Method and apparatus for determining a bridged tap length

Patent metadata

Field	Value
Publication number	US-10938981-B2
Application number	US-202016857485-A
Country	US
Kind code	B2
Filing date	Apr 24, 2020
Priority date	May 17, 2019
Publication date	Mar 2, 2021
Grant date	Mar 2, 2021

Abstract

The apparatus includes a memory configured to store executable code; and a processor configured to execute the executable code and cause the apparatus to perform the operations of generating and training. The generating generates a dataset specifying, for a plurality of communication lines, i) a channel frequency response of a communication line having one or two bridged taps, and ii) a set of M lengths of bridged taps associated with the communication line, with M greater than one. The training trains, based on the dataset, a machine learning model, the machine learning model configured for determining, based on the channel frequency response of a communication line, a set of M lengths of bridged taps associated with the communication line.

First claim

The invention claimed is:

1. An apparatus comprising
a memory configured to store executable code; and
a processor configured to execute the executable code and cause the apparatus to perform the operations of
generating a dataset specifying, for each communication line of a plurality of communication lines,
a channel frequency response of a respective communication line of the plurality of communication lines, the communication line having one or two bridged taps, and
a set of M lengths of bridged taps associated with the respective communication line, with M greater than one, and

training, based on the dataset, a machine learning model, the machine learning model configured for determining, based on the channel frequency response of the respective communication line, a set of M lengths of bridged taps associated with the respective communication line.

2. The apparatus according to claim 1 , wherein the training the machine leaning model comprises updating parameters of the machine learning model based on an error representative of a relative comparison between target lengths and predicted lengths.

3. The apparatus according to claim 1 , wherein the training the machine leaning model comprises updating parameters of the machine learning model based on an error representative of a comparison between target lengths and predicted lengths and of a length distribution associated with a communication network.

4. The apparatus according to claim 3 , wherein the processor is configured to further cause the apparatus to perform
determining said length distribution based on iteratively,
updating parameters of the machine learning model based on the dataset and a current estimation of the length distribution,
determining lengths based on the updated machine learning model and the channel frequency responses of the plurality of communication lines of a real communication network, and
updating the current estimation of the length distribution based on the determined lengths.

5. The apparatus according to claim 1 , wherein the generating the dataset comprises determining the channel frequency responses based on circuit simulation.

6. The apparatus according to claim 1 , wherein the generating the dataset comprises determining the channel frequency responses for a plurality of communication lines having a single wire bridged tap and for a plurality of communication lines having a double wire bridged tap.

7. The apparatus according to claim 1 , wherein the generating the dataset comprises determining the channel frequency responses for a plurality of communication lines having an open-ended bridged tap and for a plurality of communication lines having a close-ended bridged tap.

8. The apparatus according to claim 1 , wherein the generating the dataset comprises determining the channel frequency responses for a plurality of communication lines having only one bridged tap and for a plurality of communication lines having at least two bridged taps.

9. The apparatus according to claim 1 , wherein the processor is configured to further cause the apparatus to perform:
obtaining the channel frequency response of the respective communication line, and
determining a set of M lengths of bridged taps associated with the respective communication line, based on the channel frequency response and the trained machine learning model.

10. A computer-implemented method comprising:
generating a dataset specifying, for each communication line of a plurality of communication lines,
a channel frequency response of a respective communication line of the plurality of communication lines having one or two bridged taps, and
a set of M lengths of bridged taps associated with the respective communication line, with M greater than one,

training, based on the dataset, a machine learning model, the machine learning model configured for determining, based on the channel frequency response of the respective communication line, a set of M lengths of bridged taps associated with the respective communication line.

11. The method according to claim 10 , comprising:
deploying the trained machine learning model in another apparatus.

12. An apparatus obtained by the method of claim 11 , comprising a processor configured to:
obtain the channel frequency response of the respective communication line,
determine a set of M lengths of bridged taps associated with the respective communication line, based on the channel frequency response and the trained machine learning model.

13. A computer-implemented method for monitoring a communication network, comprising:
obtaining the channel frequency response of the respective communication line,
determining a set of M lengths of bridged taps associated with the respective communication line, based on the channel frequency response and a trained machine learning model generated by the method of claim 10 .

14. A non-transitory computer-readable medium storing instructions, which when executed by a processor, causes an apparatus including the processor to perform the method of claim 10 .

Assignees

• Nokia Solutions & Networks Oy

Inventors

• Dupuis Nicolas
• Van Damme Axel

Classifications

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N20/00

  Machine learning · CPC title

• H04B3/46 Primary

  Monitoring; Testing · CPC title

• H04M3/306

  for frequencies above the voice frequency, e.g. xDSL line qualification (test methods, test equipment and test arrangements for subscriber lines using xDSL modems H04M3/304; systems modifying transmission characteristics according to link quality H04L1/0001; monitoring and/or testing of line transmission systems H04B3/46) · CPC title