Method, apparatus and computer program for predicting a future quality of service of a wireless communication link

Patent metadata

Field	Value
Publication number	US-11489602-B2
Application number	US-202117205879-A
Country	US
Kind code	B2
Filing date	Mar 18, 2021
Priority date	Mar 20, 2020
Publication date	Nov 1, 2022
Grant date	Nov 1, 2022

Abstract

An apparatus, method and computer program for predicting a future quality of service of a wireless communication link based on a predicted future environmental model t predicted by determining a trajectory of active wireless transceivers. The method includes determining an environmental model of active transceivers in the environment of the mobile transceiver, determining information on a trajectory of the active transceivers, determining a predicted future environmental model of the active transceivers at a point in time of the future based on the information on the trajectory of the active transceivers, and predicting the future quality of service of the wireless communication link for the point in time of the future using a machine-learning model. The machine-learning model provides information on a predicted quality of service for a given environmental model. The predicted future environmental model is used as input to the machine-learning model.

First claim

The invention claimed is:

1. An apparatus for predicting a future quality of service of a wireless communication link between a mobile transceiver and a further mobile transceiver, the apparatus comprising:
one or more interfaces for communicating in a mobile communication system; and
a control module configured to predict the future quality of service of the wireless communication link between the mobile transceiver and the further mobile transceiver by:
determining an environmental model of one or more active transceivers in the environment of the mobile transceiver;
determining information on a trajectory of movement of the one or more active transceivers;
determining a predicted future environmental model of the one or more active transceivers at a point in time of the future based on the information on the trajectory of movement of the one or more active transceivers; and
predicting the future quality of service of the wireless communication link for the point in time of the future using a machine-learning model,
wherein the machine-learning model is trained to provide information on a predicted quality of service for a given environmental model, and
wherein the predicted future environmental model is used as input to the machine-learning model.

2. The apparatus of claim 1 , wherein determining the information on the trajectory of movement of the one or more active transceivers comprises tracking a movement of the one or more active transceivers, and extrapolating the trajectory of movement of the one or more active transceivers based on the movement of the one or more active transceivers.

3. The apparatus of claim 1 , wherein determining the information on the trajectory of movement of the one or more active transceivers comprises receiving the information on the trajectory of movement of the one or more active transceivers from the one or more active transceivers.

4. The apparatus of claim 1 , wherein determining the information on the trajectory of movement of the one or more active transceivers comprises aligning the trajectory of movement of the one or more active transceivers with a map of the environment of the mobile transceiver.

5. The apparatus of claim 1 , wherein determining the information on the trajectory of movement of the one or more active transceivers comprises receiving information on a planned route of the one or more active transceivers from the one or more active transceivers.

6. The apparatus of claim 1 , wherein the future quality of service of the wireless communication link is predicted for at least two points in time of the future.

7. The apparatus of claim 6 , wherein the future quality of service of the wireless communication link is predicted for the at least two points in time of the future by determining the predicted future environmental model of the one or more active transceivers at the at least two points in time of the future, and using the predicted future environmental model of the one or more active transceivers at the at least two points in time of the future as inputs for the machine-learning model.

8. The apparatus of claim 1 , wherein a plurality of environmental models of the one or more active transceivers are determined over a plurality of points in time, the method comprising determining a quality of service of the wireless communication link at the plurality of points in time, and training the machine-learning model using the plurality of environmental models at the plurality of points of time as training input and the quality of service of the wireless communication link at the corresponding plurality of points in time as training output of the training of the machine-learning model.

9. The apparatus of claim 1 , wherein the machine-learning model is trained to implement a regression algorithm.

10. The apparatus of claim 1 , wherein the machine-learning model is trained to provide a probability distribution on the predicted quality of service for a given environmental model.

11. The apparatus of claim 1 , wherein the one or more active transceivers are placed on a grid within the environmental model, the grid comprising a plurality of adjoining cells, wherein the one or more active transceivers are aggregated per cell within the grid.

12. The apparatus of claim 11 , wherein the grid is a circular grid.

13. The method of claim 12 , wherein the grid is a circular grid.

14. The apparatus of claim 1 , wherein the predicted quality of service relates to at least one of a packet inter-reception time, a packet error rate, a latency and a data rate.

15. A method for predicting a future quality of service of a wireless communication link between a mobile transceiver and a further mobile transceiver, the method comprising:
determining an environmental model of one or more active transceivers in the environment of the mobile transceiver;
determining information on a trajectory of movement of the one or more active transceivers;
determining a predicted future environmental model of the one or more active transceivers at a point in time of the future based on the information on the trajectory of movement of the one or more active transceivers; and
predicting the future quality of service of the wireless communication link for the point in time of the future using a machine-learning model,
wherein the machine-learning model is trained to provide information on a predicted quality of service for a given environmental model, and
wherein the predicted future environmental model is used as input to the machine-learning model.

16. The method of claim 15 , wherein determining the information on the trajectory of movement of the one or more active transceivers comprises tracking a movement of the one or more active transceivers, and extrapolating the trajectory of movement of the one or more active transceivers based on the movement of the one or more active transceivers.

17. The method of claim 15 , wherein determining the information on the trajectory of movement of the one or more active transceivers comprises receiving the information on the trajectory of movement of the one or more active transceivers from the one or more active transceivers.

18. The method of claim 15 , wherein determining the information on the trajectory of movement of the one or more active transceivers comprises aligning the trajectory of movement of the one or more active transceivers with a map of the environment of the mobile transceiver.

19. The method of claim 15 , wherein determining the information on the trajectory of movement of the one or more active transceivers comprises receiving information on a planned route of the one or more active transceivers from the one or more active transceivers.

20. The method of claim 15 , wherein the future quality of service of the wireless communication link is predicted for at least two points in time of the future.

21. The method of claim 20 , wherein the future quality of service of the wireless communication link is predicted for the at least two points in time of the future by determining the predicted future environmental model of the one or more active transceivers at the at least two points in time of the future, and using the predicted future environmental model of the one or more active transceivers at the at least two points in time of the future as inputs for the machine-learning model.

22. The method of claim 15 , wherein a plurality of environmental models of the one or more active transceivers are determ

Assignees

• Volkswagen Ag

Inventors

• Jornod Guillaume
• Pfadler Andreas

Classifications

• H04W24/06 Primary

  Testing, {supervising or monitoring} using simulated traffic · CPC title

• G06N20/00

  Machine learning · CPC title

• H04B17/373 Primary

  Predicting channel quality {or other radio frequency [RF]} parameters · CPC title

• H04B17/3913

  Predictive models, e.g. based on neural network models · CPC title

• H04W4/40

  for vehicles, e.g. vehicle-to-pedestrians [V2P] · CPC title