Feature Analysis of Current Unbalance in Electrical Distribution Systems Using Random Forest
Article Sidebar
Main Article Content
Abstract
The building sector accounts for more than 130 exajoules (EJ) of global energy consumption, representing approximately 30% of the total energy demand, with a continuous upward trend. Notably, energy demand in buildings surged during the COVID-19 crisis and increased by approximately 20% between 2000 and 2007. A significant portion of this energy consumption is attributed to lighting and air-conditioning systems. The rising electricity demand in buildings adversely impacts power quality, leading to issues such as harmonic distortion, voltage unbalance, and current unbalance in electrical distribution systems. This study investigates the application of the Machine Learning-based Random Forest Regressor model to analyze the causes of current unbalance in a building’s power distribution system. A case study was conducted using electricity consumption data from a facility at the College of Industrial Technology and Management, Rajamangala University of Technology. The analysis results indicate that power features significantly influence current unbalance, with Power Phase A contributing the most at 74.73%, followed by Power Phase C at 10.98% and Power Phase B at 9.55%. These findings provide valuable insights for optimizing maintenance strategies and improving the efficiency of building power distribution systems.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The content and information in the article published in Journal of Rajamangala University of Technology Srivijaya It is the opinion and responsibility of the author of the article. The editorial journals do not need to agree. Or share any responsibility.
References
Beňa, Ľ., Gáll, V., Kanálik, M., Kolcun, M., Margitová, A., Mészáros, A. and Urbanský, J. 2021. Calculation of the overhead transmission line conductor temperature in real operating conditions. Electrical Engineering 103: 769-780. DOI: https://doi.org/10.1007/s00202-020-01107-2
Breiman, L. 2001. Random forest, Machine Learning. Statistics Department, University of California, Berkeley. DOI: https://doi.org/10.1023/A:1010933404324
Chawda, G.S., Shaik, A.G., Shaik, M., Padmanaban, S., Holm-Nielsen, J.B., Mahela, O.P. and Kaliannan, P. 2020. Comprehensive review on detection and classification of power quality disturbances in utility grid with renewable energy penetration. IEEE Access 8: 146807-146830. DOI: https://doi.org/10.1109/ACCESS.2020.3014732
Drovtar, I., Niitsoo, J., Rosin, A., Kilter, J. and Palu, I. 2012. Electricity consumption analysis and power quality monitoring in commercial buildings, pp. 1-6. In Electric Power Quality and Supply Reliability. Department of Fundamentals of Electrical Engineering and Electrical Machines, Tallinn, Estonia. DOI: https://doi.org/10.1109/PQ.2012.6256212
Hadd, A. and Rodgers, J.L. 2020. Understanding correlation matrices. Sage Publications. DOI: https://doi.org/10.4135/9781071878613
Hastie, T., Tibshirani, R., Friedman, J., Hastie, T., Tibshirani, R. and Friedman, J. 2009. The elements of statistical learning: data mining, inference, and prediction. springer, New York. DOI: https://doi.org/10.1007/978-0-387-84858-7
Jove, E., González-Cava, J.M., Casteleiro-Roca, J.L., Alaiz-Moretón, H., Baruque, B., Leitão, P., Pérez, J.A.M. and Calvo-Rolle, J.L. 2021. An intelligent system for harmonic distortions detection in wind generator power electronic devices. Neurocomputing 456: 609-621. DOI: https://doi.org/10.1016/j.neucom.2020.07.155
Mahmoud, R.A.A. 2021. Detection and assessment scheme of voltage and current unbalance for three phase synchronous generators using dual numerical techniques based on correlation and deviation percentage concepts. The Journal of Engineering 2021(9): 477-495. DOI: https://doi.org/10.1049/tje2.12051
Melo, F.C., da Graça, G.C. and Panão, M.J.O. 2023. A review of annual, monthly, and hourly electricity use in buildings. Energy and Buildings 293: 113201. DOI: https://doi.org/10.1016/j.enbuild.2023.113201
Moon, S. and Lee, S. 2019. High-reliable temperature prediction considering stray load loss for large induction machine. IEEE Transactions on Magnetics 55(6): 1-5. DOI: https://doi.org/10.1109/TMAG.2019.2901862
Popa, G.N., Iagăr, A. and Diniș, C.M. 2020. Considerations on current and voltage unbalance of nonlinear loads in residential and educational sectors. Energies 14(1): 102. DOI: https://doi.org/10.3390/en14010102
Santamouris, M. and Vasilakopoulou, K. 2021. Present and future energy consumption of buildings: Challenges and opportunities towards decarbonisation. e-Prime-Advances in Electrical Engineering, Electronics and Energy 100002(1): 1-14. DOI: https://doi.org/10.1016/j.prime.2021.100002
Schonlau, M. and Zou, R.Y. 2020. The random forest algorithm for statistical learning. The Stata Journal 20(1): 3-29. DOI: https://doi.org/10.1177/1536867X20909688
Sinuraya, E., Soemantri, M. and Rafif, I. 2022. Evaluation and Mitigation of Voltage and Current Unbalance at MSTP Undip Jepara. Journal of Physics: Conference Serie 2406(1): 012013. 1-9. DOI: https://doi.org/10.1088/1742-6596/2406/1/012013
Vinayagam, A., Veerasamy, V., Radhakrishnan, P., Sepperumal, M. and Ramaiyan, K. 2021. An ensemble approach of classification model for detection and classification of power quality disturbances in PV integrated microgrid network. Applied Soft Computing 106: 107294. DOI: https://doi.org/10.1016/j.asoc.2021.107294
Wang, C., Du, J. and Fan, X. 2022. High-dimensional correlation matrix estimation for general continuous data with Bagging technique. Machine Learning 111(8): 2905-2927. DOI: https://doi.org/10.1007/s10994-022-06138-3
Wang, S. and Chen, H. 2019. A novel deep learning method for the classification of power quality disturbances using deep convolutional neural network. Applied Energy 235: 1126-1140. DOI: https://doi.org/10.1016/j.apenergy.2018.09.160
