Streaming server statistics and predictive mitigation

Patent metadata

Field	Value
Publication number	US-11789809-B2
Application number	US-202217744798-A
Country	US
Kind code	B2
Filing date	May 16, 2022
Priority date	Jun 29, 2017
Publication date	Oct 17, 2023
Grant date	Oct 17, 2023

Abstract

Aspects of the present disclosure involve systems and methods for improving the performance of a telecommunications network by monitoring the performance of one or more storage drives. Operational data is received from a plurality of storage drives of a storage server of a telecommunications network. A plurality of operational coefficients for each of the plurality of storage drives is derived based on the operational data, and a cluster plot is created from the plurality of operational coefficients for each of the plurality of storage drives. A distance is calculated between a subset of operational coefficients of the plurality of operational coefficients of the cluster plot, and a remedial action is initiated on a storage drive of the plurality of storage drives when a calculated distance of an operational coefficient associated with the storage drive exceeds a distance value from a cluster of the cluster plot.

First claim

We claim:

1. A method for operating a telecommunications network, the method comprising:
receiving operational data from a plurality of storage drives of a storage server of a telecommunications network;
deriving a plurality of operational coefficients for each of the plurality of storage drives based on the operational data;
generating a cluster plot comprising the plurality of operational coefficients for each of the plurality of storage drives;
calculating a distance between a subset of each operational coefficient of the plurality of operational coefficients of the cluster plot;
determining a type of remedial action based on the distance between a subset of operational coefficients of the cluster plot; and
initiating a remedial action of the determined type of remedial action on a storage drive of the plurality of storage drives when a calculated distance of an operational coefficient associated with the storage drive exceeds a distance value from a cluster of the cluster plot.

2. The method of claim 1 , further comprising:
obtaining operational data from a model storage drive; and
calculating a plurality of operational coefficients for the model storage drive, wherein the cluster plot further comprises a plot of the plurality of operational coefficients for the model storage drive.

3. The method of claim 2 , further comprising:
calculating a distance between each of the plurality of operational coefficients of the cluster plot and the plurality of operational coefficients for the model storage drive,
wherein the remedial action is based at least on a calculated distance between a particular operational coefficient for at least one storage drive and at least one of the plurality of operational coefficients for the model storage drive.

4. The method of claim 1 , wherein the type of remedial action is at least one of reformatting, resetting, or taking offline one of the plurality of storage drives.

5. The method of claim 1 , wherein the operational data is one or more of transactions per second, average wait time to execute a read or write to the storage drive, an average request size, number of write requests, number of read requests, or percentage of utilization of the storage drive.

6. The method of claim 1 , wherein deriving the plurality of operational coefficients for each of the plurality of storage drives further comprises adjusting the operational coefficients through one or more machine learning techniques that model a performance of each of the plurality of storage drives.

7. The method of claim 1 , further comprising determining a performance variance of storage device from the plurality of storage devices based on the distance between each operational coefficient from a cluster associated with the plurality of operational coefficients of the cluster plot, the distance indicating a degree of operational disparity from the cluster.

8. A system comprising:
a plurality of storage drives of a storage server; and
a telecommunications network that provides communication between the plurality of storage drives, wherein the telecommunications network:
receives operational data from the plurality of storage drives of the storage server;
derives a plurality of operational coefficients for each of the plurality of storage drives based on the operational data;
generates a cluster plot comprising the plurality of operational coefficients for each of the plurality of storage drives;
calculates a distance between a subset of each operational coefficient of the plurality of operational coefficients of the cluster plot;
determines a type of remedial action based on the distance between a subset of operational coefficients of the cluster plot; and
initiates a remedial action of the type of remedial action on a storage drive of the plurality of storage drives when a calculated distance of an operational coefficient associated with the storage drive exceeds a distance value from a cluster of the cluster plot.

9. The system of claim 8 , wherein the telecommunications network further:
obtains operational data from a model storage drive; and
calculates a plurality of operational coefficients for the model storage drive, wherein the cluster plot further comprises a plot of the plurality of operational coefficients for the model storage drive.

10. The system of claim 8 , wherein the telecommunications network further:
calculates a distance between each of the plurality of operational coefficients of the cluster plot and the plurality of operational coefficients for a model storage drive,
wherein the remedial action is based at least on a calculated distance between a particular operational coefficient for the storage drive and at least one of the operational coefficients for the model storage drive.

11. The system of claim 8 , wherein the type of remedial action is at least one of reformatting, resetting, or taking offline one of the plurality of storage drives.

12. The system of claim 8 , wherein the operational data is one or more of transactions per second, average wait time to execute a read or write to the storage drive, an average request size, number of write requests, number of read requests, or percentage of utilization of the storage drive.

13. The system of claim 8 , wherein deriving the plurality of operational coefficients for each of the plurality of storage drives further comprises adjusting the operational coefficients through one or more machine learning techniques that model a performance of each of the plurality of storage drives.

14. The system of claim 8 , wherein the telecommunications network further determines a performance variance of the storage drive from the plurality of storage drives based on the distance between each operational coefficient from a cluster associated with the plurality of operational coefficients of the cluster plot, the distance indicating a degree of operational disparity from the cluster.

15. A non-transitory computer-readable medium comprising instructions stored thereon, the instructions executable by one or more processors of a computing system to:
receive operational data from a plurality of storage drives of a storage server of a telecommunications network;
derive a plurality of operational coefficients for each of the plurality of storage drives based on the operational data;
generate a cluster plot comprising the plurality of operational coefficients for each of the plurality of storage drives;
calculate a distance between a subset of each operational coefficient of the plurality of operational coefficients of the cluster plot;
determine a type of remedial action based on the distance between a subset of operational coefficients of the cluster plot; and
initiate a remedial action of the type of remedial action on a storage drive of the plurality of storage drives when a calculated distance of an operational coefficient associated with the storage drive exceeds a distance value from a cluster of the cluster plot.

16. The non-transitory computer-readable medium of claim 15 , further comprising instructions executable to:
obtain operational data from a model storage drive; and
calculate a plurality of operational coefficients for the model storage drive, wherein the cluster plot further comprises a plot of the plurality of operational coefficients for the model storage drive.

17. The non-transitory computer-readable medium of claim 15 , further comprising instructions executable to:
calculate a distance between each of the plurality of operational coefficients of the cluster plot and the plurality

Assignees

• Level 3 Communications Llc

Inventors

• Hopkins William
• Gowin Lawrence W

Classifications

• G06F11/0793 Primary

  Remedial or corrective actions (recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40) · CPC title

• H04L41/142 Primary

  using statistical or mathematical methods · CPC title

• G06F3/0619

  in relation to data integrity, e.g. data losses, bit errors · CPC title

• G06F11/079

  Root cause analysis, i.e. error or fault diagnosis (in a hardware test environment G06F11/22; in a software test environment G06F11/36) · CPC title

• G06F11/0754

  by exceeding limits · CPC title