Quantile regression-based wind power fluctuation interval analysis method

Abstract

The invention discloses a quantile regression-based wind power fluctuation interval analysis method. The method comprises the steps of obtaining output power data of a wind power plant firstly; determining the quantiles of the output power data of the wind power plant; establishing a regression function and a regression model for each quantile by adopting a support vector machine; next, solving the regression model of each quantile by adopting a prime-dual interior point method, and calculating the quantile in the next moment; S6: obtaining the actually measured value of the wind power data atthe next moment; and finally, returning to the repeated cycle to obtain the output power data fluctuation interval of the wind power plant. The quantile regression-based wind power fluctuation interval analysis method provided by the invention can realize the adaptive selection of the regression functions through the support vector machine without making any assumed conditions on the random disturbance terms, so as to determine the quantile regression models; next, the models are solved by the prime-dual interior point method with infeasible initial points, so that wind power fluctuation interval analysis for the further moments is realized; and by virtue of the method, the complete wind power fluctuation interval analysis result can be obtained, and the newest change condition also can be reflected in real time.

Description

technical field [0001] The invention relates to the technical field of new energy power generation, in particular to a method for analyzing intervals of wind power fluctuations based on quantile point regression. Background technique [0002] At present, most of the research on wind power forecasting focuses on the forecasting of wind power expectation. However, due to the strong dispersion of wind power random law, taking this as the forecast result will inevitably make the scheduling decision-making results unrealistic or even unfeasible. For this reason, it is necessary to increase the analysis of the possible fluctuation range and corresponding probability of wind power power in the forecasting process (hereinafter collectively referred to as fluctuation range analysis). Because the fluctuation interval analysis can give the probability distribution of wind power fluctuations in the future, it is helpful for decision makers to better understand the uncertainties and risk...

AI Technical Summary

Problems solved by technology

Because the fluctuation interval analysis can give the probability distribution of wind power fluctuations in the future, it is helpful for decision makers to better understand the uncertainties and risks that may exist in future changes, and to make more reasonable decisions, such as hypothetical predictions The errors obey the multivariate Gaussian distribution and the Beta distribution respectively, and the estimation of the distribution parameters is implemented to obtain the probability distribution function of the prediction error, which has positive significance for scheduling decisions, but it is difficult to find a distribution function consistent with the assumption in practice

Images