Wavelet LSTM for Fault Forecasting in Electrical Power Grids

被引:48
作者
Branco, Nathielle Waldrigues [1 ]
Matos Cavalca, Mariana Santos [1 ]
Stefenon, Stefano Frizzo [2 ,3 ]
Quietinho Leithardt, Valderi Reis [4 ,5 ]
机构
[1] Santa Catarina State Univ, Dept Elect Engn, R Paulo Malschitzki 200, BR-89219710 Joinville, Brazil
[2] Fdn Bruno Kessler, Via Sommar 18, I-38123 Trento, Italy
[3] Univ Udine, Dept Math Informat & Phys Sci, Via Sci 206, I-33100 Udine, Italy
[4] Lusofona Univ Humanities & Technol, COPELABS, Campo Grande 376, P-1749024 Lisbon, Portugal
[5] Inst Politecn Portalegre, Res Ctr Endogenous Resources Valorizat, VALORIZA, P-7300555 Portalegre, Portugal
关键词
electrical power grids; fault forecasting; long short-term memory; time series forecasting; wavelet transform; TIME-SERIES; INSULATORS; MULTISTEP; FUZZY; PREDICTION; COMPONENTS; NETWORKS; MODEL;
D O I
10.3390/s22218323
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
An electric power distribution utility is responsible for providing energy to consumers in a continuous and stable way. Failures in the electrical power system reduce the reliability indexes of the grid, directly harming its performance. For this reason, there is a need for failure prediction to reestablish power in the shortest possible time. Considering an evaluation of the number of failures over time, this paper proposes performing failure prediction during the first year of the pandemic in Brazil (2020) to verify the feasibility of using time series forecasting models for fault prediction. The long short-term memory (LSTM) model will be evaluated to obtain a forecast result that an electric power utility can use to organize maintenance teams. The wavelet transform has shown itself to be promising in improving the predictive ability of LSTM, making the wavelet LSTM model suitable for the study at hand. The assessments show that the proposed approach has better results regarding the error in prediction and has robustness when statistical analysis is performed.
引用
收藏
页数:17
相关论文
共 87 条
[1]   Improving time series forecasting using LSTM and attention models [J].
Abbasimehr, Hossein ;
Paki, Reza .
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, 2022, 13 (01) :673-691
[2]   Discrete wavelet transform and energy eigen value for rotor bars fault detection in variable speed field-oriented control of induction motor drive [J].
Ameid, Tarek ;
Menacer, Arezki ;
Talhaoui, Hicham ;
Azzoug, Youness .
ISA TRANSACTIONS, 2018, 79 :217-231
[3]   Electric Field Distribution and Leakage Currents in Glass Insulator Under Different Altitudes and Pollutions Conditions using FEM Simulations [J].
Araya, Jersim ;
Montana, Johny ;
Schurch, Roger .
IEEE LATIN AMERICA TRANSACTIONS, 2021, 19 (08) :1278-1285
[4]   A Bias and Variance Analysis for Multistep-Ahead Time Series Forecasting [J].
Ben Taieb, Souhaib ;
Atiya, Amir F. .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2016, 27 (01) :62-76
[5]   A Low-Cost Evaluation and Correction Method for the Soluble Salt Components of the Insulator Contamination Layer [J].
Cao, Bin ;
Wang, Liming ;
Yin, Fanghui .
IEEE SENSORS JOURNAL, 2019, 19 (13) :5266-5273
[6]   Web Traffic Time Series Forecasting Using LSTM Neural Networks with Distributed Asynchronous Training [J].
Casado-Vara, Roberto ;
Martin del Rey, Angel ;
Perez-Palau, Daniel ;
de-la-Fuente-Valentin, Luis ;
Corchado, Juan M. .
MATHEMATICS, 2021, 9 (04) :1-22
[7]   Evaluation of Deep Learning Models for Multi-Step Ahead Time Series Prediction [J].
Chandra, Rohitash ;
Goyal, Shaurya ;
Gupta, Rishabh .
IEEE ACCESS, 2021, 9 :83105-83123
[8]   Research on Recognition Method of Electrical Components Based on YOLO V3 [J].
Chen, Haipeng ;
He, Zhentao ;
Shi, Bowen ;
Zhong, Tie .
IEEE ACCESS, 2019, 7 :157818-157829
[9]  
Chunlan Yang, 2021, 2021 IEEE Sustainable Power and Energy Conference (iSPEC), P2883, DOI 10.1109/iSPEC53008.2021.9735502
[10]   Classification of Contaminated Insulators Using k-Nearest Neighbors Based on Computer Vision [J].
Corso, Marcelo Picolotto ;
Perez, Fabio Luis ;
Stefenon, Stefano Frizzo ;
Yow, Kin-Choong ;
Garcia Ovejero, Raul ;
Quietinho Leithardt, Valderi Reis .
COMPUTERS, 2021, 10 (09)