Short-term wind speed and wind power prediction method
A wind speed prediction and wind speed technology, applied in fluid velocity measurement, velocity/acceleration/impact measurement, power measurement, etc., can solve problems such as programming, no visual interface, complex physical model, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0047] The wind speed prediction method of optimizing the GM(1,1) model is as follows:
[0048] Step 1: Use the actual wind speed measured by the wind tower or anemometer as the actual input value of the prediction model.
[0049] Step 2: Optimizing the traditional gray forecasting model by using the numerical approximation principle.
[0050] 1. Wind speed prediction model optimization scheme
[0051] The improvement of wind speed prediction model is mainly to provide high-precision wind speed prediction input value for wind power prediction. Only when the accuracy of wind speed prediction value is improved, wind power prediction can be accurate. For this reason, the present invention first uses the principle of numerical approximation to improve the existing gray GM (1, 1) prediction model. Specific steps are as follows:
[0052] 1.1 Basic principles of traditional gray GM (1, 1) model for predicting wind speed
[0053] Using the traditional GM(1,1) model before optimiza...
Embodiment 2
[0104] Example 2 Time Series Dynamic Neural Network Forecasting Wind Power
[0105] Due to the short-term correlation of wind speed, it is not necessary to establish a specific mathematical model of the time series when using the dynamic neural network to predict the time series. Compared with other neural network prediction models, the dynamic neural network has better prediction accuracy for the one-dimensional time series prediction, which provides a realistic basis for the selection of time series dynamic neural network for wind power prediction.
[0106] 2.1 Wind Power Prediction Method
[0107] Taking the above predicted wind speed as input and fan power as output, a single-input and single-output network is constructed, and the transfer function adopts the hyperbolic tangent function:
[0108]
[0109]
[0110] In formula (14), x is the neuron input, to transfer the function value.
[0111] The error correction adopts the "instantaneous backpropagation algorit...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap