面向新型电力系统的异常数据检测方法

doi:10.3969/j.issn.2097-0706.2024.05.002

摘要/Abstract

摘要：

随着新型电力系统的快速发展，电力系统产生的数据数量不断增值、种类也愈发多样。复杂化的数据环境为电力系统异常数据诊断带来了新的挑战。对目前电力系统中常用的异常数据检测方法进行总结，介绍了基于传统技术、机器学习、深度学习的检测方法，并分析了3类算法的检测原理、特点以及不足。最后，对新型电力系统中异常数据检测会遇到的挑战以及发展趋势进行了展望。

关键词: 新型电力系统, 异常数据, 机器学习, 深度学习, 传统技术, 异常检测

Abstract:

With the rapid development of new power systems， massive data with various types are generated from the power systems. The complicated data conditions bring new challenges to anomaly data detection for power systems. In a summary on commonly used methods for anomalous power data in detecting， traditional technology-based， machine learning-based and deep learning-based detection methods are introduces. The working principle， characteristics and shortcomings of the three types of detecting methods are analysed. In the end， the challenges and development trends of anomalous data detection in new power systems are looked forward.

Key words: new power system, abnormal data, machine learning, deep learning traditional technology, anomaly detection

中图分类号:

TK01：TM727

王亮, 邓松. 面向新型电力系统的异常数据检测方法[J]. 综合智慧能源, 2024, 46(5): 12-19.

WANG Liang, DENG Song. Anomalous data detection methods for new power systems[J]. Integrated Intelligent Energy, 2024, 46(5): 12-19.

图/表 2

参考文献 40

[1]	ANSCOMBE F J, GUTTMAN I. Rejection of outliers[J]. Technometrics, 1960, 2(2):123-146.
[2]	CHANDOLA V, BANERJEE A, KUMAR V. Anomaly detection: A survey[J]. ACM Computing Surveys (CSUR), 2009, 41(3): 1-58.
[3]	ASEFI S, MITROVIC M, ĆETENOVIĆ D, et al. Anomaly detection and classification in power system state estimation: Combining model-based and data-driven methods[J]. Sustainable Energy, Grids and Networks, 2023, 35: 101116.
[4]	KNORR E M, NG R T. Finding intensional knowledge of distance-based outliers[C]// Proceedings of 25th International Conference on Very Large Data Bases,1999:211-222.
[5]	ANGIULLI F, PIZZUTI C. Fast outlier detection in high dimensional spaces[C]// European conference on principles of data mining and knowledge discovery. Berlin, Heidelberg: Springer Berlin Heidelberg,2002:15-27.
[6]	李碧君, 薛禹胜, 顾锦汶, 等. 基于快速分解正交变换状态估计算法的坏数据检测与辨识[J]. 电力系统自动化, 1999, 23(20):1-4,26.
	LI Bijun, XUE Yusheng, GU Jinwen, et al. Bad data detection and identification based on fast decomposition orthogonal transform state estimation algorithm[J]. Automation of Electric Power Systems, 1999, 23(20):1-4,26.
[7]	BREUNIG M M, KRIEGEL H P, NG R T, et al. Optics-of: Identifying local outliers[C]// Proceedings of Third European Conference on Principles of Data Mining and Knowledge Discovery.1999: 262-270.
[8]	BREUNIG M M, KRIEGEL H P, NG R T, et al. LOF: Identifying density-based local outliers[C]// Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data. 2000: 93-104.
[9]	LIU S Y, ZHAO Y X, LIN Z Z, et al. Data-driven event detection of power systems based on unequal-interval reduction of PMU data and local outlier factor[J]. IEEE Transactions on Smart Grid, 2019, 11(2): 1630-1643.
[10]	YU S Q, LI X R, ZHAO L Y, et al. Hyperspectral anomaly detection based on low-rank representation using local outlier factor[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 18(7): 1279-1283.
[11]	MA J, TENG Z S, TANG Q, et al. Measurement error prediction of power metering equipment using improved local outlier factor and kernel support vector regression[J]. IEEE Transactions on Industrial Electronics, 2021, 69(9): 9575-9585.
[12]	TIRULO A, CHAUHAN S, ISSAC B. Ensemble LOF-based detection of false data injection in smart grid demand response system[J]. Computers and Electrical Engineering, 2024, 116: 109188.
[13]	ZHANG J F, ZHANG H, DING S, et al. Power consumption predicting and anomaly detection based on transformer and K-means[J]. Frontiers in Energy Research, 2021,9: 779587.
[14]	NI Y R, ZENG X J, LIU Z L, et al. Faulty feeder detection of single phase-to-ground fault for distribution networks based on improved K-means power angle clustering analysis[J]. International Journal of Electrical Power & Energy Systems, 2022, 142: 108252.
[15]	HUANG L, CHANG J, YANG F, et al. An anomaly detection method for electric power information system based on improved k-means[J]. Journal of Shenzhen University Science & Engineering, 2020, 37(2):214-220.
[16]	CHIANG H D, XU T S, LV X L, et al. Hierarchical trust-tech-enhanced k-means methods and their applications to power grids[J]. IEEE Open Access Journal of Power and Energy, 2022, 9: 560-572.
[17]	YANG Y N, XUE Y, CAI H, et al. Electricity stealing time recognition method based on difference and K-means clustering[C]// IOP Conference Series: Earth and Environmental Science. IOP Publishing, 2021, 647(1): 012075.
[18]	LENG D, QIU Z. Identification of anomaly detection in power system state estimation based on fuzzy C-means algorithm[J]. International Transactions on Electrical Energy Systems, 2023: 7553080.
[19]	ANGELOS E W S, SAAVEDRA O R, CORTÉS O A C, et al. Detection and identification of abnormalities in customer consumptions in power distribution systems[J]. IEEE Transactions on Power Delivery, 2011, 26(4): 2436-2442.
[20]	宋军英, 何聪, 李欣然, 等. 基于特征指标降维及熵权法的日负荷曲线聚类方法[J]. 电力系统自动化, 2019, 43(20): 65-72.
	SONG Junying, HE Cong, LI Xinran, et al. Daily load curve clustering method based on feature index dimension reduction and entropy weight method[J]. Automation of Electric Power Systems, 2019, 43(20):65-72.
[21]	MIRAFTABZADEH S M, LONGO M, BRENNA M. Knowledge extraction from PV power generation with deep learning autoencoder and clustering-based algorithms[J]. IEEE Access, 2023, 11: 69227-69240.
[22]	LIU W J, LEI P F, XU D, et al. Anomaly recognition diagnosis and prediction of massive data flow based on time-GAN and DBSCAN for power dispatching automation system[J]. Processes, 2023, 11(9): 2782.
[23]	MA W, MA M, ZHANG Z, et al. Anomaly detection of mountain photovoltaic power plant based on spectral clustering[J]. IEEE Journal of Photovoltaics, 2023, 13(4): 621-631.
[24]	PARVEZ I, AGHILI M, SARWAT A I, et al. Online power quality disturbance detection by support vector machine in smart meter[J]. Journal of Modern Power Systems and Clean Energy, 2019, 7(5): 1328-1339.
[25]	CHOI J, ROSHANZADEH B, MARTINEZ-RAMON M, et al. An unsupervised cyberattack detection scheme for AC microgrids using Gaussian process regression and one-class support vector machine anomaly detection[J]. IET Renewable Power Generation, 2023, 17(8): 2113-2123.
[26]	武玉坤, 李伟, 倪敏雅, 等. 单类支持向量机融合深度自编码器的异常检测模型[J]. 计算机科学, 2022, 49(3):144-151. doi: 10.11896/jsjkx.210100142
	WU Yukun, LI Wei, NI Minya, et al. Anomaly detection model based on one-class support vector machine fused deep auto-encoder[J]. Computer Science, 2022, 49(3):144-151. doi: 10.11896/jsjkx.210100142
[27]	ROY S D, DEBBARMA S. A novel OC-SVM based ensemble learning framework for attack detection in AGC loop of power systems[J]. Electric Power Systems Research, 2022, 202: 107625.
[28]	LI S M, PANDEY A, HOOI B, et al. Dynamic graph-based anomaly detection in the electrical grid[J]. IEEE Transactions on Power Systems, 2021, 37(5): 3408-3422.
[29]	ZENG X J, YANG M, FENG C, et al. A generalized wind turbine anomaly detection method based on combined probability estimation model[J]. Journal of Modern Power Systems and Clean Energy, 2022, 11(4):1136-1148.
[30]	CARRATÙ M, GALLO V, IACONO S D, et al. A novel methodology for unsupervised anomaly detection in industrial electrical systems[J]. IEEE Transactions on Instrumentation and Measurement, 2023,72: 1-12.
[31]	GAO H, YANG D, CAI G, et al. Machine learning-based reliability improvement of ambient mode extraction for smart grid utilizing isolation forest[J]. IEEE Transactions on Power Systems, 2022, 38(5):4752-4760.
[32]	HALLAC D, NYSTRUP P, BOYD S. Greedy Gaussian segmentation of multivariate time series[J]. Advances in Data Analysis and Classification, 2019, 13(3):727-751. doi: 10.1007/s11634-018-0335-0
[33]	WANG X, FLORES R, BROUWER J, et al. Real-time detection of electrical load anomalies through hyper-dimensional computing[J]. Energy, 2022,261:125042.
[34]	吕政权, 李朝阳, 王海峰, 等. 基于GRU-CNN的综合能源网络安全攻击检测方法[J]. 华电技术, 2021, 43(2): 9-14.
	LYU Zhengquan, LI Zhaoyang, WANG Haifeng, et al. An intrusion detection method for integrated energy network based on GRU-CNN[J]. Huadian Technology, 2021, 43(2): 9-14.
[35]	任一鸣, 杜董生, 邓祥帅, 等. 基于GRU和GWO-KELM的电力线路故障诊断[J]. 综合智慧能源, 2024, 46(3): 54-62. doi: 10.3969/j.issn.2097-0706.2024.03.007
	REN Yiming, DU Dongsheng, DENG Xiangshuai, et al. Power line fault diagnosis based on GRU and GWO-KELM[J]. Integrated Intelligent Energy, 2024, 46(3): 54-62. doi: 10.3969/j.issn.2097-0706.2024.03.007
[36]	ZULFAUZI I A, DAHLAN N Y, SINTUYA H, et al. Anomaly detection using k-means and long-short term memory for predictive maintenance of large-scale solar (LSS) photovoltaic plant[J]. Energy Reports, 2023,9: 154-158.
[37]	王文博, 刘绚, 林海, 等. 基于深度学习的电力工控流量应用层报文异常检测[J]. 电力系统自动化, 2023, 47(11):69-76.
	WANG Wenbo, LIU Xun, LIN Hai, et al. Deep learning based anomaly detection for application-layer message of power industrial control communication traffic[J]. Automation of Electric Power Systems, 2023, 47(11):69-76.
[38]	WANG G, WANG C, SHAHIDEHPOUR M, et al. Deep semi-supervised learning method for false data detection against forgery and concealing of faults in cyber-physical power systems[J]. IEEE Transactions on Smart Grid, 2024, 15(1):944-958.
[39]	MAAMAR A, BENAHMED K. A hybrid model for anomalies detection in AMI system combining k-means clustering and deep neural network[J]. Computers, Materials & Continua, 2019, 60(1): 15-39.
[40]	MESTAV K R, WANG X Y, TONG L. A deep learning approach to anomaly sequence detection for high-resolution monitoring of power systems[J]. IEEE Transactions on Power Systems, 2022, 38(1): 4-13.