History segmented sequence search and time sequence rarefaction-based wind power forecast method

Abstract

The invention discloses a history segmented sequence search and time sequence rarefaction-based wind power forecast method. The method comprises the following steps of: normalizing wind power historydata and determining window width optimum values of searched segmented time sequences according to power time sequence fluctuation features and basic statistical characteristics; calculating matchingdegrees between all the history segmented time sequence and a segmented time sequence at the current moment by taking the newest segmented time sequence at the current moment as a standard and synthesizing a correlation index and a similarity distance index; sorting the matching degrees according to a big-to-small sequence, and determining a number of optimum history segmented sequences accordingto an average matching degree aggregation principle; aiming the current segmented time sequence at each moment, determining a number of corresponding optimum history segmented sequences and a number of corresponding optimum average history segmented sequences; aiming at all the moments for training the time sequences, establishing a time sequence rarefaction-based power forecast model; and solvingthe model by adoption of a multiplier alternating direction method to obtain parameters of the model, wherein the parameters are used for future power forecast.

Description

technical field [0001] The invention relates to the field of power system operation and control, in particular to a wind power prediction method based on historical segmented sequence search and time series thinning. Background technique [0002] With the depletion of non-renewable resources such as coal and oil and the increasingly serious energy dilemma, renewable energy such as wind energy, solar energy, tidal energy and biomass energy has attracted more and more attention worldwide. Wind power is the renewable energy with the most mature technology and the most development value in the renewable energy generation technology. The development of wind power is of great significance to ensure energy security, adjust energy structure, reduce environmental pollution, and achieve sustainable development. [0003] The intermittent nature of wind energy in nature determines that wind power has strong fluctuations. As the number and installed capacity of wind farms continue to in...

AI Technical Summary

Problems solved by technology

[0005] Generally speaking, the existing ultra-short-term wind power forecasting models based on time-series characteristics have two deficiencies: first, such models usually assume that the future output values ​​of time series are only related to recent historical data, while It has nothing to do with older data, so only a small amount of recent historical data is used as the input value of the model to predict future values, but this actually limits the information sources used for prediction, because the wind power time series has a certain periodicity and even Seasonality, therefore, the future output value of a time series will also be affected by older data; second, even if the traditional model only uses a small amount of recent historical data as the input value of the forecasting model, in these limited historical data There will also be some data, which have no correlation with future output values, that is to say, they are introduced into the prediction model as redundant or even interference information, which is not conducive to the improvement of wind power prediction accuracy

Images