# US 10,373,072 B2 · Cognitive-based dynamic tuning

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

- Number: US 10,373,072 B2
- Document ID: US10373072B2
- Status: Granted
- Kind: B2
- Application number: 14/991,063
- Filed: 2016-01-08
- Published: 2017-07-13
- Granted: 2019-08-06
- Earliest claimed: 2016-01-08
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Diane Britton; Reza Ghasemi; Chon N. Lei; Robert Maher; Vanessa V. Michelini
- Web page: https://patentgrep.com/patent/US10373072B2

## CPC

- G06F 11/3409: {for performance assessment}
- G06F 8/60: Software deployment
- G06F 8/65: Updates (security arrangements therefor G06F21/57)
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method, system, and computer program product for performing cognitive-based dynamic tuning of a software-based system include monitoring live operation of the system, and determining whether tuning is needed based on the monitoring. Analyzing information and suggesting a change in one or more parameters is based on the determining, the information including an output of a learning algorithm that learns an effect of changes in one or more of the one or more parameters on performance of the system.

## Claims

### Claim 1

A computer-implemented method of performing cognitive-based dynamic tuning of a software-based system, the method comprising:
monitoring, using a processor, live operation of the system;
determining whether tuning of the system is needed based on the monitoring;
analyzing information and suggesting a change in one or more parameters of the system based on the determining using the processor, the information including an output of a learning algorithm that learns an effect of changes in one or more of the one or more parameters on performance of the system; and
implementing the change in the one or more parameters of the system and checking the performance of the system based on the suggesting the change in the one or more parameters.

### Claim 2 (depends on 1)

The computer-implemented method according to claim 1, further comprising determining if the change in the one or more parameters is possible prior to the implementing the change.

### Claim 3 (depends on 2)

The computer-implemented method according to claim 2, further comprising providing a message to a local system administrator when the change in the one or more parameters is not possible.

### Claim 4 (depends on 1)

The computer-implemented method according to claim 1, further comprising the learning algorithm learning the effect of the change in the one or more parameters on the performance of the system.

### Claim 5 (depends on 1)

The computer-implemented method according to claim 1, further comprising undoing the change in the one or more parameters based on the checking indicating that the performance of the system is degraded based on the change.

### Claim 6 (depends on 1)

The computer-implemented method according to claim 1, wherein the analyzing the information and the suggesting the change include analyzing operational directives set by an administrator that limit the change in the one or more parameters.

### Claim 7 (depends on 1)

The computer-implemented method according to claim 1, wherein the analyzing the information includes analyzing historical information and real-time information about the performance of the system.

### Claim 8

A system to perform cognitive-based dynamic tuning, the system comprising:
a memory device configured to store operational directives set by an administrator; and
a processor configured to monitor live operation of the system, determine whether tuning of the system is needed based on the monitoring, and analyze information and suggest a change in one or more parameters of the system based on determining that the system requires tuning, the information including an output of a learning algorithm that learns an effect of changes in one or more of the one or more parameters on performance of the system and the operational directives that limit the change in the one or more parameters, wherein the processor implements the change in the one or more parameters of the system and checks the performance of the system based on suggesting the change in the one or more parameters.

### Claim 9 (depends on 8)

The system according to claim 8, wherein the processor determines if the change in the one or more parameters is possible prior to implementing the change, and provides a message to the administrator when the change in the one or more parameters is not possible.

### Claim 10 (depends on 8)

The system according to claim 8, wherein the learning algorithm learns the effect of the change in the one or more parameters on the performance of the system.

### Claim 11 (depends on 8)

The system according to claim 8, wherein the processor undoes the change in the one or more parameters based on the performance of the system being degraded based on the change.

### Claim 12 (depends on 8)

The system according to claim 8, wherein the information includes historical information and real-time information about the performance of the system.

### Claim 13

A computer program product for performing cognitive-based dynamic tuning of a software-based system, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to perform a method comprising:
monitoring live operation of the system;
determining whether tuning of the system is needed based on the monitoring;
analyzing information and suggesting a change in one or more parameters of the system based on the determining, the information including an output of a learning algorithm that learns an effect of changes in one or more of the one or more parameters on performance of the system; and
implementing the change in the one or more parameters of the system and checking the performance of the system based on the suggesting the change in the one or more parameters.

### Claim 14 (depends on 13)

The computer program product according to claim 13, further comprising determining if the change in the one or more parameters is possible prior to the implementing the change and providing a message to a local system administrator when the change in the one or more parameters is not possible.

### Claim 15 (depends on 13)

The computer program product according to claim 13, further comprising the learning algorithm learning the effect of the change in the one or more parameters on the performance of the system.

### Claim 16 (depends on 13)

The computer program product according to claim 13, further comprising undoing the change in the one or more parameters based on the checking indicating that the performance of the system is degraded based on the change.

### Claim 17 (depends on 13)

The computer program product according to claim 13, wherein the analyzing the information and the suggesting the change include analyzing operational directives set by an administrator that limit the change in the one or more parameters, and the analyzing the information further includes analyzing historical information and real-time information about the performance of the system.
