Evaluating electronic network devices in view of cost and service level considerations

Patent metadata

Field	Value
Publication number	US-9565080-B2
Application number	US-201313861857-A
Country	US
Kind code	B2
Filing date	Apr 12, 2013
Priority date	Nov 15, 2012
Publication date	Feb 7, 2017
Grant date	Feb 7, 2017

Abstract

The described implementations relate to processing of electronic data. One implementation is manifest as one or more computer-readable storage devices comprising instructions which, when executed by one or more processing devices, cause the one or more processing devices to perform acts. The acts can include determining service levels provided by multiple network configurations, determining costs associated with the multiple network configurations, and evaluating the multiple network configurations based on both the costs and the service levels. The multiple network configurations can include redundantly-deployed devices. Furthermore, some implementations may determine cost/service level metrics that can be used to compare devices based on expected costs to provide a particular service level.

First claim

The invention claimed is:

1. A method performed by one or more processing devices, the method comprising:
determining a first number of first network devices of a first network device classification for deployment in a network stamp of an application;
determining a second number of second network devices of a second network device classification for deployment in the network stamp of the application;
determining an expected first service level provided by a first redundant configuration of the first number of first network devices, the expected first service level being determined using first production data reflecting availability or reliability of the first network devices when deployed redundantly;
determining an expected second service level provided by a second redundant configuration of the second number of second network devices, the expected second service level being determined using second production data reflecting availability or reliability of the second network devices when deployed redundantly; and
predicting expected application service levels of the application with the first redundant configuration and the second redundant configuration incorporated into the network stamp of the application, the predicting being based at least on the expected first service level and the expected second service level.

2. The method of claim 1 , wherein the first network device classification is a first network device model and the second network device classification is a second network device model.

3. The method of claim 1 , further comprising:
ranking the first network device classification relative to the second network device classification based at least on the expected application service levels.

4. The method of claim 1 , further comprising:
determining a first total number of ports on the first network devices;
determining the first number of first network devices subject to a specified oversubscription ratio based at least on the first total number of ports;
determining a second total number of ports on the second network devices; and
determining the second number of second network devices subject to the specified oversubscription ratio based at least on the second total number of ports.

5. The method of claim 4 , further comprising:
determining a first aggregate capacity for the first total number of ports based at least on a first per-port capacity of the ports on the first network devices;
determining a second aggregate capacity for the second total number of ports based at least on a second per-port capacity of the ports on the second network devices; and
outputting the first aggregate capacity, the second aggregate capacity, the first per-port capacity, and the second per-port capacity.

6. A system comprising:
one or more processing devices; and
one or more computer-readable storage devices comprising instructions which, when executed by the one or more processing devices, cause the one or more processing devices to:
obtain first production data reflecting failures of deployed first network devices of a first network device classification;
based at least on the first production data, determine a first expected service level of a first redundant configuration of a first number of the first network devices;
obtain second production data reflecting failures of deployed second network devices of a second network device classification;
based at least on the second production data, determine a second expected service level of a second redundant configuration of a second number of the second network devices; and
predict a first overall network service level provided by a tree of devices incorporating the first redundant configuration and a second overall network service level provided by the tree of devices incorporating the second redundant configuration.

7. The system of claim 6 , the first production data comprising first failure events logged by the deployed first network devices and the second production data comprising second failure events logged by the deployed second network devices.

8. The system of claim 7 , wherein the instructions, when executed by the one or more processing devices, cause the one or more processing devices to:
filter various first events logged by the deployed first network devices to obtain the first failure events, the various first events being filtered to remove other first events that did not actually impact carrying of network traffic by the deployed first network devices; and
filter various second events logged by the deployed second network devices to obtain the second failure events, the various second events being filtered to remove other second events that did not actually impact carrying of network traffic by the deployed second network devices.

9. The system of claim 7 , wherein the instructions, when executed by the one or more processing devices, cause the one or more processing devices to:
filter various first events logged by the deployed first network devices to obtain the first failure events, the various first events being filtered to remove redundant first events that relate to failures identified by the first failure events; and
filter various second events logged by the deployed second network devices to obtain the second failure events, the various second events being filtered to remove redundant second events that relate to failures identified by the second failure events.

10. The system of claim 7 , wherein the instructions, when executed by the one or more processing devices, cause the one or more processing devices to:
filter various first events logged by the deployed first network devices to obtain the first failure events, the various first events being filtered to remove first spurious failure events logged while the deployed first network devices are operational; and
filter various second events logged by the deployed second network devices to obtain the second failure events, the various second events being filtered to remove second spurious failure events logged while the deployed second network devices are operational.

11. The system of claim 6 , the first redundant configuration and the second redundant configuration being active-active configurations.

12. The system of claim 11 , the first redundant configuration comprising first access routers or aggregation switches of a first model, the second redundant configuration comprising second access routers or aggregation switches of a second model.

13. The system of claim 6 , the first redundant configuration and the second redundant configuration being active-standby configurations.

14. The system of claim 13 , the first redundant configuration comprising first access routers or aggregation switches of a first model, the second redundant configuration comprising second access routers or aggregation switches of a second model.

15. A method comprising:
monitoring deployed first network devices of a first network device classification to detect first failure events logged by the deployed first network devices;
based at least on the first failure events, predicting a first expected service level of a first redundant configuration of a first number of the first network devices;
monitoring deployed second network devices of a second network device classification to detect second failure events logged by the deployed second network devices;
based at least on the second failure events, predicting a second expected service level of a second redundant configuration of a second number of the second network devices;
predicting a first overall network service level provi

Assignees

• Microsoft Corp
• Microsoft Technology Licensing Llc

Inventors

• Jain Navendu

Classifications

• H04L41/0893

  Assignment of logical groups to network elements · CPC title

• H04L29/06

  Electricity · mapped topic

• H04L41/0826 Primary

  for reduction of network costs (H04L41/0833 takes precedence) · CPC title

• H04L41/069

  using logs of notifications; Post-processing of notifications · CPC title

• H04L41/0668

  by dynamic selection of recovery network elements, e.g. replacement by the most appropriate element after failure · CPC title