Study on the Integrated Model for Short-Term Wind Power Forecasting Based on D-S Evidence Theory

Abstract

The forecasting of wind speed and wind power is significant to the integration of wind power with power system. An accurate forecasting can relieve the impact on power system, increase the penetration of wind power and make the wind power more competitive. In this paper, an integrated model for short-term wind power forecasting based on D-S evidence theory in uncertain reasoning is proposed to predict the wind speed and power. The weights of single models are extracted as the evidence to the result, then the combined model is presented with multi-fusion of the belief function, and the wind power is obtained by fitting wind speed and direction. The result from the integrated model is compared with the single ones'. Furthermore, the results from different combination models are compared. The fact is certified that the integrated model based on D-S evidence theory has high accuracy and adaptability.