Predictive Allocation of Multimedia Server Resources

• US 20090183218A1
• Filed: 01/10/2008
• Published: 07/16/2009
• Est. Priority Date: 01/10/2008
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Knowledge Ventures, L.P. (AT&T, Inc.)
• Inventors: Sullivan, Aaron R., Li, Zhi, Savoor, Raghvendra
• Granted Patent: US 10,070,164 B2
• Time in Patent Office: Days
• US Class Current: 725/114
• CPC Class Codes: H04N 21/23103 using load balancing strategies, e.g. by placing or distributing content on different disks, different memories or different servers storage management G06F3/0604; allocation of resources considering the load in multiprogramming arrangements G06F9/505; techniques for rebalancing the load in a distributed system G06F9/5083; access to distributed or replicated servers, e.g. load balancing, in data networks H04L67/1001
• CPC Class Codes: H04N 21/2405 Monitoring of the internal components or processes of the server, e.g. server load allocation of resources in multiprogramming arrangements G06F9/50; performance measurement of computer activity G06F11/34
• CPC Class Codes: H04N 21/254 Management at additional data server, e.g. shopping server, rights management server arrangements for maintenance or administration in data networks H04L41/00; network services using third party service providers H04L67/53

Abstract

Disclosed are techniques for dynamic allocation of multimedia server resources among multimedia transmission services of a service provider based on predicted resource usage by each multimedia transmission service. A predictive usage model of the utilization of server resources by one or more multimedia transmission services is generated for various combinations of operating characteristics, such as time of day, day of week, programming event or content, network status, and the like. The predictive usage model can be generated using past resource utilization characteristics of the multimedia transmission services from prior time periods having the same or similar characteristics. The service provider then can use the predictive usage model to more efficiently allocate multimedia server resources among the multimedia transmission services for upcoming time periods, which may be of fixed or variable duration.

Claims

1. In a multimedia content distribution system comprising a service provider configured to distribute multimedia content to a plurality of viewer premises via a network, a method comprising:

determining, at the service provider, a first allocation of multimedia server resources between a plurality of multimedia transmission services for a first time period based on a predictive usage model of multimedia server resources by the plurality of multimedia transmission services; and

allocating resources of one or more multimedia servers of the service provider between the plurality of multimedia transmission services for the first time period based on the first allocation.

2. The method of claim 1, wherein the first allocation of multimedia server resources comprises a prioritization of the plurality of multimedia transmission services for the first time period.

3. The method of claim 1, wherein the first allocation of multimedia server resources comprises selectively enabling a filtering mechanism for one or more of the plurality of multimedia transmission services for the first time period.

4. The method of claim 1, wherein:

the service provider comprises a plurality of multimedia servers; and

the first allocation of multimedia server resources comprises an allocation of each of at least a subset of the plurality of multimedia servers to a corresponding multimedia transmission service of the plurality of multimedia transmission services.

5. The method of claim 4, wherein the first allocation further comprises an allocation of each resource of a plurality of available resources of a multimedia server to a multimedia transmission service of the plurality of multimedia transmission services.

6. The method of claim 5, wherein the plurality of available resources of the multimedia server comprises at least one of:

network interface resources;

bus resources;

input/output (I/O) resources;

memory resources;

cache resources; and

processor resources.

7. The method of claim 1, wherein the first allocation comprises an allocation of at least a portion of each resource of a plurality of available resources of a multimedia server of the service provider to a corresponding multimedia transmission service.

8. The method of claim 1, wherein the plurality of multimedia transmission services comprises at least one of:

a linear program broadcast service;

a packet retransmission multicast service;

a program multicast service; and

a content burst unicast service.

9. The method of claim 8, wherein the content burst unicast service comprises an instant channel change service.

10. The method of claim 1, further comprising:

determining the first allocation from the predictive use model based on at least one of;

a time of day of the first time period;

a day of the week of the first time period;

a day of the month of the first time period;

a date of the first time period;

a programming event occurring during the first time period; and

a status of the network.

11. The method of claim 1, further comprising:

determining multimedia server resource utilization characteristics by each of the plurality of multimedia transmission services for at least a second time period preceding the first time period; and

generating the predicative usage model based on the multimedia server resource utilization characteristics.

12. The method of claim 11, wherein the first time period and the second time period share in common at least one of:

a same time of day;

a same day of the week;

a same day of the month;

a same date;

a same programming event; and

a same status of the network.

13. The method of claim 1, further comprising:

determining, at the service provider, a second allocation of multimedia server resources between the plurality of multimedia transmission services for a second time period based on the predictive usage model; and

allocating resources of one or more multimedia servers of the service provider between the plurality of multimedia transmission services for the second time period based on the second allocation.

14. In a multimedia content distribution system comprising a service provider configured to distribute multimedia content to a plurality of viewer premises via a network, a method comprising:

determining, at the service provider, multimedia server resource utilization characteristics for each of a plurality of multimedia transmission services for a set of one or more time periods;

generating a predictive usage model of multimedia server resources based on the multimedia server resource utilization characteristics; and

storing data representative of the predictive usage model at a data store for subsequent access.

15. The method of claim 14, wherein the multimedia server resources comprise at least one of:

network interface resources;

bus resources;

input/output (I/O) resources;

memory resources;

cache resources; and

processor resources.

16. The method of claim 14, wherein the plurality of multimedia transmission services comprises at least one of:

a linear program broadcast service;

a packet retransmission multicast service;

a program multicast service; and

a content burst unicast service.

17. A multimedia content distribution system comprising:

a first multimedia server coupled to a network, the first multimedia server comprising multimedia server resources configured to support multimedia transmission services for transmission of multimedia content via the network;

a data store to store data representative of a predictive usage model of multimedia server resources by a plurality of multimedia transmission services; and

a resource allocation module configured to;

for each time period of a sequence of one or more time periods;

determine a first allocation of the multimedia server resources between the plurality of multimedia transmission services for the time period based on the predictive usage model; and

allocate the multimedia server resources to the plurality of multimedia transmission services for the time period based on the first allocation.

18. The multimedia content distribution system of claim 17, further comprising:

a second multimedia server coupled to the network, the second multimedia server comprising multimedia server resources configured to provide multimedia transmission services for transmission of multimedia content via the network; and

wherein the resource allocation module further is configured to;

for each time period of the sequence of time periods;

determine a second allocation of multimedia server resources of the second multimedia server between the plurality of multimedia transmission services for the time period based on the predictive usage model; and

allocate the multimedia server resources of the second multimedia server to the plurality of multimedia transmission services for the time period based on the second allocation.

19. The multimedia content distribution system of claim 17, wherein the first allocation of multimedia server resources comprises at least one of:

a prioritization of the plurality of multimedia transmission services for the time period;

a selective enabling of a filtering mechanism for one or more of the plurality of multimedia transmission services for the time period; and

an allocation of each resource of a plurality of available resources of the first multimedia server to a corresponding multimedia transmission service of the plurality of multimedia transmission services.

20. The multimedia content distribution system of claim 19, wherein the plurality of available resources of the first multimedia server comprise at least one of:

network interface resources;

bus resources;

input/output (I/O) resources;

memory resources;

cache resources; and

processor resources.

21. The multimedia content distribution system of claim 17, wherein the plurality of multimedia transmission services comprises at least one of:

a linear program broadcast service;

a packet retransmission multicast service;

a program multicast service; and

a content burst unicast service.

22. The multimedia content distribution system of claim 17, wherein the resource allocation module is configured to determine the first allocation for the time period from the predictive usage model based on at least one of:

a time of day of the time period;

a day of the week of the time period;

a day of the month of the time period;

a date of the time period;

a programming event occurring during the time period; and

a status of the network during the time period.

23. The multimedia content distribution system of claim 17, further comprising:

a predictive modeling module configured to;

determine multimedia server resource utilization characteristics for each of the plurality of multimedia transmission services for a second sequence of one or more of time periods preceding the first sequence of one or more time periods; and

generating the predicative usage model based on the multimedia server resource utilization characteristics.

24. The multimedia content distribution system of claim 23, wherein the resource allocation module is configured to determine the first allocation of multimedia server resources for a first time period of the first sequence from the predictive usage model based on the multimedia server resource utilization characteristics for a second time period of the second sequence, the first time period and the second time period comprising at least one characteristic in common.

25. The multimedia content distribution system of claim 24, wherein the at least one characteristic in common comprises at least one of:

a same time of day;

a same day of the week;

a same day of the month;

a same date;

a same programming event;

a same programming category; and

a same status of the network.

26. A computer readable medium embodying a computer program, the computer program comprising instructions configured to manipulate one or more processors to:

determine multimedia server resource utilization characteristics of a multimedia server for each of a plurality of multimedia transmission services for a set of one or more time periods;

generate a predictive usage model of multimedia server resources based on the multimedia server resource utilization characteristics; and

store data representative of the predictive usage model at a data store for subsequent access.

27. The computer readable medium of claim 26, wherein the multimedia server resources comprise at least one of:

network interface resources;

bus resources;

input/output (I/O) resources;

memory resources;

cache resources; and

processor resources.

28. The computer readable medium of claim 26, wherein the plurality of multimedia transmission services comprises at least one of:

a linear program broadcast service;

a packet retransmission multicast service;

a program multicast service; and

a content burst unicast service.