Method for predicting mobile traffic based on LS-SVM
A prediction method and traffic volume technology, applied in electrical components, wireless communication, network planning, etc., can solve problems such as unreasonable selection of input variables, poor accuracy, and slow speed of the algorithm, so as to improve generalization ability and calculation efficiency , reduce the dimensionality, simplify the effect of complexity
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach 1
[0070] Specific implementation mode one: the following combination Figure 1 to Figure 3 Describe this embodiment, the method of this embodiment includes the following steps:
[0071] Step 1, select the traffic volume historical data within one month before the current moment, and use the traffic volume historical data as a training sample to carry out LS-SVM modeling to obtain the LS-SVM prediction model;
[0072] Step 2. Preprocessing the new input sample, which is a combination of traffic data at multiple times before the current time, and reconstructing the phase space of the new input sample according to the set embedding dimension and delay time, Construct a new input sample reconstruction vector and perform normalization processing so that all data are between [-1, 1];
[0073] Step 3. Input the normalized new input sample reconstruction vector to the LS-SVM prediction model obtained in step 1, output the predicted value, and store it;
[0074] Step 4. Determine wheth...
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