Proposition of a PSO fuzzy polynomial neural network for short-term load forecasting

At present, several artificial intelligence (AI) techniques are used to identify complex systems. The data collected is extremely important, as it enables the evaluation, prediction and correction variables' behavior in any given process. The most recent methods tend to associate such techniques in order to obtain models that are continuously closer to those desired. This paper presents a method based on polynomial neural networks and fuzzy logics, optimized by a technique known as particle swarm optimization. The idea consists in generating a final structure that is compact, flexible and capable of producing good results when applied to resolving system identification problems and time series forecasting.