Method and apparatus for distributing media content

A method, comprising:

• receiving, by a system comprising a processor, a forecast of demand for media content items for streaming from a network of media servers in response to requests from subscriber devices;
• receiving, by the system, a set of constraints on storage capacity of the media servers and bandwidth for communication links in the network;
• 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 a solution of the linear programming model, wherein the linear programming model of the network of media servers comprises a plurality of packing linear programs, wherein the packing linear programs comprise a block-diagonal structure of modeling blocks comprising fractional uncapacitated facility locations problems;
• initializing a scaling factor for a variable of the linear programming model;
• calculating iteratively, by the system and via an exponential potential function, a series of additional boundary estimates for the linear programming model, wherein the scaling factor is adiusted 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, by the system, a placement of copies of the media content items at the media servers, and the routing of the requests over the communications links in the network, according to the improved boundary estimate.

A non-transitory machine-readable storage medium, comprising executable instructions that, when executed by a 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;
• initializing a boundary estimate for an optimization of a linear programming model describing the network of media servers wherein the boundary estimate is an estimate of a solution of the linear programming model, wherein the linear programming model of the network of media servers comprises a plurality of packing linear programs, wherein the packing linear programs comprise a block-diagonal structure of modeling blocks comprising fractional uncapacitated facility locations problems;
• and
• 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 adiusted 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 subject to the set of constraints on storage capacity of the media servers and on bandwidth for the communication links in the network;
• and
• provisioning the placement of the copies of the media content items at the media servers, and a routing of the requests over the communications links in the network, according to the improved boundary estimate.