Short-term wind speed combined forecasting method for wind turbine cabin of wind power plant
A technology for wind turbines and wind farms, applied in instruments, biological neural network models, data processing applications, etc., and can solve problems such as errors and large forecasts
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
example 1
[0068] For the collected wind speed data of #7 wind turbine, the starting point of simulation forecast N={620, 626, 632, 638, 644, 650, 656, 662, 668, 674, 680} and the forecast step size L f = 1, construct two simulation experiment sets to determine the optimal parameters of the two sub-models, the construction method of the simulation experiment set is: the sub-model established by the DTW method or the PCC method, for the length L of the wind speed sequence for similarity comparison, the The wind speed formed by the first I wind speed sequences most similar to {v(#7,N-L+1),v(#7,N-L+2),...,v(#7,N)} sequence set Q P , the output of the training set P is {v(#7,N-L+1),v(#7,N-L+2),...,v(#7,N)}; the test set T and the training set P The same; by using the simulation error of {v(#7,N-L+1),v(#7,N-L+2),…,v(#7,N)} as the standard, let I∈[ 2,6], L∈[4,36], S∈[0.1,0.5], L, I, and S are optimized using the particle swarm optimization algorithm, the maximum number of iterations is 30, a...
example 2
[0074]In order to verify the universality of this application, a total of 31 wind turbines from #7 to #37 are used to simulate the 11 starting points of the forecast in Experiment 1, and when the forecast step size is 1 to 6, the method provided by this patent includes two sub-models The combined model is compared with BP neural network extrapolation method, GRNN neural network extrapolation method and ARIMA time series method, and the results are listed in Table 3. It can be seen from Table 3 that the forecast accuracy of COM-PSO-GRNN is the highest regardless of the error standard of MSE or MAE, and the accuracy of the three extrapolation methods from high to low is GRNN neural network extrapolation method and BP neural network Extrapolation and ARIMA time series methods, stating:
[0075] 1) Short-term wind speed forecast based on similarity principle is feasible, and its effect is better than that based on extrapolation;
[0076] 2) The DTW-PSO-GRNN sub-model is superior ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com