# US 9,438,487 B2 · Bandwith policy management in a self-corrected content delivery network > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 9,438,487 B2 - Document ID: US9438487B2 - Status: Granted - Kind: B2 - Application number: 13/935,381 - Filed: 2013-07-03 - Published: 2015-01-08 - Granted: 2016-09-06 - Earliest claimed: 2013-07-03 - Assignees: Ericsson Inc. - Applicants: Ericsson Television Inc. - Inventors: Chris Phillips; Jimmie Rodgers - Web page: https://patentgrep.com/patent/US9438487B2 ## CPC - H04L 47/52: by attributing bandwidth to queues - H04L 41/0894: Policy-based network configuration management - H04L 41/145: {involving simulating, designing, planning or modelling of a network} - H04L 41/147: for predicting network behaviour - H04L 41/5025: by proactively reacting to service quality change, e.g. by reconfiguration after service quality degradation or upgrade - H04L 41/509: {wherein the managed service relates to media content delivery, e.g. audio, video or TV} - H04L 43/0882: Utilisation of link capacity - H04L 47/20: Traffic policing - H04L 47/26: using explicit feedback to the source, e.g. choke packets - H04L 47/30: in combination with information about buffer occupancy at either end or at transit nodes - H04L 47/70: Admission control; Resource allocation - H04L 47/805: {QOS or priority aware} - H04L 47/83: based on usage prediction - H04L 67/55: Push-based network services - H04L 67/5681: Pre-fetching or pre-delivering data based on network characteristics - G06F 16/9574: {of access to content, e.g. by caching} - H04L 41/0896: Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities (flow or congestion control using dynamic resource allocation, e.g. in-call renegotiation, H04L47/76) - H04L 43/16: Threshold monitoring - H04L 65/61: for supporting one-way streaming services, e.g. Internet radio - H04L 65/762: {at the source (reformatting of additional data in video distribution servers H04N21/2355)} - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract In one embodiment of a network pipe optimization method, a network element may obtain at least one of a push pipe utilization report and a pull pipe utilization report from each distribution node of the content delivery network. Based on the utilization reports, the network element may determine new push pipe weights and new pull pipe weights for distribution pipes associated with each distribution node of the content delivery network. Using at least one of the new push pipe weights and new pull pipe weights, a network pipe utilization model associated with the content delivery network may be simulated. Responsive to determining that the simulated network pipe utilization model yields an improved utilization of the content delivery network, the new push pipe weights and new pull pipe weights may be distributed to each distribution node in the content delivery network. ## Claims ### Claim 1 A network pipe usage optimization method operable in a content delivery network, the method comprising: obtaining at least one of a push pipe utilization report and a pull pipe utilization report from each distribution node of the content delivery network, wherein the distribution nodes are organized into multiple hierarchical levels, the push pipe utilization and pull pipe utilization reports indicating current consumption of push content and pull content via all outgoing distribution pipes from a distribution node to another downstream CDN node; determining new push pipe weights and new pull pipe weights for the outgoing distribution pipes associated with each distribution node of the content delivery network responsive to the push pipe and pull pipe utilization reports and a pre-provisioning push policy from a popularity policy management node with respect to a particular push content to be distributed via the CDN; simulating, using at least one of the new push pipe weights and new pull pipe weights, a network pipe utilization model associated with the content delivery network; and responsive to determining that the simulated network pipe utilization model yields an improved utilization of the content delivery network, distributing the new push pipe weights and new pull pipe weights to each distribution node in the content delivery network, wherein the new push pipe weights and new pull pipe weights are operative to apportion bandwidth of each outgoing distribution pipe from a distribution node to another downstream CDN node. ### Claim 2 (depends on 1) The method as recited in claim 1, further comprising: prior to determining the new push pipe weights and new pull pipe weights, determining if the push pipe utilization and pull pipe utilization reports from a distribution node indicate exceeding a threshold utilization level for that distribution node. ### Claim 3 (depends on 2) The method as recited in claim 2, further comprising: determining if push and pull pipe utilization parameters can be forecasted for over a period of time using at least one of anticipated content popularity distributions and current push content and pull content policies; and if so, calculating the new push pipe weights and new pull pipe weights based on forecasted push and pull pipe utilization. ### Claim 4 (depends on 1) The method as recited in claim 1, further comprising: if the simulated network pipe utilization model does not yield an improved utilization of the content delivery network, readjusting new push pipe weights and new pull pipe weights until an iterative simulation of the network pipe utilization model yields an improved utilization. ### Claim 5 (depends on 4) The method as recited in claim 4, further comprising: if the iteratively simulated network pipe utilization model does not yield an improved utilization of the content delivery network, generating a bandwidth warning report to a policy management node associated with the content delivery network. ### Claim 6 (depends on 1) The method as recited in claim 1, wherein the new push pipe weights and new pull pipe weights are determined further based upon which of the distribution nodes will be provisioned for supporting upcoming push content pipes responsive to anticipated popularity distributions of content to be delivered by the content delivery network. ### Claim 7 (depends on 6) The method as recited in claim 6, wherein the anticipated popularity distributions are determined based on at least one of content-specific trend data in a geographical region serviced by the content delivery network, demographic data of subscribers serviced by the content delivery network, and content-specific revenue sales data. ### Claim 8 A network element configured to operate in association with a content delivery network, the network element comprising: one or more processors; a memory subsystem coupled to the one or more processors, the memory subsystem including a persistent memory; and a network pipe usage optimization module implemented in the persistent memory and configured to be executed by the one or more processors for performing: obtaining at least one of a push pipe utilization report and a pull pipe utilization report from each distribution node of the content delivery network, wherein the distribution nodes are organized into multiple hierarchical levels, the push pipe utilization and pull pipe utilization reports indicating current consumption of push content and pull content via all outgoing distribution pipes from a distribution node to another downstream CDN node; determining new push pipe weights and new pull pipe weights for the outgoing distribution pipes associated with each distribution node of the content delivery network responsive to the push pipe and pull pipe utilization reports and a pre-provisioning push policy from a popularity policy management node with respect to a particular push content to be distributed via the CDN; simulating, using at least one of the new push pipe weights and new pull pipe weights, a network pipe utilization model associated with the content delivery network; and responsive to determining that the simulated network pipe utilization model yields an improved utilization of the content delivery network, distributing the new push pipe weights and new pull pipe weights to each distribution node in the content delivery network, wherein the new push pipe weights and new pull pipe weights operate to apportion bandwidth of each outgoing distribution pipe from a distribution node to another downstream CDN node. ### Claim 9 (depends on 8) The network element as recited in claim 8, wherein the network pipe usage optimization module is further configured to: prior to determining the new push pipe weights and new pull pipe weights, determine if the push pipe utilization and pull pipe utilization reports from a distribution node indicate exceeding a threshold utilization level for that distribution node. ### Claim 10 (depends on 9) The network element as recited in claim 9, wherein the network pipe usage optimization module is further configured to: determine if push and pull pipe utilization parameters can be forecasted for over a period of time using at least one of anticipated content popularity distributions and current push content and pull content policies; and if so, calculating the new push pipe weights and new pull pipe weights based on forecasted push and pull pipe utilization. ### Claim 11 (depends on 9) The network element as recited in claim 9, wherein the network pipe usage optimization module is further configured to: if the simulated network pipe utilization model does not yield an improved utilization of the content delivery network, readjust new push pipe weights and new pull pipe weights until an iterative simulation of the network pipe utilization model yields an improved utilization. ### Claim 12 (depends on 11) The network element as recited in claim 11, wherein the network pipe usage optimization module is further configured to: if the iteratively simulated network pipe utilization model does not yield an improved utilization of the content delivery network, generating a bandwidth warning report to a policy management node associated with the content delivery network. ### Claim 13 (depends on 9) The network element as recited in claim 9, wherein the network pipe usage optimization module is configured to determine the new push pipe weights and new pull pipe weights further based upon which of the distribution nodes will be provisioned for supporting upcoming push content pipes responsive to anticipated popularity distributions of content to be delivered by the content delivery network. ### Claim 14 (depends on 13) The network element as recited in claim 13, wherein the anticipated popularity distributions are determined based on at least one of content-specific trend data in a geographical region serviced by the content delivery network, demographic data of subscribers serviced by the content delivery network, and content-specific revenue sales data.