초록 ▼

A feedback-based adaptive network is described wherein at least a portion of the network elements report operating information relating to network conditions to a centralized data store. The information which is reported to the data store is analyzed by a policy engine which includes a plurality of

A feedback-based adaptive network is described wherein at least a portion of the network elements report operating information relating to network conditions to a centralized data store. The information which is reported to the data store is analyzed by a policy engine which includes a plurality of application specific plug-in policies for analyzing selected information from the data store and for computing updated control information based upon the analysis of the information. The updated control information is fed back to selected network elements to thereby affect operation of the selected elements. Typically, when the operation of a network element has been affected, its corresponding operating information will change. The new or changed network element operating information is then reported to the data store and analyzed by the policy engine. The policy engine may then generate new or updated control information for affecting the operation of selected elements in the network. In this way, the dynamic and automatic feedback control of network elements is provided in order to allow the network to adapt to changing conditions. Events relating to changing conditions in the network may be reported to selected elements in the network using an event notification service. Additionally the adaptive, feedback-based network of the present invention may include a network quality monitoring system for evaluating performance characteristics or other aspects of the network based upon predetermined standards or criteria. If it is determined that a particular characteristic of the network does not conform with the standards established for that characteristic, the policy which controls that particular characteristic of the network may be automatically and dynamically modified to thereby affect the network performance.

대표청구항 ▼

1. A method for providing dynamic feedback control of network elements in a data network, the data network including a plurality of network elements, each of said network elements having a plurality operating parameters associated therewith, said operating parameters being related to at least one co

1. A method for providing dynamic feedback control of network elements in a data network, the data network including a plurality of network elements, each of said network elements having a plurality operating parameters associated therewith, said operating parameters being related to at least one control parameter of said element, said method comprising: retrieving information related to a first subset of network elements from a first data source; analyzing at least a portion of said retrieved information based upon selected guidelines to determine whether a performance of at least a portion of said network conforms with predetermined criteria; and automatically sending updated control information to at least one network element based upon said analysis of said information when it is determined that a performance of the at least a portion of the network fails to conform with predetermined criteria; wherein the portion of retrieved information which is analyzed includes at least one type of information selected from a group comprising: committed information rate information;excess information rate information;committed burst size information;excess burst size information;network congestion information;queue length information relating to selected circuits within the network; anddropped packet information.2. The method of claim 1 wherein the portion of retrieved information which is analyzed includes committed information rate information.3. The method of claim 1, wherein the updated control information specifies a limit on the operation of at least one network element.4. The method of claim 3 wherein the portion of retrieved information which is analyzed includes committed information rate information.5. The method of claim 1 wherein the portion of retrieved information which is analyzed includes excess information rate information.6. The method of claim 5 further comprising: receiving an event notification message relating to an error reported by a specific network element; and suspending analysis of information related to said specific network element in response to reception of said error notification message. 7. The method of claim 6 wherein the portion of retrieved information which is analyzed includes excess burst size information.8. The method of claim 7 wherein the portion of retrieved information which is analyzed includes dropped packet information.9. The method of claim 1 wherein the portion of retrieved information which is analyzed includes committed burst size information.10. The method of claim 1 wherein the portion of retrieved information which is analyzed includes excess burst size information.11. The method of claim 1 wherein the portion of retrieved information which is analyzed includes information relating to queue lengths at selected circuits within the network.12. The method of claim 1 wherein the portion of retrieved information which is analyzed includes dropped packet information.13. The method of claim 1 further including automatically updating control parameters of a second subset of network elements in response to said analysis of said portion of retrieved information to thereby affect performance of said network portion.14. The method of claim 1 further including transmitting said updated control information to a second data source.15. The method of claim 14 wherein said first data source and said second data source reside within a common device.16. A computer program product for providing dynamic feedback control of network elements in a data network, the data network including a plurality of network elements, each of said network elements having a plurality operating parameters associated therewith, said operating parameters being related to at least one control parameter of said element, the computer program product comprising: at least one computer readable medium; computer program instructions stored within the at least one computer readable product configured to: retr ieve information related to a first subset of network elements from a first data source;analyze at least a portion of said retrieved information based upon selected guidelines to determine whether a performance of at least a portion of said network conforms with predetermined criteria; andautomatically send updated control information to at least one network element based upon said analysis of said information when it is determined that a performance of the at least a portion of the network fails to conform with predetermined criteria;wherein the portion of retrieved information which is analyzed includes at least one type of information selected from a group comprising:committed information rate information;excess information rate information;committed burst size information;excess burst size information;network congestion information;queue length information relating to selected circuits within the network; anddropped packet information.17. The computer program product of claim 16 wherein the portion of retrieved information which is analyzed includes committed information rate information.18. The computer program product of claim 16, wherein the updated control information specifies a limit on the operation of at least one network element.19. The computer program product of claim 18 wherein the portion of retrieved information which is analyzed includes committed information rate information.20. The computer program product of claim 16 wherein the portion of retrieved information which is analyzed includes excess information rate information.21. The computer program product of claim 20 wherein the computer program instructions stored within the at least one computer readable product are further configured to: receive an event notification message relating to an error reported by a specific network element; and suspend analysis of information related to said specific network element in response to reception of said error notification message. 22. The computer program product of claim 21 wherein the portion of retrieved information which is analyzed includes excess burst size information.23. The computer program product of claim 22 wherein the portion of retrieved information which is analyzed includes dropped packet information.24. The computer program product of claim 16 wherein the portion of retrieved information which is analyzed includes committed burst size information.25. The computer program product of claim 16 wherein the portion of retrieved information which is analyzed includes excess burst size information.26. The computer program product of claim 16 wherein the portion of retrieved information which is analyzed includes information relating to queue lengths at selected circuits within the network.27. The computer program product of claim 16 wherein the portion of retrieved information which is analyzed includes dropped packet information.28. The computer program product of claim 16 wherein the computer program instructions stored within the at least one computer readable product are further configured to automatically update control parameters of a second subset of network elements in response to said analysis of said portion of retrieved information to thereby affect performance of said network portion.29. The computer program product of claim 16 wherein the computer program instructions stored within the at least one computer readable product are further configured to transmit said updated control information to a second data source.30. The computer program product of claim 29 wherein said first data source and said second data source reside within a common device.31. A policy engine for providing dynamic feedback control of network elements in a data network, the data network including a plurality of network elements, each of said network elements having a plurality operating parameters associated therewith, said operating parameters being related to at least one control parameter of said element, said policy engine comprising: at least one CPU; memory; and at least one interface for retrieving information related to a first subset of network elements from a first data source; said policy engine being operable to analyze at least a portion of said retrieved information based upon selected guidelines to determine whether a performance of at least a portion of said network conforms with predetermined criteria; said policy engine being further operable to automatically send updated control information to at least one network element based upon said analysis of said retrieved information when it is determined that a performance of the at least a portion of the network fails to conform with predetermined criteria; wherein the portion of retrieved information which is analyzed includes at least one type of information selected from a group comprising: committed information rate information;excess information rate information;committed burst size information;excess burst size information;network congestion information;queue length information relating to selected circuits within the network; anddropped packet information.32. The policy engine of claim 31 wherein the portion of retrieved information which is analyzed includes committed information rate information.33. The policy engine of claim 31 wherein the portion of retrieved information which is analyzed includes excess information rate information.34. The policy engine of claim 31 wherein the portion of retrieved information which is analyzed includes committed burst size information.35. The policy engine of claim 31 wherein the portion of retrieved information which is analyzed includes excess burst size information.36. The policy engine of claim 31 wherein the portion of retrieved information which is analyzed includes information relating to queue lengths at selected circuits within the network.37. The policy engine of claim 31 wherein the portion of retrieved information which is analyzed includes dropped packet information.38. The policy engine of claim 31 wherein said policy engine includes a plurality of plug-in policies, each policy specifying a specific set of guidelines for analyzing said information.39. The policy engine of claim 31 wherein the updated control information specifies a limit on the operation of at least one network element.40. The policy engine of claim 31 wherein said policy engine is further operable to automatically update control parameters in a second subset of network elements in response to said analysis of said portion of retrieved information to thereby affect performance of said network portion.41. The policy engine of claim 31 wherein said policy engine is further operable to transmit said updated control information to a second data source.42. The policy engine of claim 41 wherein said first data source and said second data source reside within a common device.43. The policy engine of claim 31 further including an event handling entity operable to receive event notification information relating to at least one network element.44. The policy engine of claim 43 wherein said event handling entity is further operable to report errors detected by said policy engine to an event notification server.