Observation assisted bandwidth management

• US 10,314,091 B2
• Filed: 03/14/2013
• Issued: 06/04/2019
• Est. Priority Date: 03/14/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Rodbro, Christoffer Asgaard, Chen, Mingyu, Dumitras, Adriana, Rosenberg, Jonathan David
• Primary Examiner(s): Elnoubi, Said M
• Application Number:
  US13/828,721
• Publication Number:
  US 20140273990A1
• Time in Patent Office: 2,273 Days
• Field of Search: 4554522, 455405
• CPC Class Codes: H04W 28/20 Negotiating bandwidth
• CPC Class Codes: H04W 76/14 Direct-mode setup

Abstract

Observation assisted bandwidth management techniques are described. In one or more implementations, a request is received at a terminal to initiate a call with another terminal. Responsive to the request, a communication is formed to be communicated to a service provider for bandwidth parameters, the request including network parameters associated with the terminal. The bandwidth parameters, received form the service provider, are used as part of a model to estimate an amount of bandwidth that is available for the call. The call with the other terminal is initiated, the call configured to at least initially consume the estimated amount of bandwidth.

Claims

1. A system comprising:

at least one processor; and

at least one storage device, providing instructions from one or more modules, wherein the modules, when executed with the at least one processor, cause the at least one processor to perform operations comprising;

collecting data from a plurality of terminals, the data describing wireless network access conditions experienced by respective said terminals;

assigning historical bandwidth parameters that are based on the collected data from the plurality of terminals to one or more of a plurality of clusters of bandwidth parameters, the assigning based on historical network parameters associated with the data that are collected from the respective said terminals,

wherein respective sets of bandwidth parameters are assigned to respective clusters based on a clustering of the historical network parameters that are derived from variable bandwidth observations made in multiple wireless network accesses from one or more terminals of the plurality of terminals, and wherein the respective clusters group the historical network parameters based on observed characteristics of the multiple wireless network accesses;

receiving a request for wireless network access by a requesting terminal, the request containing one or more current network parameters associated with the requesting terminal at a time of the request;

determining a plurality of the clusters of bandwidth parameters applicable to the requesting terminal at the time of the request based upon;

identifying the current network parameters contained within the request being similar to historical network parameters of the determined clusters, based on comparing the observed characteristics associated with a respective cluster to observed characteristics of the wireless network access by the requesting terminal, and

obtaining respective bandwidth parameters associated with the determined clusters; and

distributing the respective bandwidth parameters to the requesting terminal, the distributed bandwidth parameters usable by the requesting terminal to predict an amount of bandwidth that is available for a subsequent network communication between the requesting terminal and another terminal via the wireless network access.

2. The system of claim 1, wherein the wireless network access is used to perform a call, and wherein the call is configured to be performed peer-to-peer between the requesting terminal that formed the request and the another terminal.

3. The system of claim 1, wherein the predicted amount of bandwidth is formed using the distributed bandwidth parameters as part of a model by the requesting terminal.

4. The system of claim 3, wherein the model employs one or more quality-of-service measures.

5. The system of claim 1, further comprising adjusting at least one of the distributed bandwidth parameters based on observations made during the wireless network access and using the adjusted distributed bandwidth parameters to predict an adjusted amount of bandwidth that is available for the wireless network access.

6. The system of claim 1, wherein the wireless network access is used to perform a call, and wherein the current network parameters describe devices and other infrastructure that is to be involved during the call.

7. The system of claim 1, wherein the observed characteristics associated with a respective cluster that are compared to the observed characteristics of the requesting terminal include one or more of:

a network provider, a signal strength, a network communication device, a wireless access point, a geographical location, a network access type, a network protocol, a time of day, a day of week, a subscription information, or a roaming information.

8. The system of claim 3, wherein the model is a statistical model or employs machine learning.

9. A method comprising:

collecting data from a plurality of terminals, the data describing wireless network access conditions experienced by respective said terminals;

assigning historical bandwidth parameters that are based on the collected data from the plurality of terminals to one or more of a plurality of clusters of bandwidth parameters, the assigning based on historical network parameters associated with the data that are collected from the respective said terminals,

wherein respective sets of bandwidth parameters are assigned to respective clusters based on a clustering of the historical network parameters that are derived from variable bandwidth observations made in multiple wireless network accesses from one or more terminals of the plurality of terminals, and wherein the respective clusters group the historical network parameters based on observed characteristics of the multiple wireless network accesses;

receiving a request for wireless network access by a requesting terminal, the request containing one or more current network parameters associated with the requesting terminal at a time of the request;

determining a plurality of the clusters of bandwidth parameters applicable to the requesting terminal at the time of the request based upon;

identifying the current network parameters contained within the request being similar to historical network parameters of the determined clusters, based on comparing the observed characteristics associated with a respective cluster to observed characteristics of the wireless network access by the requesting terminal, and

obtaining respective bandwidth parameters associated with the determined clusters; and

distributing the respective bandwidth parameters to the requesting terminal, the distributed bandwidth parameters usable by the requesting terminal to predict an amount of bandwidth that is available for a subsequent network communication between the requesting terminal and another terminal via the wireless network access.

10. The method of claim 9, wherein the wireless network access is used to perform a call, and wherein the call is configured to be performed peer-to-peer between the requesting terminal that formed the request and the another terminal.

11. The method of claim 10, wherein the current network parameters describe devices and other infrastructure that is to be involved in the call.

12. The method of claim 11, wherein the observed characteristics associated with a respective cluster that are compared to the observed characteristics of the requesting terminal include one or more of:

network provider, signal strength, network communication device, wireless access point, geographical location, network access type, network protocol, time of day, day of week, subscription information, or roaming information.

13. The method of claim 9, wherein the predicted amount of bandwidth is formed using the distributed bandwidth parameters as part of a model by the requesting terminal.

14. The method of claim 13, wherein the model employs one or more quality-of-service measures.

15. One or more computer-readable hardware storage media having instructions stored thereon that, responsive to execution by a computing device, causes the computing device to perform operations comprising:

collecting data from a plurality of terminals, the data describing wireless network access conditions experienced by respective said terminals;

assigning historical bandwidth parameters that are based on the collected data from the plurality of terminals to one or more of a plurality of clusters of bandwidth parameters, the assigning based on historical network parameters associated with the data that are collected from the respective said terminals,

wherein respective sets of bandwidth parameters are assigned to respective clusters based on a clustering of the historical network parameters that are derived from variable bandwidth observations made in multiple wireless network accesses from one or more terminals of the plurality of terminals, and wherein the respective clusters group the historical network parameters based on observed characteristics of the multiple wireless network accesses;

receiving a request for wireless network access by a requesting terminal, the request containing one or more current network parameters associated with the requesting terminal at a time of the request;

determining a plurality of the clusters of bandwidth parameters applicable to the requesting terminal at the time of the request based upon;

identifying the current network parameters contained within the request being similar to historical network parameters of the determined clusters, based on comparing the observed characteristics associated with a respective cluster to observed characteristics of the wireless network access by the requesting terminal, and

obtaining respective bandwidth parameters associated with the determined clusters; and

distributing the respective bandwidth parameters to the requesting terminal, the distributed bandwidth parameters usable by the requesting terminal to predict an amount of bandwidth that is available for a subsequent network communication between the requesting terminal and another terminal via the wireless network access.

16. The computer-readable hardware storage media of claim 15, wherein the wireless network access is used to perform a call, and wherein the call is configured to be performed peer-to-peer between the requesting terminal that formed the request and the another terminal.

17. The computer-readable hardware storage media of claim 16, wherein the current network parameters describe devices and other infrastructure that is to be involved in the call.

18. The computer-readable hardware storage media of claim 17, wherein the observed characteristics associated with a respective cluster that are compared to the observed characteristics of the requesting terminal include one or more of:

network provider, signal strength, network communication device, wireless access point, geographical location, network access type, network protocol, time of day, day of week, subscription information, or roaming information.

19. The computer-readable hardware storage media of claim 15, wherein the predicted amount of bandwidth is formed using the distributed bandwidth parameters as part of a model by the requesting terminal.

20. The computer-readable hardware storage media of claim 19, wherein the model employs one or more quality-of-service measures.