PREDICTIVE NETWORK SYSTEM AND METHOD

• US 20170279739A1
• Filed: 06/09/2017
• Published: 09/28/2017
• Est. Priority Date: 09/28/2010
• Status: Active Grant

• Current Assignee: Ohio State Innovation Foundation (Ohio State University), University of Southern California
• Original Assignee: Ohio State Innovation Foundation (Ohio State University), University of Southern California
• Inventors: Gamal, Hesham El, Eryilmaz, Atilla, Caire, Giuseppe, Sha, Fei, McLaughlin, Margaret
• Granted Patent: US 10,187,327 B2
• Time in Patent Office: Days
• CPC Class Codes: H04L 47/823 Prediction of resource usage
• CPC Class Codes: H04L 47/83 based on usage prediction
• CPC Class Codes: H04W 28/02 Traffic management, e.g. flow control or congestion control
• CPC Class Codes: H04W 28/16 Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]

Abstract

A proactive networking system and method is disclosed. The network anticipates the user demands in advance and utilizes this predictive ability to reduce the peak to average ratio of the wireless traffic and yield significant savings in the required resources to guarantee certain Quality of Service (QoS) metrics. The system and method focuses on the existing cellular architecture and involves the design and analysis of learning algorithms, predictive resource allocation strategies, and incentive techniques to maximize the efficiency of proactive cellular networks. The system and method further involve proactive peer-to-peer (P2P) overlaying, which leverages the spatial and social structure of the network. Machine learning techniques are applied to find the optimal tradeoff between predictions that result in content being retrieved that the user ultimately never requests, and requests that are not anticipated in a timely manner.

Claims

1. A computerized method performed by a network server comprising;

collecting from a mobile device a plurality of network content requests;

comparing the plurality of requests against a statistical model to predict future network content requests from the mobile device, the statistical model based at least in part on network content requests from a plurality of mobile devices;

generating, from the comparison, a list of anticipated network content requests from the mobile device; and

serving, to the mobile device, network content responsive to one or more of the anticipated network content requests, wherein the network content is configured to be stored in a local memory at the mobile device, thereby being available for display on the mobile device upon a user'"'"'s request.

2. The computerized method of claim 1, wherein the list of anticipated requests comprises a deadline for each anticipated request and wherein the request is served before the deadline.

3. The computerized method of claim 2, wherein the deadline is a time.

4. The computerized method of claim 1, further comprising the step of detecting a wireless network.

5. The computerized method of claim 4, wherein the network content responsive to one or more of the anticipated network content requests are served via the detected wireless network.

6. The computerized method of claim 5, wherein the detected network is a wireless local area network.

7. The computerized method of claim 4, wherein detecting the network comprises receiving a location of the mobile user device.

8. The computerized method of claim 7, wherein the location comprises a GPS coordinate.

9. The computerized method of claim 7, wherein the location indicates that the mobile user device is within range of a wireless network.

10. A computerized method comprising:

collecting from a mobile device a plurality of network content requests initiated by the mobile device;

analyzing the plurality of requests with a statistical model to predict anticipated network content requests from the mobile device, the statistical model based, at least in part, on network content requests from the mobile device;

generating a first predicted anticipated network content request from the mobile device; and

serving, to the mobile device, network content responsive to one or more of the anticipated network content requests, wherein the network content is configured to be stored in a local memory at the mobile device, thereby being available for display on the mobile device upon a user'"'"'s request.

11. The computerized method of claim 10, wherein the statistical model is further based, at least in part, on network content requests from a plurality of mobile devices.

12. The computerized method of claim 10, wherein the first predicted anticipated network content request is one of a plurality of generated predicted anticipated network content requests in a list.

13. The computerized method of claim 10, wherein the statistical model comprises daily network content requests from the mobile device.

14. The computerized method of claim 10, wherein analyzing the plurality of requests comprises clustering content from the plurality of mobile devices based on similarity in topics.

15. A computerized method performed by a network server comprising;

collecting from a mobile user device a plurality of requests from a user for content from a network, the plurality of requests initiated by the mobile user device;

analyzing the plurality of requests for content from the mobile user device against a statistical model to predict anticipated requests from the user mobile device, the statistical model utilizing dynamic data requests for content from the network obtained from a plurality of mobile devices;

generating a list of anticipated requests for content from the individual user;

serving a request, before an actual request for content, to the mobile user device content data responsive to each anticipated request in the list, the content data configured to be stored in a memory in the mobile user device; and

receiving at least one actual request for content from the individual user initiated at the mobile user device, wherein in response to the at least one actual request for content from the individual user, the content data from the memory is presented on the mobile device.

16. The computerized method of claim 15, wherein serving comprises establishing a timeslot for serving network content.

17. The computerized method of claim 15, wherein the timeslot is before a deadline.

18. The computerized method of claim 15, wherein generating a list of anticipated requests comprises clustering content based on similarity in topics.

19. The computerized method of claim 15, further comprising providing an incentive to the mobile user device, the incentive responsive to the at least one actual request.

20. A system comprising:

a memory, wherein the memory stores;

a plurality of requests from a user for content from a network, the plurality of requests initiated by a mobile user device; and

a processor, wherein the processor is configured to;

analyze the plurality of requests for content from the mobile user device against a statistical model to predict anticipated requests from the user mobile device, the statistical model utilizing dynamic data requests for content from the network obtained from a plurality of mobile devices;

generate a list of anticipated requests for content from the individual user;

serve a request, before an actual request for content, to the mobile user device content data responsive to each anticipated request in the list, the content data configured to be stored in a memory in the mobile user device; and

receive at least one actual request for content from the individual user initiated at the mobile user device, wherein in response to the at least one actual request for content from the individual user, the content data from the memory is presented on the mobile device.