Method for power load condition density prediction
A technology of power load and conditional density, applied in forecasting, instrumentation, data processing applications, etc., can solve problems such as undiscovered
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0046]The method for predicting the density of electric load conditions provided by the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0047] The power load condition density prediction method provided by the present invention includes the following steps performed in order:
[0048] Step 1) model establishment: based on the neural network structure and the quantile regression model, establish the quantile regression model of the electric load neural network;
[0049] Step 2) Model solution: In the above-mentioned electric load neural network quantile regression model, since the asymmetric "check function" function (check function) is used as the loss function, it will be non-differentiable at point 0, which brings great difficulties to the model solution. come difficult; the present invention uses the Huber norm to correct the asymmetric "tick" function in the electric load neural network quantile ...
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