Smart Charging of Electric Vehicles

• Grant number: 25/07053-0
• Support Opportunities: Scholarships abroad - Research Internship - Scientific Initiation
• Start date: August 01, 2025
• End date: November 30, 2025
• Field of knowledge: Engineering - Electrical Engineering - Power Systems
• Principal Investigator: Lucas Teles de Faria
• Grantee: Luana Beatriz Pereira dos Santos
• Supervisor: Maria Nataly Banol Arias
• Host Institution: Faculdade de Engenharia e Ciências (FEC). Universidade Estadual Paulista (UNESP). Campus de Rosana. Rosana , SP, Brazil
• Institution abroad: University of Twente (UT), Netherlands
• Associated to the scholarship: 23/15158-0 - Estimation of Electric Vehicles Insertion in Power Distributin Systems via Spatial Data Analysis, BP.IC

Abstract

Uncontrolled and arbitrary charging of electric vehicles can have significant impacts on electric power distribution systems, including substantial increases in energy losses, voltage deviations, and overloading of equipment and substations. Given the increased adoption of electric vehicles in the medium and long term, studies that consider smart charging strategies become essential. These strategies can mitigate the impact on the electrical grid, ensuring the safe and efficient operation of the electrical system. In this context, this project aims to develop a smart charging strategy for electric vehicles by applying machine learning algorithms to historical data. Conducting studies that address behavior predictions and updating the consumption profile in real time becomes essential to minimize deviations between planning and operation. The application of tools for real-time or online analysis is of utmost importance, as the energy demand of electric vehicle charging stations can vary due to the addition of new users. In this way, historical data from a charging station will be analyzed to make future predictions based on profiles evaluated a priori (offline planning). Additionally, online planning will be performed, which will represent an update of the offline planning made a priori based on the dynamic behavior of the load and the adjustment of electric vehicle charging profiles in the medium and long term.