Analyzing the Brazilian project of energy expansion
Jorge Luiz de Macedo 1 , Irenilza de Alencar Nääs 1 *
More Detail
1 Paulista University, São Paulo, SP, BRAZIL* Corresponding Author

Abstract

The Brazilian energy grid encompasses mainly hydroelectric power, despite investments in other energy sources. The country’s energy forecast is based on the demand and the contracted projects to supply the consumers’ needs. The present study aimed to analyze the Brazilian investment in energy based on the installed capacity and the country’s forecast. The research question evaluated whether the future energy investments comply with the country’s agreement in reducing emissions and focusing on sustainable development. Primary data were retrieved from governmental open sources and organized. The dependent variables were the data on installed capacity in 2021 (MW), forecast capacity for 2024 (MW), and growth (%). Applying the random forest model, data mining using the Rapidminer Studio was applied to the database. Decision tree algorithms were obtained involving the studied variables. The accuracy was 68% and kappa (κ)=0.60 (prediction result is suitable when accuracy is ≥60%, and κ≥0.60). Three decision tree models were selected to represent the chosen attributes based on the coherence of the decision flow amongst the studied variables. Using data mining, the prediction models of the energy investment in Brazil show the energy forecast for 2024. The current study points out that future investments in energy sources in the electric grid in Brazil aim for diversity since it plans for solar and wind energy sources; nevertheless, it also includes thermal and hydroelectric energy sources.

License

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Article Type: Research Article

EUR J SUSTAIN DEV RES, Volume 7, Issue 4, 2023, Article No: em0227

https://doi.org/10.29333/ejosdr/13409

Publication date: 18 Jun 2023

Article Views: 1011

Article Downloads: 738

Open Access References How to cite this article