MLP neural network as load forecasting tool on short- term horizon

This paper focus on multilayer feedforward neural networks, the most popular and widely-used paradigms in many applications, including energy forecasting Precisely, it provides a multilayer perceptron (MLP) architecture, capable to forecast the DPcg (difference between the electricity produced and consumed) in relation with solar radiation, for shortterm horizon. The forecasting accuracy and precision, in capturing nonlinear interdependencies between the load and solar radiation of this structure is illustrated and discussed using a data based obtain from an experimental photovoltaic amphitheatre of minimum dimension 0.4kV/10kW.