Multi-variate network survivability analysis

• US 8,700,958 B2
• Filed: 03/06/2012
• Issued: 04/15/2014
• Est. Priority Date: 08/11/2006
• Status: Active Grant

• Current Assignee: Riverbed Technology, LLC (Riverbed Technology Incorporated)
• Original Assignee: Riverbed Technology Incorporated
• Inventors: Jeyachandran, Vinod, Singh, Pradeep K., Cohen, Alain J., Narayanaswamy, Shobana, Vankov, Vanko
• Primary Examiner(s): GUYTON, PHILIP A
• Application Number:
  US13/412,623
• Publication Number:
  US 20130007524A1
• Time in Patent Office: 770 Days
• Field of Search: 714/4, 714/33, 714/46, 714/57
• US Class Current: 714/33
• CPC Class Codes: H04L 41/0681 Configuration of triggering conditions
• CPC Class Codes: H04L 41/5009 Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF]
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level
• CPC Class Codes: H04L 43/16 Threshold monitoring

Abstract

Network survivability is quantified in such a way that failure cases can be compared and ranked against each other in terms of the severity of their impact on the various performance measures associated with the network. The degradation in network performance caused by each failure is quantified based on user-defined sets of thresholds of degradation severity for each performance measure. Each failure is simulated using a model of the network, and a degradation vector is determined for each simulated failure. A comparison function is defined to map the degradation vectors into an ordered set, and this ordered set is used to create an ordered list of network failures, in order of the network degradation caused by each failure.

Claims

1. A system for assessing failures in a network, said system comprising:

a user interface that is configured to receive a plurality of user-specified potential failure conditions that have not yet occurred within the network; and

at least one processor configured by to;

simulate each of the plurality of failure conditions on a model of the network,

determine a performance of the model of the network under each of the plurality of failure conditions, the performance being defined by a plurality of performance measures,

map each performance measure of each failure condition to one of a plurality of degrees of degradation severity, and

order the plurality of failure conditions in a rank order based on the degree of degradation severity of each performance measure for each failure condition.

2. The system of claim 1, wherein the user interface is configured to provide information for displaying an ordered list of select failure conditions based on the rank ordering.

3. The system of claim 1, wherein the user interface is configured to receive from a user a set of criteria associated with one or more degradation parameters.

4. The system of claim 1, wherein the user interface is configured to provide information for displaying the performance measures for one or more failure conditions, including an indication of the degree of degradation severity associated with each performance measure.

5. A non-transitory computer-readable medium that includes a program that, when executed by a processor, causes the processor to:

receive a plurality of user-specified potential failure conditions that have not yet occurred within the network;

simulate each of the plurality of failure conditions on a model of the network,

determine a performance of the model of the network under each of the plurality of failure conditions, the performance being defined by a plurality of performance measures,

map each performance measure of each failure condition to one of a plurality of degrees of degradation severity, and

order the plurality of failure conditions in a rank order based on the degree of degradation severity of each performance measure for each failure condition.

6. The medium of claim 5, wherein the program causes the processor to provide information for displaying an ordered list of select failure conditions based on the rank ordering.

7. The medium of claim 5, wherein the program causes the processor to receive from a user a set of criteria associated with one or more degradation parameters.

8. The medium of claim 5, wherein the program causes the processor to provide information for displaying the performance measures for one or more failure conditions, including an indication of the degree of degradation severity associated with each performance measure.

9. A method comprising:

receiving, via a user interface, a plurality of user-specified potential failure conditions that have not yet occurred within the network;

simulating, by a processing system, each of the plurality of failure conditions on a model of the network,

determining, by the processing system, a performance of the model of the network under each of the plurality of failure conditions, the performance being defined by a plurality of performance measures,

mapping, by the processing system, each performance measure of each failure condition to one of a plurality of degrees of degradation severity, and

ordering, by the processing system, the plurality of failure conditions in a rank order based on the degree of degradation severity of each performance measure for each failure condition.

10. The method of claim 9, including providing information for displaying an ordered list of select failure conditions based on the rank ordering.

11. The method of claim 9, including receiving from a user a set of criteria associated with one or more degradation parameters.

12. The method of claim 9, including providing information for displaying the performance measures for one or more failure conditions, including an indication of the degree of degradation severity associated with each performance measure.