Multimodal Operation Data Mining for Grid Operation Violation Risk Prediction

被引:1
作者
Meng, Lingwen [1 ]
Zhong, Jingliang [1 ]
Luo, Shasha [1 ]
Zhu, Xinshan [2 ]
Wang, Yulin [2 ]
Zhang, Shumei [2 ]
机构
[1] Elect Power Sci Res Inst Guizhou Power Grid Guizho, Guiyang 550000, Peoples R China
[2] Tianjin Univ, Sch Elect Automat & Informat Engn, Tianjin 300072, Peoples R China
关键词
violation dictionary construction; operation risk prediction; random forests; independent component analysis; mutual information; ALGORITHMS;
D O I
10.3390/en17215424
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
With the continuous expansion of the power grid, the issue of operational safety has attracted increasing attention. In power grid operation control, unauthorized operations are one of the primary causes of personal accidents. Therefore, preventing and monitoring unauthorized actions by power grid operators is of critical importance. First, multimodal violation data are integrated through information systems, such as the power grid management platform, to construct a historical case database. Next, word vectors for three types of operation-related factors are generated using natural language processing techniques, and key vectors are selected based on generalized correlation coefficients using mutual information, enabling effective dimensionality reduction. Independent component analysis is then employed for feature extraction and further dimensionality reduction, allowing for the effective characterization of operational scenarios. For each historical case, a risk score is derived from a violation risk prediction model constructed using the Random Forests (RF) algorithm. When a high-risk score is identified, the K-Nearest Neighbor (KNN) algorithm is applied to locate similar scenarios in the historical case database where violations may have occurred. Real-time violation risk assessment is performed for each operation, providing early warnings to operators, thereby reducing the likelihood of violations, and enhancing the safety of power grid operations.
引用
收藏
页数:15
相关论文
共 24 条
[1]   Towards Sustainable Energy Grids: A Machine Learning-Based Ensemble Methods Approach for Outages Estimation in Extreme Weather Events [J].
Alhaddad, Ulaa ;
Basuhail, Abdullah ;
Khemakhem, Maher ;
Eassa, Fathy Elbouraey ;
Jambi, Kamal .
SUSTAINABILITY, 2023, 15 (16)
[2]  
[Anonymous], 2012, P CONSTR RES C 2012
[3]  
Awasthi S., 2024, J. Inst. Eng. Ser. B, V105, P621, DOI [10.1007/s40031-024-00994-4, DOI 10.1007/S40031-024-00994-4]
[4]   Fuzzy KNN Method With Adaptive Nearest Neighbors [J].
Bian, Zekang ;
Vong, Chi Man ;
Wong, Pak Kin ;
Wang, Shitong .
IEEE TRANSACTIONS ON CYBERNETICS, 2022, 52 (06) :5380-5393
[5]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[6]   Safety Risk Assessment of Electric Power Operation Site Based On Variable Precision Rough Set [J].
Chang, Zhengwei ;
Deng, Yuanshi ;
Wu, Jie ;
Xiong, Xingzhong ;
Chen, Mingju ;
Wang, Hong ;
Xie, Xiaona .
JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS, 2022, 31 (14)
[7]   A Lightweight Detection Scheme for the Safety of Human Behaviors in Power Construction Sites [J].
Chen, Bo ;
Zhang, Hongyu ;
Li, Ying ;
Fang, Xiao ;
Chen, Haiyang .
JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS, 2023, 32 (14)
[8]  
Ding Yi, 2021, 2021 International Conference on Wireless Communications and Smart Grid (ICWCSG), P561, DOI 10.1109/ICWCSG53609.2021.00119
[9]   Fast and robust fixed-point algorithms for independent component analysis [J].
Hyvärinen, A .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (03) :626-634
[10]   Independent component analysis:: algorithms and applications [J].
Hyvärinen, A ;
Oja, E .
NEURAL NETWORKS, 2000, 13 (4-5) :411-430