Signal Processing and Deep Learning Techniques for Power Quality Events Monitoring and Classification

Abstract

Power quality disturbances (PQDs) have major challenges in embedded generation systems, renewable energy networks, and HVDC/HVAC electrical power transmission networks. Due to PQDs, electrical power network can have disruption in the protection system, security system, and energy-saving system. PQDs also affect the operation cost and consistency of electrical power systems. This paper presents an innovative method based on compressive sensing (CS), singular spectrum analysis (SSA), wavelet transform (WT) and deep neural network (DNN) for monitoring and classification of PQDs. Feature extraction and selection is an essential part of the classification of PQDs. In this paper, initially, SSA time-series tool and multi-resolution wavelet transform are introduced to extract the features of PQDs, and then CS technique is used to reduce the dimensionality of the extracted features. Finally, DNN-based classifier is used to classify the single-and-combined PQDs. The DNN architecture is constructed utilizing the restricted Boltzmann machine, which is then fine-tuned by back-propagation. The heart of this paper is to enhance the classification and monitoring accuracy and comparison of the results of WT-based classifier with SSA-based classifier. The proposed method is tested using 15 types of single and combined PQDs. These disturbances are transitory in the transmission and distribution networks such as voltage sag, swell, transient, interruption, harmonic, etc. The simulation and experimental results demonstrate that the SSA-based DNN classifier has significantly higher potential than the WT-based classifier to classify the power quality events under noisy and noiseless conditions.

Keywords:

• power quality disturbance classification
• wavelet transform
• compressive sensing
• deep neural network
• singular spectrum analysis

Acknowledgment

Authors would like to thanks all the reviewers who review our manuscript and National Natural Science Foundation of China and Priority Academic Program Development (PAPD) of Jiangsu Higher Education Institute China who provided funding for this project.

Competing Interests

The authors declare that they have no competing interests.

Additional information

Funding

This work was supported by National Natural Science Foundation of China [51505195]; Jiangsu International Science and Technology Cooperation Project [BZ2017067]; Jiangsu Provincial Key Research and Development Program [BE2018372]; Jiangsu Natural Science Foundation [BK20181443]; Zhenjiang City Key Research and Development Program [NY2018001]; (PAPD) and Blue project of Jiangsu Province.

Notes on contributors

Hui Liu

Hui Liu was born in Nanjing, Jiangsu, China in 1980. She received the B.S. degree from Jiangsu University of Science and Technology, in 2001, the M.S. and Ph.D. degrees both from School of Electrical and Information Engineering, Jiangsu University, China, in 2004 and 2009 respectively. She is currently working as professor and M.Sc. supervisor in the School of Electrical and Information Engineering, Jiangsu University. Her research interests include power quality analysis, agricultural information automation, and biomedical signal process.

Fida Hussain

Fida Hussain has Ph.D. in Electrical Engineering and specialty in Power Electronics and Power Transmission from Jiangsu University, China. He is currently working as postdoctoral researcher at Jiangsu University, China. The B.E degree from D.U.E.T. Pakistan, in 2009 and the M.E. and M.S. degrees from Hamdard University and NED University of Engineering and Technology, Pakistan, in 2011 and 2015, respectively. He was an assistant professor at Hamdard University from 2013 to 2015. His research interests include smart grids, deep and machine learning, power system automation, and hydropower automation.

Yue Shen

Yue Shen was born in Suqian, Jiangsu, China in 1978. He received a B.S. degree from Jiangsu University of Science and Technology, in 2001, the M.S. and Ph.D. degrees both from School of Electrical and Information Engineering, Jiangsu University, China, in 2004 and 2012, respectively. He is currently professor and M.Sc. and Ph.D. supervisor in School of Electrical and Information Engineering, Jiangsu University. His research interests include power quality analysis, agricultural automation, and embedded system.

Ruben Morales-Menendez

Ruben Morales-Menendez has Ph.D. in Artificial Intelligence from Tecnologico de Monterrey. He was a Visiting Scholar with the Laboratory of Computational Intelligence, University of British Columbia, Vancouver, BC, Canada, from 2000 to 2003. He has been a consultant specializing in the analysis and design of automatic control systems for continuous processes for more than 30 years. Currently, he is the Dean of Graduate Studies of the School of Engineering and Sciences at Tecnologico de Monterrey. Dr. Morales-Menendez is a member of the National Researchers System of Mexico Level II, the Mexican Academy of Sciences and the Engineering Academy of Mexico. His research interests include fault diagnosis, monitoring systems, automotive control systems, and educational systems in engineering.

Muhammad Abubakar

Muhammad Abubakar is pursuing Ph.D. degree in Power Electronics and Power Drive from Jiangsu University, China. He received M.S. degree from Islamic University, Pakistan. Currently, he is working on power quality monitoring and classification. His research interests include machine learning, deep learning, and fault diagnosis.

Sheikh Junaid Yawar

Sheikh Junaid Yawar received a B.E. and M.E. degrees from NED University of Engineering and Technology, Pakistan in 2009 and 2012 respectively. The MBA degree from Virtual University of Pakistan, in 2019. Currently, he is pursuing Ph.D. degree from Hamdard University, Pakistan. He was Lecturer at Hamdard University from 2013 to 2015. He is currently an Assistant Professor and B.E. supervisor at the Department of Electrical Engineering, Sir Syed University of Engineering and Technology, Pakistan. His research interests include power quality improvement, power electronics inverters, and HVAC transmissions.

Haris Jawad Arain

Haris Jawad Arain is pursuing M.E. degree Energy Systems Engineering from QUEST Nawabshah, Pakistan. He received B.E. degree from Department of Energy and Environment Engineering, Quaid-e-Awam University, Pakistan, in 2012. He was Lab Engineer at Hamdard University from 2013 to 2015. Currently, he is working as Lab Engineer at Quaid-e-Awam University of Engineering Science and Technology, NawabShah, Pakistan. His research interests include energy system with specialization in power systems automation, deep learning, and fault diagnosis.