Methods and apparatus for network use optimization

• US 6,816,456 B1
• Filed: 02/04/2000
• Issued: 11/09/2004
• Est. Priority Date: 02/04/2000
• Status: Expired due to Term

• Current Assignee: AT&T Corporation (AT&T, Inc.)
• Original Assignee: AT&T Corporation (AT&T, Inc.)
• Inventors: Tse-Au, Elizabeth Suet Hing
• Primary Examiner(s): HSU, ALPUS
• Application Number:
  US09/497,480
• Time in Patent Office: 1,740 Days
• Field of Search: 370/230, 370/230.1, 370/231, 370/235, 370/235.1, 370/252, 370/253, 370/389, 370/395.1, 370/395.2, 370/395.21, 370/395.4, 370/395.41, 370/395.42, 370/395.43, 709/226, 709/230, 709/232, 709/234, 709/235, 709/238, 709/240
• US Class Current: 370/230.1
• CPC Class Codes: H04L 41/5054 Automatic deployment of services triggered by the service manager, e.g. service implementation by automatic configuration of network components
• CPC Class Codes: H04L 43/045 for graphical visualisation of monitoring data
• CPC Class Codes: H04L 43/062 related to network traffic
• CPC Class Codes: H04L 43/087 Jitter
• CPC Class Codes: H04L 43/0894 Packet rate
• CPC Class Codes: H04L 43/106 using time related information in packets, e.g. by adding timestamps
• CPC Class Codes: H04L 43/12 Network monitoring probes
• CPC Class Codes: H04L 43/14 using software, i.e. software packages network security related monitoring H04L63/1408
• CPC Class Codes: H04L 47/10 Flow control; Congestion control
• CPC Class Codes: H04L 47/11 Identifying congestion
• CPC Class Codes: H04L 47/2416 Real-time traffic
• CPC Class Codes: H04L 47/2433 Allocation of priorities to traffic types
• CPC Class Codes: H04L 47/2441 relying on flow classification, e.g. using integrated services [IntServ]
• CPC Class Codes: H04L 47/41 by acting on aggregated flows or links
• CPC Class Codes: Y02D 30/50 in wire-line communication networks, e.g. low power modes or reduced link rate

Abstract

A method and apparatus for assessing network traffic loads, separating the network traffic into the traffic classes either with or without specific client priority/business input, and managing the allocation of available network resources based on the class of the traffic. Differentiated traffic classes of communication services, such as time sensitive and non-time sensitive, may be specified via a set of parameters to permit a network to provide corresponding services that result in a guaranteed amount of available network resources, such as bandwidth. The set of parameters allows the network operator to categorize each type of network traffic into traffic classes and designate a predetermined level of network resources per class, thereby achieving the QoS—Quality of Service—and predictable traffic service performance guarantee appropriate to the needs of the end users of the network in a multi-class, multi-priority network environment.

Claims

1. A method for operating a network, comprising:

receiving from a client one or more network use specifications;

grouping data traffic for the client into a set of traffic classes based on traffic type and the network use specifications, wherein the traffic classes are grouped into a class hierarchy tree including a root node and a second level of nodes below the root node and a second level of nodes below the root node in the class hierarchy tree, the second level of nodes including at least one of a time-sensitive, non-time-sensitive and default node; and

allocating network resources to the data traffic based on the set of traffic classes to provide a class of service.

2. The method according to claim 1, wherein each of the second level nodes further includes at least one business unit node on a third level below each respective second level nodes in the class hierarchy tree.

3. The method according to claim 2, wherein each of the business unit nodes further include at least one of the traffic classes on a fourth level below each respective business unit node in the third level of the class hierarchy tree.

4. The method according to claim 3, wherein each of the traffic classes includes an allocated bandwidth which each of the traffic classes is permitted to use on the network.

5. The method according to claim 4, wherein the allocated bandwidth is a portion of a bandwidth available on the network and is based on at least a peak bandwidth utilization and a mean bandwidth utilization corresponding to each of the traffic classes.

6. The method according to claim 5, wherein the allocated bandwidth is further based on an alpha value, the alpha value being an indication of the sensitivity to delay of the respective traffic class.

7. The method according to claim 4, wherein each of the traffic classes further includes a bounded variable that indicates a bounded or unbounded state of the traffic class, wherein when a traffic class is in the unbounded state, the traffic class can use any excess allocated bandwidth of other traffic classes which depend from a same parent node, and when the traffic class is in a bounded state, the traffic class can use only the allocated bandwidth of that traffic class.

8. The method according to claims 4, wherein each of the business unit nodes further includes a bounded variable that indicates a bounded or unbounded state of the business unit, when a business unit node is unbounded the business unit may additionally use the network resources of other business unit nodes which depend from a same parent node, and when a business unit node is bounded, the business unit node may only use the allocated network resources for that business unit node.

9. The method according to claim 4, wherein each of the second level nodes further includes a bounded variable that indicates a bounded or unbounded state of the node, when a second level node is unbounded, the node may additionally use the network resources of other second level nodes, and when a second level node is bounded, the node may only use the allocated network resources for that second level node.

10. The method according to claim 1, wherein the network use specification is generated from a set of client preferences gathered from the client by at least one of a client interviewing process and a client questioning process.

11. The method according to claim 10, wherein the network use specification further includes prior use data of the network.

12. The method according to claim 1, wherein the network use specification is generated from a history file containing prior use data of the network, the prior use data being organized into the traffic classes based on a degree of network resource consumption.

13. The method according to claim 12, wherein allocating network resources further includes generating a network control program that allocates the network resources between the data traffic based on the set of traffic classes and the history file to provide guaranteed class of service to these traffic types.

14. The method according to claim 12, wherein the network use specification can be flexibly generated with or without input from a client.

15. The method according to claim 14, wherein the network control program apportions the network resources between the data traffic based on the set of traffic classes to provide a differentiated bandwidth treatment according to a client'"'"'s priority on the data traffic when the client'"'"'s input is available, and a guaranteed bandwidth treatment and class of service on the data traffic when a client'"'"'s input is not available.

16. The method according to claim 14, further comprising generating a network control program that includes using a set of engineering rules and a minimal set of service provisioning tools to provide at least one of a differentiated bandwidth treatment and quality of service according to a client'"'"'s priority of the data traffic when client'"'"'s input is available, and a guaranteed bandwidth treatment and class of service on the data traffic when a client'"'"'s input is not available.

17. The method according to claim 12, wherein each of the traffic classes includes an allocated bandwidth which each of the traffic classes is permitted to use on the network.

18. The method according to claim 17, wherein the allocated bandwidth is a portion of a bandwidth available to the network and is based on at least a peak bandwidth utilization and a mean bandwidth utilization corresponding to each of the traffic classes.

19. The method according to claim 18, wherein the allocated bandwidth is further based on an alpha value, the alpha value being an indication of the sensitivity to delay of the respective traffic class.

20. The method according to claim 17, wherein each of the traffic classes further includes a bounded variable that indicates a bounded or unbounded state of the traffic class, wherein when a traffic class is in the unbounded state, the traffic class can use the allocated bandwidth of other traffic classes which depend from a same parent node, and when the traffic class is in a bounded state, the traffic class can use only the allocated bandwidth of that traffic class.

21. The method according to claim 20, wherein allocating the amount of network resource further includes configuring a network resource controller and setting the bounded variable based on an engineering judgment on the bandwidth required by the traffic type when the client input is not available.

22. A method for optimizing network performance, comprising:

receiving from a client one or more network use specifications;

classifying data traffic for the client into one of a plurality of traffic classes based on one or more network use specifications and available network resources of the network, wherein the traffic classes are grouped into a class hierarchy tree including a root node and a second level of nodes below the root node and a second level of nodes below the root node in the class hierarchy tree, the second level of nodes including at least one of a time-sensitive, non-time-sensitive and default node; and

controlling an amount of network resources that the data traffic can use based on the traffic class of the data traffic to produce a quality of service for each of the traffic classes.

23. The method according to claim 22, wherein each of the traffic classes includes an allocated bandwidth which each of the traffic classes is permitted to use on the network.

24. The method according to claim 23, wherein the allocated bandwidth is a portion of a bandwidth available to the network and is based on at least a peak bandwidth utilization and a mean bandwidth utilization corresponding to each of the traffic classes.

25. The method according to claim 24, wherein the allocated bandwidth is further based on an alpha value, the alpha value being an indication of the sensitivity to delay of the respective traffic class.

26. The method according to claim 23, wherein each of the traffic classes further includes a bounded variable that indicates a bounded or unbounded state of the traffic class, wherein when a traffic class is in the unbounded state, the traffic class can use the allocated bandwidth of other traffic classes which depend from a same parent node, and when the traffic class is in a bounded state, the traffic class can use only the allocated bandwidth of that traffic class.

27. The method according to claim 22, wherein the network use specification is generated from a set of client preferences gathered from a client by at least one of a client interviewing process and a client questioning process.

28. The method according to claim 27, wherein the network use specification further includes prior use data of the network.

29. A method for operating a network, comprising:

collecting from a client prior use data of the network;

generating a network performance specification for the client based on the prior use data, the network performance specification including at least a plurality of traffic classes and traffic parameters, wherein the traffic classes are grouped into a class hierarchy tree including a root node and a second level of nodes below the root node and a second level of nodes below the root node in the class hierarchy tree, the second level of nodes including at least one of a time-sensitive, non-time-sensitive and default node; and

allocating network resources to the data traffic based on the network performance specification.

30. The method according to claim 29, wherein each of the traffic parameters include an allocated bandwidth which each of the traffic classes is permitted to use on the network.

31. The method according to claim 30, wherein the allocated bandwidth is a portion of a bandwidth available on the network and is based on at least a peak bandwidth utilization and a mean bandwidth utilization corresponding to each of the traffic classes.

32. The method according to claim 31, wherein the allocated bandwidth is further based on an alpha value, the alpha value being an indication of the sensitivity to delay of the respective traffic class.

33. The method according to claim 30, wherein each of the traffic parameters further includes a bounded variable that indicates a bounded or unbounded state of the traffic class, wherein when a traffic class is in the unbounded state, the traffic class can use the allocated bandwidth of other traffic classes which depend from a same parent node, and when the traffic class is in a bounded state, the traffic class can use only the allocated bandwidth of that traffic class.

34. The method according to claim 29, wherein the network performance specification is generated from a set of client preferences gathered from the client by at least one of a client interviewing process or a client questioning process.

35. The method according to claim 34, wherein the network performance specification further includes prior use data of the network.