Leveraging Deep Learning Algorithms for Predicting Power Outages and Detecting Faults: A Review
Mohammed Rizvi *
Exelon Corporation, USA.
*Author to whom correspondence should be addressed.
Abstract
Power outage prediction and fault detection play crucial roles in ensuring the reliability and stability of electrical power systems. Traditional methods for predicting power outages and detecting faults rely on rule-based approaches and statistical analysis, which often fall short of accurately capturing the complex patterns and dynamics of power systems. Deep learning algorithms, with their ability to learn automatically representations from large amounts of data, have emerged as promising solutions for addressing these challenges. In this literature review, we present an overview of deep learning algorithms applied to power outage prediction and fault detection. The purpose of this literature review is to explore the uses, effectiveness and advantages and disadvantages of utilizing deep learning algorithms in this domain. Various deep-learning models were explored in the context of power outage prediction and fault detection. Convolutional Neural Networks (CNNs) are effective in analyzing spatial dependencies and patterns in power system data, such as voltage levels and load distributions. Recurrent Neural Networks (RNNs), particularly Long Short Term Memory (LSTM) networks, excel in capturing temporal dependencies and patterns in time series data such as power demand and line currents. Generative Adversarial Networks (GANs) offer a unique approach by generating synthetic power system data for training purposes. This literature review involve collecting historical power system data from various sites. Deep-learning algorithms demonstrated promising results in power outage prediction and fault detection. It achieved a high accuracy rate of 95% in predicting power outages and accurately classified various fault types with an average precision of 92%. The findings highlight the advantages of deep learning algorithms in power outage prediction and fault detection. This literature review provides a comprehensive review of deep learning algorithms in the context of power outage prediction and fault detection.
Keywords: Deep learning, CNN, RNN, GAN, fault detection
How to Cite
References
Santi M. Predicting faults in power grids using machine learning methods; 2019.
Yi W, Zhang H, Ma S, Ma B. Research on circuit board fault detection algorithm based on computer vision technology. 2022 3rd International Conference on Information Science, Parallel and Distributed Systems, ISPDS 2022, Institute of Electrical and Electronics Engineers Inc. 2022;413–416. DOI: 10.1109/ISPDS56360.2022.9874098
Jaech A, Zhang B, Ostendorf M, Kirschen DS. Real-time prediction of the duration of distribution system outages; Apr. 2018. [Online]. Available:http://arxiv.org/abs/1804.01189
Bodda S, Thawait A, Agnihotri P. Comparative analysis of deep learning and machine learning techniques for power system fault type classification and location prediction. 2022 IEEE International IOT, Electronics and Mechatronics Conference, IEMTRONICS 2022, Institute of Electrical and Electronics Engineers Inc.; 2022.
DOI:10.1109/IEMTRONICS55184.2022.9795781.
Mgaya S, Maziku H. Machine learning approach for classifying power outage in secondary electric distribution network. Tanzania Journal of Engineering and Technology. Jul. 2022;41(1):1–9. DOI: 10.52339/tjet.vi.767
‘Power Outage Prediction for DFW and Houston using ML and Time Series’.
Veera T, Satya V, Anil Babu S. Machine learning for power demand, availability and outage forecasting for a microgrid in Tezpur University India’. [Online]. Available:http://www.teknik.uu.se/education/
Azad S, Sabrina F, Wasimi S, Transformation of smart grid using machine learning. 2019 29th Australasian Universities Power Engineering Conference, AUPEC 2019, Institute of Electrical and Electronics Engineers Inc.; Nov. 2019. DOI: 10.1109/AUPEC48547.2019.211809
Mnyanghwalo D, Kundaeli H, Kalinga E, Hamisi N. Deep learning approaches for fault detection and classifications in the electrical secondary distribution network: Methods comparison and recurrent neural network accuracy comparison. Cogent Eng. 2020;7(1). DOI: 10.1080/23311916.2020.1857500
Maduako I, et al. Deep learning for component fault detection in electricity transmission lines. J Big Data. Dec. 2022; 9(1). DOI: 10.1186/s40537-022-00630-2
Ruan H, Dorneanu B, Arellano-Garcia H, Xiao P, Zhang L. Deep learning-based fault prediction in wireless sensor network embedded cyber-physical systems for industrial processes. IEEE Access. 2022; 10:10867–10879.
DOI: 10.1109/ACCESS.2022.3144333
Chen X, He S, An Z, Zhang X, Huang L, Lin S. Surface defect detection of electric power equipment in substation based on improved YOLO-V4 algorithm. 2020 10th International Conference on Power and Energy Systems (ICPES); 2020. DOI:10.1109/ICPES51309.2020.9349721/20/$31.00
Rajawat AS, et al. Electrical fault detection for industry 4.0 using fusion deep learning algorithm. EPE 2022 - Proceedings of the 2022 12th International Conference and Exposition on Electrical and Power Engineering, Institute of Electrical and Electronics Engineers Inc. 2022;658–662. DOI: 10.1109/EPE56121.2022.9959762
Zhang Y, Zhang J, Yin X, Chen Z, Miao K. A comparison study among various techniques in the application of power system anomaly detection, diagnostics and monitoring. Proceedings - 2022 Power System and Green Energy Conference, PSGEC 2022, Institute of Electrical and Electronics Engineers Inc. 2022;576–580. DOI:10.1109/PSGEC54663.2022.9881147
Khalid S, Song J, Raouf I, Kim HS. Advances in fault detection and diagnosis for thermal power plants: A review of intelligent techniques. Mathematics. Apr. 01, 2023;11(8), MDPI. DOI: 10.3390/math11081767
Cioffi R, Travaglioni M, Piscitelli G, Petrillo A, De Felice F. Artificial intelligence and machine learning applications in smart production: Progress, trends, and directions. Sustainability (Switzerland). Jan. 01, 2020;12(2), MDPI.
DOI: 10.3390/su12020492
Li M, Cai C, Sun Y. A method for identifying transmission line faults based on deep learning. Institute of Electrical and Electronics Engineers (IEEE). Mar. 2023; 3295–3300. DOI: 10.1109/cac57257.2022.10055852
Gao J, Wang H, Shen H. Task failure prediction in cloud data centers using deep learning. IEEE Trans Serv Comput. 2022; 15(3):1411–1422. DOI: 10.1109/TSC.2020.2993728
Huang J, Li M, Zhang Y, Mu L, Ao Z, Gong H. Fault detection and classification for sensor faults of UAV by deep learning and time-frequency analysis. Chinese Control Conference, CCC, IEEE Computer Society. Jul. 2021;4420–4424.
DOI: 10.23919/CCC52363.2021.9550141
Adel A, Sulaiman B. Predicting electrical faults in power distribution network. [Online]. Available:https://scholarworks.rit.edu/theses
Rajawat AS, et al. Electrical fault detection for industry 4.0 using fusion deep learning algorithm. EPE 2022 - Proceedings of the 2022 12th International Conference and Exposition on Electrical and Power Engineering, Institute of Electrical and Electronics Engineers Inc. 2022;658–662. DOI: 10.1109/EPE56121.2022.9959762
Khediri A, Laouar MR. Deep-belief network based prediction model for power outage in smart grid. ACM International Conference Proceeding Series, Association for Computing Machinery; Jul. 2018.
DOI: 10.1145/3213187.3287611
Xi P, Feilai P, Yongchao L, Zhiping L, Long L. Fault detection algorithm for power distribution network based on sparse selfencoding neural network. Proceedings - 2017 International Conference on Smart Grid and Electrical Automation, ICSGEA 2017, Institute of Electrical and Electronics Engineers Inc. Nov. 2017;9–12. DOI: 10.1109/ICSGEA.2017.19
Wang X. Machine learning applications in power systems. [Online]. Available:http://digitalrepository.smu.edu.
Saad MH, Said A. Machine learning-based fault diagnosis for research nuclear reactor medium voltage power cables in fraction Fourier domain. Electrical Engineering. Feb. 2023;105(1):25–42.
DOI: 10.1007/s00202-022-01649-7
Bouchiba N, Kaddouri A. Application of machine learning algorithms for power systems fault detection. 2021 9th International Conference on Systems and Control, ICSC 2021, Institute of Electrical and Electronics Engineers Inc. 2021;127–132. DOI: 10.1109/ICSC50472.2021.9666726
IEEE Instrumentation and Measurement Society, IEEE Instrumentation and Measurement Society. TC-39--Measurements in Power Systems, and Institute of Electrical and Electronics Engineers, AMPS 2018 9th IEEE International Workshop on Applied Measurements for Power Systems: 2018 workshop proceedings.
Mullainathan S, Spiess J. Machine learning: An applied econometric approach. Journal of Economic Perspectives, American Economic Association. Mar. 2017;87–106. DOI: 10.1257/jep.31.2.87
Erfanian AM, Ramezani A. Using deep learning network for fault detection in UAV. 2022 8th International Conference on Control, Instrumentation and Automation, ICCIA 2022, Institute of Electrical and Electronics Engineers Inc.; 2022. DOI: 10.1109/ICCIA54998.2022.9737206
Bouchiba N, Kaddouri A. Performance comparison of Fuzzy logic and deep learning algorithms for fault detection in electrical power transmission system. 2021 IEEE Electrical Power and Energy Conference, EPEC 2021, Institute of Electrical and Electronics Engineers Inc. 2021;101–106. DOI: 10.1109/EPEC52095.2021.9621580