New Neural Networks Strategy Used to Improve Wind Speed Forecasting

Abstract

Wind speed forecasting is critical for wind energy conversion systems since it greatly influences the issues such as the scheduling of a power system, and the dynamic control of the wind turbine. The wind forecast problem aims to find an estimate f( t + k) of the wind vector y( t + k) based on the previous n measurements. Artificial neural networks ANN is a technique basically used to map random input vector(s) to the corresponding random output vector without pre-assuming any fixed relationship between them. Different network structures, learning rates, and inputs are believed to result in different forecast accuracies. However, in literature it was discovered that, different inputs and learning rates, as well as model structures, directly influence the forecast accuracy. In this paper, we present a robust and reliable forecast method by applying a new learning Strategy. This new method allows a renewal learning data in time. A simple multilayer perceptron (MLP) with Levenberg-Marquardt learning algorithm technique is used for predicting the wind speed. For our algorithm a neural network is developed to estimate just one value f( t + 1), then it is taken up with a new set of learning enriched by data freshly measured. The wind data used are the hourly mean wind speed collected at an observation sites in Ksar El chellala, (Algeria). Simulation results are reported, showing that the estimated wind speed values, predicted by the proposed learning algorithm technique, are in good agreement with the experimental measured values. The present paper deals with the development of an adaptive neural network model for the hourly forecasting of wind speed.