Forecast of Distributed Electrical Generation System Capacity Based on Seasonal Micro Generators using ELM and PSO

This work proposes the development of a computational tool that goal at forecasting the daily generation capacity of electric power in a distributed system based on micro generators that use renewable and seasonal sources. In the specific case, wind and photovoltaic microgenerators are used, which can be found in smart homes. The forecasting tool is based in Extreme Learning Machine (ELM) which is an artificial neural network model. The parameter selection implemented for ELM is based on the Particle Swarm Optimization (PSO). The forecasting system used the mathematical models of the seasonal micro-generators and a meteorological database of the geographic region where the distributed system is located. The tests performed indicate that the Mean Square Error Root (REQM) of the forecast is 7.3 percent.