A wind power plant random output scene generation method and device

Abstract

The invention relates to a wind power plant random output scene generation method and device. The method comprises the steps of determining a prediction error of wind power plant prediction output byusing a pre-acquired cumulative state transition probability matrix and a conditional probability cumulative distribution function of the prediction error; determining a random output scene of the wind power plant in a prediction period according to the prediction error of the predicted output of the wind power plant and the predicted output of the wind power plant; wherein the pre-acquired cumulative state transition probability matrix of the prediction error and the conditional probability cumulative distribution function are acquired according to the prediction error of the historical prediction output of the wind power plant; The prediction error of the wind power plant in the prediction period is determined based on the prediction error of the historical prediction output of the windpower plant, so that the random output scene of the wind power plant in the prediction period is obtained, and the wind power prediction output accuracy of the wind power plant is improved.

Description

technical field [0001] The invention relates to the field of new energy technologies, in particular to a method and device for generating a random output scene of a wind farm. Background technique [0002] Wind power generation has strong randomness and volatility, so there are certain errors in the predicted output of wind farms. In the process of formulating the day-ahead scheduling plan of the power system, it is necessary to fully consider the uncertainty of the prediction error of the predicted output of the wind farm on the basis of the predicted output of the wind farm. [0003] At present, academic short-term optimal scheduling methods considering the uncertainty of forecast errors are mainly stochastic programming methods and robust optimization methods. The stochastic planning method needs to be based on a series of wind power output random scenarios, and an optimal scheduling model is established for each scenario to obtain the optimal scheduling results under th...

AI Technical Summary

Problems solved by technology

[0004] However, the existing technology for obtaining random output scenarios based on historical forecast errors does not take into account the uneven distribution of forecast errors in the state interval, resulting in inaccurate wind power forecast output values ​​in random output scenarios

Images