Modeling and Forecasting Energy Consumption in Urban Environments: Exploring the Potential of Machine Learning in Predicting Energy Consumption

• Grant number: 24/02900-3
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Effective date (Start): June 01, 2024
• Effective date (End): December 31, 2024
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Murilo Varges da Silva
• Grantee: Vinicius de Souza Santos
• Host Institution: Instituto Federal de Educação, Ciência e Tecnologia de São Paulo (IFSP). Campus Birigui. Birigüi , SP, Brazil

Abstract

This research project aims to develop a predictive model using Random Forest to predict energy consumption in urban environments. Starting with the analysis of energy consumption patterns and literature review on energy prediction models, the project focuses on the construction and calibration of a Random Forest model. Tests will be carried out to validate its accuracy and effectiveness, followed by analysis and interpretation of the results. The project also includes documenting the research process and developing practical recommendations for energy and urban planning. To develop the project, an infrastructure will be required that includes access to historical energy consumption databases, advanced machine learning tools and computing capabilities to process and analyze large volumes of data. The research will also require specialized knowledge in data analysis, predictive modeling and energy management. The infrastructure can be made available by research institutions or partnerships with companies in the energy sector.