ZHAO Feng, LIAO DiThis email address is being protected from spambots. You need JavaScript enabled to view it., CHEN Xiao Qiang, and WANG Ying
School of Automation and Electrical Engineering, Lanzhou 730070, China
Received: July 3, 2023 Accepted: September 23, 2023 Publication Date: November 5, 2023
Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.
In order to improve the classification accuracy of power quality disturbances, a new method combining convolutional neural network (CNN) and attention mechanism bidirectional long short memory network (ABiLSTM) for power quality disturbances classification is proposed. Firstly, spatial features of disturbance signals are extracted through CNN. Secondly, the BiLSTM hidden layer learns the internal dynamic transformation rules of local features extracted by CNN and extracts temporal features; Using attention mechanism to distinguish features extracted by BiLSTM through weighting, and mining deep temporal correlations. Finally, the disturbance classification results are output through the fully connected layer. During the experiment, the power quality disturbance signal is simulated by MATLAB Simulink. The data set obtained from the simulation is used for training and testing the algorithm, and the real data set is used to verify the algorithm. The experimental results indicate that the CNN-ABiLSTM model can automatically recognize and classify features related to power quality disturbances. Compared with other methods, this method overcomes the limitations of traditional signal analysis and feature selection, and the classification accuracy of CNN-ABiLSTM for power quality disturbance signals is 99.79%, which is superior to CNN, CNN-LSTM, and ABiLSTM methods.
Keywords: Power quality; Convolutional neural network; Bidirectional long and short term memory network; Attention mechanism; Disturbance classification
[1] F. Wang, X. Quan, and L. Ren, (2021) “Review of power quality disturbance detection and identification methods" Proceedings of the CSEE 41(12): 4104–4120.
[2] S. Z. Zhang Yi Li Ke, (2023) “Power Quality Feature Recognition of Industrial Users Based on Data Correlation Analysis" Transactions of China Electrotechnical Society: 1–16.
[3] Y. Wang, (2021) “Research Review on Power Quality Disturbance Detection [J]" Power System Protection and Control 49(13): 174–186.
[4] Z. Y. Wang Renming Wang Hongyang, (2020) “Hybrid Power quality Disturbance Identification Method Based on piecewise Improved S-transform and Random Forest" Power System Protection and Control 48(07): 19–28.
[5] S. Karasu and Z. Saraç, (2022) “The effects on classifier performance of 2D discrete wavelet transform analysis and whale optimization algorithm for recognition of power quality disturbances" Cognitive Systems Research 75: 1–15. DOI: 10.1016/j.cogsys.2022.05.001.
[6] Y. Mei, Y. Wang, X. Zhang, S. Liu, Q. Wei, and Z. Dou, (2022) “Wavelet packet transform and improved complete ensemble empirical mode decomposition with adaptive noise based power quality disturbance detection" Journal of Power Electronics 22(8): 1334–1346. DOI: 10.1007/s43236-022-00440-y.
[7] P. Dash, E. N. Prasad, R. K. Jalli, and S. Mishra, (2022) “Multiple power quality disturbances analysis in photovoltaic integrated direct current microgrid using adaptive morphological filter with deep learning algorithm" Applied Energy 309: 118454. DOI: 10.1016/j.apenergy.2021.118454.
[8] C. C. Qu Hezuo Li Xiaoming, (2018) “Power quality disturbance classification based on convolutional neural network" Engineering Journal of Wuhan University 51(06): 534–539.
[9] S. Y. Chen Zixuan Xi Yanhui, (2022) “Classification of composite power quality disturbances based on Kalman filtering and deep confidence networks" Power System Protection and Control 50(07): 81–90.
[10] W. Xuechun, (2021) “Research on Power Quality Analysis Method Based on LSTM Network" Chang ’an University:
[11] Z. Y. Cao Mengzhou, (2020) “Power quality disturbance classification based on convolutional long and short term memory Network." Power System Protection and Control 48(02): 86–92.
[12] H. E. Belkis E, (2022) “A new deep learning method for the classification of power quality disturbances in hybrid power system" Electrical Engineering 104(06): DOI: 10.1007/s00202-022-01581-w.
[13] I. P. bibinitperiod E. Society, (2019) “IEEE Std 1159TM2019 IEEE recommended practice for monitoring electric power quality" Washington: IEEE:
[14] S. G. Yang Jianfeng Jiang Shuang, (2019) “Complex power quality disturbance identification based on piecewise improved S-transform" Power System Protection and Control 47(09): 64–71.
[15] H. H. CUI C DUAN Y, (2022) “Detection and Classification of Multiple Power Quality Disturbances Using Stockwell Transform and Deep Learning" IEEE Transactions on Instrumentation and Measurement 71: 1–12. DOI: 10.1109/TIM.2022.3214284.
[16] W. J. Zheng Wei Lin Ruiquan, (2021) “Power quality disturbance classification based on GAF and convolutional neural network" Power System Protection and Control 49(11): 97–104.
[17] M. Y. Wang Hong Lin Haiqi, (2020) “Method of Voltage Sag Causes Based on Bidirectional LSTM and Attention Mechanism" Journal of Electrical Engineering & Technology 15(04): DOI: 10.1007/s42835-020-00413-w.
[18] Z. Y. Ji Xingquan Zeng Ruomei, (2022) “CNN-LSTM short-term Electricity price prediction based on attention mechanism" Power System Protection and Control 50(17): 125–132.
[19] Z. Z. Ren Jianji Wei Huihui, (2022) “Ultra-shortterm Power Load forecasting Based on CNN-BiLSTMAttention" Power System Protection and Control 50(08): 108–116. DOI: 10.19783/j.cnki.pspc.211187.
[20] M. G. MA Z, (2022) “A hybrid attention-based deep learning approach for wind power prediction" Applied Energy: DOI: 10.1016/j.apenergy.2022.119608.
[21] C. N. Li Zuming Lu Qianyun, (2021) “Recognition of hybrid PQ disturbances based on chaos ensemble integrated decision tree" Power System Protection and Control 49(21): 18–27.
[22] I. P. E. Society, (2021) “IEEE PES working group P1433 power quality definitions" Accessed:
We use cookies on this website to personalize content to improve your user experience and analyze our traffic. By using this site you agree to its use of cookies.
