Study and learning of artificial neural networks for application in electric load forecasting

• Grant number: 05/02879-3
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: November 01, 2005
• End date: October 31, 2007
• Field of knowledge: Engineering - Electrical Engineering - Power Systems
• Principal Investigator: Anna Diva Plasencia Lotufo
• Grantee: Kenji Nose Filho
• Host Institution: Faculdade de Engenharia (FEIS). Universidade Estadual Paulista (UNESP). Campus de Ilha Solteira. Ilha Solteira , SP, Brazil

Abstract

Electric load forecasting is very important for planning and operation of electrical power systems. Neural networks are very important for these applications, better than the traditional statistical methods, such as ARIMA of Box&Jenkins. The feedforwar neural network with the backpropagation trainning is one of the most used in several applications found in the literature. This work intends to develop and implement a feedforward neural network with backpropagation training using the toolboxes of MATLAB a very used tool with schoolars and apply to forecast electrical loads with data of a Brazilian system. (AU)