Grey correlation time sequence based short-term wind speed forecasting method

Abstract

The invention discloses a grey correlation time sequence based short-term wind speed forecasting method, which comprises the steps of (10) forming historical wind speed time sequence data, wherein actually measured wind speeds of a wind power plant are arranged according to a time sequence so as to form a historical wind speed time sequence; (20) acquiring a training sample set, wherein the historical wind speed time sequence is differentiated so as to acquire the training sample set; (30) acquiring a grey correlation optimization wind speed forecasting model, wherein optimized decision-making analysis under multiple targets is carried out on the order number of a time sequence model by applying a grey correlation decision-making analysis method, and grey time sequence model training is carried out by applying the training sample set so as to acquire an optimal wind speed forecasting model; (40) acquiring the differentiated short-term forecast wind speed, wherein short-term wind speed forecasting is carried out on the wind power plant by using the optimal wind speed forecasting model so as to acquire the differentiated short-term forecast wind speed; and (50) acquiring the actual short-term forecast wind speed, wherein inverse differentiation is carried out on the short-term forecast wind speed so as to acquire the short-term forecast wind speed of the wind power plant. The short-term wind speed forecasting method disclosed by the invention is small in forecast error.

Description

technical field [0001] The invention belongs to the technical field of wind speed prediction in wind farms, in particular to a short-term wind speed prediction method based on gray relational time series. Background technique [0002] Wind power has good prospects and competitiveness in renewable energy. However, wind energy is affected by various factors such as temperature, air pressure, terrain, altitude, latitude, etc. It is an intermittent and random energy source. Large-scale wind power connected to the grid will inevitably bring severe challenges to the safe and stable operation of the power system. , so it is very necessary for the prediction of wind speed and power generation. Accurate prediction of wind speed and power generation in wind farms will help the power system dispatching department to adjust the dispatching plan in time when necessary, thereby effectively reducing the adverse impact of wind power generation on the entire power grid. [0003] Existing m...

AI Technical Summary

Problems solved by technology

[0004] However, this method has a limited ability to process sudden changes in the predicted wind speed. When the fluctuations in the predicted wind speed and the training wind speed fluctuate greatly, the prediction model cannot keep up with the changes in the measured wind speed, resulting in large short-term wind speed prediction errors.

Images