Pavitr Jain,
Vikas Sharma,
Vivek Verma,
Avnish Soni,
Arpit Kumar,
Ritish Sharma,
- Student, Department of Statistics, Greater Noida Institute of Technology IP Campus, Uttar Pradesh, India
- Student, Department of Statistics, Greater Noida Institute of Technology IP Campus, Uttar Pradesh, India
- Student, Department of Statistics, Greater Noida Institute of Technology IP Campus, Uttar Pradesh, India
- Student, Department of Statistics, Greater Noida Institute of Technology IP Campus, Uttar Pradesh, India
- Student, Department of Statistics, Greater Noida Institute of Technology IP Campus, Uttar Pradesh, India
- Student, Department of Statistics, Greater Noida Institute of Technology IP Campus, Uttar Pradesh, India
Abstract
Accurate electricity demand forecasting plays a vital role in energy planning, efficient power system operation, and sustainable resource management. This study conducts a comparative evaluation of the Autoregressive Integrated Moving Average (ARIMA) and Seasonal Autoregressive Integrated Moving Average (SARIMA) models using ten years of monthly electricity consumption data collected from a national electricity regulatory authority. The performance of both models is assessed using forecasting accuracy metrics, including Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE), while model suitability is further evaluated through the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC).The findings indicate that the SARIMA model consistently outperforms the ARIMA model due to its ability to effectively capture the seasonal patterns inherent in electricity demand data. In particular, SARIMA achieves approximately a 34% reduction in MAPE over the forecasting horizon, demonstrating superior predictive performance. Residual diagnostic tests further confirm the reliability of the SARIMA model by satisfying key statistical assumptions, including white noise, normality, and homoscedasticity. These results suggest that incorporating seasonality into time-series forecasting significantly enhances prediction accuracy. The study provides valuable insights for utility companies, policymakers, and grid operators seeking dependable short- to medium-term electricity demand forecasting tools to support informed decision-making, optimize energy distribution, improve grid stability, and promote sustainable energy management practices.
Keywords: Time series forecasting, ARIMA, SARIMA, energy planning, demand forecasting
[This article belongs to Research & Reviews : Journal of Statistics ]
References
- Box GEP, Jenkins GM. Time series analysis: Forecasting and control. Rev ed. San Francisco: Holden-Day; 1976.
- Contreras J, Espinola R, Nogales FJ, Conejo AJ. ARIMA models to predict next-day electricity prices. IEEE Trans Power Syst. 2003;18(3):1014-20.
- Ediger VS, Akar S. ARIMA forecasting of primary energy demand by fuel in Turkey. Energy Policy. 2007;35(3):1701-8.
- Hyndman RJ, Athanasopoulos G. Forecasting: Principles and practice. 3rd ed. Melbourne: OTexts; 2021.
- Makridakis S, Spiliotis E, Assimakopoulos V. The M4 competition: Results, findings, conclusion, and way forward. Int J Forecast. 2018;34(4):802-8.
- Pappas SS, Ekonomou L, Karamousantas DC, Chatzarakis GE, Katsikas SK, Liatsis P. Electricity demand loads modeling using autoregressive moving average (ARMA) models. Energy. 2008;33(9):1353-60.
- Qiu X, Ren Y, Suganthan PN, Amaratunga GAJ. Empirical mode decomposition based ensemble deep learning for load demand time series forecasting. Appl Soft Comput. 2017;54:246-55.
- Salazar-Macias L, Torres-Jimenez E, Flores-Becerra G. Seasonal ARIMA-based forecasting for electricity demand in developing economies. Energy Rep. 2023;9:4512-24.
- Taylor JW. Short-term electricity demand forecasting using double seasonal exponential smoothing. J Oper Res Soc. 2003;54(8):799-805.
- Zhang GP. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing. 2003;50:159-75.
- Abdualgalil B, Khalid S. Short-term electricity demand forecasting using SARIMA and regression models under climate variability. Sustain Energy Grids Netw. 2021;27:100480.
- Daut MAM, Hassan MY, Abdullah H, Rahman HA, Abdullah MP, Hussin F. Building electrical energy consumption forecasting analysis using conventional and artificial intelligence methods. Renew Sustain Energy Rev. 2017;70:1108-18.
- Nguyen TT, Nguyen TD. Hybrid SARIMA-LSTM model for medium-term electricity demand forecasting in emerging markets. Energy Rep. 2022;8:3612-25.
- Ribeiro AMNC, do Carmo PRX, Rodrigues IR, Sadok D, Lynn T, Endo PT. Short-term firm-level energy-consumption forecasting for energy-intensive industries. Electronics. 2020;9(9):1-20.
- Sehovac L, Grolinger K. Deep learning for load forecasting: Sequence-to-sequence recurrent neural networks with attention. IEEE Access. 2020;8:36411-26.
- Spiliotis E, Assimakopoulos V, Nikolopoulos K. Forecasting with a hybrid method utilizing data smoothing, a variation of the Theta method and shrinkage of seasonal factors. Int J Prod Econ. 2019;209:92-102.
- Wang Y, Zhang N, Tan Y, Hong T, Kirschen DS, Kang C. Combining probabilistic load forecasts. IEEE Trans Smart Grid. 2019;10(4):3664-74.
- Ziel F, Weron R. Day-ahead electricity price forecasting with high-dimensional structures: Univariate vs. multivariate modeling frameworks. Energy Econ. 2018;70:396-420.
Research & Reviews : Journal of Statistics
| Volume | 15 | |
| Issue | 02 | |
| Received | 04/07/2026 | |
| Accepted | 13/07/2026 | |
| Published | 25/07/2026 | |
| Publication Time | 21 Days |