Load forecasting as a computational tool to support smart grids

Load forecasting is a fundamental task for the planning, operation and exploration of the Electric Power Systems. The importance of forecasting has become more evident with the restructuring of the national energy sector and the creation of projects linked to smart grids, namely in Portugal - o InovGrid. This paper describes the computational forecast model of the Daily Load Diagram based on the Levenberg-Marquardt algorithm of Artificial Neural Networks. The data to be used are the time series of active power recorded by the EDP Distribution Telemetry System and the climatic time series of the Portuguese Institute of the Sea and Atmosphere, collected on the city of Évora, one of the first smart cities in Portugal. The forecast horizon is short term: from 24 hours to a week. The good results observed by the statistical error indicators were obtained.