# US 2019/0317788 A1 · Longevity based computer resource provisioning

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

- Number: US 2019/0317788 A1
- Document ID: US20190317788A1
- Status: Published application
- Kind: A1
- Application number: 15/953,131
- Filed: 2018-04-13
- Published: 2019-10-17
- Earliest claimed: 2018-04-13
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: Willis Lang; Jose Manuel Picado Leiva
- Web page: https://patentgrep.com/patent/US20190317788A1

## CPC

- G06F 9/45558: {Hypervisor-specific management and integration aspects}
- G06F 9/5061: {Partitioning or combining of resources}
- G06F 9/5077: {Logical partitioning of resources; Management or configuration of virtualized resources (specific details on emulation or internal functioning of virtual machines G06F9/455)}
- G06N 20/00: Machine learning
- G06F 2009/45562: {Creating, deleting, cloning virtual machine instances}
- G06F 2009/4557: {Distribution of virtual machine instances; Migration and load balancing}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Computer resources are provisioned for a virtual machine based on expected lifespan. After a request to create a virtual machine is received, the virtual machine can be classified into one of a plurality of longevity classes utilizing a machine learning classifier based on data pertaining to the requestor or the virtual machine. The longevity classes capture different lifespans of the virtual machine between when the virtual machine is created and when the virtual machine is deleted. Subsequently, resources for the virtual machine are provisioned from a hardware resource pool of a set of disjoint resource pools specific to the longevity class of the virtual machine.

## Claims

### Claim 1

A computer resource provisioning system, comprising:
a processor coupled to a memory, the processor configured to execute computer-executable instructions stored in the memory that when executed cause the processor to perform the following actions:
detecting a request to create a virtual machine from a requestor;
classifying the virtual machine into one of a plurality of longevity classes with a machine learning classifier based on data pertaining to one or more of the requestor or the virtual machine, wherein the longevity classes capture different lifespans of the virtual machine between when the virtual machine is created and when the virtual machine is deleted; and
provisioning resources for the virtual machine from a hardware resource pool of a set of disjoint resource pools specific to the longevity class of the virtual machine.

### Claim 2 (depends on 1)

The system of claim 1, the machine learning classifier generates a predictive score and the virtual machine is classified into one of the plurality of longevity classes based on comparison of the predictive score to a threshold.

### Claim 3 (depends on 1)

The system of claim 1, the plurality of longevity classes comprises a long-lived class and a short-lived class based on predetermined times that correspond to each class.

### Claim 4 (depends on 1)

The system of claim 1 further comprising:
detecting a misclassification of a virtual machine based on lifespan; and
updating the machine learning classifier automatically with the misclassification.

### Claim 5 (depends on 4)

The system of claim 4 further comprising migrating resources of a misclassified virtual machine from a first resource pool to a second resource pool, wherein the second resource pool corresponds to a correct longevity class.

### Claim 6 (depends on 1)

The system of claim 1 further comprising classifying a database service implemented by the virtual machine into the one or a plurality of longevity classes.

### Claim 7 (depends on 6)

The system of claim 6 further comprising classifying the database service based on historical actions of the requestor.

### Claim 8 (depends on 6)

The system of claim 6 further comprising classifying the database service based on a name of the database or a size of the database.

### Claim 9 (depends on 1)

They system of claim 1, the machine learning classifier implements a random forest model to classify the virtual machine.

### Claim 10

A method of resource provisioning comprising:
detecting a request to create a virtual machine from a requestor;
classifying the virtual machine into one of a plurality of longevity classes with a machine learning classifier based on data pertaining to one or more of the requestor or the virtual machine, wherein longevity classes capture different predicted lifespans between when the virtual machine is created and when the virtual machine is deleted; and
provisioning resources for the virtual machine from a hardware resource pool disjoint from other resource pools and specific to the longevity class of the virtual machine.

### Claim 11 (depends on 10)

The method of claim 10 further comprising classifying the virtual machine based on a comparison of predictive score produced by the machine learning classifier to a predetermined threshold.

### Claim 12 (depends on 10)

The method of claim 10 further comprising classifying the virtual machine into one of the plurality of longevity classes comprising a short-lived class and a long-lived class based on a predetermined time that corresponds to each class.

### Claim 13 (depends on 10)

The method of claim 10 further comprising:
detecting a misclassification of a virtual machine based on lifespan; and
updating the machine learning classifier automatically based on the misclassification.

### Claim 14 (depends on 13)

The method of claim 13 further comprising moving a misclassified virtual machine to a different longevity class corresponding with its current lifespan.

### Claim 15 (depends on 10)

The method of claim 10 further comprising classifying a database service implemented by the virtual machine into the one of a plurality of longevity classes.

### Claim 16 (depends on 15)

The method of claim 15 further comprising classifying the database service based on at least one of historical actions of the requestor, name of the database, or size of the database provided by the database service.

### Claim 17

A system for provisioning computer resources, comprising:
means for classifying a virtual machine into one of a plurality of longevity classes with a machine learning classifier based on identity of a requestor that requests creation of the virtual machine and features of the virtual machine; and
means for provisioning resources for the virtual machine from a hardware resource pool from a set of disjoint resource pools and designated for the longevity class of the virtual machine.

### Claim 18 (depends on 17)

The system of claim 17, the machine learning classifier further produces a predictive score and the virtual machine is classified into one of the plurality of longevity classes based on comparison the predictive score to a predetermined threshold.

### Claim 19 (depends on 18)

The system of claim 18, the machine learning classifier produces the predictive score further based on at least one of creation time, name of the virtual machine, or size of the virtual machine.

### Claim 20 (depends on 17)

The system of claim 17 further comprising:
means for detecting misclassification of the virtual machine; and
means for migrating virtual machine resources from a first resource pool to a second resource pool correspond to a correct classification of the virtual machine.
