Learning and Analysis of Dynamic Models for Grid Discrete Events Based on Log Information

doi:10.16182/j.issn1004731x.joss.23-FZ0800

Abstract

Abstract:

With the increasing scale of power grid, the massive amount of log information generated by devices in the power grid poses a challenge to the manual analysis of abnormal grid conditions. The log information generated during the operation of the power grid has the typical discrete sequential characteristics. By analyzing the log information of grid alarm messages, a station event transition probability model and an event sequence risk calculation method are proposed to effectively model and analyze the abnormal operation level of primary and secondary systems in substations. The proposed method not only successfully identifies the event sequences corresponding to grid failures that have been manually recarded by dispatchers but also identifies the abnormal alarm information sequences that have not been recorded by dispatchers. This helps analyze and assess the operational situation of power grid equipment, discover potential risks, and improve the efficiency of substation maintenance.

Key words: power system, alarm information, dynamic feature learning, anomaly detection, risk assessment

CLC Number:

TM769

Zhu Danlong, Yan Yunqi, Chen Ying, Zhang Jiaqi, Jin Longxing, Fu Wei. Learning and Analysis of Dynamic Models for Grid Discrete Events Based on Log Information[J]. Journal of System Simulation, 2023, 35(10): 2193-2201.

Figures/Tables 9

Table 1

Fig. 1

Table 2

Table 3

Fig. 2

Fig. 3

Fig. 4

Table 4

Fig. 5

References 15

1	魏利胜, 张倩. 基于改进的UKF智能电网虚假数据攻击检测[J]. 系统仿真学报, 2023, 35(7): 1508-1516.
	Wei Lisheng, Zhang Qian. Detection of False Data Injection Attack in Smart Grid Based on Improved UKF[J]. Journal of System Simulation, 2023, 35(7): 1508-1516.
2	刘兴华, 董思文, 田佳强. 基于卡尔曼滤波分解的配电网安全状态估计[J]. 系统仿真学报, 2023, 35(6): 1191-1202.
	Liu Xinghua, Dong Siwen, Tian Jiaqiang. Secure State Estimation of Distribution Network Based on Kalman Filter Decomposition[J]. Journal of System Simulation, 2023, 35(6): 1191-1202.
3	汪崔洋. 基于告警信号文本挖掘的电力调控智能分析与故障诊断[D]. 杭州: 浙江大学, 2019.
	Wang Cuiyang. Intelligent Analysis and Fault Diagnosis of Power Disnatching Based on Alarm Signal Text Mining[D]. Hangzhou: Zhejiang University, 2019.
4	Zhu Yongli, Huo Limin, Lu Jinling. Bayesian Networks-based Approach for Power Systems Fault Diagnosis[J]. IEEE Transactions on Power Delivery, 2006, 21(2): 634-639.
5	Lo K L, Ng H S, Trecat J. Extended Petri Net Models for Fault Diagnosis for Substation Automation[J]. IEE Proceedings-generation, Transmission and Distribution, 1999, 146(3): 229-234.
6	Fukui C, Kawakami J. An Expert System for Fault Section Estimation Using Information From Protective Relays and Circuit Breakers[J]. IEEE Power Engineering Review, 1986, PER-6(10): 29-30.
7	邓甜甜, 熊荫乔, 何贤浩. 一种基于时序性告警的新型聚类算法[J]. 计算机科学, 2020, 47(增1): 440-443, 473.
	Deng Tiantian, Xiong Yinqiao, He Xianhao. Novel Clustering Algorithm Based on Timing-featured Alarms[J]. Computer Science, 2020, 47(S1): 440-443, 473.
8	林斌, 曾瑛, 李星南, 等. 基于近邻传播聚类的电力通信告警分析方法[J]. 电子设计工程, 2016, 24(16): 142-145.
	Lin Bin, Zeng Ying, Li Xingnan, et al. An Analysis Method of Power Communication Alarm Information Based on Affinity Propagation Clustering[J]. Electronic Design Engineering, 2016, 24(16): 142-145.
9	郭云. 基于深度学习的电网故障诊断[D]. 北京: 华北电力大学(北京), 2020.
	Guo Yun. Power System Fault Diagnosis Based on Deep Learning[D]. Beijing: North China Electric Power University(Beijing), 2020.
10	Andrade J R, Rocha C, Silva R, et al. Data-driven Anomaly Detection and Event Log Profiling of SCADA Alarms[J]. IEEE Access, 2022, 10: 73758-73773.
11	刘家瑞, 杨国田, 王孝伟. 基于孪生深度神经网络的风电机组故障诊断方法[J]. 系统仿真学报, 2022, 34(11): 2348-2358.
	Liu Jiarui, Yang Guotian, Wang Xiaowei. A Wind Turbine Fault Diagnosis Method Based on Siamese Deep Neural Network[J]. Journal of System Simulation, 2022, 34(11): 2348-2358.
12	杜修明, 秦佳峰, 郭诗瑶, 等. 电力设备典型故障案例的文本挖掘[J]. 高电压技术, 2018, 44(4): 1078-1084.
	Du Xiuming, Qin Jiafeng, Guo Shiyao, et al. Text Mining of Typical Defects in Power Equipment[J]. High Voltage Engineering, 2018, 44(4): 1078-1084.
13	王哲. 基于文本挖掘的电网告警信息智能识别及应用研究[D]. 济南: 山东大学, 2021.
	Wang Zhe. Research on Intelligent Recognition and Application of Alarm Information in Power Grid Based on Text Mining[D]. ji'nan: Shandong University, 2021.
14	周志华. 机器学习[M]. 北京: 清华大学出版社, 2016.
	Zhou Zhihua. Machine Learning[M]. Beijing: Tsinghua University Press, 2016.
15	深圳供电局有限公司. 深圳电网调度及厂站监控系统信息采集技术管理细则[R]. [出版地不详]: 深圳供电局有限公司, 2019.

设备名称	规范信息描述
220 kV 母线保护	220 kV×M-×M母线保护I动作跳220 kV×M
	220 kV×M-×M母线保护I动作跳220 kV母联(分段)20××
	220 kV×M-×M失灵保护I动作跳220 kV×M
	220 kV×M-×M母线保护I动作线路跟跳
	……
220 kV 线路间隔	220 kV××线××主一保护动作
	220 kV××线××主一保护重合闸动作
	220 kV××线××保护第一组出口跳闸
	220 kV××线××保护第二组出口跳闸
	……

告警信息
处理前	2018-09-15 14:17:25，秀丽站＃1、＃2主变故障录波屏启动录波复归
	2018-09-26 17:00:00，塘朗站 220 kV 翡朗甲线9517保护第二组出口跳闸动作
	2018-09-28 15:52:00，玉翠站 110 kV 民翠线1679保护通信中断动作
处理后	2018-09-15 14:17:25/TIME 秀丽站/SUB #1/EQP #2主变/EQP 故障录波屏/CM 启动录波/BEH 复归/ACT
	2018-09-26 17:00:00/TIME 塘朗站/SUB 220 kV/ VOLT 翡朗甲线9517/EQP 保护/CM 第二组/OTH 出口跳闸/BEH 动作/ACT
	2018-09-28 15:52:00/TIME 玉翠站/SUB 110 kV/ VOLT 民翠线1679/EQP 保护/CM 通信中断/BEH 动作/ACT

风险阈值	召回率	假正例率
1	0.99	0.43
2	0.95	0.15
4	0.90	0.06
5	0.89	0.04
10	0.74	0.02
20	0.53	0.01

[1]	Li Dongsheng, Liu Ye, Song Yankan, Shen Chen. Electromagnetic Transient Equivalent Modeling Method for Wind Power Clusters Adapted to Expected Faults [J]. Journal of System Simulation, 2023, 35(10): 2101-2112.
[2]	Guangqiu Huang, He Wang. Dynamic Risk Assessment of VOCs Cross Regional Flow Based on Petri Nets [J]. Journal of System Simulation, 2023, 35(1): 57-68.
[3]	Ningke Sun, Yan Wang, Zhicheng Ji. Anomaly Detection Method of Electrical Power Consumption Based on Deep Autoencoder [J]. Journal of System Simulation, 2022, 34(12): 2557-2565.
[4]	Dong Shuqin, Zhang Bin. Network Traffic Anomaly Detection Method for Imbalanced Data [J]. Journal of System Simulation, 2021, 33(3): 679-689.
[5]	Liu Xuan, Li Xiangyang, He Fang, Zhao Jianwei, Zhang Fenggan. Hyperspectral RX Anomaly Detection Method Based on the Fusion of Spatial and Spectral Feature [J]. Journal of System Simulation, 2021, 33(12): 2891-2900.
[6]	Tang Hanwen, Zhang Tao, Li Yumei, Li Lei, Zhang Jinghua, Hu Dongliang. Research on Stick-slip Vibration Level Estimation of Near-bit Based on Optimized XGBoost [J]. Journal of System Simulation, 2021, 33(11): 2704-2710.
[7]	Dong Weijie, Huang Min, He Guoqing, Bao Wei, Wang Yilong, Liu Quan. An Electromechanical-electromagnetic Transient Stability Simulation System for AC/DC Hybrid Power System [J]. Journal of System Simulation, 2021, 33(11): 2711-2719.
[8]	Li haibin, Wang jialiang, Li haiyan. Uncertainty Quantitative Analysis in Risk Assessment of Returning to School in the Post-COVID-19 Era [J]. Journal of System Simulation, 2021, 33(1): 13-23.
[9]	Song Xiaorui, Zou Ling, Wu Lingda, Xu Wanpeng. Hyperspectral Image Anomaly Detection Based on Background Reconstruction [J]. Journal of System Simulation, 2020, 32(7): 1287-1293.
[10]	Chen Ying, He Dandan. Abnormal Behavior Detection via Super-Pixels Time Context Feature [J]. Journal of System Simulation, 2018, 30(9): 3538-3545.
[11]	Li Haiying, Xue Zhuocheng. Stability Analysis of Post-fault Power Angle Based on Relevance Vector Machine [J]. Journal of System Simulation, 2018, 30(8): 3098-3104.
[12]	Wang Weiyi, Xiao Lei, Lin Dejun. Simulation Research on Generator Sets of Offshore Drilling Platform [J]. Journal of System Simulation, 2018, 30(2): 664-671.
[13]	Huang Song, Wang Yan, Ji Zhicheng. Study of Dynamic Economic Load Dispatch Using Particle Swarm Optimization with Multi-information Characteristics [J]. Journal of System Simulation, 2017, 29(9): 2159-2167.
[14]	Yu Miao, Shang Weipeng, Lu Ning. Coordinated Control of Power System Based on Direct Neural Dynamic Programming Method [J]. Journal of System Simulation, 2017, 29(4): 699-707.
[15]	He Zhi, Nie Zhicheng, Qin Yining, Fan Youping. Parameter Identification Method Based on LagrangeMultiplier and Measuring Residual Error [J]. Journal of System Simulation, 2017, 29(12): 2964-2971.