Metodologia de previsão na intensificação de energias renováveis no ambiente de expectativa para uma transição energética confiável

Abstract

This study focuses on the Brazilian energy scenario and highlights the progressive increase in the use of renewable sources in the country's electrical energy matrix. The main objective of this study is to contribute to the search for solutions and encourage debates and reflections on the future actions necessary for energy planning. To achieve this, the research employs computational tools based on machine learning and data mining, using government and energy market data sources. The research methodology begins with the analysis of historical data related to the electricity market in Brazil, including policies, national guidelines and regulatory mechanisms. The research then uses machine learning and data mining tools to forecast the electricity market in the country. These forecasts are then compared with the horizon predicted by the Ten-Year Energy Expansion Plan 2030. The methodology used includes the execution of forecast models, highlighting the behavior of the energy market over time, using three different methods: Multilayer Neural Networks Perceptron (MLP), Gaussian Process Regression (GPR) and Linear Regression to project electrical generation by source in Brazil. The results indicate considerable growth in renewable sources in the national energy market until 2030, approaching the objective of the Ten-Year Energy Expansion Plan of reaching 90% renewability, covering sources such as hydroelectric, biomass, wind and solar. The Linear Regression method achieves 86% renewability, while the Gaussian Process Regression method achieves 90%, and the Multilayer Perceptron Neural Networks method reaches 88%. Likewise, the scenarios proposed for the Brazilian energy market intended to gradually increase the use of renewable sources in the electrical energy matrix and its growth potential. The projection of the electricity market forecast made it possible to identify market behavior patterns, allowing trends and changes in the market to be anticipated. These forecasts are intended to provide information to support the development of actions in the energy planning process, contributing to the transition to more sustainable and renewable sources of energy in Brazil.