US 11,886,720 B2Granted

Determining storage system configuration recommendations based on vertical sectors and size parameters using machine learning techniques

AssigneeEMC IP Holding Company LLC

InventorsShou-Huey Jiang, Bina K. Thakkar, Deepak Gowda

Life of this patent

Estimating the term…

Loading patent…

Abstract

Methods, apparatus, and processor-readable storage media for determining storage system configuration recommendations based on vertical sectors and size parameters using machine learning techniques are provided herein. An example computer-implemented method includes obtaining data pertaining to multiple storage systems; segmenting, into one or more segments, the multiple storage systems based on one or more vertical sectors and one or more size parameters of an enterprise associated with each storage system; identifying, within each of the segments, each storage system running one or more vertical sector-specific applications; clustering, within each of the segments, the storage systems running one or more vertical sector-specific applications based on configuration information using at least one machine learning technique; generating one or more storage system configuration templates based on the clustering; and performing one or more automated actions based on the one or more generated storage system configuration templates.

Claims20

Dependent claims

A computer-implemented method comprising:

obtaining data pertaining to multiple storage systems;
separating, into two or more segments, the multiple storage systems based at least in part on one or more vertical sectors of an enterprise associated with each storage system, wherein separating based at least in part on one or more vertical sectors of an enterprise comprises deriving vertical sector information associated with the enterprise using identifying information, attributed to the enterprise, which corresponds to multiple aspects of enterprise operations;
filtering, from each of the two or more segments, each storage system that does not meet at least one of one or more size-related parameter thresholds corresponding to the enterprise associated with the storage system, wherein the one or more size-related parameter thresholds comprise at least one of a storage capacity-related threshold, a storage system performance-related threshold, and an enterprise resources-related threshold;
identifying, within each of the two or more filtered segments, each storage system running one or more vertical sector-specific applications;
clustering, within each of the two or more filtered segments, the storage systems running one or more vertical sector-specific applications based at least in part on configuration information using at least one machine learning technique in conjunction with one or more di stance calculations;
generating one or more storage system configuration templates based at least in part on the clustering;
and
performing one or more automated actions based at least in part on the one or more generated storage system configuration templates;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.

6 more elements

A non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes the at least one processing device:

to obtain data pertaining to multiple storage systems;
to separate, into two or more segments, the multiple storage systems based at least in part on one or more vertical sectors of an enterprise associated with each storage system, wherein separating based at least in part on one or more vertical sectors of an enterprise comprises deriving vertical sector information associated with the enterprise using identifying information, attributed to the enterprise, which corresponds to multiple aspects of enterprise operations;
to filter, from each of the two or more segments, each storage system that does not meet at least one of one or more size-related parameter thresholds corresponding to the enterprise associated with the storage system, wherein the one or more size-related parameter thresholds comprise at least one of a storage capacity-related threshold, a storage system performance-related threshold, and an enterprise resources-related threshold;
to identify, within each of the two or more filtered segments, each storage system running one or more vertical sector-specific applications;
to cluster, within each of the two or more filtered segments, the storage systems running one or more vertical sector-specific applications based at least in part on configuration information using at least one machine learning technique in conjunction with one or more di stance calculations;
to generate one or more storage system configuration templates based at least in part on the clustering;
and
to perform one or more automated actions based at least in part on the one or more generated storage system configuration templates.

5 more elements

An apparatus comprising:

at least one processing device comprising a processor coupled to a memory;
the at least one processing device being configured:
to obtain data pertaining to multiple storage systems;
to separate, into two or more segments, the multiple storage systems based at least in part on one or more vertical sectors of an enterprise associated with each storage system, wherein separating based at least in part on one or more vertical sectors of an enterprise comprises deriving vertical sector information associated with the enterprise using identifying information, attributed to the enterprise, which corresponds to multiple aspects of enterprise operations;
to filter, from each of the two or more segments, each storage system that does not meet at least one of one or more size-related parameter thresholds corresponding to the enterprise associated with the storage system, wherein the one or more size-related parameter thresholds comprise at least one of a storage capacity-related threshold, a storage system performance-related threshold, and an enterprise resources-related threshold;
to identify, within each of the two or more filtered segments, each storage system running one or more vertical sector-specific applications;
to cluster, within each of the two or more filtered segments, the storage systems running one or more vertical sector-specific applications based at least in part on configuration information using at least one machine learning technique in conjunction with one or more di stance calculations;
to generate one or more storage system configuration templates based at least in part on the clustering;
and
to perform one or more automated actions based at least in part on the one or more generated storage system configuration templates.

7 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/929,271Filed 15 Jul 2020
Published: US 2022/0019358 A120 Jan 2022
Granted: 30 Jan 2024
Term ends: Not estimatedThe source records don’t support an estimate.

Classification8 codes

G06F 3/0629
Making use of a particular technique: configuration or reconfiguration of storage systems
G06F 3/0604
Specifically adapted to achieve a particular effect: improving or facilitating administration, e.g. storage management
G06F 3/0653
Making use of a particular technique: monitoring storage devices or systems
G06F 3/067
Adopting a particular infrastructure: distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]