Taboo Search Algorithm Based ANN Model for Wind Speed Prediction

Abstract

Wind power is fluctuate, intermittent and stochastic. The large capacity wind power connected with power grids will bring austere challenge to the safety and stabilization of power system operation. Wind speed prediction is an effective approach for this problem. ANN (artificial neural network) has been used extensively in wind speed prediction. But ANN is apt to getting into local minima and its convergence rate is slow. Tabu search is a kind of intelligent algorithm, which can achieve the global optimizations. This paper put forward a wind speed prediction model of neural network based on tabu search algorithm. How to decide the input of a neural network is a difficult issue. This paper put forward a simple linear correlation analysis method for the input selection. The result shows that with appropriate input parameters, the wind speed prediction model of neural network based on tabu search algorithm can improve the prediction precision.