Use of Machine Learning Algorithms in Power System Load Forecasting: A review

Open Access

Year : 2021 | Volume : | Issue : 1 | Page : 23-30

    Balarihun Mawtyllup

  1. Bikramjit Goswami

  1. , Assam Don Bosco University Airport Road, Azara, Guwahati, India
  2. , Assam Don Bosco University Airport Road, Azara, Guwahati, India


The electrical load forecasting has become one of the most important fields of research for secured, efficient, accurate, reliable power dispatch and management. The main aim of load demand forecasting is to predict the load demand for accurate generation scheduling, system security and economic dispatch of load at any time. Many Authors have done research on the evaluation of load forecasting methods, to improve the accuracy of prediction. In load forecasting, it is essential to cover all time zones from short term to long term, to have a better management of the power system. It is challenging to have an accuracy result with less input data. Machine learning methods have obtained more attention as dealing with randomness in load arrangement is the need. This paper presents the review of several machine learning methods used for load forecasting, viz., SVM, Regression, ANN, Fuzzy logic etc. and to evaluate performance of different methods using electricity consumption dataset, compare between different methods as well as in analyzing calculation complexities of parameters such as-MAPE, RMSE etc.

Keywords: Load forecasting, Machine Learning, ANN, Regression, RMSE.

[This article belongs to International Journal of Microwave Engineering and Technology(ijmet)]

How to cite this article: Balarihun Mawtyllup, Bikramjit Goswami Use of Machine Learning Algorithms in Power System Load Forecasting: A review ijmet 2021; 7:23-30
How to cite this URL: Balarihun Mawtyllup, Bikramjit Goswami Use of Machine Learning Algorithms in Power System Load Forecasting: A review ijmet 2021 {cited 2021 Dec 14};7:23-30. Available from:

Full Text PDF Download

Browse Figures


1. Behnam Farsi, ManarAmayri, Nizar Bouguila, and Ursula Eicker. On Short term Load Forecasting using Machine Learning Technique and a Novel Parallel Deep LSTM-CNN Approach. (2021) IEEE Access (Volume: 9) 31191–31212.
2. Weilin Guo, Liang Che, Mohammad Shahidehpour, xin Wan. Machine Learning based Methods in Short-term Load Forecasting (2021) The Electricity Journal, 2021–Elsevier.
3. ElvisaBecirovic and MarijanaCosovic. Machine learning technique for short term load forecasting.2021.
4. Ibrahim Salem johan, Vaclav Snasel and Stanislav Misak. Intelligent System for Power Load Forecasting: a study review. (2020) Energies (2020), 13, 6105; doi:10.3390/en13226105.
5. Khursheed Aurangzeb. Short term Power Load Forecasting using Learning Models for Energy management community. (2019) 978-1-5386-8125-1/19/$31.00 ©2019 IEEE.
6. Manish Kumar Singla, Parag Nijhawan, Joyti Gupta, Dr Amandeep Singh Oberoi. Electrical load Forecasting using Machine Learning. (2019) International Journal of Advanced Trends in Computer Science and Engineering, 8 (3), May-June 2019, 615–619,Volume 8, No.3, May-June 2019.
7. Abdelkarim El Khantach, Mohamed Hamlich and Nour eddinebelbounaguia. Short-term load forecasting using machine learning and periodicity decomposition. (2019) AIMS Energy, 7 (3): 382–394. DOI: 10.3934/energy.2019.3.382.
8. Noman Shabir, Roya Ahmadiahangar, Lauri Kutt, Argo Rosin. Comparison of Machine Learning based method for residential Load Forecasting. (2019) 978-1-7281-2650-0/19/$31.00 ©2019 IEEE.
9. Jason Runge and Radu Zmeureanu. Forecasting energy used in Building using Artificial Neural Network: A review. (2019) Energies 2019, 12, 3254; doi:10.3390/en12173254.
10. Tahreem Anwar, Bhaskar Sharma, Koushik Chakraborty and Himanshu Sirohia. Introduction to Load Forecasting. (2018) International Journal of Pure and Applied Mathematics Volume 119 No. 15 2018, 1527-1538 ISSN: 1314-3395.
11. David Scoot, Tom Simpson, Nikolaos Dervilis, Timothy Rogers, Keith Worden. Machine learning for energy load forecasting. (2018) IOP Conf. Series: Journal of Physics: Conf. Series 1106 (2018) 012005 doi :10.1088/1742-6596/1106/1/012005.
12. Hossein Sangrody, Ning Zhou, SalinTatun, Benyamin Khorramdel, Mahdi Motalleb, MortezaSarailoo. Long term forecasting using Machine learning methods. (2018).
13. Eliana Vivas, Hector Allende-Cid and Rodrigo Salas. A Systematic Review of Statistical and Machine Learning Methods for Electrical Power Forecasting with Report MAPE score. (2018) Entropy 2020, 22, 1412; doi:10.3390/e22121412.
14. B.yildiz, J.I.Bilbao, A.B. Sproul. A review and analysis of regression and machine learning models on commercial building electricity load forecasting. (2017) Renewable and Sustainable Energy Reviews 73 (2017) 1104–1122.
15. Senthil Kumar P. A review of soft computing Technique in Short-Term Load Forecasting. (2017) International Journal of Applied Engineering Research ISSN 0973-4562 Volume 12, Number 18 (2017) pp. 7202-7206.
16. A.S Khwaja, X. Zhang, A. Anpalagan, B.Venkatesh. Boosted neural networks for improvement short-term electric load forecasting. (2017) Research, 143,431-437.
17. N. Phuangpornpitak and W.Prommee. A study of load demand Forecasting Models in Electric Power system Operation and Planning. (2016) GMSARN International Journal 10 (2016) 19–24.
18. Priti Gohil, Monika Gupta. Short-term Load Forecasting using fuzzy logic. (2014) INTERNATIONAL JOURNAL OF ENGINEERING DEVELOPMENT AND RESEARCH ISSN: 2321-9939.
19. Samuel Felix Fux, ArazAshouri, Michael Janosch Benz, Lino Guzzella. Short-Term Thermal and electrical and load forecasting in building. (2013).
20. Amit JainmE. Srinivas, RasmimayeeRauta. Short term Load Forecasting using Fuzzy Adaptive Inference and Similarity. (2009) 978-1-4244-5612-3/09/$26.00 c 2009 IEEE.
21. Sachdeva, S., & Verma, C.M. (2008, October). Load forecasting using fuzzy methods. In Power System Technology and IEEE Power India Conference, 2008. POWERCON 2008. Joint International Conference on (pp. 1-4). IEEE.
22. H. J. Sadaei, P.C.D.L.E. Silva, F.G. Guimarães, and M. H. Lee, ‘‘Short-term load forecasting by using a combined method of convolutional neural networks and fuzzy time series,’’ Energy, vol. 175, pp. 365–377.
23. Turiel I, Boschen R, Seedall M, Levine M. Simplified energy analysis methodology for commercial buildings. Energy Build 1984;6:67–83. 7788(84)90008-2.
24. Katipamula S, Kissock JK, Claridge DE. The functional basis of steady-state tliermal energy use in air-side HVAC Equipment; 1995. p. 117.”

Regular Issue Open Access Article
Volume 7
Issue 1
Received November 16, 2021
Accepted December 11, 2021
Published December 14, 2021