Wind Power Probabilistic Prediction Method and Device

Abstract

The present invention relates to a method and device for probabilistic forecasting of wind power power. The method includes: obtaining statistical characteristics of wind farm forecast errors according to historical output power and historical forecast power; wind speed fluctuations based on historical forecast power and NWP forecast results of wind farms To obtain the complete set of conditions for wind power probability prediction; through the K-means clustering algorithm, divide the complete set of conditions into several conditional subsets; form a conditional empirical distribution for the error set under each conditional subset, and test its digital characteristics Whether it coincides with the numerical features in the statistical characteristics of the wind farm prediction error; if it coincides, perform clustering again through the K-means clustering algorithm; and obtain the wind power probability prediction result according to the wind power prediction results and conditional empirical distribution at each moment. The invention also relates to a prediction device. The wind power probability prediction method provided by the invention can provide error distribution functions differently and has higher prediction accuracy.

Description

technical field [0001] The invention relates to a wind power probability prediction method, in particular to a wind power probability prediction method and device. Background technique [0002] The randomness, volatility, and uncertainty of wind resources and the uncontrollability of wind power output have brought great troubles to the safe and stable operation of the power system. Wind power forecasting technology has become an essential technology. [0003] However, in actual operation, prediction errors in wind power prediction results cannot be avoided. Traditional wind power prediction generally uses point prediction of wind power, which cannot provide information on wind power uncertainty. Unpredictable prediction errors exist in traditional wind power forecasting, resulting in inaccurate forecasting, which affects the safety and stability analysis of the power system, thereby affecting the effectiveness of operational decision-making results. Contents of the invent...

AI Technical Summary

Problems solved by technology

[0003] However, in actual operation, prediction errors in wind power prediction results cannot be avoided. Traditional wind power prediction generally uses point prediction of wind power, which cannot provide information on wind power uncertainty.

Unpredictable prediction errors exist in traditional wind power forecasting, resulting in inaccurate forecasting, which affects the safety and stability analysis of the power system, thus affecting the effectiveness of operational decision-making results

Images