A regional wind power forecasting method and system based on spatio-temporal quantile regression

Abstract

The disclosure provides a regional wind power prediction method and system based on spatiotemporal quantile regression, which collects the operation and numerical weather forecast data of multiple wind farms within a preset time period, converts the collected data into feature maps, and establishes training set, verification set and test set; establish a spatio-temporal quantile regression model, use the training set training set, verification set and test set to train and optimize the model; collect the operating data and environmental data of each wind farm in real time, according to the optimized The spatio-temporal quantile regression model is used to predict regional wind power generation in a certain period of time in the future; this disclosure uses the spatio-temporal quantile regression model to perform short-term non-parametric probability prediction of regional wind power, which solves the problem of large input information. The selection of explanatory variables in regional wind power forecasting can greatly improve the accuracy and reliability of forecasting, and provide a specific solution for regional wind power generation probability forecasting with big data.

Description

technical field [0001] The present disclosure relates to the technical field of wind power forecasting, in particular to a regional wind power forecasting method and system based on spatiotemporal quantile regression. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art. [0003] Due to the intermittent and fluctuating characteristics of wind power generation, a high proportion of wind power will pose a serious challenge to the safe and stable operation of the power system. Accurate short-term wind power forecasting can effectively alleviate the adverse effects of wind power. Previous studies have mainly focused on point forecasting of wind power generation. However, forecast errors are inevitable due to the inherent intermittent and fluctuating nature of the wind. Alternatively, probabilistic forecasts can quantify wind uncertainty information such...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the deficiencies of the prior art, the present disclosure provides a regional wind power forecasting method and system based on spatio-temporal quantile regression, which solves the problem of selection of explanatory variables in regional wind power forecasting with large input information , which greatly improves the accuracy and reliability of wind power forecasting, and provides a specific solution for regional wind power generation probability forecasting with the characteristics of big data

Images