[Show abstract][Hide abstract] ABSTRACT: This paper proposes a novel technique that combines orthogonal least-squares (OLS) and culture algorithm (CA) to construct the radial basis function (RBF) network for the wind power forecast. By reason of the fluctuation and volatility in wind, wind power generations provide a challenge to the security and stability of the electric system, thus the growing revolution in wind energy encourages more accurate prediction models. The RBF network is composed of three-layer structure, which contains the input, hidden, and output layer. To simplify it, the OLS algorithm is used primarily to determine the number of the centers in the hidden layer. The culture algorithm is a class of computational models derived from observing the culture evolution process in nature and has three major components. In this paper, it is used to tune the parameters in the network. The experimental results reveal the effectiveness and accuracy of the above-mentioned approach, implying it can serve as a promising alternative for wind power forecast.
[Show abstract][Hide abstract] ABSTRACT: The growing revolution in wind energy encourages more accurate models for wind speed forecasting as the wind is fluctuate, periodic and volatile. An artificial neural network (ANN) method is used to predict the average hourly wind speed. Different from the multilayer perception network (MLP) which is more conversant, this paper presents a novel technique based on radial basis function (RBF) network using the orthogonal least-squares (OLS) algorithm, and also discusses how to organize the inputs of the network. The results reveal the effectiveness and accuracy of the proposed new approach to forecasting. Furthermore, the future work perspective is present at the end of this paper.