Energy price forecasting based on artificial neural networks in the very short-term horizon: an analysis of technical variables from financial markets

• Grant number: 19/13220-5
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: September 01, 2019
• End date: August 31, 2020
• Field of knowledge: Engineering - Electrical Engineering - Power Systems
• Principal Investigator: Ricardo Augusto Souza Fernandes
• Grantee: Gabriel Pires Sobreira
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil

Abstract

This scientific initiation project has as main objective the implementation of an approach based on Artificial Neural Networks (ANN) with the purpose of obtaining estimates of the energy price for the Ontario market - Canada. However, to meet this objective, it will be extracted features by calculating technical variables commonly used in financial markets. In the sequence, a selection of attributes/features will be performed to determine the variables most relevant to the estimation process done by ANNs. Thus, it will be verified the performance of ANNs against the very short-term horizon, that is, estimates for an hour ahead, which are of great importance to the energy markets that are currently inserted in the context of Smart Grids.