METHOD AND APPARATUS FOR DISTRIBUTING MEDIA CONTENT

• US 20150149653A1
• Filed: 11/25/2013
• Published: 05/28/2015
• Est. Priority Date: 11/25/2013
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Lee, Seungjoon, Applegate, David Lee, Ramakrishnan, Kadangode, Gopalakrishnan, Vijay, Archer, Aaron Francis
• Granted Patent: US 9,407,676 B2
• Time in Patent Office: Days
• US Class Current: 709/231
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• CPC Class Codes: G06F 9/5027 the resource being a machine, e.g. CPUs, Servers, Terminals
• CPC Class Codes: H04L 41/145 involving simulating, designing, planning or modelling of a network
• CPC Class Codes: H04L 45/124 using a combination of metrics
• CPC Class Codes: H04L 65/60 Network streaming of media packets
• CPC Class Codes: H04L 65/612 for unicast
• CPC Class Codes: H04L 65/762 at the source reformatting of additional data in video distribution servers H04N21/2355
• CPC Class Codes: H04L 65/80 Responding to QoS
• CPC Class Codes: H04L 67/1017 based on a round robin mechanism
• CPC Class Codes: H04L 67/1023 based on a hash applied to IP addresses or costs
• CPC Class Codes: H04L 67/1029 using data related to the state of servers by a load balancer
• CPC Class Codes: H04L 67/568 Storing data temporarily at an intermediate stage, e.g. caching

Abstract

A system that incorporates teachings of the present disclosure may include, for example, initializing a boundary estimate for an optimization of a linear programming model describing a network of media servers for servicing requests for media content items from subscriber devices, where the boundary estimate is an estimate of an infeasible solution of the linear programming model, and calculating iteratively, using an exponential potential function, additional boundary estimates for the linear programming model, wherein the calculating resolves to an improved boundary estimate that corresponds to placement of copies of the media content items at the media servers subject to a set of constraints on storage capacity of media servers and on bandwidth for communication links in the network. Other embodiments are disclosed.

Claims

1. A server comprising:

a processor; and

a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising;

receiving a forecast of demand for media content items for streaming from a network of media servers in response to requests from subscriber devices;

receiving a set of constraints on storage capacity of the media servers and a bandwidth for communication links in the network;

initiating a boundary estimate for evaluating a linear programming model of the network of media servers, wherein the boundary estimate is an estimate of an infeasible solution of the linear programming model;

initializing a scaling factor for a variable of the linear programming model;

calculating iteratively, using an exponential potential function, a series of additional boundary estimates for the linear programming model, wherein the scaling factor is adjusted by discrete steps for each iteration of the calculating and wherein the calculating resolves to an improved boundary estimate that corresponds to placement of copies of the media content items at the media servers and to routing of requests for the media content items from local media servers to non-local media servers so as to reduce total data traffic over the communication links in the network according to the constraints; and

provisioning the placement of the copies and the routing of the requests according to the improved boundary estimate.

2. The server of claim 1, wherein the exponential potential function allows fractions of the media content items be calculated, and wherein the processor further performs operations comprising re-calculating, via the exponential potential function, the improved boundary estimate to round the fractions of the media content items into integer numbers of the media content.

3. The server of claim 2, wherein the additional boundary estimates do not comprise a binary search for the improved boundary estimate.

4. The server of claim 1, wherein the boundary estimates are associated with a lower boundary for the linear programming model.

5. The server of claim 1, wherein a particular media content item is streamed from a local media server if the particular media content item is stored at the local media server and is streamed from a non-local media server if the particular media content item is not stored at the local media server.

6. The server of claim 1, wherein the calculating further comprises:

determining via a first portion of the calculating a first plurality of variables associated with the linear programming model according to parallel computation of a plurality of functional blocks;

substituting the first plurality of variables that are determined via the parallel computation into the linear programming model; and

determining via a second portion of the calculating a second plurality of variables associated with the linear programming model according to sequential programming of the plurality of functional blocks according to the substituting.

7. The server of claim 1, wherein the calculating further comprises smoothing ordinary duals of the exponential potential function.

8. The server of claim 1, wherein the calculating further comprises:

capturing a priority sampling of a first portion of the calculating to estimate a predicted boundary estimate for a first iteration of the exponential potential function;

identifying the predicted boundary estimate as outside of a useful range; and

aborting the first iteration according to the identifying.

9. The server of claim 1, wherein the media content items comprise video on demand content items.

10. The server of claim 1, wherein the calculating further comprises shuffling functional blocks in the linear programming model between iterations of the calculating.

11. The server of claim 1, wherein the improved boundary estimated is calculated to within a fixed percentage of one of feasibility, optimality, or a combination thereof.

12. A method, comprising:

receiving, by a system comprising a processor, a forecast of demand for media content items;

receiving, by the system, a set of constraints on storage capacity of media servers and bandwidth for communication links in a network of media servers;

initializing, by the system, a boundary estimate for an optimization of a linear programming model describing the network of media servers for servicing requests for the media content items from subscriber devices by streaming the media content items to the subscriber devices over the network, wherein the boundary estimate is an estimate of an infeasible solution of the linear programming model;

calculating iteratively, by the system and via an exponential potential function, additional boundary estimates for the linear programming model to generate an improved boundary estimate; and

provisioning, by the system, a placement of copies of the media content items according to the improved boundary estimate.

13. The method of claim 12, further comprising initializing, by the system, a scaling factor for a variable of the linear programming model, wherein the calculating further comprises adjusting the scaling factor, by discrete steps, for each iteration of the calculating.

14. The method of claim 13, wherein the scaling factor is continuously adjusted downward.

15. The method of claim 12, wherein the exponential potential function allows fractions of the media content items be calculated, and wherein the processor further performs operations comprising re-calculating, by the system and via the exponential potential function, the improved boundary estimate to round the fractions of the media content items into integer numbers of the media content items.

16. The method of claim 12, wherein the media content items comprise video on demand items.

17. The method of claim 12, wherein a particular media content item is streamed from a local media server if the particular media content item is stored at the local media server and is streamed from a non-local media server if the particular media content item is not stored at the local media server.

18. The method of claim 12, wherein the improved boundary estimate is calculated to within a fixed percentage of one of feasibility, optimality, or a combination thereof.

19. A machine-readable storage medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:

initializing a boundary estimate for an optimization of a linear programming model describing a network of media servers for servicing requests for media content items from subscriber devices, wherein the boundary estimate is an estimate of an infeasible solution of the linear programming model; and

calculating iteratively, using an exponential potential function, additional boundary estimates for the linear programming model, wherein the calculating resolves to an improved boundary estimate that corresponds to placement of copies of the media content items at the media servers subject to a set of constraints on storage capacity of media servers and on bandwidth for communication links in the network.

20. The machine-readable storage medium of claim 19, further comprising executable instructions that cause the processor to perform operations comprising re-calculating, via the exponential potential function, the improved boundary estimate to round fractions of the media content items into integer numbers of the media content items.