New approach to analysis machine learning base power quality in a test grid system - power quality analysis using machine learning

Aug 2, 2026

Upload by Liam

Renewable energy integration with modern grid technologies raises critical concerns about electricity quality. Machine learning methods support power quality data analysis to assess and mitigate disturbances across electrical systems. The study proposes a novel framework for power quality analysis using real-time data from multiple appliances, captured by a sensor-based power data collection system. Extracted signals are processed to detect and classify voltage and current harmonics and transients, then machine learning is used to identify, classify, and predict issues using historical records.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages3

Reading Time8 min

AccessFree to download

Abstract

Machine learning for power quality assessment

Sensor-based data collection and signal processing

Classification and prediction of harmonics and transients

10/28/24 , 4:18 PM Scopus-Print Document Documents Salam, S. M.a , Rashid, M. M.a , Ali, M.Y.b , Yvette, S.c New approach to analysis machine learning base power quality in a test grid system (2024) AIP Conference Proceedings, 3161 (1), [art. no. 020129](art. no. 020129) , . DOI: 10. 1063/5 .0229873 a Department of Mechatronics Engineering, International Islamic University Malaysia, Jalan Gombak, Kuala Lumpur, 53100, Malaysia b Mechanical Engineering Programme Area, Universiti Teknologi Brunei, Jalan Tungku Link Gadong, Bandar Seri Begawan, BE1410, Brunei Darussalam c Asia Pacific University, Jalan Teknologi 5, Taman Teknologi Malaysia, Kuala Lumpur, 57000, Malaysia Abstract The integration of renewable energy sources with advanced power grid technologies has raised concerns over electricity quality. The use of machine learning techniques enables the assessment of power quality data analysis for the purposes of identifying and mitigating disturbances. This study presents a novel approach to power quality analysis in various power systems, using machine learning algorithms. The proposed methodology involves the processing and analysis of real-time power quality data obtained from various appliances. This data is extracted using a power data collection system equipped with sensors. Subsequently, machine learning techniques and algorithms are employed to identify and classify voltage and current harmonics, as well as transients. The system uses machine learning techniques to identify, classify, and predict power quality issues by using historical data. © 2024 Author(s) . References Jabbar, R.A. , Al-Dabbagh, M. , Muhammad, A. , Khawaja, R.H. , Akmal, M. , Arif, M.R.(2008) Proc. AUPEC'08 , pp. 1-5. Chia, Y.K. , Nabipour, H. , Chua, H.S. , Kang, C.C. (2022) Int. J. Elect. Electronic Eng. Telecomm. , 11, pp. 18-23. Salam, S.M. , Rashid, M.M. (2022) Proc. 8th Int. Conf. Mechatronics Eng. , pp. 90-94. Muslimin, Z. , Suyuti, A. , Palantei, E. , Gunadin, I.C. (2022) Int. J. Elect. Electronic Eng. Telecomm. , 11, pp. 102-108. Indrabayu Salam, S.M. , Uddin, M.I. , Bin Moinuddin, M.R. (2019) Proc. 4th Int. Conf. Elect. Infor. Comm. Tech. , 1-5. Salam, S.M. , Mohammad, N. (2020) Proc. IEEE Region 10 Symp. (TENSYMP) , pp. 831-834. Salam, S.M. , Mohammad, N. , Hossain, F. (2021) Proc. 5th Int. Conf. Elect. Infor. Comm. Tech. , pp. 1-6. Rashid, M.M. , Alazmi, A.M. , Salam, S.M. (2001) Asian J. Elect. Electronic Eng. , 2, p. 2. Adeli, H. , Cheng, N. (1994) J. Aerosp. Eng. , 7, pp. 104-118. Lee, Y. , Wei, C.-H. (2010) Comp. Civ. Infrastruct. Eng. , 25, pp. 132-148. [https://www.scopus.com/citation/print.uri?origin=recordpage&sid=&src=s&stateKey=OFD_1852992314&eid=2-s2.0-85203995167&sort=&clickedL](https://www.scopus.com/citation/print.uri?origin=recordpage&sid=&src=s&stateKey=OFD_1852992314&eid=2-s2.0-85203995167&sort=&clickedL)… 1/3 10/28/24 , 4:18 PM Scopus-Print Document Liu, X.H. , Danczyk, A. (2009) Comp. Aided Civ. Infrastruct. Eng. , 24, pp. 535-550. Cavalieri, S. , Mirabella, O. (1999) A Novel Learning Algorithm Which Improves the Partial Fault Tolerance of Multilayer Neural Networks , University of Catania Ramesh, S. , Yaghoubi, A. , Lee, K.Y.S. , Chin, K.M.C. , Purbolaksono, J. , Hamdi, M. , Hassan, M.A. (2013) J. Mech. Behav. Biomed. Mater. , 25, pp. 63-69. Manladan, S.M. , Yusof, F. , Ramesh, S. , Fadzil, M. (2016) Int. J. Adv. Manuf. Tech. , 86, pp. 1805-1825. Ramesh, S. , Tan, C.Y. , Peralta, C.L. , Teng, W.D. (2007) Sci. Tech. Adv. Mater. , 8, pp. 257-263. Duraisamy, N. , Numan, A. , Ramesh, K. , Choi, K.-H. , Ramesh, S. , Ramesh, S.(2015) Mater. Letts. , 161, pp. 694-697. Manladan, S.M. , Yusof, F. , Ramesh, S. , Zhang, Y. , Luo, Z. , Ling, Z. (2017) J. Mater. Proc. Tech. , 250, pp. 45-54. Francis, K.A. , Liew, C.-W. , Ramesh, S. , Ramesh, K. , Ramesh, S. (2016) Ionics, 22, pp. 919-925. Ramesh, S. , Amiriyan, M.

FAQs

What problem does the study address?

The study targets electricity quality concerns in power grids, especially disturbances that affect power quality.

How is data collected for the proposed method?

Real-time power quality data from various appliances is collected using a power data collection system equipped with sensors.

Which power quality issues does the machine learning model identify?

It is used to identify and classify voltage and current harmonics, as well as transients, and to predict power quality issues using historical data.

Aug 2, 2026

Upload by Liam