# US 2023/0273665 A1 · Management of performance and power consumption of edge devices

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

- Number: US 2023/0273665 A1
- Document ID: US20230273665A1
- Status: Published application
- Kind: A1
- Application number: 17/682,796
- Filed: 2022-02-28
- Published: 2023-08-31
- Earliest claimed: 2022-02-28
- Assignees: Dell Products L.P.
- Applicants: Dell Products L.P.
- Inventors: Michael Robillard; Amy N. Seibel
- Web page: https://patentgrep.com/patent/US20230273665A1

## CPC

- G06F 1/3209: Monitoring remote activity, e.g. over telephone lines or network connections
- G06F 1/3215: Monitoring of peripheral devices
- G06F 1/3287: by switching off individual functional units in the computer system
- G06F 1/329: by task scheduling
- G06F 9/505: {considering the load}
- G06F 9/5094: {where the allocation takes into account power or heat criteria (power management in computers in general G06F1/3203; thermal management in computers in general G06F1/206)}
- G06F 9/542: {Event management; Broadcasting; Multicasting; Notifications}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Techniques are disclosed for management of edge devices. For example, a method comprises coordinating operation of a plurality of edge devices in a system to process a plurality of workloads. The coordinating of the operation of the plurality of edge devices in the system comprises coordinating one or more times for changing a state of at least a subset of the plurality of edge devices from a first state corresponding to a first level of activity to a second state corresponding to a second level of activity. By way of further example, the coordinating of the operation of the plurality of edge devices in the system may further comprise coordinating one or more times for the processing of the plurality of workloads by at least the subset of the plurality of edge devices in the system.

## Claims

### Claim 1

A method, comprising:
coordinating operation of a plurality of edge devices in a system to process a plurality of workloads;
wherein the coordinating of the operation of the plurality of edge devices in the system comprises coordinating one or more times for changing a state of at least a subset of the plurality of edge devices from a first state corresponding to a first level of activity to a second state corresponding to a second level of activity; and
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.

### Claim 2 (depends on 1)

The method of claim 1, wherein the coordinating of the operation of the plurality of edge devices in the system further comprises coordinating one or more times for the processing of the plurality of workloads by at least the subset of the plurality of edge devices in the system.

### Claim 3 (depends on 1)

The method of claim 1, further comprising buffering a plurality of notifications corresponding to the plurality of workloads for the plurality of edge devices in the system.

### Claim 4 (depends on 3)

The method of claim 3, wherein the plurality of edge devices in the system are configured to retrieve the buffered plurality of notifications.

### Claim 5 (depends on 1)

The method of claim 1, further comprising receiving a plurality of notifications corresponding to the plurality of workloads for the plurality of edge devices in the system, wherein the plurality of notifications comprise one or more of an alarm, a local message notification, a remote message notification, an update notification, and a sensor notification.

### Claim 6 (depends on 1)

The method of claim 1, wherein the coordinating of the operation of the plurality of edge devices in the system is based, at least in part, on increasing a ratio of edge device performance to edge device power dissipation.

### Claim 7 (depends on 1)

The method of claim 1, wherein the coordinating of the operation of the plurality of edge devices in the system is based, at least in part, on one or more constraints, wherein the one or more constraints comprise at least one of a type of respective ones of the plurality of edge devices in the system, priority of respective ones of a plurality of notifications corresponding to the plurality of workloads and a threshold number of the plurality notifications to be received before enabling the operation of the plurality of edge devices in the system.

### Claim 8 (depends on 1)

The method of claim 1, further comprising synchronizing a relative time across the plurality of edge devices in the system.

### Claim 9 (depends on 1)

The method of claim 1, further comprising:
receiving a plurality of notifications corresponding to the plurality of workloads for the plurality of edge devices in the system; and
logging metadata corresponding to the plurality of notifications.

### Claim 10 (depends on 9)

The method of claim 9, further comprising inputting the metadata to one or more machine learning models, wherein the one or more machine learning models are configured to predict at least one of when new notifications for one or more of the plurality of edge devices will be issued, priority of respective ones of the plurality of notifications, dependencies between at least one of the plurality of notifications and the plurality of edge devices, and one or more times for waking at least the subset of the plurality of edge devices which reduces a number of wakeup times for at least the subset of the plurality of edge devices.

### Claim 11 (depends on 10)

The method of claim 10, further comprising inputting to the one or more machine learning models at least one of a type of one or more of the plurality of edge devices in the system, a type of one or more of the plurality of notifications, and a predetermined priority of one or more of the plurality of notifications.

### Claim 12 (depends on 10)

The method of claim 10, further comprising inputting to the one or more machine learning models data comprising at least one of a current sleep level of one or more of the plurality of edge devices in the system and one or more historical sleep levels of the one or more of the plurality of edge devices in the system.

### Claim 13 (depends on 10)

The method of claim 10, further comprising inputting to the one or more machine learning models historical data comprising state change events of one or more of the plurality of edge devices in the system.

### Claim 14 (depends on 10)

The method of claim 10, wherein the one or more machine learning models are further configured to predict one or more times for the processing of the plurality of workloads which align with the one or more times for waking at least the subset of the plurality of edge devices.

### Claim 15

An apparatus, comprising:
at least one processor and at least one memory storing computer program instructions wherein, when the at least one processor executes the computer program instructions, the apparatus is configured:
to coordinate operation of a plurality of edge devices in a system to process a plurality of workloads;
wherein, in coordinating of the operation of the plurality of edge devices in the system, the apparatus is configured to coordinate one or more times for changing a state of at least a subset of the plurality of edge devices from a first state corresponding to a first level of activity to a second state corresponding to a second level of activity.

### Claim 16 (depends on 15)

The apparatus of claim 15, wherein, in coordinating of the operation of the plurality of edge devices in the system, the apparatus is further configured to coordinate one or more times for the processing of the plurality of workloads by at least the subset of the plurality of edge devices in the system.

### Claim 17 (depends on 15)

The apparatus of claim 15, wherein the apparatus is further configured to buffer a plurality of notifications corresponding to the plurality of workloads for the plurality of edge devices in the system.

### Claim 18

A computer program product stored on a non-transitory computer-readable medium and comprising machine executable instructions, the machine executable instructions, when executed, causing a processing device:
to coordinate operation of a plurality of edge devices in a system to process a plurality of workloads;
wherein, in coordinating of the operation of the plurality of edge devices in the system, the machine executable instructions cause the processing device to coordinate one or more times for changing a state of at least a subset of the plurality of edge devices from a first state corresponding to a first level of activity to a second state corresponding to a second level of activity.

### Claim 19 (depends on 18)

The computer program product of claim 18, wherein, in coordinating of the operation of the plurality of edge devices in the system, the machine executable instructions further cause the processing device to coordinate one or more times for the processing of the plurality of workloads by at least the subset of the plurality of edge devices in the system.

### Claim 20 (depends on 18)

The computer program product of claim 18, wherein the machine executable instructions further cause the processing device to buffer a plurality of notifications corresponding to the plurality of workloads for the plurality of edge devices in the system.
