System and method for predicating short-time wind power

Abstract

The invention discloses a system and a method for predicating short-time wind power. The method comprises the following steps of adopting a Kalman algorithm to preprocess wind speed data, to enable the data to be smooth and stable; carrying out phase space reconstructing on the preprocessed data, and determining delay time and embedding dimensions; utilizing an Elman neural network to establish a wind speed predicting model to predict the wind speed; according to a power conversion formula, converting the wind speed into power, and outputting the predicted power value. After being proved by multiple experiments, compared with the prior art, the predicting precision is obviously improved.

Description

technical field [0001] The present invention relates to a short-term wind power prediction system and method, in particular to a short-term wind power prediction based on Kalman filter phase space reconstruction based on Elman neural network. Background technique [0002] Due to the relatively late start of wind power forecasting research in my country, at present, it is mainly theoretical exploration, and most of the forecasting systems are in the exploration and research stage. Research on forecasting methods to gradually improve forecasting accuracy. The uncontrollability of natural factors and the randomness, intermittency and volatility of wind power output power will bring severe challenges to the safe and stable operation of wind power grid-connected. The improvement of short-term wind power prediction accuracy will help the power system dispatching department to arrange dispatching plans reasonably and effectively reduce the impact of wind power on the entire power g...

AI Technical Summary

Problems solved by technology

[0003] At present, the methods for wind power prediction can be divided into two categories: one is based on the physical model, which considers the environmental terrain, roughness and other information, and obtains prediction results based on relevant data such as digital weather forecast; the other One is to establish a wind speed or wind power prediction model based on existing historical data such as wind speed and wind power. Some of them need to predict a single wind turbine, and then stack the frame to obtain the entire field power. Although the prediction accuracy is high, the calculation The amount is large and the prediction speed is slow; some need to directly predict the power of the whole field, the calculation amount is small, the prediction speed is fast, and the disadvantage is that the prediction accuracy is low

Images