Meteorological Factor-Based Early Warning of Power Grid Faults via the Meta-Fuse Framework
DOI:
https://doi.org/10.4108/ew.11474Keywords:
Power grid fault prediction, Convolutional Neural Networks, Multi-Head Attention, BiLSTMAbstract
INTRODUCTION: Extreme weather events increasingly threaten power grid resilience, causing cascading failures, while conventional models fail to capture complex interactions among meteorological, topological, and spatiotemporal factors.
OBJECTIVES: This paper aims to develop Meta-Fuse, a meteorological attention-based fused model, for early warning of power grid faults under environmental uncertainty.
METHODS: This study utilizes methods grounded in the analysis of social networks. The proposed framework integrates Triangular Topology Aggregation Optimization, a CNN-BiLSTM pipeline for spatiotemporal feature extraction, and a multi-head attention classifier, fused via a hybrid CRITIC-entropy strategy.
RESULTS: The model achieves a classification accuracy of 0.9464 with incomplete weather data and maintains a sensitivity of 0.9309 with high-dimensional features, outperforming traditional architectures.
CONCLUSION: Meta-Fuse demonstrates effective topology-informed learning and multimodal fusion, confirming its value for proactive resilience strategies in weather-exposed power systems.
Downloads
References
[1] Varbella, Anna, Blazhe Gjorgiev and Giovanni Sansavini. “Geometric deep learning for online prediction of cascading failures in power grids.” Reliab. Eng. Syst. Saf. 2023; 237: 109341.
[2] LI Y, WEI L-F, ZHAO Y, et al. Analysis and discussion on lightning protection of transmission line in marine area. Zhejiang Electric Power. 2017; 36(1): 14-18.
[3] Vineeth VV, Vijayalakshmi VJ. A novel deep learning approach for estimating and classifying short-term voltage stability events in modern power systems with composite load and distributed energy resources. Electr Eng. 2025;107:1783–1795.
[4] ZHANG W, SHENG W-X, LIU K-Y, et al. A prediction method of fault risk level for distribution network considering correlation of weather factors. Power System Technology. 2018; 42(8): 2391-2398.
[5] WANG L, SHENG L-L, MA M-C. Fault diagnosis and trace method of power system based on big data platform. In: IOP Conference Series: Materials Science and Engineering. Proceedings of the Conference; 2018; Tianjin, China. Bristol, UK: IOP Publishing; 2018. p. 394-401.
[6] Gao Z, Liu X. An overview on fault diagnosis, prognosis and resilient control for wind turbine systems. Processes. 2021;9(2):300.
[7] Zhang, Jiahao, Lan Cheng, Zhile Yang, Qinge Xiao, Sohail Khan, Rui Liang, Xinyu Wu and Yuanjun Guo. “An enhanced semi-supervised learning method with self-supervised and adaptive threshold for fault detection and classification in urban power grids.” Energy and AI. 2024; 17: 100377.
[8] Liu J, Duan Z, Liu H. A grid fault diagnosis framework based on adaptive integrated decomposition and cross-modal attention fusion. Neural Netw. 2024; 178: 106400.
[9] Zhao S, Zhang T, Cai L, et al. Triangulation topology aggregation optimizer: A novel mathematics-based meta-heuristic algorithm for continuous optimization and engineering applications. Expert Systems with Applications. 2024;238:121744.
[10] Guerraiche K, Bouadjmi A, Dekhici L. Intelligent fault detection and location in electrical high-voltage transmission lines. Revue Roumaine des Sciences Techniques — Série Électrotechnique et Énergétique. 2024;69(3):269-276.
[11] Chen X, Tang J, Li W. Probabilistic operational reliability of composite power systems considering multiple meteorological factors. IEEE Trans Power Syst. 2020;35(1):85-97.
[12] Stankovski A, Gjorgiev B, Locher L, et al. Power blackouts in Europe: Analyses, key insights, and recommendations from empirical evidence. Joule. 2023;7(11):2468-2484.
[13] Karnavas YL, Nivolianiti E. Optimal load frequency control of a hybrid electric shipboard microgrid using jellyfish search optimization algorithm. Appl Sci. 2023;13(10):6128.
[14] Fallah S, Ganjkhani M, Shamshirband S, et al. Computational intelligence on short-term load forecasting: a methodological overview. Energies. 2019;12(3):393.
[15] Kuster C, Rezgui Y, Mourshed M. Electrical load forecasting models: a critical systematic review. Sustainable Cities and Society. 2017;35:257-270.
[16] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. 2017.
[17] Guo X, Yang Y, He Z, et al. Fault diagnosis method based on MSCNN-BiLSTM for marine engine rolling bearing. In: 2024 3rd International Joint Conference on Information and Communication Engineering (JCICE). Proceedings of the JCICE 2024; 10-12 May 2024; Fuzhou, China. Piscataway, NJ, USA: IEEE; 2024. p. 212-216.
[18] Liao X, Mao Y. Rolling bearing fault diagnosis method based on attention mechanism and CNN-BiLSTM. Proceedings of SPIE. 2023;12722:8.
[19] Li Y, Ma J. Rolling bearing fault diagnosis based on channel attention multi-scale convolution-BiLSTM network. In: 2024 IEEE 13th Data Driven Control and Learning Systems Conference (DDCLS). Proceedings of the DDCLS 2024; 17-19 May 2024; Kaifeng, China. Piscataway, NJ, USA: IEEE; 2024. 61-66.
[20] Bach, A., Le, T. D., and Petit, M. Deployability of a Probabilistic Earth Fault Location Method for MV Distribution Feeders. IEEE Trans. Power Deliv. 2024; 39(2): 1174-1185.
[21] Lili B, Zhennan H, Yanfeng L, et al. A hybrid de-noising algorithm for the gear transmission system based on CEEMDAN-PE-TFPF. Entropy. 2018;20(5):361.
[22] Fazlipour Z, Mashhour E, Joorabian M. A deep model for short-term load forecasting applying a stacked autoencoder based on LSTM supported by a multi-stage attention mechanism. Applied Energy. 2022;327:120063.
[23] Thakkar A, Lohiya R. A survey on intrusion detection system feature selection, model, performance measures, application perspective, challenges, and future research directions. Artif Intell Rev. 2022;55(1):453-563
[24] Thakkar A, Lohiya R. A survey on intrusion detection systems: Feature selection, models, and challenges. Artif Intell Rev. 2022;55(1):453–563.
[25] Santos GG, Menezes TS, Barra PHA, et al. An efficient fault diagnostic approach for active distribution networks considering adaptive detection thresholds. Int J Electr Power Energy Syst. 2022;136:107663.
[26] Poursaeed AH, Namdari F. Online transient stability assessment implementing the weighted least-square support vector machine with the consideration of protection relays. Prot Control Mod Power Syst. 2025;10(1):1-17.
[27] Sun F. Wind turbine bearing failure diagnosis using multi-scale feature extraction and residual neural networks with block attention. Actuators. 2024;13:401.
[28] Boyd JD, Tyler JH, Murphy AM, et al. Learning from power signals: an automated approach to electrical disturbance identification within a power transmission system. Sensors. 2024;24(2):483.
[29] Najafzadeh M, Pouladi J, Abedinzade T. Fault detection, classification and localization along the power grid line using optimized machine learning algorithms. Int J Comput Intell Syst. 2024;17(1):1-18.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Yong Jiang, Yuanqing Shi, Weifeng Cao, Renzhi Zhang, Zehui Xie, Wei Deng
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
