Photovoltaic power supply power prediction method based on positive and negative error variable weights
A technology of photovoltaic power generation and prediction method, which is applied in prediction, data processing application, calculation and other directions, and can solve the problems of poor prediction effect and inability to meet the requirements of prediction accuracy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0090] Taking the actual data of a photovoltaic field in Gansu on October 15th as an example, the test data is predicted by using the selected optimal parameters. The gray prediction power changes with time, and the results can be seen as figure 2 shown. The overall prediction trend is very close to the actual power generation, but the accuracy needs to be improved when the power generation is zero.
[0091] Also use the historical data of a photovoltaic power station in Northwest China, and perform 2500 iterations by selecting different numbers of neurons. Depend on image 3 It can be seen that the error when the number of neurons is different, it can be seen that the prediction error of 16 neurons is the smallest, and the interference in the recursive network only exists in the expected output, the prediction accuracy of the network is higher than the interference variance, and the error is negligible. And with the increase of the network training rate, it has an inhibit...
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