Wind power short-term power prediction method based on relative error entropy evaluation method
A relative error and power prediction technology, applied in wind power generation, biological neural network model, single network parallel feed arrangement, etc., can solve problems such as complex solution process, failure to reflect, influence of wind power prediction accuracy, etc., to improve prediction accuracy Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0071] like figure 1 Shown is the system used in the wind power short-term power prediction method based on the relative error entropy method of the present invention, including the Bayesian neural network established through data acquisition and preprocessing, error feedback weighted time series, and unbiased gray power prediction of wind power Verhulst three prediction models and a combination prediction model based on the above three prediction models using the relative error entropy method, and use the combination prediction model to obtain prediction results; the system established by the present invention is mainly used for wind power prediction in the next 8 hours.
[0072] like figure 2 Shown is a kind of wind power short-term power prediction method based on the relative error entropy value method of the present invention, specifically comprises the following steps:
[0073] Step 1, obtain the historical data of wind power weather and wind power output power, and pr...
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