Electric load forecasting is a fundamental study for the operation and planning of electrical power systems. Considering the electric energy sector deregulation, the greater competitiveness and the technological and philosophical transformations arising from the design and construction of smart grids, the knowledge of the future behavior of the electric energy systems loads becomes essential for the adequate decision making. Within this context, research addressing load forecasting will take place in the long, medium, short and very short-term scenarios. Furthermore, researchers and power companies have encouraged in the application of artificial intelligence techniques to design robust and flexible models that provide a reliable solution, with high accuracy and high computational performance. Therefore, this project aims to develop an intelligent system for short-term load forecasting in electric power systems. More specifically, artificial intelligence techniques will be used for designing the predictor module, especially, artificial neural networks and/or fuzzy logic. The data for load forecasting will be obtained through information provided by the National Electric System Operator (NESO), in order to provide the project with current and safe information.
News published in Agência FAPESP Newsletter about the scholarship: