Energy impact assessment of electric vehicle insertion in the Brazilian scenario, 2020 – 2050: a machine learning approach to fleet projection

Abstract

The transportation sector stands out on the world stage as one of the largest consumers of energy and the trend towards electrification of the light vehicle fleet is proving to be challenging, given the impacts generated by growing demand of energy and mainly in the generation of electricity. In Brazil, the electricity generation mix comprises around 83% of renewable sources, basically composed of hydraulic, wind and biomass sources, making it reasonable to consider the electrification of the transportation sector as one of the measures to be adopted in the promotion of sector sustainability. This article contributes to energy planning through the long-term projection of the Brazilian fleet of light vehicles, and the simulation of their impacts on energy demand, in three scenarios of insertion of plug-in electric vehicles. In this sense, statistical methodologies applied to historical data series and supervised Machine Learning algorithms for curve fitting were used, as well as the well-to-wheels approach in the fuel life cycle to estimate the energy demand. The projections included three scenarios for the insertion of electric vehicles with annual increases in demand for electricity generation which would correspond to 0.6%, 0.9% and 4.2% of additional electricity generation demand in the year 2050, with reference to the year 2020. The electrification of the fleet also proved to be advantageous in terms of reducing the use of fossil fuels and promising in terms of sustainability in the transport sector. The results of these studies will provide fundamental information for energy planning, as well as for public policy decision-making.