. Power System Protection and Control, 2016, 44(5): 10-16.
[4]	沈同, 夏清. 实现资源时空优化配置的现货市场及其应用研究[J]. 智慧电力, 2018, 46(1): 1-6.
	SHEN Tong, XIA Qing. Spot market with temporal and spatial distribution optimization of resource and its application in China[J]. Smart Power, 2018, 46(1): 1-6.
[5]	吴洋, 辛茹, 邹文滔, 等. 提升电力现货市场出清结果可解释性的综合分析方法[J]. 南方电网技术, 2022, 16(6): 113-123.
	WU Yang, XIN Ru, ZOU Wentao, et al. Comprehensive analysis method for enhancing the explainability of electricity spot market clearing results[J]. Southern Power System Technology, 2022, 16(6): 113-123.
[6]	史新红, 郑亚先, 薛必克, 等. 机组运行约束对机组节点边际电价的影响分析[J]. 电网技术, 2019, 43(8): 2658-2665.
	SHI Xinhong, ZHENG Yaxian, XUE Bike, et al. Effect analysis of unit operation constraints on locational marginal price of unit nodes[J]. Power System Technology, 2019, 43(8): 2658-2665.
[7]	罗钢, 马辉, 陈晔, 等. 南方(以广东起步)电力现货市场模拟运行分析[J]. 南方电网技术, 2018, 12(12): 49-54.
	LUO Gang, MA Hui, CHEN Ye, et al. Analysis of simulation operation of electricity spot market in Southern China (starting from Guangdong Province)[J]. Southern Power System Technology, 2018, 12(12): 49-54.
[8]	王一, 马子明, 谭跃凯, 等. 广东日前电力市场方案设计与市场仿真[J]. 电力需求侧管理, 2018, 20(1): 10-14.
	WANG Yi, MA Ziming, TAN Yuekai, et al. Day-ahead power market design and market simulation in Guangdong Province[J]. Power Demand Side Management, 2018, 20(1): 10-14.
[9]	刘敦楠, 李瑞庆, 陈雪青, 等. 电力市场监管指标及市场评价体系[J]. 电力系统自动化, 2004, 28(9): 16-21.
	LIU Dunnan, LI Ruiqing, CHEN Xueqing, et al. Surveillance indices and evaluating system of electricity market[J]. Automation of Electric Power Systems, 2004, 28(9): 16-21.
[10]	刘敦楠, 陈雪青, 何光宇, 等. 电力市场评价指标体系的原理和构建方法[J]. 电力系统自动化, 2005, 29(23): 2-7.
	LIU Dunnan, CHEN Xueqing, HE Guangyu, et al. General principle and constitution process of evaluating indices system for electricity market[J]. Automation of Electric Power Systems, 2005, 29(23): 2-7.
[11]	罗舒瀚, 蒋传文, 王旭, 等. 新电改背景下售电公司的购售电策略及风险评估[J]. 电网技术, 2019, 43(3): 944-953.
	LUO Shuhan, JIANG Chuanwen, WANG Xu, et al. Power trading strategy and risk assessment of electricity retailing company under power system reform[J]. Power System Technology, 2019, 43(3): 944-953.
[12]	史连军, 庞博, 刘敦楠, 等. 新电改下北京电力交易中心电力市场综合指数的交易分析[J]. 电力系统自动化, 2019, 43(6): 163-170.
	SHI Lianjun, PANG Bo, LIU Dunnan, et al. Power market transaction analysis of index of Beijing electric power exchange center under new electricity reform[J]. Automation of Electric Power Systems, 2019, 43(6): 163-170.
[13]	郑海雁, 金农, 季聪, 等. 电力用户用电数据分析技术及典型场景应用[J]. 电网技术, 2015, 39(11): 3147-3152.
	ZHENG Haiyan, JIN Nong, JI Cong, et al. Analysis technology and typical scenario application of electricity big data of power consumers[J]. Power System Technology, 2015, 39(11): 3147-3152.
[14]	朱天怡, 艾芊, 贺兴, 等. 基于数据驱动的用电行为分析方法及应用综述[J]. 电网技术, 2020, 44(9): 3497-3507.
	ZHU Tianyi, AI Qian, HE Xing, et al. An overview of data-driven electricity consumption behavior analysis method and application[J]. Power System Technology, 2020, 44(9): 3497-3507.
[15]	陈静, 郑垂锭, 李桂敏, 等. 考虑行业关联度的工业用户用电异常识别研究[J]. 仪器仪表学报, 2023, 44(4): 72-81.
	CHEN Jing, ZHENG Chuiding, LI Guimin, et al. Research on power consumption anomaly identification of industrial users considering industry relevance[J]. Chinese Journal of Scientific Instrument, 2023, 44(4): 72-81.
[16]	刘宣, 唐悦, 卢继哲, 等. 基于概率预测的用电采集终端电量异常在线实时识别方法[J]. 电力系统保护与控制, 2021, 49(19): 99-106.
	LIU Xuan, TANG Yue, LU Jizhe, et al. Online real time anomaly recognition method for power consumption of electric energy data acquisition terminal based on probability prediction[J]. Power System Protection and Control, 2021, 49(19): 99-106.
[17]	程超鹏, 彭显刚, 曾勇斌, 等. 相异模型下Stacking集成结构的异常用电用户识别方法[J]. 电网技术, 2021, 45(12): 4828-4836.
	CHENG Chaopeng, PENG Xiangang, ZENG Yongbin, et al. An abnormal power user recognition method for stacking integrated structures with different models[J]. Power System Technology, 2021, 45(12): 4828-4836.
[18]	郑思达, 梁琪琳, 彭鑫霞, 等. 基于模糊聚类的异常用电行为识别研究[J]. 电测与仪表, 2020, 57(19): 40-44.
	ZHENG Sida, LIANG Qilin, PENG Xinxia, et al. Research on abnormal power consumption behavior identification based on fuzzy clustering[J]. Electrical Measurement & Instrumentation, 2020, 57(19): 40-44.
[19]	彭显刚, 郑伟钦, 林利祥, 等. 基于密度聚类和Fréchet判别分析的电价执行稽查方法[J]. 电网技术, 2015, 39(11): 3195-3201.
	PENG Xiangang, ZHENG Weiqin, LIN Lixiang, et al. A method to inspect the implementation of electricity price based on density clustering analysis and Fréchet discriminant analysis[J]. Power System Technology, 2015, 39(11): 3195-3201.
[20]	林幕群, 彭显刚, 林利祥, 等. 基于数据挖掘技术的电价执行在线稽查模型[J]. 广东电力, 2016, 29(1): 108-112.
	LIN Muqun, PENG Xiangang, LIN Lixiang, et al. Online inspection model for electricity price implementation based on data mining technology[J]. Guangdong Electric Power, 2016, 29(1): 108-112.
[21]	陆俊, 陈志敏, 龚钢军, 等. 基于极限学习机的居民用电行为分类分析方法[J]. 电力系统自动化, 2019, 43(2): 97-104.
	LU Jun, CHEN Zhimin, GONG Gangjun, et al. Classification analysis method for electricity consumption behavior based on extreme learning machine algorithm[J]. Automation of Electric Power Systems, 2019, 43(2): 97-104.
[22]	李春燕, 蔡文悦, 赵溶生, 等. 基于优化SAX和带权负荷特性指标的AP聚类用户用电行为分析[J]. 电工技术学报, 2019, 34 (Sup.1): 368-377.
	LI Chunyan, CAI Wenyue, ZHAO Rongsheng, et al. Analysis of power consumption behavior of AP cluster users based on optimized SAX and weighted load characteristic index[J]. Transactions of China Electrotechnical Society, 2019, 34 (Sup.1): 368-377.
[23]	孙吉贵, 刘杰, 赵连宇. 聚类算法研究[J]. 软件学报, 2008, 19(1): 48-61.
	SUN Jigui, LIU Jie, ZHAO Lianyu. Clustering algorithms research[J]. Journal of Software, 2008, 19(1): 48-61.
[24]	章永来, 周耀鉴. 聚类算法综述[J]. 计算机应用, 2019, 39(7): 1869-1882. doi: 10.11772/j.issn.1001-9081.2019010174
	ZHANG Yonglai, ZHOU Yaojian. Review of clustering algorithms[J]. Journal of Computer Applications, 2019, 39(7): 1869-1882. doi: 10.11772/j.issn.1001-9081.2019010174
[25]	杨俊闯, 赵超. K-Means聚类算法研究综述[J]. 计算机工程与应用, 2019, 55(23): 7-14. doi: 10.3778/j.issn.1002-8331.1908-0347
	YANG Junchuang, ZHAO Chao. Survey on K-Means clustering algorithm[J]. Computer Engineering and Applications, 2019, 55(23): 7-14. doi: 10.3778/j.issn.1002-8331.1908-0347
[26]	蔡晓妍, 戴冠中, 杨黎斌. 谱聚类算法综述[J]. 计算机科学, 2008, 35(7): 14-18.
	CAI Xiaoyan, DAI Guanzhong, YANG Libin. Survey on spectral clustering algorithms[J]. Computer Science, 2008, 35(7): 14-18.
[27]	游广增, 汤翔鹰, 胡炎, 等. 基于典型运行场景聚类的电力系统灵活性评估方法[J]. 上海交通大学学报, 2021, 55(7): 802-813. doi: 10.16183/j.cnki.jsjtu.2020.012
	YOU Guangzeng, TANG Xiangying, HU Yan, et al. Flexibility evaluation method for power system based on clustering of typical operating scenarios[J]. Journal of Shanghai Jiao Tong University, 2021, 55(7): 802-813.
[28]	刘敦楠, 徐尔丰, 刘明光, 等. 面向分布式电源就地消纳的园区分时电价定价方法[J]. 电力系统自动化, 2020, 44(20): 19-28.
	LIU Dunnan, XU Erfeng, LIU Mingguang, et al. TOU pricing method for park considering local consumption of distributed generator[J]. Automation of Electric Power Systems, 2020, 44(20): 19-28.
[29]	陈烨, 吴浩, 史俊祎, 等. 奇异值分解方法在日负荷曲线降维聚类分析中的应用[J]. 电力系统自动化, 2018, 42(3): 105-111.
	CHEN Ye, WU Hao, SHI Junyi, et al. Application of singular value decomposition algorithm to dimension-reduced clustering analysis of daily load profiles[J]. Automation of Electric Power Systems, 2018, 42(3): 105-111.
[30]	杜将武, 唐小强, 罗志伟, 等. 面向综合能源园区的丰枯电价定价方法[J]. 发电技术, 2023, 44(2): 261-269. doi: 10.12096/j.2096-4528.pgt.21119
	DU Jiangwu, TANG Xiaoqiang, LUO Zhiwei, et al. Pricing method for season of use in integrated energy park[J]. Power Generation Technology, 2023, 44(2): 261-269. doi: 10.12096/j.2096-4528.pgt.21119
[31]	李海侠, 林继灿, 李赓, 等. 基于加权余弦相似度与极限学习机的电力负荷短期预测[J]. 科学技术与工程, 2020, 20(11): 4370-4374.
	LI Haixia, LIN Jican, LI Geng, et al. Short-term power load forecasting based on weighted cosine similarity and extreme learning machine[J]. Science Technology and Engineering, 2020, 20(11): 4370-4374.
[32]	徐先峰, 赵依, 刘状壮, 等. 用于短期电力负荷预测的日负荷特性分类及特征集重构策略[J]. 电网技术, 2022, 46(4): 1548-1556.
	XU Xianfeng, ZHAO Yi, LIU Zhuangzhuang, et al. Daily load characteristic classification and feature set reconstruction strategy for short-term power load forecasting[J]. Power System Technology, 2022, 46(4): 1548-1556.
[33]	刘科研, 季玉琦, 陆凌芝, 等. 基于负荷分布匹配与熵权法的配电网无功优化[J]. 电网技术, 2017, 41(12): 3980-3988.
	LIU Keyan, JI Yuqi, LU Lingzhi, et al. Reactive power optimization in distribution network based on load distribution matching and entropy weight method[J]. Power System Technology, 2017, 41(12): 3980-3988.
[34]	许梦田, 王洪哲, 赵成萍, 等. 基于短期风功率预测的数据预处理算法研究[J]. 可再生能源, 2019, 37(1): 119-125.
	XU Mengtian, WANG Hongzhe, ZHAO Chengping, et al. Research on data preprocessing policy based on short-term wind power prediction[J]. Renewable Energy Resources, 2019, 37(1): 119-125.

时段	时间
峰段	9:00—11:00、14:00—16:00
平段	7:00—9:00、16:00—21:00
谷段	11:00—13:00、21:00—次日7:00

分类数量	k-means聚类		层次聚类		谱聚类
分类数量	CH指标	收敛时间/s	CH指标	收敛时间/s	CH指标	收敛时间/s
2	295.26	3.51	95.43	10.19	422.60	1.91
3	305.41	2.89	109.78	8.76	440.34	1.95
4	253.64	4.81	88.72	9.96	412.20	3.44
5	204.93	5.22	77.09	8.41	364.24	4.34
6	188.46	6.21	69.76	8.69	321.66	6.37
7	192.49	6.81	64.21	9.03	296.30	5.16
8	177.18	7.80	59.95	9.02	278.04	4.69
9	171.84	7.03	57.08	8.53	258.66	5.31
10	153.04	7.22	54.27	8.44	247.54	6.09

余弦相似度范围	用户占比/%
余弦相似度范围	小型商业电力用户	中小型工业电力用户	大型工业电力用户
[0.00, 0.86)	0.54	0.54	0.87
[0.86, 0.88)	0.27	0.38	0.44
[0.88, 0.90)	0.87	0.71	0.98
[0.90, 0.92)	0.92	1.03	0.87
[0.92, 0.94)	1.14	1.09	1.31
[0.94, 0.96)	1.85	2.12	3.16
[0.96, 0.98)	20.94	14.25	7.96
[0.98, 1.00]	73.46	79.87	84.41

电力市场环境下电力用户电价特征提取和异常识别方法

Feature Extraction and Anomaly Identification Method for Power Customer Price in Power Market Enviroment

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 34

相关文章 15

编辑推荐

Metrics

本文评价

[1]	包家汉, 孙德尚, 黄建中, 胡政. 基于自适应阈值的型钢精确角点FAST检测算法[J]. 上海交通大学学报, 2025, 59(5): 691-702.
[2]	刘长玺, 齐国民, 王继成, 李天野, 杨健, 雷霞. 考虑碳排放权交易的两阶段电力现货市场模式设计[J]. 上海交通大学学报, 2025, 59(3): 342-353.
[3]	娄为, 胡蓉, 于谨铭, 张希鹏, 樊飞龙, 刘嵩源. 内嵌市场博弈模型的电网-抽水蓄能多主体协调调度[J]. 上海交通大学学报, 2025, 59(3): 365-375.
[4]	孙欣, 王思敏, 谢敬东, 江海林, 王森. 考虑多维影响因素的改进Transformer-PSO短期电价预测方法[J]. 上海交通大学学报, 2024, 58(9): 1420-1431.
[5]	殷高文, 沈非凡, 黄晟, 魏娟, 屈尹鹏, 王鹏达. 面向电力市场多时间尺度场景应用的风储系统调度方法[J]. 上海交通大学学报, 2024, 58(9): 1410-1419.
[6]	邓佳莉, 胡昊, 戴磊. 动态充电电价将如何影响电动卡车车队运营：两阶段随机规划模型[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(6): 1050-1062.
[7]	刘增敏1, 2, 3, 4, 6, 王申涛5, 姚莉秀1, 2, 3, 蔡云泽1, 2, 3, 4, 6. 基于目标检测和特征提取网络的运动无人机平台下多目标跟踪[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(3): 388-399.
[8]	李威, 李然, 胡炎, 王曦炜, 熊康. 计及碳成本的区域间电价差与跨区电力交易量评估模型[J]. 上海交通大学学报, 2024, 58(12): 1835-1845.
[9]	张宪文, 殷高文, 沈非凡, 黄晟, 魏娟. 计及风电不确定性及碳交易的储能参与电力市场竞价策略[J]. 上海交通大学学报, 2024, 58(12): 1868-1880.
[10]	牛国臣, 孙翔宇, 苑峥岩. 基于双流特征提取的车路协同感知方法[J]. 上海交通大学学报, 2024, 58(11): 1826-1834.
[11]	任曦骏, 宋竹萌, 王宝, 叶钰童, 潘思佳, 王梦圆, 徐潇源. 输配电价改革背景下两部制电价的应用现状与发展前景[J]. 上海交通大学学报, 2024, 58(10): 1479-1488.
[12]	陈熠, 王晗, 徐潇源, 胡友琳, 严正, 曾丹, 冯凯. 省间-省内两级市场协调下两阶段分布鲁棒经济调度模型[J]. 上海交通大学学报, 2023, 57(9): 1114-1125.
[13]	吴磊, 韩冬, 毛贵江, 刘微, 周扬飞. 适应分布式发电市场化交易的过网费计算方法[J]. 上海交通大学学报, 2023, 57(7): 887-898.
[14]	刘飞, 车琰瑛, 田旭, 许德操, 周慧洁, 李知艺. 新型电力系统下的抽水蓄能电站成本疏导机制:综述与展望[J]. 上海交通大学学报, 2023, 57(7): 757-768.
[15]	曾志贤，曹建军，翁年凤，袁震，余旭. 基于细粒度联合注意力机制的图像-文本跨模态实体分辨[J]. J Shanghai Jiaotong Univ Sci, 2023, 28(6): 728-737.