Enhanced Prediction of Electricity Peak Load via Machine Learning and Time Series Analysis

S. Suriya; R. Agusthiyar

doi:10.21271/ZJPAS.38.2.14

Authors

S. Suriya Department of Computer Science and Applications, SRM Institute of Science and Technology, Ramapuram Campus, Chennai, India,
R. Agusthiyar Department of Computer Science and Applications, SRM Institute of Science and Technology, Ramapuram Campus, Chennai, India,

DOI:

https://doi.org/10.21271/ZJPAS.38.2.14

Keywords:

ARIMA, Multivariate, Lasso, XGR Regressor

Abstract

Accurate short-term electricity demand forecasting is essential for ensuring reliable power supply, optimizing grid operations, and supporting sustainable energy planning. In Tamil Nadu, seasonal variability, economic growth, and climatic anomalies make peak demand prediction particularly challenging. This study aims to develop a robust forecasting framework that addresses these challenges by integrating statistical time-series modeling with machine learning techniques. Historical monthly peak demand data from April 2006 to March 2023, sourced from the Tamil Nadu Transmission Corporation, were analyzed alongside climate and socio-economic variables. Preprocessing involved missing value imputation, stationarity checks, and feature engineering, followed by model development using Autoregressive Integrated Moving Average (ARIMA), Vector Autoregression (VAR), and a hybrid VAR–machine learning ensemble incorporating Lasso, Ridge, and XGBoost regressors. Model performance was evaluated using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). Results show that the ARIMA model achieved the lowest MAPE (1.26%), outperforming VAR and hybrid approaches, particularly in capturing seasonal trends. However, error margins increased during anomalous months influenced by extreme weather events, highlighting the need for incorporating additional real-time predictors. This research demonstrates that a well-calibrated ARIMA model offers a reliable and practical solution for Tamil Nadu’s short-term peak demand forecasting, providing actionable insights for policymakers, utility planners, and grid operators.

References

Akhtar, S., Adeel, M., Iqbal, M., Namoun, A., Tufail, A., Kim, K.-H., 2023. Deep learning methods utilization in electric power systems. Energy Rep. 10, 2138–2151. https://doi.org/10.1016/j.egyr.2023.09.028

Amosedinakaran, S., Jeyakumar, S.J., Elangovan, K., Rani, K., 2020. Electricity demand forecasting using differential evolution algorithm for Tamil Nadu’, in: Proceedings of the Fourth International Conference on Trends in Electronics and Informatics (ICOEI. IEEE, pp. 732–736.

Dollah, R., Aris, H., 2018. A big data analytics model for household electricity consumption tracking and monitoring’, in: 2018 IEEE Conference on Big Data and Analytics (ICBDA. IEEE, pp. 44–49.

Ghaib, F.A., 2024. One-dimensional electrical resistivity prospecting for small dam projects: A case study Smaquli Dam, East Erbil City, Kurdistan Region of Iraq. Zanco J. Pure Appl. Sci. 36, 84–93. https://doi.org/10.21271/ZJPAS.36.4.9

Hameed, S.G., Al-Jumur, S.M.R.K., 2023. Prediction of long-term surface temperature variation in Kurdistan Region using Meteonorm Weather Generator (MWG. Zanco J. Pure Appl. Sci. 35, 40–52. https://doi.org/10.21271/ZJPAS.35.5.4

Haykin, S., 1999. Neural networks: A comprehensive foundation.

Ismael, R.Q., Sadeq, H.A., 2025. Sequential hybrid integration of U-Net and fully convolutional networks with Mask R-CNN for enhanced building boundary segmentation from satellite imagery. Zanco J. Pure Appl. Sci. 37, 157–171. https://doi.org/10.21271/ZJPAS.37.3.13

Kong, W., Dong, Z.Y., Jia, Y., Hill, D.J., Xu, Y., Zhang, Y., 2019. Short-term residential load forecasting based on LSTM recurrent neural network’. IEEE Trans. Smart Grid 10, 841–851.

Mirlatifi, A.M., Egelioglu, F., Atikol, U., 2015. An econometric model for annual peak demand for small utilities’. Energy 89, 35–44.

Neves, S.A., Marques, A.C., Fuinhas, J.A., 2018. On the drivers of peak electricity demand: What is the role played by battery electric cars?’. Energy 159, 905–915.

Osman, Z.H., Awad, M.L., Mahmoud, T.K., 2009. Neural network based approach for short-term load forecasting, in: 2009 IEEE/PES Power Systems Conference and Exposition. Presented at the 2009 IEEE/PES Power Systems Conference and Exposition (PSCE), IEEE, Seattle, WA, USA, pp. 1–8. https://doi.org/10.1109/PSCE.2009.4840035

Pandoh, A., Wasekar, A.S., Sarkar, S., 2021. Smart electricity meter monitoring and prediction using iSocket’, in: 7th International Conference on Advanced Computing & Communication Systems (ICACCS. IEEE, pp. 1–6.

Park, J., Kim, M., Hong, S., Jeung, Y., 2020. Prediction of individual household energy bills using deep learning’, in: 2020 35th International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC. IEEE, pp. 500–504.

Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., 2017. Automatic differentiation in PyTorch.

Prasetyo, H., Tularsih, Y.T., Pandansari, F., Prasetya, S.B., Priyandono, A., Dermawan, A.S., 2021. Design of power monitoring system based on Internet of Things (IoT) with calibration interface’, in: International Conference on ICT for Smart Society (ICISS. IEEE, pp. 1–5.

Rallapalli, S.R., Ghosh, S., 2012. Forecasting monthly peak demand of electricity in India—A critique’. Energy Policy 45, 516–520.

Shapi, M.K.M., Ramli, N.A., Awalin, L.J., 2021. Energy consumption prediction by using machine learning for smart building: Case study in Malaysia’. Dev. Built Environ. 5, 100037.

Siryani, J., Tanju, B., Eveleigh, T.J., 2017. A machine learning decision-support system improves the internet of things’ smart meter operations’. IEEE Internet Things J. 4, 1056–1066.

Sulaiman, M.H., Mustaffa, Z., 2024. Enhancing wind power forecasting accuracy with hybrid deep learning and teaching-learning-based optimization. Clean. Energy Syst. 9, 100139. https://doi.org/10.1016/j.cles.2024.100139

Suriya, S., Agusthiyar, D., 2023. Comparative study based on the consumption of electricity bill for the Indian states with various machine learning algorithms’. J. Balk. Tribol. Assoc. 29, 211–218.

Than, M.M., Thein, T., 2018. Electricity price prediction for geographically distributed data centers in multi-region electricity markets’, in: 3rd International Conference on Computer and Communication Systems (ICCCS. IEEE, pp. 89–93.

Zhang, G.P., 2003. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50, 159–175. https://doi.org/10.1016/S0925-2312(01)00702-0