Abstract
Electrical power outages can have negative impacts and can lead to fatal outputs that can lead to blackouts. Increased understanding and prediction of these disturbances can help to avoid the occurrence of significant disturbances and decrease the after-effects too. Previous works have focused to predict the type of electricity disturbance and their occurrences. This paper aims to develop a system that predicts the duration of power outages using machine learning and deep learning techniques. The proposed system uses preprocessing and feature selection with classification using KNN, decision tree, random forest classifiers, SVM and neural network on an open-source dataset containing electrical disturbances. The results indicate that neural networks can better predict the electrical power outage duration ranges than classic machine learning techniques.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
O.P. Veloza, F. Santamaria, Analysis of major blackouts from 2003 to 2015: classification of incidents and review of main causes. Electr. J. 29(7), 42–49 (2016)
S. Omran, E.M. El Houby, Prediction of electrical power disturbances using machine learning techniques. J. Ambient Intel. Human. Comput. 1–17 (2019)
C. Brester, H. Niska, R. Ciszek, M. Kolehmainen, Weather-based fault prediction in electricity networks with artificial neural networks, in 2020 IEEE Congress on Evolutionary Computation (CEC), pp. 1–8 (IEEE, 2020)
D. Cornforth, Long tails from the distribution of 23 years of electrical disturbance data, in 2009 IEEE/PES Power Systems Conference and Exposition, pp. 1–8 (IEEE, 2009)
D. Cornforth, Applications of data mining to time series of electrical disturbance data, in 2009 IEEE Power and Energy Society General Meeting, pp. 1–8 (IEEE, 2009)
D. Cornforth, K. Nesbitt, Quality assessment of clusters of electrical disturbances: a case study, in 2013 IEEE 8th Conference on Industrial Electronics and Applications (ICIEA), pp. 247–254 (IEEE, 2013)
E. Bompard, A. Estebsari, T. Huang, G. Fulli, A framework for analyzing cascading failure in large interconnected power systems: a post-contingency evolution simulator. Int. J. Electr. Power Energy Syst. 81, 12–21 (2016)
D. Owerko, F. Gama, A. Ribeiro, Predicting power outages using graph neural networks, in 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP), pp. 743–747 (IEEE, 2018)
A. Arif, Z. Wang, Distribution network outage data analysis and repair time prediction using deep learning, in 2018 IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS), pp. 1–6 (IEEE, 2018)
H. Sun, Z. Wang, J. Wang, Z. Huang, N. Carrington, J. Liao, Data-driven power outage detection by social sensors. IEEE Trans. Smart Grid 7(5), 2516–2524 (2016)
J.R. Quinlan, Induction of decision trees. Mach. Learn. 1(1), 81–106 (1986)
K. Thurnhofer-Hemsi, E. López-Rubio, M.A. Molina-Cabello, K. Najarian, Radial basis function kernel optimization for support vector machine classifiers (2020). arXiv preprint arXiv:2007.08233
A. Liaw, M. Wiener, Classification and regression by random forest. R News 2(3), 18–22 (2002)
D.P. Kingma, J. Ba, Adam: A Method for Stochastic Optimization (2014). arXiv preprint arXiv:1412.6980
J. Schmidhuber, Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Doshi, R., Saini, R.D., Kansal, S. (2022). Time Duration Prediction of Electrical Power Outages. In: Khosla, A., Aggarwal, M. (eds) Smart Structures in Energy Infrastructure. Studies in Infrastructure and Control. Springer, Singapore. https://doi.org/10.1007/978-981-16-4744-4_4
Download citation
DOI: https://doi.org/10.1007/978-981-16-4744-4_4
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-4743-7
Online ISBN: 978-981-16-4744-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)