Estimating time duration of bandwidth availability
US9985906B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 3, 2016 |
| Grant date | May 29, 2018 |
| Priority date | — |
| Expiry date | Nov 26, 2036 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04W84/12
- WIPO fieldDigital communication
- WIPO sectorElectrical engineering
Abstract
In one embodiment, a device in an access network receives network condition data regarding the access network and requested flow characteristic data. The requested flow characteristic data is indicative of one or more flow characteristics requested by one or more subscribers for different periods of time. The device trains a machine learning-based classifier using the network condition data and the request flow characteristic data and receives a particular flow characteristic request from a particular subscriber node. The particular request indicates one or more requested flow characteristics for a specified time period. The device determines a probability of the access network being able to accommodate the particular flow characteristic request by classifying the particular flow characteristic request using the trained classifier. The device sends a flow characteristic response to the node of the particular subscriber node based on the determined probability.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.