# US 2023/0145526 A1 · Predict new system status based on status changes

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

- Number: US 2023/0145526 A1
- Document ID: US20230145526A1
- Status: Published application
- Kind: A1
- Application number: 17/453,712
- Filed: 2021-11-05
- Published: 2023-05-11
- Earliest claimed: 2021-11-05
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Juergen Holtz; Andreas Stay; Alexander Terekhov; Elena Lopez De Dicastillo
- Web page: https://patentgrep.com/patent/US20230145526A1

## CPC

- G05B 23/0243: {model based detection method, e.g. first-principles knowledge model}
- H04L 41/145: {involving simulating, designing, planning or modelling of a network}
- G05B 13/048: {using a predictor}
- G06F 11/34: Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation {; Recording or statistical evaluation of user activity, e.g. usability assessment}
- H04L 41/149: for prediction of maintenance
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A computer-implemented method for predicting an effect of an intervention on managed computing resources using a first system automation management system, comprising an automated operations controller and at least one automation agent is disclosed. The method comprises sending initial state data of the first system automation management system to a second system automation management system which is a functional duplicate of the first system automation management system, sending a status change command and a related expected response vector, equivalent to a result of the intervention to the second system automation management system, determining, by the second system automation management system, a predicted response vector of the managed computing resources in response to the received status change command, and responding, by the second system automation management system, with the determined response vector and a set of predicted actions derived therefrom.

## Claims

### Claim 1

A computer-implemented method for predicting an effect of an intervention on a managed computing resources using a first system automation management system including an automated operations controller and at least one automation agent, the method comprising:
sending initial state data of the first system automation management system to a second system automation management system which is a functional duplicate of the first system automation management system;
sending a status change command and a related expected response vector, equivalent to a result of the intervention to the second system automation management system;
determining, by the second system automation management system, a predicted response vector of the managed computing resources in response to the received status change command; and
responding, by the second system automation management system, with the determined response vector and a set of predicted actions derived therefrom.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the intervention is a status change to the managed computing resources or a detected unexpected result from the at least one automation agent of the first system automation management system.

### Claim 3 (depends on 1)

The method according to claim 1, wherein the expected response vector and/or the predicted response vector is indicative for a current or future behavior of a set of resources of the first system automation management system.

### Claim 4 (depends on 1)

The method according to claim 1, wherein a managed computing resource is at least one selected out of the group comprising a process being executed on a hardware device, a hardware device and a sub-component thereof.

### Claim 5 (depends on 1)

The method according to claim 1, wherein the initial state data are derived from a snapshot of a current status of the first system automation management system.

### Claim 6 (depends on 1)

The method according to claim 1, wherein the set of predicted actions is indicative for operational commands to the managed computing resources.

### Claim 7 (depends on 1)

The method according to claim 1, wherein the expected response vector is a NULL vector.

### Claim 8 (depends on 1)

The method according to claim 1, wherein the expected response vector and the determined response vector is each a matrix representing different pretended or final outcomes for each resource, wherein each element of the matrix relates to a resource.

### Claim 9 (depends on 1)

The method according to claim 1, wherein the first system automation management system continues operation without any impact from the sending the status change and the related response vector to the second system automations management system.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
streaming continuously the current state of the first system automation management system to the second system automation management system.

### Claim 11 (depends on 1)

The method of claim 1, wherein the response vector is a matrix representing a sequence of response vectors in time.

### Claim 12

A predicting system for predicting an effect of an intervention on managed computing resources using a first system automation management system, comprising an automated operations controller and at least one automation agent, the predicting system comprising:
a processor set; and
a computer readable storage medium;
wherein:
the processor set is structured, located, connected, and/or programmed to run program instructions stored on the computer readable storage medium; and
the program instructions which, when executed by the processor set, cause the processor set to predict an effect of an intervention on managed computing resources by:
sending initial state data of the first system automation management system to a second system automation management system which is a functional duplicate of the first system automation management system;
sending a status change command and a related expected response vector, equivalent to a result of the intervention to the second system automation management system;
determining, by the second system automation management system, a predicted response vector of the managed computing resources in response to the received status change command; and
responding, by the second system automation management system, with the determined response vector and a set of predicted actions derived therefrom.

### Claim 13 (depends on 12)

The predicting system according to claim 12, wherein the intervention is a status change to the managed computing resources or a detected unexpected result from the at least one automation agent of the first system automation management system.

### Claim 14 (depends on 12)

The predicting system according to claim 12, wherein the expected response vector and/or the predicted response vector is indicative for a current or future behavior of a set of resources of the first system automation management system.

### Claim 15 (depends on 12)

The predicting system according to claim 12, wherein a managed computing resource is at least one selected out of the group comprising a process being executed on a hardware device, a hardware device and a sub-component thereof.

### Claim 16 (depends on 12)

The predicting system according to claim 12, wherein the initial state data are derived from a snapshot of a current status of the first system automation management system.

### Claim 17 (depends on 12)

The predicting system according to claim 12, wherein the set of predicted actions is indicative for operational commands to the managed computing resources.

### Claim 18 (depends on 12)

The predicting system according to claim 12, wherein the expected response vector is a NULL vector.

### Claim 19 (depends on 12)

The predicting system according to claim 12, wherein the expected response vector and the determined response vector is each a matrix representing different pretended or final outcomes for each resource, wherein each element of the matrix relates to a resource.

### Claim 20

A computer program product for predicting an effect of an intervention on a managed computing resources using a first system automation management system, comprising an automated operations controller and at least one automation agent, the computer program product comprising a computer-readable storage medium having a set of instructions stored therein which, when executed by a processor, causes the processor to predict an effect of an intervention on a managed computing resource by:
sending initial state data of the first system automation management system to a second system automation management system which is a functional duplicate of the first system automation management system;
sending a status change command and a related expected response vector, equivalent to a result of the intervention to the second system automation management system;
determining, by the second system automation management system, a predicted response vector of the managed computing resources in response to the received status change command; and
responding, by the second system automation management system, with the determined response vector and a set of predicted actions derived therefrom.
