# US 2022/0027371 A1 · Load balancing in streams parallel regions

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

- Number: US 2022/0027371 A1
- Document ID: US20220027371A1
- Status: Published application
- Kind: A1
- Application number: 16/935,427
- Filed: 2020-07-22
- Published: 2022-01-27
- Earliest claimed: 2020-07-22
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Henry Chiu; Bradley William Fawcett; Jingdong SUN; Jason A. Nikolai; Paul Gerver
- Web page: https://patentgrep.com/patent/US20220027371A1

## CPC

- G06F 16/24568: {Data stream processing; Continuous queries}
- H04L 65/80: Responding to QoS
- G06F 9/5083: {Techniques for rebalancing the load in a distributed system}
- G06F 16/24532: {of parallel queries}
- H04L 47/125: by balancing the load, e.g. traffic engineering
- H04L 65/60: Network streaming of media packets
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

In response to receiving a flow of data, one or more operators in a parallel region included in a distributed data processing system for stream processing the flow of data are initialized. In response to identifying a change to the flow of data or a change to the distributed data processing system, at least one of the flow of data and a size of the parallel region included in the distributed data processing system are dynamically adjusted. The flow of data is processed via the dynamically adjusted one of the flow of data and the parallel region included in the distributed data processing system.

## Claims

### Claim 1

A method, the method comprising:
responsive to determining a rate of a flow of data, initializing, by one or more computer processors, one or more operators in a parallel region included in a distributed data processing system for stream processing of the flow of data based on the determined rate;
responsive to identifying a change in the flow of data or a change in the distributed data processing system, dynamically adjusting, by one or more computer processors, the flow of data in the distributed data processing system; and
processing, by one or more computer processors, the flow of data via the dynamically adjusted flow of data in the distributed data processing system.

### Claim 2

(canceled)

### Claim 3 (depends on 1)

The method of claim 1, wherein the step of dynamically adjusting, by one or more computer processors, the flow of data in the distributed data processing system, comprises:
dynamically adjusting, by one or more computer processors, the flow of data between the one or more operators in the parallel region to balance a load of the flow of data.

### Claim 4 (depends on 1)

The method of claim 1, wherein the step of dynamically adjusting, by one or more computer processors, the flow of data in the distributed data processing system, comprises:
achieving, by one or more computer processors, a highest data rate to the parallel region.

### Claim 5 (depends on 1)

The method of claim 1, wherein the step of dynamically adjusting, by one or more computer processors, the flow of data in the distributed data processing system, comprises:
responsive to a reduction in one or more computing resources included in the distributed data processing system, dynamically throttling, by one or more computer processors, the flow of data in the distributed data processing system.

### Claim 6 (depends on 1)

The method of claim 1, wherein the step of dynamically adjusting, by one or more computer processors, the flow of data in the distributed data processing system, comprises:
responsive to receiving a higher priority flow of data, queuing, by one or more computer processors, one or more data tuples which comprise the higher priority flow of data over one or more other flows of data.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
dynamically learning, by one or more computer processors, a plurality of load balancing methodologies via machine learning techniques based on a plurality of distributed data processing scenarios; and
applying, by one or more computer processors, one of the plurality of learned load balancing methodologies for a specific distributed data processing scenarios that is best able to process the flow of data in the specific distributed data processing scenario.

### Claim 8 (depends on 1)

The method of claim 1, wherein the step of dynamically adjusting, by one or more computer processors, the flow of data in the distributed data processing system, comprises:
responsive to a failover, transmitting, by one or more computer processors, the flow of data to a redundant distributed data processing system; and
responsive to a failback, restoring, by one or more computer processors, the flow a data to the distributed data processing system.

### Claim 9 (depends on 1)

The method of claim 1, wherein the step of dynamically adjusting, by one or more computer processors, the flow of data in the distributed data processing system, comprises:
responsive to a change in a quantity of operators in the parallel region, dynamically adjusting, by one or more computer processors, the flow of data to the parallel region, wherein:
responsive to an increase in the quantity of operators, increase the flow of data; and
responsive to a decrease in the quantity of operators, decrease the flow of data.

### Claim 10

A computer program product, the computer program product comprising:
one or more computer readable storage media; and
program instructions stored on the one or more computer readable storage media, the program instructions comprising:
responsive to determining a flow of data, program instructions to initialize one or more operators in a parallel region included in a distributed data processing system for stream processing of the flow of data based on the determined rate;
responsive to identifying a change in the flow of data or a change in the distributed data processing system, program instructions to dynamically adjust the flow of data in the distributed data processing system; and
program instructions to process the flow of data via the dynamically adjusted flow of data in the distributed data processing system.

### Claim 11

(canceled)

### Claim 12 (depends on 10)

The computer program product of claim 10, wherein the program instructions to dynamically adjust the flow of data in the distributed data processing system, comprise:
program instructions to dynamically adjust the flow of data between the one or more operators in the parallel region to balance a load of the flow of data.

### Claim 13 (depends on 10)

The computer program product of claim 10, wherein the program instructions to dynamically adjust the flow of data in the distributed data processing system, comprise:
program instructions to achieve a highest data rate to the parallel region.

### Claim 14 (depends on 10)

The computer program product of claim 10, wherein the program instructions to dynamically adjust the flow of data in the distributed data processing system, comprise:
responsive to a reduction in one or more computing resources included in the distributed data processing system, program instructions to dynamically throttle the flow of data in the distributed data processing system.

### Claim 15 (depends on 10)

The computer program product of claim 10, wherein the program instructions to dynamically adjust the flow of data in the distributed data processing system, comprise:
responsive to receiving a higher priority flow of data, program instructions to queue one or more data tuples which comprise the higher priority flow of data over one or more other flows of data.

### Claim 16 (depends on 10)

The computer program product of claim 10, further comprising program instructions stored on the one or more computer readable storage media, to:
dynamically learn a plurality of load balancing methodologies via machine learning techniques based on a plurality of distributed data processing scenarios; and
apply one of the plurality of learned load balancing methodologies for a specific distributed data processing scenarios that is best able to process the flow of data in the specific distributed data processing scenario.

### Claim 17 (depends on 10)

The computer program product of claim 10, wherein the program instructions to dynamically adjust the flow of data in the distributed data processing system, comprise:
responsive to a failover, program instructions to transmit the flow of data to a redundant distributed data processing system; and
responsive to a failback, program instructions to restore the flow a data to the distributed data processing system.

### Claim 18 (depends on 10)

The computer program product of claim 10, wherein the program instructions to dynamically adjust the flow of data in the distributed data processing system, comprise:
responsive to a change in a quantity of operators in the parallel region, program instructions to dynamically adjust the flow of data to the parallel region, wherein:
responsive to an increase in the quantity of operators, the flow of data is increased; and
responsive to a decrease in the quantity of operators, the flow of data is decreased.

### Claim 19

A computer system, the computer system comprising:
one or more computer processors;
one or more computer readable storage media; and
program instructions stored on the one or more computer readable storage media for execution by the one or more computer processors, the program instructions comprising:
responsive to determining a flow of data, program instructions to initialize one or more operators in a parallel region included in a distributed data processing system for stream processing of the flow of data based on the determined rate;
responsive to identifying a change in the flow of data or a change in the distributed data processing system, program instructions to dynamically adjust the flow of data in the distributed data processing system; and
program instructions to process the flow of data via the dynamically adjusted flow of data in the distributed data processing system.

### Claim 20

(canceled)
