Wind Farm Wind Speed And Power Output Prediction

The research on wind power is deeply and widely at home and abroad. But wind speed forecasting and wind power forecasting in wind farm still can't make us satisfied. And in our country few people work on this subject. This paper makes research and discussion in the field. When Wind Power Penetration is over a given ratio, it will severely influence power quality and the operation of power system. If wind speed or wind power in wind farm can be forecasted accurately, when necessary, dispatching department can adjust dispatching plan according to the forecasted data ahead of time. So it will lessen the unfavorable influence caused by wind power to the entire electrical network. Moreover it has other significance to power system.This paper introduces foreign researches in this field so far, and illustrates the theory and application of time series method and ANN(artificial neural network). Firstly builds the basic model with time series method, which aims to obtain the variables largely influencing forecasting result. Then applies the results of time series method into ANN, which can make out the quantity of ANN's input variables. Furthermore puts forward rolling method to adjust weight factors. The method solves the problem that ANN's weight factors becomes unsuitable with time passing by. The test shows the mathematical model has certain actual value.In the end, this paper contrasts accuracy of wind speed forecasting with wind power forecasting. Then points out, owing to the self- regular difference between wind speed and wind power, the forecasting accuracy between them still exits difference.