ANALYSIS AND FORECASTING OF RENEWABLE ENERGY CONSUMPTION USING DATA-DRIVEN METHODS
DOI:
https://doi.org/10.69980/yn64ej21Keywords:
renewable energy consumption, time-series forecasting, machine learning, energy transitionAbstract
Renewable energy is gaining significance for energy security, emissions reduction, and the shift to sustainable energy systems. In this study, long-term consumption patterns of renewable energies have been analysed, and statistical and machine-learning approaches for predicting future energy use have been compared. Records of monthly renewable energy supply were analysed for the last 50 years (1973-2023) for major energy sources and economic sectors. Historical pattern and seasonal behaviour were identified through descriptive statistics, trend analysis, sectoral comparison, source-level assessment and time-series decomposition. Models for forecasting performance were then tested on seasonal naïve, xHolt-Winters, SARIMA, Random Forest, Gradient Boosting and Support Vector Regression. The results showed that there was a significant growth in the share of renewable energy in the long term, with electric power having the highest share of the sectoral contribution in 2023. Renewable energy's share of energy was growing and was becoming more important, including wind, solar, biofuels, waste and wood. The monthly time series showed a definite upward trend and an annual seasonality pattern. The SARIMA model performed best with the lowest RMSE and MAPE among the evaluated models, followed by Holt–Winters. The machine-learning models yielded less out-of-sample accuracy than. Renewables forecasts were for continued steady expansion through 2026, with increasing uncertainty further out in time. The results illustrate that statistical time-series forecasting is still useful for forecasting renewable energy in the long run, and can be applied to energy planning, infrastructure development, and policymaking.
References
[1]Abdul Baseer, M., Almunif, A., Alsaduni, I., & Tazeen, N. (2023). Electrical power generation forecasting from renewable energy systems using artificial intelligence techniques. Energies, 16(18), 6414.
[2]Alazemi, T., Darwish, M., & Radi, M. (2024). Renewable energy sources integration via machine learning modelling: A systematic literature review. Heliyon, 10(4).
[3]Alkhayat, G., Hasan, S. H., & Mehmood, R. (2022). SENERGY: A novel deep learning-based auto-selective approach and tool for solar energy forecasting. Energies, 15(18), 6659.
[4]Alotaibi, M. A. (2022). Machine learning approach for short-term load forecasting using deep neural network. Energies, 15(17), 6261.
[5]Çevik Bektaş, S., & Altaş, I. H. (2024). DWT-BILSTM-based models for day-ahead hourly global horizontal solar irradiance forecasting. Neural Computing and Applications, 36(21), 13243-13253.
[6]Chatzipanagi, A., Jaeger-Waldau, A., LETOUT, S., MOUNTRAKI, A., GEA, B. J., GEORGAKAKI, A., ... & SCHMITZ, A. (2022). Clean Energy Technology Observatory: Photovoltaics in the European Union-2024 status report on technology development, trends, value chains and markets.
[7]Gagnon, P., Pham, A., Cole, W., Awara, S., Barlas, A., Brown, M., ... & Williams, T. (2023). 2023 standard scenarios report: A us electricity sector outlook (No. NREL/TP--6A40-87724). National Renewable Energy Laboratory (NREL), Golden, CO (United States).
[8]Gajdzik, B., Kumar, S., & Wolniak, R. (2026). Dynamic Clustering of Renewable Energy Capacity: A Comparative Study of the EU-27 and 15 RCEP Countries. Sustainability (2071-1050), 18(10), 4651.
[9]Grzeszczyk, T. A., & Grzeszczyk, M. K. (2022). Justifying short-term load forecasts obtained with the use of neural models. Energies, 15(5), 1852.
[10]Ibrahim, B., Rabelo, L., Gutierrez-Franco, E., & Clavijo-Buritica, N. (2022). Machine learning for short-term load forecasting in smart grids. Energies, 15(21), 8079.
[11]International Energy Association. (2025). Renewables 2025: Analysis and Forecasts to 2030.
[12]Islam, M. K., Hassan, N. M. S., Rasul, M. G., Emami, K., & Chowdhury, A. A. (2023). Forecasting of solar and wind resources for power generation. Energies, 16(17), 6247.
[13]King, A. (2024). U.S. renewable energy consumption [Data set]. Kaggle. https://www.kaggle.com/datasets/alistairking/renewable-energy-consumption-in-the-u-s
[14]Klyuev, R. V., Morgoev, I. D., Morgoeva, A. D., Gavrina, O. A., Martyushev, N. V., Efremenkov, E. A., & Mengxu, Q. (2022). Methods of forecasting electric energy consumption: A literature review. Energies, 15(23), 8919.
[15]Limmeechokchai, B., Winyuchakrit, P., Pita, P., & Misila, P. (2023). Climate Change 2022: Climate Change 2022 Mitigation of Climate Change: Buildings. International Journal of Building, Urban, Interior and Landscape Technology, 21(2), 61-69.
[16]Lundberg, S. M., Erion, G., Chen, H., DeGrave, A., Prutkin, J. M., Nair, B., ... & Lee, S. I. (2020). From local explanations to global understanding with explainable AI for trees. Nature machine intelligence, 2(1), 56-67.
[17]Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2022). M5 accuracy competition: Results, findings, and conclusions. International journal of forecasting, 38(4), 1346-1364.
[18]Malakouti, M. (2026). Machine learning for renewable energy forecasting: advances, challenges, and future directions. Sustainable Energy Research, 13(1), 14.
[19]Manno, A., Martelli, E., & Amaldi, E. (2022). A shallow neural network approach for the short-term forecast of hourly energy consumption. Energies, 15(3), 958.
[20]Marzouk, O. (2025). Summary of the 2023 report of TCEP (tracking clean energy progress) by the International Energy Agency (IEA), and proposed process for computing a single aggregate rating. Available at SSRN 5099325.
[21]Marzouk, O. A. (2023). 2030 Ambitions for hydrogen, clean hydrogen, and green hydrogen. Engineering Proceedings, 56(1), 14.
[22]Moghimi, S. M., Gulliver, T. A., & Thirumai Chelvan, I. (2024). Energy management in modern buildings based on demand prediction and machine learning—A review. Energies, 17(3), 555.
[23]Mustafa, H., Bexheti, A., & Alija, S. (2025). Investments in renewable energy in the most developed OECD countries and the Western Balkan countries. European Chronicle, 10(2), 42-59.
[24]Nikolaidis, P. (2024). Smart grid forecasting with mimo models: A comparative study of machine learning techniques for day-ahead residual load prediction. Energies, 17(20), 5219.
[25]Radhi, S. M., Al-Majidi, S. D., Abbod, M. F., & Al-Raweshidy, H. S. (2024). Machine learning approaches for short-term photovoltaic power forecasting. Energies, 17(17), 4301.
[26]Rezaee, E., & Silva, S. R. P. (2026). Solar energy in 2025: Global deployment, cost trends, and the role of energy storage in enabling a resilient smart energy infrastructure. Energy & Environmental Materials, 9(3), e70199.
[27]Román-Portabales, A., López-Nores, M., & Pazos-Arias, J. (2021). Systematic review of electricity demand forecast using ANN-based machine learning algorithms.
