Prediction of Renewable Energy Contribution to Global Primary Energy Needs Using Random Forest Algorithm
Keywords:
Climate change, Data-driven planning, Energy forecasting, Renewable energy, Random forestAbstract
The global energy crisis and climate change have triggered an urgent need for renewable energy. Renewable energy sources, such as solar, wind, and water, provide a sustainable solution as they are environmentally friendly and can significantly reduce the impacts. The role of renewable energy is increasingly vital in creating a more stable energy system and supporting the transition to a low-carbon economy. This study aims to predict the contribution of renewable energy to global primary energy needs to support data-driven strategic planning. A data-driven strategy ensures that policies are based on accurate, reliable information. By analyzing historical data, stakeholders can understand trends, identify patterns, and make more accurate projections for the future. This approach helps reduce uncertainty in decision-making and enhances the effectiveness of designing policies. The Random Forest algorithm is applied to build a predictive model, with evaluation using Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE) to assess the forecasting accuracy. The data used in this study is derived from the Renewable Energy World Wide 1965~2022 dataset in the renewable-share-energy CSV file. The results show good forecasting accuracy for the World with a MAPE of 11.28% and RMSE of 1.60, indicating the Random Forest model's ability to capture renewable energy data patterns at a global level. This research provides valuable insights for sustainable energy planning and strategic decision-making in renewable energy.
References
Dou, Y., Tan, S., & Xie, D. (2023). Comparison of machine learning and statistical methods in the field of renewable energy power generation forecasting: a mini review. Frontiers in Energy Research, 11, 1218603.
Freeman, E. A., Moisen, G. G., Coulston, J. W., & Wilson, B. T. (2016). Random forests and stochastic gradient boosting for predicting tree canopy cover: comparing tuning processes and model performance. Canadian Journal of Forest Research, 46(3), 323-339.
Gufron, H., Rusirawan, D., & Widyawati, L. (2022). Forecasting Produksi Energi PLTS 1 kWp Menggunakan Mesin Pembelajaran Dengan Algoritma Support Vector Machine. Jurnal Tekno Insentif, 16(2), 79-91.
Iannace, G., Ciaburro, G., & Trematerra, A. (2019). Wind turbine noise prediction using random forest regression. Machines, 7(4), 69.
Karakan, A. (2024). Predicting Energy Production in Renewable Energy Power Plants Using Deep Learning. Energies, 17(16), 4031.
Khaleel, M. M., Alsharif, A., & Imbayah, I. I. K. (2022). Renewable energy technologies: Recent advances and future predictions. African Journal of Advanced Pure and Applied Sciences (AJAPAS), 58-64.
Lestari, V. P. (2021). Permasalahan Dan Tatangan Program Peningkatan Kontribusi Energi Baru Dan Terbarukan Dalam Bauran Energi Nasional. Pusat Kajian Akuntabilitas Keuangan Negara
Lubis, A. (2007). Energi terbarukan dalam pembangunan berkelanjutan. Jurnal Teknologi Lingkungan BPPT, 8(2), 151118.
Olcay, K., Tunca, S. G., & Özgür, M. A. (2024). Forecasting and performance analysis of energy production in solar power plants using long short-term memory (LSTM) and random forest models. IEEE Access.
Sulistyono, S. (2012). Pemanasan global (Global Warming) dan hubungannya dengan penggunaan bahan bakar fosil. Swara Patra: Majalah Ilmiah PPSDM Migas, 2(2).
Yang, M., Zhao, M., Liu, D., Ma, M., & Su, X. (2021). Improved random forest method for ultra-short-term prediction of the output power of a photovoltaic cluster. Frontiers In Energy Research, 9, 749367.
