Technique for assessing connection quality

Patent metadata

Field	Value
Publication number	US-12563426-B2
Application number	US-202018023835-A
Country	US
Kind code	B2
Filing date	Oct 2, 2020
Priority date	Oct 2, 2020
Publication date	Feb 24, 2026
Grant date	Feb 24, 2026

Abstract

A technique for assessing connection quality in a wireless communication network is disclosed. A method implementation of the technique includes obtaining a radio frequency, RF, channel response measurement indicative of a channel gain in time and frequency observed at a location covered by the wireless communication network, and determining, based on the RF channel response measurement, an estimated connection quality at the location using a machine learning model trained to map RF channel response measurement based features to corresponding connection qualities.

First claim

The invention claimed is:

1 . A method for assessing connection quality in a wireless communication network, the method comprising:
obtaining a radio frequency, RF, channel response measurement indicative of a channel gain in time and frequency observed at a location covered by the wireless communication network; determining, based on the RF channel response measurement, an estimated connection quality at the location using a machine learning model trained to map RF channel response measurement based features to corresponding connection qualities; the machine learning model being one of a plurality of machine learning models trained to map RF channel response measurement based features to corresponding connection qualities, each of the plurality of machine learning models being trained using training data obtained from measurements performed at locations covered by different representative wireless communication networks, each being representative of a different type of RF environment; and the plurality of machine learning models being used as an ensemble in which each of the plurality of machine learning models is used to estimate a respective connection quality based on the RF channel response measurement, and the estimated connection quality being determined based on the respective connection qualities.

2 . The method of claim 1 , wherein the channel gain is measured in time and frequency based on reference symbols transmitted from a base station of the wireless communication network.

3 . The method of claim 1 , wherein the RF channel response measurement based features are representative of channel gain in time and frequency, and wherein determining the estimated connection quality based on the RF channel response measurement includes inputting the measured channel gain in time and frequency to the machine learning model.

4 . The method of claim 1 , wherein a multipath resolution algorithm is applied on the RF channel response measurement to determine an observed multipath RF propagation pattern, wherein the RF channel response measurement based features are representative of multipath RF propagation patterns, and wherein determining the estimated connection quality based on the RF channel response measurement includes inputting the determined multipath RF propagation pattern to the machine learning model.

5 . The method of claim 4 , wherein the multipath RF propagation pattern comprises a number and strength of a plurality of RF propagation paths observed at the location, and optionally a direction of different ones of the plurality of RF propagation paths.

6 . The method of claim 1 , wherein the RF channel response measurement is obtained from Ultra-Reliable Low-Latency Communication, URLLC, traffic communicated in the wireless communication network.

7 . The method of claim 1 , wherein the machine learning model is trained using training data comprising a plurality of sets of RF channel response measurement based features as input data, the plurality of sets of RF channel response measurement based features obtained from RF channel response measurements indicative of channel gain in time and frequency performed at different locations covered by a representative wireless communication network, and corresponding connection qualities measured at the different locations as output data.

8 . The method of claim 7 , wherein the wireless communication network covers an industrial environment, wherein additional training data is continuously obtained from one or more wireless devices carrying out industrial tasks in the industrial environment, and wherein the additional training data is used to enhance the machine learning model.

9 . The method of claim 1 , wherein the machine learning model is selected from the plurality of machine learning models based on the RF channel response measurement using a classifier trained to map RF channel response measurement based features to corresponding types of RF environments.

10 . The method of claim 1 , wherein obtaining the RF channel response measurement and determining the estimated connection quality is performed for a plurality of locations covered by the wireless communication network, and wherein the resulting estimated connection qualities are used to generate a connection quality map for an area covered by the wireless communication network.

11 . The method of claim 10 , wherein the wireless communication network covers an industrial environment, wherein measured connection qualities are continuously obtained from one or more wireless devices carrying out industrial tasks in the industrial environment, and wherein the connection quality map is updated based on the measured connection qualities.

12 . The method of claim 10 , wherein the connection quality map is segmented into different areas depending on a grade of connection quality that can be provided in the respective area.

13 . The method of claim 1 , wherein, when the estimated connection quality is lower than a required connection quality value in an area covered by the wireless communication network, one or more mitigation actions are triggered to improve connection quality in the area.

14 . The method of claim 13 , wherein the one or more mitigation actions comprise at least one of:
deploying one or more additional base stations in the area, allocating one or more additional base stations to serve a cell covering the area, adapting an RF reflection property of at least one metasurface provided in the area, and determining a radio link configuration required to achieve the connection quality value in the area and applying the determined radio link configuration in the wireless communication network.

15 . The method of claim 14 , wherein determining the radio link configuration includes adding a safety margin onto channel quality values reported from wireless devices in the wireless communication network, the safety margin accounting for possible drops in channel gain, and selecting a modulation and coding scheme, MCS, depending on the channel quality values with the safety margin.

16 . A method for training a machine learning model configured to assess connection quality in a wireless communication network, the method comprising:
training the machine learning model using training data comprising a plurality of sets of RF channel response measurement based features as input data, the plurality of sets of RF channel response measurement based features being obtained from RF channel response measurements indicative of channel gain in time and frequency performed at different locations covered by a representative wireless communication network, and corresponding connection qualities measured at the different locations as output data; the machine learning model being one of a plurality of machine learning models trained to map RF channel response measurement based features to corresponding connection qualities, each of the plurality of machine learning models being trained using training data obtained from measurements performed at locations covered by different representative wireless communication networks, each being representative of a different type of RF environment; and the plurality of machine learning models being used as an ensemble in which each of the plurality of machine learning models is used to estimate a respective connection quality based on the RF channel response measurement, and the estimated connection quality being determined based on the respective connection qualities.

17 . A computing device for assessing connection quality i

Assignees

• Ericsson Telefon Ab L M
• Valea Ab

Inventors

• Borsos Tamas
• Rácz András
• Veres András

Classifications

• H04W24/10

  Scheduling measurement reports {; Arrangements for measurement reports} · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/0442

  characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/04

  Architecture, e.g. interconnection topology · CPC title