Outage Estimation in Electric Power Distribution Systems Using a Neural Network Ensemble

Outages in an overhead power distribution system are caused by multiple environmental factors, such as weather, trees, and animal activity. Since they form a major portion of the outages, the ability to accurately estimate these outages is a significant step towards enhancing the reliability of power distribution systems. Earlier research with statistical models, neural networks, and committee machines to estimate weather-related and animal-related outages has reported some success. In this paper, a deep neural network ensemble model for outage estimation is proposed. The entire input space is partitioned with a distinct neural network in the ensemble performing outage estimate in each partition. A novel algorithm is proposed to train the neural networks in the ensemble, while simultaneously partitioning the input space in a suitable manner. The proposed approach has been compared with the earlier approaches for outage estimation for four U.S. cities. The results suggest that the proposed method significantly improves the estimates of outages caused by wind and lightning in power distribution systems. A comparative analysis with a previously published model for animal-related outages further establishes the overall effectiveness of the deep neural network ensemble.

[1]  Aman Jantan,et al.  Comprehensive Review of Artificial Neural Network Applications to Pattern Recognition , 2019, IEEE Access.

[2]  A. Pahwa,et al.  Regression models for outages due to wind and lightning on overhead distribution feeders , 2011, 2011 IEEE Power and Energy Society General Meeting.

[3]  A. Pahwa,et al.  A Probabilistic Approach for Animal-Caused Outages in Overhead Distribution Systems , 2006, 2006 International Conference on Probabilistic Methods Applied to Power Systems.

[4]  Haitham Abu-Rub,et al.  Deep Learning in Smart Grid Technology: A Review of Recent Advancements and Future Prospects , 2021, IEEE Access.

[5]  A. Pahwa,et al.  Exponential regression models for wind and lightning caused outages on overhead distribution feeders , 2011, 2011 North American Power Symposium.

[6]  Min Gui,et al.  Bayesian Network Model With Monte Carlo Simulations for Analysis of Animal-Related Outages in Overhead Distribution Systems , 2011, IEEE Transactions on Power Systems.

[7]  H C Caswell,et al.  Weather Normalization of Reliability Indices , 2011, IEEE Transactions on Power Delivery.

[8]  Mohammad Rastegar,et al.  Outage Cause Detection in Power Distribution Systems Based on Data Mining , 2021, IEEE Transactions on Industrial Informatics.

[9]  Carlos Henggeler Antunes,et al.  Comparison of a genetic algorithm and simulated annealing for automatic neural network ensemble development , 2013, Neurocomputing.

[10]  Anil Pahwa,et al.  AdaBoost$^{+}$: An Ensemble Learning Approach for Estimating Weather-Related Outages in Distribution Systems , 2014, IEEE Transactions on Power Systems.

[11]  Shengli Wu,et al.  Effective Neural Network Ensemble Approach for Improving Generalization Performance , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[12]  Joonas Karjalainen,et al.  PREDICTING ELECTRICITY OUTAGES CAUSED BY CONVECTIVE STORMS , 2018, 2018 IEEE Data Science Workshop (DSW).

[13]  Adnan M. Abu-Mahfouz,et al.  A Review of Machine Learning Approaches to Power System Security and Stability , 2020, IEEE Access.

[14]  Anil Pahwa,et al.  Estimating Animal-Related Outages on Overhead Distribution Feeders Using Boosting , 2015 .

[15]  Sung-Kwun Oh,et al.  Reinforced Fuzzy Clustering-Based Ensemble Neural Networks , 2020, IEEE Transactions on Fuzzy Systems.

[16]  Abbas Khosravi,et al.  A Survey of Computational Intelligence Techniques for Wind Power Uncertainty Quantification in Smart Grids , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[17]  Arif I. SARWAT,et al.  Weather-based interruption prediction in the smart grid utilizing chronological data , 2016 .

[18]  Badrul Chowdhury,et al.  Statistical Analysis of Animal-Related Outages in Power Distribution Systems - A Case Study , 2019, 2019 IEEE Power & Energy Society General Meeting (PESGM).

[19]  Adamu I. Abubakar,et al.  Progress on Artificial Neural Networks for Big Data Analytics: A Survey , 2019, IEEE Access.

[20]  Saba Mylvaganam,et al.  Some Case Studies of Power Outages with Possible Machine Learning Strategies for their Predictions , 2018, 2018 28th EAEEIE Annual Conference (EAEEIE).

[21]  Xiuchen Jiang,et al.  Predicting Weather-Related Failure Risk in Distribution Systems Using Bayesian Neural Network , 2021, IEEE Transactions on Smart Grid.

[22]  D. Opitz,et al.  Popular Ensemble Methods: An Empirical Study , 1999, J. Artif. Intell. Res..

[23]  L. Cooper,et al.  When Networks Disagree: Ensemble Methods for Hybrid Neural Networks , 1992 .

[24]  ψψAABB xxAA,et al.  Markov Random Fields , 1982, Encyclopedia of Social Network Analysis and Mining.

[25]  Vivienne Sze,et al.  Efficient Processing of Deep Neural Networks: A Tutorial and Survey , 2017, Proceedings of the IEEE.

[26]  Yanika Kongsorot,et al.  Parallelized Metaheuristic-Ensemble of Heterogeneous Feedforward Neural Networks for Regression Problems , 2019, IEEE Access.

[27]  Yakup Genc,et al.  Deep Network Ensembles for Aerial Scene Classification , 2019, IEEE Geoscience and Remote Sensing Letters.