PREDICTIVE NETWORK SYSTEM AND METHOD

• US 20140113600A1
• Filed: 09/28/2011
• Published: 04/24/2014
• 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 University
• Inventors: El Gamal, Hesham, Eryilmaz, Atilla, Caire, Giuseppe, Sha, Fei, McLaughlin, Margaret
• Granted Patent: US 9,680,766 B2
• Time in Patent Office: Days
• US Class Current: 455/414.3
• 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 for delivering data resources in a network comprising:

(a) collecting from a plurality of user devices requests for data resources from said network;

(b) generating a list of anticipated requests for data resources by analyzing said requests from said plurality of user devices;

(c) for a plurality of anticipated requests in said list;

(1) downloading to a site accessible to said user devices data resources responsive to said anticipated requests;

(2) storing at said site said data resources responsive to said anticipated requests; and

(d) in response to at least one actual user request for a data resource, transferring from said site to said user'"'"'s device said data resource responsive to said actual user request.

2. The computerized method of claim 1 wherein said list of anticipated requests comprises for each request an expiration time for downloading to said site a data resource responsive to said anticipated request.

3. The computerized method of claim 1 wherein generating a list of anticipated requests for data resources by analyzing said requests from said plurality of user devices comprises clustering actual requests according to user interests.

4. The computerized method of claim 1 wherein generating a list of anticipated requests for data resources by analyzing said requests from said plurality of user devices comprises clustering data resources based on similarity in topics.

5. The computerized method of claim 1 wherein data resources are selected from the group consisting of:

dynamic data resources and static data resources.

6. The computerized method of claim 1 wherein said user devices are mobile devices.