# US 2025/0211487 A1 · Energy consumption-aware network management

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

- Number: US 2025/0211487 A1
- Document ID: US20250211487A1
- Status: Published application
- Kind: A1
- Application number: 18/988,248
- Filed: 2024-12-19
- Published: 2025-06-26
- Earliest claimed: 2023-12-22
- Assignees: Nokia Technologies Oy
- Applicants: Nokia Technologies Oy
- Inventors: Miltiadis FILIPPOU; Niraj NANAVATY
- Web page: https://patentgrep.com/patent/US20250211487A1

## CPC

- H04L 41/0833: for reduction of network energy consumption
- H04L 41/145: {involving simulating, designing, planning or modelling of a network}
- H04L 41/16: using machine learning or artificial intelligence
- H04L 43/08: Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A network node transmits at least one measurement configuration to one or more devices for carrying out one or more measurements for determining at least one energy consumption estimate for at least one operation in a plurality of inter-related machine learning operations for network management. The plurality of inter-related machine learning operations comprises (i) one or more operations for collecting data, (ii) one or more data transfer operations to transmit the collected data to the network node, and (iii) one or more data storage operations to store the collected data and (iv) one or more data processing operations to process the collected data. At least one energy consumption estimate is determined using the one or more measurements. At least one network management related configuration is determined for carrying out one or more of the plurality of inter-related machine learning operations on the basis of the at least one energy consumption estimate for controlling energy consumption.

## Claims

### Claim 1

A network node comprising:
at least one processor; and
at least one memory storing instructions that, when executed by the at least one processor, cause the network node to carry out at least:
transmit at least one measurement configuration to one or more devices for carrying out one or more measurements for determining at least one energy consumption estimate for at least one operation in a plurality of inter-related machine learning operations for network management, wherein the plurality of inter-related machine learning operations comprises one or more operations for collecting data, one or more data transfer operations to transmit the collected data to the network node, and one or more data storage operations to store the collected data and one or more data processing operations to process the collected data;
receive, from at least one of the one or more devices, at least one message comprising information on the one or more measurements and determine at least one energy consumption estimate using the received information,
or
receive, from at least one of the one or more devices, at least one message comprising at least one energy consumption estimate determined using the one or more measurements;
and
determine at least one network management related configuration for carrying out one or more of the plurality of inter-related machine learning operations on the basis of the at least one energy consumption estimate for controlling energy consumption.

### Claim 2 (depends on 1)

The network node of claim 1, further caused to:
transmit, to the one or more devices, the at least one network management related configuration, or
carry out the one or more of the plurality of inter-related machine learning operations.

### Claim 3 (depends on 1)

The network node of claim 1, wherein the at least one network management related configuration is determined on the basis of on a net energy balance between an accumulated energy consumption estimated for executing one or more of the plurality of inter-related machine learning operations and energy saved by at least one action carried out based on at least one output of at least one of the inter-related machine learning operations, wherein the accumulated energy consumption is based on the at least one energy consumption estimate.

### Claim 4 (depends on 1)

The network node of claim 1, wherein the at least one network management related configuration comprises timing and/or a location in association with carrying out the at least one operation in a plurality of inter-related machine learning operations for network management.

### Claim 5 (depends on 1)

The network node of claim 1, wherein the plurality of inter-related machine learning operations are part of a machine learning process based on at least one machine learning model for network management, the at least one network management related configuration comprises at least one of the following:
one or more parameters of the machine learning model to be updated, an instruction to trigger retraining of the machine learning model, an instruction to trigger inference of the machine learning model, an instruction to trigger training data collection for the machine learning model, an instruction to trigger inference data collection for the machine learning model, an instruction to replace the machine learning based model by another machine learning based model, and an instruction to stop execution of one or more of the plurality of inter-related machine learning operations.

### Claim 6 (depends on 1)

The network node of claim 1, wherein the one or more of the plurality of inter-related machine learning operations comprises at least one of the following:
updating at least one parameter of at least one of the plurality of inter-related machine learning operations,
triggering at least one of the plurality of inter-related machine learning operations, and
deactivating execution of at least one of the plurality of inter-related machine learning operations.

### Claim 7 (depends on 1)

The network node of claim 1, further caused, as an option to the determining the at least one network management related configuration, to:
transmit the at least one energy consumption estimate to a network management entity, and
receive the at least one network management related configuration from the network management entity.

### Claim 8 (depends on 1)

The network node of claim 1, further caused to:
control validity of the at least one energy consumption estimate by using an associated timestamp.

### Claim 9

A user equipment comprising:
at least one processor; and
at least one memory storing instructions that, when executed by the at least one processor, cause the user equipment to carry out at least:
receive, from a network node, at least one measurement configuration for carrying out one or more measurements for determining at least one energy consumption estimate for at least one operation in a plurality of inter-related machine learning operations for network management, wherein the plurality of inter-related machine learning operations comprises one or more operations for collecting data, one or more data transfer operations to transmit the collected data to the network node, and one or more data storage operations to store the collected data and one or more data processing operations to process the collected data, and
carry out one or more measurements in association with the at least one measurement configuration, and transmit, to the network node, at least one message comprising information on the one or more measurements,
or
determine at least one energy consumption estimate using information obtained by the one or more measurements and transmit, to the network node, at least one message comprising information on the determined at least one energy consumption estimate.

### Claim 10 (depends on 9)

The user equipment of claim 9, further caused to:
determine or receive at least one network management related configuration for carrying out one or more of the plurality of inter-related machine learning operations on the basis of the at least one energy consumption estimate for controlling energy consumption.

### Claim 11 (depends on 10)

The user equipment of claim 10, wherein the at least one network management related configuration is determined on the basis of on a net energy balance between (i) an accumulated energy consumption estimated for executing one or more of the plurality of inter-related machine learning operations and (ii) energy saved by at least one action carried out based on at least one output of at least one of the inter-related machine learning operations, wherein the accumulated energy consumption is based on the at least one energy consumption estimate.

### Claim 12 (depends on 9)

The user equipment of claim 9, wherein the at least one network management related configuration comprises timing and/or a location in association with carrying out the at least one operation in a plurality of inter-related machine learning operations for network management.

### Claim 13 (depends on 10)

The user equipment of claim 10, further caused to:
carry out the one or more of the plurality of inter-related machine learning operations.

### Claim 14 (depends on 9)

The user equipment of claim 9, wherein the plurality of inter-related machine learning operations are part of a machine learning process based on a machine learning model for network management, the at least one network management related configuration comprises at least one of the following:
one or more parameters of the machine learning model to be updated, an instruction to trigger retraining of the machine learning model, an instruction to trigger inference of the machine learning model, an instruction to trigger training data collection for the machine learning model, an instruction to trigger inference data collection for the machine learning model, an instruction to replace the machine learning based model by another machine learning based model, and an instruction to stop execution of one or more of the plurality of inter-related machine learning operations.

### Claim 15 (depends on 9)

The user equipment of claim 9, wherein the one or more of the plurality of inter-related machine learning operations comprises at least one of the following:
updating at least one parameter of at least one of the plurality of inter-related machine learning operations,
triggering at least one of the plurality of inter-related machine learning operations, and
deactivating execution of at least one of the plurality of inter-related machine learning operations.

### Claim 16 (depends on 9)

The user equipment of claim 9, further caused to:
control validity of the at least one energy consumption estimate by using an associated timestamp.

### Claim 17

A method comprising
transmitting, by a network node, at least one measurement configuration to one or more devices for carrying out one or more measurements for determining at least one energy consumption estimate for at least one operation in a plurality of inter-related machine learning operations for network management, wherein the plurality of inter-related machine learning operations comprises (i) one or more operations for collecting data, (ii) one or more data transfer operations to transmit the collected data to the network node, and (iii) one or more data storage operations to store the collected data and (iv) one or more data processing operations to process the collected data;
receiving, from at least one of the one or more devices, at least one message comprising information on the one or more measurements and determining at least one energy consumption estimate using the received information,
or
receiving, from at least one of the one or more devices, at least one message comprising at least one energy consumption estimate determined using the one or more measurements;
and
determining at least one network management related configuration for carrying out one or more of the plurality of inter-related machine learning operations on the basis of the at least one energy consumption estimate for controlling energy consumption.

### Claim 18

(canceled)
