Method and system for predicting wind speed
A technology for predicting wind speed and wind speed prediction, which is applied in the field of wind speed prediction, and can solve problems such as least squares support vector machine performance dependence, failure to find the optimal value, over-smoothing, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0075] Embodiment 1: as figure 1 As shown, a method of predicting wind speed includes:
[0076] Step 11: Obtain the original sequence of wind speed data;
[0077] Step 12: Use the particle swarm optimization algorithm to determine the optimal preset scale parameters and optimal bandwidth parameters of the variational mode decomposition method, and decompose the original sequence into several modal function subunits according to the optimal preset scale parameters and optimal bandwidth parameters sequence;
[0078] Step 13: Using the improved differential evolution algorithm to determine the kernel parameters of the least squares support vector machine model of each modal function subsequence, the variation factor of the mutation operation in the improved differential evolution algorithm decreases with the increase of the evolution algebra, and the variation The mutated individual generated by the operation is related to the optimal individual of the previous generation, and ...
Embodiment 2
[0103] like image 3 As shown, a system for predicting wind speed includes:
[0104] Data acquisition module 21, used to acquire the original sequence of wind speed data;
[0105] The subsequence determination module 22 is used to determine the optimal preset scale parameter and the optimal bandwidth parameter of the variational mode decomposition method by using the particle swarm optimization algorithm, and according to the optimal preset scale parameter and the optimal bandwidth parameter, the The original sequence is decomposed into several modal function subsequences;
[0106] Kernel parameter determination module 23, is used for adopting improved differential evolution algorithm to determine the kernel parameter of the least squares support vector machine model of each modal function subsequence, the variation factor of mutation operation in the improved differential evolution algorithm increases with the increase of evolution algebra and the mutated individual generat...
Embodiment 3
[0129] Embodiment 3: as Figure 5 As shown, methods for predicting wind speed include:
[0130] Step 31: Obtain the short-term wind speed data of the wind farm as the original sequence of wind speed data:
[0131] The original sequence of the actual wind speed is 31 days of hourly average wind speed data, a total of 744 data, a total of 720 sample points of the data in the first 30 days were selected as the training set, the signal was decomposed and the sub-model was established; the data of the 31st day was selected in total 24 The sample points are used as the prediction set to test the prediction accuracy of the model.
[0132] Step 32: Use the particle swarm optimization algorithm to determine the optimal preset scale parameters and optimal bandwidth parameters of the variational mode decomposition method, and decompose the original sequence into modal function subunits according to the optimal preset scale parameters and optimal bandwidth parameters sequence:
[0133]...
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