Multiple radio frequency impairment estimation

Patent metadata

Field	Value
Publication number	US-12489537-B2
Application number	US-202118251089-A
Country	US
Kind code	B2
Filing date	Oct 28, 2021
Priority date	Nov 2, 2020
Publication date	Dec 2, 2025
Grant date	Dec 2, 2025

Abstract

The present disclosure relates to the detection of impairments in a received wireless communication signal. It may detect the presence of each of N types (sources) of impairments and possibly the amount of the impairment present in the received signal. The detection includes processing of the received signal by a trainable model trained to distinguish N sources of impairments by applying learning, with N being an integer larger than one. The trainable model outputs, for each source j of the N sources, a contribution of the j-th source of impairments to the obtained signal. The contribution may be binary, indicating the presence or absence of the j-th source of impairment, or may also indicate the amount of impairment.

First claim

The invention claimed is:

1 . A method for estimating radio frequency transmission impairments, the method comprising:
obtaining a signal received over a wireless channel; processing the obtained signal by a trainable model trained to distinguish N sources of impairments, N being an integer larger than one; and outputting from the trainable model, for each source j of the N sources, a contribution of the j-th source of impairments to the obtained signal; wherein the machine learning includes one or more types of machine learning methods comprising a multi-layer perceptron, long short-term memory, and/or convolutional neural network, and at least two of the N sources of impairments are processed by different types of the machine learning methods.

2 . The method according to claim 1 , wherein the sources of impairments at the transmitter side comprise one or more of the following:
frequency offset, phase offset, clock offset, power amplifier impairments, filter impairments, and/or
modulation impairments.

3 . The method according to claim 1 , wherein:
the contribution indicates one of presence or absence of contribution from a source of impairment to the received signal, and processing the obtained signal further comprises: obtaining a feature vector which comprises an element for each source j of the N sources, the element indicating a degree of contribution of the j-th source of impairments to the obtained signal; and comparing whether each j-th element of the feature vector exceeds a threshold; and for each j-th element, setting contribution of the j-th element to TRUE in case the j-th element exceeds a threshold, and setting the j-th element to FALSE otherwise.

4 . The method according to claim 1 , wherein:
the contribution of the j-th source of impairments to the obtained signal indicates a degree of the contribution which may take one of M values, M>2, and processing the obtained signal outputs a feature vector which comprises a j-th element for each source j of the N sources, the j-th element indicating the degree of contribution of the j-th source of impairments to the obtained signal.

5 . The method according to claim 1 , further comprising:
compensating the obtained signal based on the outputted contribution of the j-th source of impairments to the obtained signal.

6 . The method according to claim 1 , wherein:
the signal received over a wireless channel is received from a transmitting device, and the method further comprises transmitting an indication of the contribution for at least one of the N sources of impairments to the transmitting device.

7 . The method according to claim 6 , further comprising:
receiving, at the transmitting device, the indication of the contribution for at least one of the N sources of impairments; and applying, at the transmitting device, predistortion in accordance with the received indication.

8 . The method according to claim 1 , further comprising:
performing a physical layer authentication based on the outputted contribution of the N sources of impairments to the obtained signal.

9 . A method for training a trainable model for estimating radio frequency transmission impairments, comprising:
obtaining a training set comprising plural training data comprising input signal impaired by an impairment and by a transmission channel and an impairment indication indicating type of the impairment, signal; inputting the training set into the trainable model; adapting parameters of the trainable model according to the inputted training set; and storing the adapted parameters for use in said estimating radio frequency transmission impairments.

10 . The method according to claim 9 , wherein the obtaining of the training set comprises, for each training data in the training set:
generating an input signal, determining the impairment indication indicating type and/or parameters of the impairment; impairing the input signal with the impairment, and obtaining impaired by the impairment and a transmission channel by transmitting the impaired input signal over a wireless channel and receiving the transmitted signal.

11 . An apparatus for estimating radio frequency transmission impairments, the apparatus comprising processing circuitry configured to:
obtain a signal received over a wireless channel; process the obtained signal by a trainable model trained to distinguish N sources of impairments by applying supervised learning, N being an integer larger than one; and outputting from the trainable model, for each source j of the N sources, a contribution of the j-th source of impairments to the obtained signal; wherein the processing circuitry is further configured to train the learning module by: obtaining a training set comprising plural training data including input signal impaired by an impairment and by a transmission channel and an impairment indication indicating type of the impairment, signal; inputting the training set into the trainable module; adapting parameters of the trainable module according to the machine learning using the inputted training set; and storing the adapted parameters for use in said estimating radio frequency transmission impairments.

12 . An apparatus for receiving a signal impaired with a plurality of impairments, the apparatus comprising:
a receiver for receiving a signal received over a wireless channel, the apparatus according to claim 11 for estimating radio frequency transmission impairments in the received signal, compensation circuitry configured to: compensate the received signal for the estimated radio frequency transmission impairments, or transmit an indication of the estimated radio frequency transmission impairments as a feedback to a transmitter from which the signal was received.

Assignees

• Vestel Elektronik Sanayi Ve Ticaret As

Inventors

• Aygül Mehmet Ali
• Arslan Hüseyin

Classifications

• H04L25/0254

  using neural network algorithms · CPC title

• H04B1/1027 Primary

  assessing signal quality or detecting noise/interference for the received signal · CPC title

• H04B17/104

  of other parameters, e.g. DC offset, delay or propagation times · CPC title

• G06N3/0442

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

• G06N3/0985

  Hyperparameter optimisation; Meta-learning; Learning-to-learn · CPC title