# US 2022/0021470 A1 · Parameter setting

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

- Number: US 2022/0021470 A1
- Document ID: US20220021470A1
- Status: Published application
- Kind: A1
- Application number: 17/311,005
- Filed: 2018-12-13
- Published: 2022-01-20
- Earliest claimed: 2018-12-13
- Assignees: Telefonaktiebolaget LM Ericsson (publ)
- Applicants: Telefonaktiebolaget LM Ericsson (publ)
- Inventors: Aaron CALLARD; Akram BIN SEDIQ
- Web page: https://patentgrep.com/patent/US20220021470A1

## CPC

- H04W 24/02: Arrangements for optimising operational condition
- G06N 3/02: Neural networks
- G06N 3/045: Combinations of networks
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06N 20/20: Ensemble learning
- H04B 17/391: Modelling the propagation channel
- H04L 41/0843: {based on generic templates}
- H04L 41/0886: {Fully automatic configuration}
- H04W 24/10: Scheduling measurement reports {; Arrangements for measurement reports}
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04B: TRANSMISSION
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Apparatuses and methods are disclosed for parameter setting. In one embodiment, a method includes receiving a first signaling from the management node at the second hierarchical level, the first signaling corresponding to a first predetermined model; obtaining at least one local measurement value, the at least one local measurement value indicative of a local state of the wireless communication network; processing the at least one local measurement value based on the received first predetermined model to identify at least one parameter value independent of the management node; and managing local state of the wireless communication network by performing at least one predetermined action associated with the identified at least one parameter value.

## Claims

### Claim 1

A communication device configured to communicate with a management node over a wireless communication network, the communication device implementing a management function including automated parameter setting at a first hierarchical level of the wireless communication network independent of the management node at a second hierarchical level of the wireless communication network, the second hierarchical level being a higher level than the first hierarchical level, the communication device comprising:
a communication interface configured to receive a first signaling from the management node at the second hierarchical level, the first signaling corresponding to a first predetermined model; and
processing circuitry in communication with the communication interface, the processing circuitry configured to:
obtain at least one local measurement value, the at least one local measurement value indicative of a local state of the wireless communication network;
process the at least one local measurement value based on the received first predetermined model to identify at least one parameter value independent of the management node; and
manage the local state of the wireless communication network by performing at least one predetermined action associated with the identified at least one parameter value.

### Claim at position 2

-21. (canceled)

### Claim 22

A method for a communication device configured to communicate with a management node over a wireless communication network, the communication device implementing a management function including automated parameter setting at a first hierarchical level of the wireless communication network independent of the management node at a second hierarchical level of the wireless communication network, the second hierarchical level being a higher level than the first hierarchical level, the method comprising:
receiving a first signaling from the management node at the second hierarchical level, the first signaling corresponding to a first predetermined model;
obtaining at least one local measurement value, the at least one local measurement value indicative of a local state of the wireless communication network;
processing the at least one local measurement value based on the received first predetermined model to identify at least one parameter value independent of the management node; and
managing the local state of the wireless communication network by performing at least one predetermined action associated with the identified at least one parameter value.

### Claim 23 (depends on 22)

The method of claim 22, wherein the first predetermined model maps a predetermined set of measurement values to a predetermined set of parameter values.

### Claim 24 (depends on 23)

The method of claim 23, wherein the processing the at least one local measurement value further comprises processing the at least one local measurement value based on the mapping of the predetermined set of measurement values to the predetermined set of parameter values in the received first predetermined model to identify the at least one parameter value independent of the management node.

### Claim 25 (depends on 22)

The method of claim 22, wherein the at least one predetermined action includes at least one of:
setting at least one corresponding parameter to the identified at least one parameter value; and
triggering at least one of a remote procedure call, a second predetermined model and communication of an alarm.

### Claim 26

(canceled)

### Claim 27 (depends on 22)

The method of claim 22, further comprising receiving a second signaling, from the management node, the second signaling corresponding to a second predetermined model, the second predetermined model based on a re-evaluation of the first predetermined model.

### Claim 28 (depends on 27)

The method of claim 27, wherein the second signaling is different from the first signaling and the second predetermined model is different from the first predetermined model.

### Claim 29 (depends on 23)

The method of claim 23, wherein the managing the local state of the wireless communication network further comprises setting parameters to parameter values identified independent of the management node and based on the mapping in the first predetermined model until a second predetermined model is received, the second predetermined model being a re-evaluated parameter setting model.

### Claim 30 (depends on 23)

The method of claim 23, further comprising, as a result of a second predetermined model being received, managing the local state of the wireless communication network by setting one or more parameter to corresponding parameter values based on a mapping of a predetermined set of measurement values to a predetermined set of parameter values in the received second predetermined model.

### Claim 31 (depends on 22)

The method of claim 22, wherein the first predetermined model is configured to provide at least one output out of a plurality of predetermined outputs based on at least one input.

### Claim 32 (depends on 31)

The method of claim 31, wherein the at least one input is the obtained at least one local measurement value and the at least one output is the at least one parameter value identified independent of the management node.

### Claim 33 (depends on 22)

The method of claim 22, wherein the first predetermined model is based on at least one machine learning model.

### Claim 34 (depends on 33)

The method of claim 33, wherein the at least one machine learning model includes at least one of a decision tree, a random forest, a neural network, a support vector machine, a k-nearest neighbor and a logistic regression.

### Claim 35 (depends on 33)

The method of claim 33, wherein the at least one machine learning model maps a predetermined set of measurement values to a predetermined set of parameter values, the mapping generated at least in part based on:
providing measurement inputs to the at least one machine learning model;
the measurement inputs, calculating outputs of the at least one machine learning model; and
the outputs of the at least one machine learning model, determining at least one parameter value to be mapped to at least one measurement value in the first predetermined model.

### Claim 36 (depends on 22)

The method of claim 22, wherein the first predetermined model is represented by a look-up table.

### Claim 37 (depends on 22)

The method of claim 22, wherein the first predetermined model is received as a result of a model evaluation trigger, the model evaluation trigger being at least one of:
a time out condition of a periodic timer;
a state change of the wireless communication network; and
a remote procedure call.

### Claim 38 (depends on 22)

The method of claim 22, wherein the at least one local measurement value includes a channel quality measurement value and the identified at least one parameter value is associated with a performance measurement value.

### Claim 39 (depends on 38)

The method of claim 38, wherein the at least one parameter value includes at least one of a target block error rate value, a radio resource management parameter value and a managed object model parameter value.

### Claim 40 (depends on 22)

The method of claim 22, wherein the communication device at the first hierarchical level is one of a wireless device and a network node.

### Claim 41

(canceled)

### Claim 42 (depends on 22)

The method of claim 22, wherein the first signaling is received in at least one of a Radio Resource Control, RRC, message and a control plane interface message.

### Claim 43

A management node at a second hierarchical level configured to communicate with a communication device at a first hierarchical level over a wireless communication network, the second hierarchical level being higher than the first hierarchical level, the management node comprising:
a communication interface configured to communicate a first signaling to the communication device at the first hierarchical level, the first signaling corresponding to a first predetermined model; and
processing circuitry in communication with the communication interface, the processing circuitry configured to manage a global state of the wireless communication network by generating the first predetermined model, the first predetermined model mapping a predetermined set of measurement values to a predetermined set of parameter values.

### Claim at position 25

-56. (canceled)

### Claim 57

A method for a management node at a second hierarchical level configured to communicate with a communication device at a first hierarchical level over a wireless communication network, the second hierarchical level being higher than the first hierarchical level, the method comprising:
communicating a first signaling to the communication device at the first hierarchical level, the first signaling corresponding to a first predetermined model; and
managing a global state of the wireless communication network by generating the first predetermined model, the first predetermined model mapping a predetermined set of measurement values to a predetermined set of parameter values.

### Claim 58 (depends on 57)

The method of claim 57, further comprising generating a second predetermined model based at least in part on a re-evaluation of the first predetermined model.

### Claim 59 (depends on 58)

The method of claim 58, further comprising communicating the second predetermined model to the communication device at the first hierarchical level.

### Claim 60 (depends on 59)

The method of claim 59, wherein the second predetermined model is different from the first predetermined model.

### Claim 61 (depends on 57)

The method of claim 57, wherein the mapping of the predetermined set of measurement values to the predetermined set of parameter values in the first predetermined model is configured to permit the communication device to set at least one local parameter to at least one parameter value from the predetermined set of parameter values independent of the management node.

### Claim 62 (depends on 57)

The method of claim 57, wherein the first predetermined model is configured to provide at least one output out of a plurality of predetermined outputs based on at least one input, the at least one input corresponding to at least one of the predetermined set of measurement values and the at least one output corresponding to at least one of the predetermined set of parameter values.

### Claim 63 (depends on 57)

The method of claim 57, wherein the first predetermined model is based on at least one machine learning model.

### Claim 64 (depends on 63)

The method of claim 63, wherein the at least one machine learning model includes at least one of a decision tree, a random forest, a neural network, a support vector machine, a k-nearest neighbor and a logistic regression.

### Claim 65 (depends on 57)

The method of claim 57, wherein the mapping of the predetermined set of measurement values to the predetermined set of parameter values in the first predetermined model is generated at least in part based on:
providing measurement inputs to the at least one machine learning model;
the measurement inputs, calculating outputs of the at least one machine learning model; and
the outputs of the at least one machine learning model, determining at least one parameter value to be mapped to at least one measurement value in the first predetermined model.

### Claim 66 (depends on 57)

The method of claim 57, wherein the first predetermined model is communicated to the communication device as a result of a model evaluation trigger, the model evaluation trigger being at least one of:
a time out condition of a periodic timer;
a state change of the wireless communication network; and
a remote procedure call.

### Claim 67 (depends on 57)

The method of claim 57, the predetermined set of measurement values includes predetermined channel quality measurement values and the predetermined set of parameter values includes predetermined performance measurement values.

### Claim 68 (depends on 67)

The method of claim 67, wherein the predetermined performance measurement values include at least one of target block error rate values, radio resource management parameter values and managed object model parameter values.

### Claim 69 (depends on 57)

The method of claim 57, wherein the management node is a network node.

### Claim 70 (depends on 57)

The method of claim 57, wherein the first signaling is communicated in a Radio Resource Control, RRC, message and a control plane interface message.
