# US 2020/0004434 A1 · Determining when to replace a storage device using a machine learning module

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0004434 A1
- Document ID: US20200004434A1
- Status: Published application
- Kind: A1
- Application number: 16/023,502
- Filed: 2018-06-29
- Published: 2020-01-02
- Earliest claimed: 2018-06-29
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Matthew G. Borlick; Karl A. Nielsen; Clint A. Hardy; Lokesh M. Gupta
- Web page: https://patentgrep.com/patent/US20200004434A1

## CPC

- G06F 3/0616: {in relation to life time, e.g. increasing Mean Time Between Failures [MTBF]}
- G06F 3/0619: {in relation to data integrity, e.g. data losses, bit errors}
- G06F 3/0653: {Monitoring storage devices or systems}
- G06F 3/0683: {Plurality of storage devices}
- G06F 11/004: {Error avoidance (G06F11/07 and subgroups take precedence)}
- G06F 11/008: {Reliability or availability analysis}
- G06F 11/0727: {in a storage system, e.g. in a DASD or network based storage system (drivers for digital recording or reproducing units G06F3/06; circuits for error detection or correction within digital recording or reproducing units G11B20/18; for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS], H04L67/1097)}
- G06F 11/0751: {Error or fault detection not based on redundancy (power supply failures G06F1/30; network fault management H04L41/06)}
- G06F 11/0769: {Readable error formats, e.g. cross-platform generic formats, human understandable formats}
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 20/00: Machine learning
- G06F 11/3034: {where the computing system component is a storage system, e.g. DASD based or network based (digital input from or digital output to record carriers G06F3/06; digital recording or reproducing G11B20/18; for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS], H04L67/1097)}
- G06F 11/324: {Display of status information}
- G06F 11/3485: {for I/O devices}
- G06F 2201/81: Threshold
- G06F 2201/86: Event-based monitoring
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 5/025: Extracting rules from data
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Provided are a computer program product, system, and method for using a machine learning module to determine when to replace a storage device. Input on attributes of the storage device is provided to a machine learning module to produce an output value. A determination is made whether the output value indicates to replace the storage device. Indication is made to replace the storage device in response to determining that the output value indicates to replace the storage device.

## Claims

### Claim 1

A computer program product for determining when to replace a storage device deployed within a computing environment, the computer program product comprising a computer readable storage medium storing computer readable program code that when executed performs operations, the operations comprising:
providing input on attributes of the storage device to a machine learning module to produce an output value;
determining whether the output value indicates to replace the storage device; and
indicating to replace the storage device in response to determining that the output value indicates to replace the storage device.

### Claim 2 (depends on 1)

The computer program product of claim 1, wherein the operations further comprise:
detecting an event at the storage device, wherein the input on the attributes is provided to the machine learning module in response to detecting the event.

### Claim 3 (depends on 2)

The computer program product of claim 2, wherein the event comprises an error at the storage device.

### Claim 4 (depends on 2)

The computer program product of claim 2, wherein the event comprises detecting that a measured age of the storage device comprises a predetermined percentage of an expected lifetime of the storage device.

### Claim 5 (depends on 1)

The computer program product of claim 1, wherein the providing the input on attributes of the storage device comprises periodically providing the input to the machine learning module to periodically produce the output value based on a time interval.

### Claim 6

A computer program product for determining when to replace a storage device deployed within a computing environment, the computer program product comprising a computer readable storage medium storing computer readable program code that when executed performs operations, the operations comprising:
providing input on dynamic operating conditions of the storage device to a machine learning module to produce an indication of an expected remaining lifespan of the storage device;
determining whether the expected remaining life indicates to replace the storage device; and
indicating to replace the storage device in response to determining that the expected remaining life indicates to replace the storage device.

### Claim 7 (depends on 6)

The computer program product of claim 6, wherein the expected remaining lifespan comprises at least one of a time value, a number of write cycles, and number of writes per time period.

### Claim 8 (depends on 1)

The computer program product of claim 1, wherein the attributes used as the input to the machine learning module include a plurality of:
a response time to respond to read and write requests to the storage device;
a response time to respond to read and write requests to a storage array including the storage device;
for each of at least one error type, a number of errors of the error type in a specified time interval;
a type of the storage device;
a manufacturer of the storage device;
a storage capacity of the storage device;
a time of first use of the storage device;
a firmware level of the storage device;
a read operations per second at the storage device;
an expected remaining lifespan of the storage device; and
write operations per second at the storage device.

### Claim at position 9

9-14. (canceled)

### Claim 15

A system for determining when to replace a storage device, comprising:
a processor; and
a computer readable storage medium storing computer readable program code that when executed by the processor performs operations, the operations comprising:
providing input on attributes of the storage device to a machine learning module to produce an output value;
determining whether the output value indicates to replace the storage device; and
indicating to replace the storage device in response to determining that the output value indicates to replace the storage device.

### Claim 16 (depends on 15)

The system of claim 15, wherein the operations further comprise:
detecting an event at the storage device, wherein the input on the attributes is provided to the machine learning module in response to detecting the event.

### Claim at position 12

17-20. (canceled)

### Claim 21

A computer implemented method performed in a computer system for determining when to replace a storage device deployed within a computing environment, comprising:
providing input on attributes of the storage device to a machine learning module to produce an output value;
determining whether the output value indicates to replace the storage device; and
indicating to replace the storage device in response to determining that the output value indicates to replace the storage device.

### Claim 22 (depends on 21)

The method of claim 21, further comprising:
detecting an event at the storage device, wherein the input on the attributes is provided to the machine learning module in response to detecting the event.

### Claim at position 15

23-26. (canceled)

### Claim 27 (depends on 16)

The system of claim 16, wherein the event comprises an error at the storage device.

### Claim 28 (depends on 16)

The system of claim 16, wherein the event comprises detecting that a measured age of the storage device comprises a predetermined percentage of an expected lifetime of the storage device.

### Claim 29 (depends on 15)

The system of claim 15, wherein the providing the input on attributes of the storage device comprises periodically providing the input to the machine learning module to periodically produce the output value based on a time interval.

### Claim 30 (depends on 15)

The system of claim 15, wherein the attributes used as the input to the machine learning module include a plurality of:
a response time to respond to read and write requests to the storage device;
a response time to respond to read and write requests to a storage array including the storage device;
for each of at least one error type, a number of errors of the error type in a specified time interval;
a type of the storage device;
a manufacturer of the storage device;
a storage capacity of the storage device;
a time of first use of the storage device;
a firmware level of the storage device;
a read operations per second at the storage device;
an expected remaining lifespan of the storage device; and
write operations per second at the storage device.

### Claim 31

A computer program product for determining when to replace a storage device deployed within a computing environment, the computer program product comprising a computer readable storage medium storing computer readable program code that when executed performs operations, the operations comprising:
providing input on dynamic operating conditions of the storage device to a machine learning module to produce an indication of an expected remaining lifespan of the storage device;
determining whether the expected remaining life indicates to replace the storage device; and
indicating to replace the storage device in response to determining that the expected remaining life indicates to replace the storage device.

### Claim 32 (depends on 31)

The computer program product of claim 31, wherein the expected remaining lifespan comprises at least one of a time value, a number of write cycles, and number of writes per time period.

### Claim 33 (depends on 21)

The method of claim 21, wherein the event comprises an error at the storage device.

### Claim 34 (depends on 22)

The method of claim 22, wherein the event comprises detecting that a measured age of the storage device comprises a predetermined percentage of an expected lifetime of the storage device.

### Claim 35 (depends on 21)

The method of claim 21, wherein the providing the input on attributes of the storage device comprises periodically providing the input to the machine learning module to periodically produce the output value based on a time interval.

### Claim 36 (depends on 21)

The method of claim 21, wherein the attributes used as the input to the machine learning module include a plurality of:
a response time to respond to read and write requests to the storage device;
a response time to respond to read and write requests to a storage array including the storage device;
for each of at least one error type, a number of errors of the error type in a specified time interval;
a type of the storage device;
a manufacturer of the storage device;
a storage capacity of the storage device;
a time of first use of the storage device;
a firmware level of the storage device;
a read operations per second at the storage device;
an expected remaining lifespan of the storage device; and
write operations per second at the storage device.

### Claim 37

A method for determining when to replace a storage device deployed within a computing environment, comprising:
providing input on dynamic operating conditions of the storage device to a machine learning module to produce an indication of an expected remaining lifespan of the storage device;
determining whether the expected remaining life indicates to replace the storage device; and
indicating to replace the storage device in response to determining that the expected remaining life indicates to replace the storage device.

### Claim 38 (depends on 37)

The method of claim 37, wherein the expected remaining lifespan comprises at least one of a time value, a number of write cycles, and number of writes per time period.
