2 results about "Overlap coefficient" patented technology

The application discloses a wind power prediction method and system based on frequency domain adaptive super parameter optimization, which comprises the following steps: firstly, collecting historical wind power and meteorological data; secondly, proposing a brand-new frequency domain coverage overlap coefficient as a fitness function, combining the grey wolf optimization algorithm to adaptively optimize the super parameter of the variational mode decomposition, and using the optimized parameter to decompose the power sequence; thirdly, calculating the sample entropy of each component and reconstructing it into three categories of randomness, fluctuation and trend according to the entropy value to reduce the complexity; then, screening the strongly correlated meteorological features for each component based on the Pearson correlation coefficient, and inputting them into a prediction model for prediction; finally, superimposing the predicted values of each component to obtain the final power prediction result. The application solves the problem of artificial setting of the VMD super parameter, realizes the balance between the decomposition quality and the prediction efficiency, and significantly improves the accuracy and practicability of the ultra-short-term wind power prediction.

The invention discloses a wind power prediction method and system based on frequency domain adaptive hyper-parameter optimization. The method comprises the following steps: firstly, collecting historical wind power and meteorological data; secondly, providing a brand new frequency domain coverage overlapping coefficient as a fitness function, adaptively optimizing hyper-parameters of variational mode decomposition in combination with a grey wolf optimization algorithm, and decomposing a power sequence by using the optimized parameters; thirdly, calculating the sample entropy of each component, and reconstructing the sample entropy into a random type, a fluctuation type and a trend type according to entropy values so as to reduce the complexity; then, screening strongly correlated meteorological characteristics for each type of components based on a Pearson's correlation coefficient, and respectively inputting the meteorological characteristics into a prediction model for prediction; and finally, superposing the predicted values of the components to obtain a final power prediction result. According to the method, the problem of manual setting of VMD hyper-parameters is solved, the balance between decomposition quality and prediction efficiency is realized, and the precision and practicability of ultra-short-term wind power prediction are remarkably improved.