# US 2025/0094239 A1 · Resource management device and resource management method

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

- Number: US 2025/0094239 A1
- Document ID: US20250094239A1
- Status: Published application
- Kind: A1
- Application number: 18/728,895
- Filed: 2022-02-01
- Published: 2025-03-20
- Earliest claimed: 2022-02-01
- Assignees: Mitsubishi Electric Corporation
- Applicants: Mitsubishi Electric Corporation
- Inventors: Yusuke SETO
- Web page: https://patentgrep.com/patent/US20250094239A1

## CPC

- G06F 9/50: Allocation of resources, e.g. of the central processing unit [CPU]
- 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)}
- G06F 9/5011: {the resources being hardware resources other than CPUs, Servers and Terminals}
- G06F 2209/5019: Workload prediction
- G06F 2209/503: Resource availability
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A resource management device includes a data acquiring unit to acquire monitoring data indicating a temporal change in a use amount of a resource used in the past by each of containers included in a node among resources of the node, a prediction unit to predict a temporal change in a use amount of the resource to be used in the future by the container from each of pieces of the monitoring data, and calculate a temporal change in a total use amount of the resource to be used in the future by the containers from the prediction result, and a container deleting unit to delete one of the containers when a timing at which the total use amount of the resource becomes larger than the total of the resources of the node is included in the temporal change in the total use amount of the resource.

## Claims

### Claim 1

A resource management device, comprising:
data acquiring circuitry to acquire monitoring data indicating a temporal change in a use amount of a resource used in a past by each of one or more containers included in a node among at least one resource of the node;
prediction circuitry to predict a temporal change in a use amount of the resource to be used in a future by each of the containers from a corresponding one of pieces of the monitoring data acquired by the data acquiring circuitry, and calculate a temporal change in a total use amount of the resource to be used in the future by the one or more containers from a prediction result of the temporal change; and
container deleting circuitry to delete one of the one or more containers when a timing at which the total use amount of the resource becomes larger than a total of the resource of the node is included in the temporal change in the total use amount of the resource calculated by the prediction circuitry, wherein
the prediction circuitry
predicts, when there is no periodicity in the use amount of the resource used in the past by each of the containers, the temporal change in the use amount of the resource to be used in the future by each of the containers on a basis of a peak value of the use amount of the resource used in the past by a corresponding one of the containers,
the prediction circuitry
calculates, when there is a plurality of containers having no periodicity in the use amount of the resource used in the past among the one or more containers, a correlation coefficient between use amounts of the resource used in the past by the respective plurality of containers, and specifies, when the correlation coefficient is a negative correlation, a container having a highest peak value of the use amount of the resource used in the past among the plurality of containers, and
the total use amount of the resource to be used in the future by the one or more containers includes a use amount of the resource to be used in the future by the specified container and does not include a use amount of the resource to be used in the future by a container other than the specified container among the plurality of containers.

### Claim 2 (depends on 1)

The resource management device according to claim 1, wherein,
the prediction circuitry
detects a period of the use amount of the resource used in the past by each of the containers from the corresponding one of pieces of the monitoring data acquired by the data acquiring circuitry, and predicts the temporal change in the use amount of the resource to be used in the future by each of the containers on a basis of a temporal change in the use amount within the period.

### Claim 3 (depends on 2)

The resource management device according to claim 2, wherein
the prediction circuitry
calculates a plurality of autocorrelation functions having different delay times from each of pieces of the monitoring data acquired by the data acquiring circuitry as an autocorrelation function for the use amount of the resource used in the past by a corresponding one of the containers, and specifies a delay time of an autocorrelation function having a highest positive correlation among the plurality of autocorrelation functions as the period of the use amount.

### Claim at position 4

4-5. (canceled)

### Claim 6 (depends on 1)

The resource management device according to claim 1, wherein
the prediction circuitry
gives the temporal change in the use amount of the resource used in the past by each of the containers to a learning model, and acquires the prediction result of the temporal change in the use amount of the resource to be used in the future by each of the containers from the learning model.

### Claim 7 (depends on 1)

The resource management device according to claim 1, wherein
the prediction circuitry
gives the temporal change in the use amount of the resource used in the past by each of the containers and a temporal change in a use amount of the resource used in the past by a container different from the each of the containers to a learning model, and acquires the prediction result of the temporal change in the use amount of the resource to be used in the future by each of the containers from the learning model.

### Claim 8

A resource management device, comprising:
data acquiring circuitry to acquire monitoring data indicating a temporal change in a use amount of a resource used in a past by each of one or more containers included in a node among at least one resource of the node;
prediction circuitry to predict a temporal change in a use amount of the resource to be used in a future by each of the containers from a corresponding one of pieces of the monitoring data acquired by the data acquiring circuitry, and calculate a temporal change in a total use amount of the resource to be used in the future by the one or more containers from a prediction result of the temporal change; and
container deleting circuitry to delete one of the one or more containers when a timing at which the total use amount of the resource becomes larger than a total of the resource of the node is included in the temporal change in the total use amount of the resource calculated by the prediction circuitry, wherein
the prediction circuitry
extracts a part of data when a state of the node is a same state or when an environment of the node is a same environment from each of one or more pieces of the monitoring data acquired by the data acquiring circuitry, and predicts the temporal change in the use amount of the resource to be used in the future by each of the containers from each part of the data.

### Claim 9

(canceled)

### Claim 10 (depends on 8)

The resource management device according to claim 8, wherein
the prediction circuitry
extracts a part of data when a state of movement of the node is a same state as the part of data when the state of the node is the same state from each of the one or more pieces of the monitoring data acquired by the data acquiring circuitry.

### Claim 11 (depends on 8)

The resource management device according to claim 8, wherein
the prediction circuitry
extracts a part of data when an operating state of the node is a same state as the part of data when the state of the node is the same state from each of the one or more pieces of the monitoring data acquired by the data acquiring circuitry.

### Claim 12 (depends on 8)

The resource management device according to claim 8, wherein
the prediction circuitry
extracts a part of data when a state of another system connected to the node is a same state as the part of data when the state of the node is the same state from each of the one or more pieces of the monitoring data acquired by the data acquiring circuitry.

### Claim 13 (depends on 8)

The resource management device according to claim 8, wherein
the prediction circuitry
extracts a part of data when an environment related to weather around the node is a same environment as the part of data when the environment of the node is the same environment from each of the one or more pieces of the monitoring data acquired by the data acquiring circuitry.

### Claim 14 (depends on 8)

The resource management device according to claim 8, wherein
the prediction circuitry
extracts a part of data when an environment related to a use time of the resource is a same environment as the part of data when the environment of the node is the same environment from each of the one or more pieces of the monitoring data acquired by the data acquiring circuitry.

### Claim 15 (depends on 8)

The resource management device according to claim 8, wherein
the container deleting circuitry
determines, when the timing at which the total use amount of the resource becomes larger than the total of the resource of the node is included in the temporal change in the total use amount of the resource calculated by the prediction circuitry, a container to be deleted on a basis of a use amount of the resource of each of the containers at the timing.

### Claim 16 (depends on 8)

The resource management device according to claim 8, wherein
the container deleting circuitry
determines, when the timing at which the total use amount of the resource becomes larger than the total of the resource of the node is included in the temporal change in the total use amount of the resource calculated by the prediction circuitry, a container to be deleted on a basis of a time at which each of the containers is distributed to the node.

### Claim 17 (depends on 8)

The resource management device according to claim 8, wherein
the container deleting circuitry
determines, when the timing at which the total use amount of the resource becomes larger than the total of the resource of the node is included in the temporal change in the total use amount of the resource calculated by the prediction circuitry, a container to be deleted on a basis of an operation priority of each of the containers.

### Claim 18 (depends on 8)

The resource management device according to claim 8, wherein
the container deleting circuitry
determines, when the timing at which the total use amount of the resource becomes larger than the total of the resource of the node is included in the temporal change in the total use amount of the resource calculated by the prediction circuitry, a container to be deleted on a basis of a use amount of the resource of each of the containers at the timing, a time at which each of the containers is distributed to the node, and an operation priority of each of the containers.

### Claim 19 (depends on 8)

The resource management device according to claim 8, wherein the use amount of the resource of the node is a use rate of a central processing unit (CPU) of the node, a use amount of a memory of the node, a use amount of a storage of the node, a bandwidth use rate of a network connected to the node, or a use rate of a device connected to the node.

### Claim 20

A resource management method comprising:
acquiring monitoring data indicating a temporal change in a use amount of a resource used in a past by each of one or more containers included in a node among at least one resource of the node;
predicting a temporal change in a use amount of the resource to be used in a future by each of the containers from a corresponding one of pieces of the monitoring data, and calculating a temporal change in a total use amount of the resource to be used in the future by the one or more containers from a prediction result of the temporal change;
deleting one of the one or more containers when a timing at which the total use amount of the resource becomes larger than a total of the resource of the node is included in the temporal change in the total use amount of the resource; and
extracting a part of data when a state of the node is a same state or when an environment of the node is a same environment from each of one or more pieces of the monitoring data, and predicting the temporal change in the use amount of the resource to be used in the future by each of the containers from each part of the data.

### Claim 21 (depends on 1)

The resource management device according to claim 1, wherein
the container deleting circuitry
determines, when the timing at which the total use amount of the resource becomes larger than the total of the resource of the node is included in the temporal change in the total use amount of the resource calculated by the prediction circuitry, a container to be deleted on a basis of a time at which each of the containers is distributed to the node.

### Claim 22 (depends on 1)

The resource management device according to claim 1, wherein
the container deleting circuitry
determines, when the timing at which the total use amount of the resource becomes larger than the total of the resource of the node is included in the temporal change in the total use amount of the resource calculated by the prediction circuitry, a container to be deleted on a basis of a use amount of the resource of each of the containers at the timing, a time at which each of the containers is distributed to the node, and an operation priority of each of the containers.
