A Probability Prediction Method of Wind Power Output Based on Big Data Sample Collection

Abstract

The present invention is a method for predicting the probability of wind power output based on sample collection based on big data, which belongs to the application field of new energy technologies, and particularly relates to a method for predicting the probability of wind power output; the present invention proposes a method for predicting the probability of wind power output based on big data sample collection The prediction method divides the information of big data into different samples according to the probability of occurrence, and realizes a unified wind power output prediction model for all data. According to the different trends and probabilities of the prediction model, the collected information is compared according to different horizontal time periods, and the short-term wind power output forecast under each probability can be given, which improves the wind power consumption capacity of the grid and reduces the possibility of "nest wind power". The security of scheduling is enhanced, and by continuously updating the database, the capacity of the database is increased to strengthen the forecasting ability, and to achieve forecasting with greater range and precision.

Description

technical field [0001] The invention belongs to the application field of new energy technologies, and in particular relates to a method for predicting the probability of wind power output. Background technique [0002] In recent years, the development of renewable energy has been very rapid, especially the scale of wind power and photovoltaic construction has become larger and larger, and the installed capacity has grown exponentially. However, most of the renewable energy, especially the high wind power and solar energy currently utilized is closely related to the atmospheric environment, and its uncertainty and dispersion characteristics pose a greater challenge to the consumption of grid-connected renewable energy. The prediction of renewable energy generation capacity can adjust the grid structure in time to ensure the safe and stable operation of the grid. [0003] At present, the most used forecasting models are regression forecasting models established based on histo...

AI Technical Summary

Problems solved by technology

[0004] The dispersion of new energy determines that the characteristics of wind power output in different regions and in different periods are constantly changing. The establishment of models has limitations, the prediction deviation is large, and it is impossible to track the latest dynamic conditions. Give reasonable information about the possible situation, resulting in the reduction of grid balancing ability

Images