Improvement Of Short-term Wind Speed Forecasting Method And Its Application At The Electric Power System Optimal Dispatch

With the development of the human society, the problems of energy shortage and environmental pollution have become big problems. Thus increasing the application of renewable resource has become the consensus of all the countries in the world. And the wind power technology is the most mature technology; combined with the characteristics of pollution-free, making it widely accepted throughout the world. However, due to the intermittent and volatility of the wind speed, the electricity power of the wind driven generator sent into the power system is not stable, which has a great impact on power system. Thus if the short-term wind speed of the wind farm can be accurately predicted, and the electricity power of the wind driven generator can be known, the dispatching of the power system will be better, so as to improve the stability of the power system.In this paper, a new short-term wind speed forecasting and correction method is proposed, and the particle swarm optimization(pso) is improved, combined with the forecasting results and the algorithm the wind power system can be dispatched well. Firstly, the wind speed prediction model based on support vector machine(SVM) is established, and a preliminary forecast result is obtained with this model; Then a kind of scheme to modify the velocity mutation points is put forward and the prediction domain of the inductive incredible machine is improved, which optimize the predict results and make them more accurate; Finally the adaptive particle swarm algorithm of alternate prey is put forward and is used with the predict results to schedule IEEE- 30 node system. Through the comparative experiments the effectiveness of improved particle swarm optimization(pso) algorithm is proved, and the importance and effectiveness of the wind speed forecasting is verified.