Forecasting the Biofuel Consumption Trend on a European Scale with the Random Forest Algorithm
Abstract
The ever-increasing demand for energy worldwide, driven by population and economic growth, industrialization, as well as concerns about the environmental impact of fossil fuels, has increased the demand for renewable and clean energy. Biofuels play an important role in the worldwide transition to renewable energy. Accurate biofuel forecasting is therefore critical for regional policy making. This will enable policymakers to allocate countries' own resources towards their strategic goals, plan the necessary infrastructure and support economic growth. In this study, a forecasting model is constructed using the Random Forest Algorithm (RFA) approach to predict the trends in biofuels consumption. Therefore, firstly, statistical data for the European region (Total Europe and Other Europe) are collected for 1992-2022. These values are then predicted for the years 2025, 2030 and 2050. The values obtained in the forecasting model have found the highest successful results for the given years with the number of decision trees being 50 and the R2 value is 0.9975. The results showed that the models created for Europe can be used in renewable energy projections for future planning. Obtained results are analyzed, the measures and requirements that can be taken in line with the European Union Green Deal are interpreted.
Keywords
References
- Assouline, D., Mohajeri, N., & Scartezzini, J. L. (2018). Large-scale rooftop solar photovoltaic technical potential estimation using Random Forests. Applied energy, 217, 189-211.
- Aydın-Kandemir, F., & Sarptaş, H. (2022). Toprak Üstü Biyokütle Potansiyelinin CBS ve Uzaktan Algılama ile Belirlenmesi–Yeni Bir Yaklaşım. Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi, 24(70), 165-178.
- Breiman, L. (1996). Bagging predictors. Machine learning, 24, 123-140.
- Breiman, L. (2001). Random forests. Machine learning, 45, 5-32.
- Fan, G. F., Zhang, L. Z., Yu, M., Hong, W. C., & Dong, S. Q. (2022). Applications of random forest in multivariable response surface for short-term load forecasting. International Journal of Electrical Power & Energy Systems, 139, 108073.
- Fawagreh, K., Gaber, M. M., & Elyan, E. (2014). Random forests: from early developments to recent advancements. Systems Science & Control Engineering: An Open Access Journal, 2(1), 602-609.
- Ho, T. K. (1998). The random subspace method for constructing decision forests. IEEE transactions on pattern analysis and machine intelligence, 20(8), 832-844.
- International Energy Agency. (2021). World Energy Outlook 2021. Son erişim adresi: https://www.iea.org/reports/world-energy-outlook-2021
- International Renewable Energy Agency. (2023). Renewable Energy Statistics 2023. Son erişim adresi: https://www.irena.org/Publications/2023/Jul/Renewable-energy-statistics-2023.
- Islam, K. I., Elias, E., Carroll, K. C., & Brown, C. (2023). Exploring random forest machine learning and remote sensing data for streamflow prediction: An alternative approach to a process-based hydrologic modeling in a snowmelt-driven watershed. Remote Sensing, 15(16), 3999.