# US 2009/0276388 A1 · System and method of load balancing using fuzzy logic

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

- Number: US 2009/0276388 A1
- Document ID: US20090276388A1
- Status: Published application
- Kind: A1
- Application number: 12/419,622
- Filed: 2009-04-07
- Published: 2009-11-05
- Earliest claimed: 2007-01-09
- Assignees: International Business Machines Corporation
- Inventors: Elizabeth A. DONOHUE; Michael P. OUTLAW; Ken S. SOHAL; Matthew B. TREVATHAN
- Web page: https://patentgrep.com/patent/US20090276388A1

## CPC

- G06F 9/505: {considering the load}
- G06F 2209/5022: Workload threshold
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A system and method of load balancing using fuzzy logic and, more particularly, to a system and method of load balancing tasks over a grid environment including, for example, CPU utilization, traffic over a network and other functions. The method comprises defining cause and effect relations associated with input variables and output variables. A current utilization is assessed. The method further includes determining which cause and effect relations are associated with the current utilization and calculating a weighted balancing factor for the cause and effect relations having membership with the utilization. A load is balanced using the weighted balancing factor.

## Claims

### Claim 1

A method, comprising:
defining cause and effect relations associated with input variables and output variables;
assessing a current utilization using a processor of a management system;
determining which cause and effect relations are associated with the current utilization using the processor of the management system;
calculating a weighted balancing factor for the cause and effect relations having membership with the utilization using the processor of the management system; and
balancing a load using the weighted balancing factor using the processor of the management system.

### Claim 2 (depends on 1)

The method of claim 1, wherein the cause and effect relations are user defined.

### Claim 3 (depends on 1)

The method of claim 1, wherein the cause and effect relations are linguistic statements.

### Claim 4 (depends on 3)

The method of claim 3, wherein the cause and effect relations are defined by numerical values associated with the linguistic statements.

### Claim 5 (depends on 1)

The method of claim 1, wherein the balancing is performed at predefined intervals.

### Claim 6 (depends on 1)

The method of claim 1, wherein the balancing is overridden based on priority of a job.

### Claim 7 (depends on 1)

The method of claim 1, wherein the steps of claim 1 are provided by a service provider.

### Claim 8 (depends on 1)

The method of claim 1, wherein a service provider at least one of creates, maintains and supports a computer infrastructure that performs the steps of claim 1.

### Claim 9 (depends on 1)

The method of claim 1, wherein the steps of claim 1 are provided on a subscription, advertising, and/or fee basis.

### Claim 10 (depends on 1)

The method of claim 1, wherein at least the defining step is implemented using fuzzy logic.

### Claim 11 (depends on 10)

The method of claim 10, wherein the fuzzy logic is implemented on computer elements using at least one of processor feedback, packet profiling, and I/O monitoring.

### Claim 12 (depends on 10)

The method of claim 10, wherein the fuzzy logic uses information that is not precisely defined and creates a definable precise value for the weighted balancing factor.

### Claim 13 (depends on 1)

The method of claim 1, wherein the steps of claim 1 are configured to balance network traffic.

### Claim 14 (depends on 1)

The method of claim 1, wherein the cause and effect relations are given a value between 0 and 1.

### Claim 15 (depends on 1)

The method of claim 1, wherein the cause and effect relations are if-then rules.

### Claim 16 (depends on 15)

The method of claim 15, wherein the if-then rules have ranges.

### Claim 17 (depends on 1)

The method of claim 1, wherein the cause and effect relations are defined geometrically using shapes.

### Claim 18 (depends on 17)

The method of claim 17, wherein the shapes are overlapping equilateral triangles representative of the input variables and output variables.

### Claim 19 (depends on 18)

The method of claim 18, wherein the overlapping is a hedge defined as start points and end points.

### Claim 20 (depends on 19)

The method of claim 19, further comprising determining an intersection between at least two of the equilateral triangles associated with an output defining the current utilization.

### Claim 21 (depends on 20)

The method of claim 20, wherein the intersection forms two additional triangles used in the calculating of the weighted balancing factor.

### Claim 22 (depends on 21)

The method of claim 21, further comprising calculating a height of the two additional triangles by bisecting at least two of the equilateral triangles to form congruent triangles with the two additional triangles and using, in part, ratios between the congruent triangles.

### Claim 23 (depends on 22)

The method of claim 22, wherein the height of the two additional triangles is used to adjust a height of overlapping output triangles which are in the membership with the bisected at least two of the equilateral triangles.

### Claim 24 (depends on 23)

The method of claim 23, wherein the weighted balancing factor is calculated by finding a point that balances areas of the adjusted overlapping output triangles.

### Claim 25 (depends on 24)

The method of claim 24, wherein the point is associated with a value which is added to or subtracted from the current utilization to provide a precise value for the weighted balancing factor.
