Informer model-based power transmission line icing prediction method
A technology of transmission lines and prediction methods, applied in prediction, neural learning methods, biological neural network models, etc., can solve the problems of long prediction sequence length, poor adaptability, and weak robustness, and achieve small prediction errors, The effect of speeding up the prediction speed and improving the prediction accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0054] The present invention realizes its object of the invention, and the technical solution adopted is, a kind of transmission line icing prediction method based on Informer attention learning, and its steps are as follows:
[0055] (1) Data preprocessing
[0056] Process historical icing data, terminal pull data, weather station forecast data, weather station monitoring data, terminal information and other data, perform outlier processing and fill in missing values, and construct a multivariate sequence data set related to pull: This data set takes the pulling force value as the prediction object, and takes date, temperature, humidity, temperature, pulling force value and other icing influencing factors as the characteristic input. Let the length of the input history sequence be L x , the forward prediction length is p, the number of icing-related influencing variables is i, and the predicted pull value is f t , the preprocessed dataset dataset is expressed as follows: ...
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