UE-assisted data collection for mobility prediction
Systems and methods are disclosed herein for User Equipment (UE) assisted data collection for mobility prediction. In one embodiment, a method performed by a UE for UE-assisted data collection for mobility prediction comprises receiving, from a network node of a cellular communications system, a UE trajectory prediction model for predicting a UE trajectory. The method further comprises executing the UE trajectory prediction model to generate a predicted trajectory for the UE, comparing the actual UE trajectory to the predicted UE trajectory, and sending, to a network node of the cellular communications system, a result of the comparison of the actual UE trajectory to the predicted UE trajectory. In this manner, mobility prediction performance is improved.
1. A method, performed by a User Equipment (UE) for UE-assisted data collection for mobility prediction, the method comprising:
receiving, from a network node of a cellular communications system, a trained UE trajectory prediction model for predicting a UE trajectory;
executing the trained UE trajectory prediction model to generate a predicted trajectory for the UE;
comparing an actual UE trajectory to the predicted trajectory for the UE;
sending, to the network node of the cellular communications system, a result of the comparison of the actual UE trajectory to the predicted trajectory for the UE, and
updating the trained UE trajectory prediction model in a target UE,
wherein updating the trained UE trajectory prediction model in the target UE further comprises downloading, to the target UE, updated parameters used by the trained UE trajectory prediction model in the target UE.
2. The method of claim 1 , wherein sending the result of the comparison of the actual UE trajectory to the predicted trajectory of the UE comprises sending transition events or trajectory events.
3. The method of claim 2 , further comprising sending the result of the comparison of the actual UE trajectory to the predicted trajectory for the UE to another UE.
4. The method of claim 1 , wherein sending the result of the comparison of the actual UE trajectory to the predicted trajectory for the UE comprises sending error data that describes a difference between the actual UE trajectory and the predicted trajectory for the UE.
5. The method of claim 1 , further comprising:
subsequent to comparing the actual UE trajectory to the predicted trajectory for the UE, training or retraining the trained UE trajectory prediction model.
6. The method of claim 5 , wherein sending the result of the comparison of the actual UE trajectory to the predicted trajectory for the UE comprises uploading the trained or retrained trained UE trajectory prediction model.
7. The method of claim 5 , further comprising sending the trained or retrained trained UE trajectory prediction model to another UE.
8. The method of claim 1 , wherein receiving the trained UE trajectory prediction model comprises receiving the trained UE trajectory prediction model from a Network Data Analytics Function (NWDAF).
9. The method of claim 1 , wherein receiving the trained UE trajectory prediction model comprises receiving the trained UE trajectory prediction model from a Management Data Analytics Function, a Non-Real-Time Intelligent Controller, or a Near-Real-Time Intelligent Controller.
10. The method of claim 1 , wherein sending the result of the comparison comprises sending the result of the comparison to a Network Data Analytics Function (NWDAF).
11. The method of claim 1 , wherein sending the result of the comparison comprises sending the result of the comparison to a Management Data Analytics Function, a Non-Real-Time Intelligent Controller, or a Near-Real-Time Intelligent Controller.
12. A User Equipment (UE) for UE-assisted data collection for mobility prediction, the UE comprising:
one or more transmitters;
one or more receivers; and
processing circuitry associated with the one or more transmitters and the one or more receivers, the processing circuitry configured to cause the UE to:
receive, from a network node of a cellular communications system, a trained UE trajectory prediction model for predicting a UE trajectory;
execute the trained UE trajectory prediction model to generate a predicted trajectory for the UE;
compare an actual UE trajectory to the predicted trajectory for the UE;
send, to the network node of the cellular communications system, a result of the comparison of the actual UE trajectory to the predicted trajectory for the UE, and
updating the trained UE trajectory prediction model in a target UE,
wherein updating the trained UE trajectory prediction model in the target UE further comprises downloading, to the target UE, updated parameters used by the trained UE trajectory prediction model in the target UE.
13. A method performed by a cellular communications system for User Equipment (UE) assisted data collection for mobility prediction, the method comprising:
downloading, to a target UE, a trained UE trajectory prediction model for predicting a trajectory of the target UE;
receiving, from the target UE, information related to training or retraining the trained UE trajectory prediction model;
using the received information to train or retrain the trained UE trajectory prediction model; and
updating the trained UE trajectory prediction model in the target UE,
wherein updating the trained UE trajectory prediction model in the target UE further comprises downloading, to the target UE, updated parameters used by the trained UE trajectory prediction model in the target UE.
14. The method of claim 13 , wherein updating the trained UE trajectory prediction model in the target UE comprises downloading, to the target UE, the trained or retrained trained UE trajectory prediction model.
15. The method of claim 13 , further comprising:
prior to downloading the trained UE trajectory prediction model to the target UE, identifying the target UE.
16. The method of claim 15 , wherein identifying the target UE comprises:
receiving a plurality of Radio Base Station (RBS) transition events associated with at least one UE;
determining that an RBS transition event of a first UE involved a transition from a first RBS to a second RBS that is not a neighbor of the first RBS; and
identifying the first UE as a target for downloading the trained UE trajectory prediction model.
17. The method of claim 15 , wherein identifying the target UE comprises:
determining that a Radio Base Station (RBS) transition event of each of a plurality of UEs involved a transition from a first RBS to a second RBS that is not a neighbor of the first RBS;
identifying the plurality of UEs as potential target UEs for downloading respective trained UE trajectory prediction models; and
selecting a subset of the potential target UEs as target UEs for downloading the respective trained UE trajectory prediction models, the subset of the potential target UEs including the identified target UE.
18. The method of claim 17 , wherein selecting the subset of the potential target UEs comprises selecting the subset of the potential target UEs based on at least one parameter.
19. The method of claim 18 , wherein the at least one parameter comprises: presence of a UE in a region or area where performance of the trained UE trajectory prediction model is below a threshold, UE class or type, UE speed, type of UE motion, UE behavior, Radio Access Technology (RAT), or frequency bands supported by the UE, and/or UE battery capacity.
20. The method of claim 15 , wherein identifying the target UE comprises receiving an identity of the target UE from an Operations, Administration, and Management (OAM) node.
21. The method of claim 13 , wherein at least some of the steps of the method are performed by a Network Data Analytics Function (NWDAF) or an Operations, Administration, and Maintenance (OAM) node.
22. A system for User Equipment (UE) assisted data collection for mobility prediction, the system comprising:
at least one network node for a cellular communications system, the at least one network node adapted to:
download, to a target UE, a trained UE trajectory prediction model for predicting a trajectory of the target UE;
receive, from the target UE, information related to training or retraining the trained UE trajectory prediction model;
use the received information to train or retrain the trained UE trajectory prediction model, and
update the trained UE trajectory prediction model in the target UE,
wherein updating the trained UE trajectory prediction model in the target UE further comprises downloading, to the target UE, updated parameters used by the trained UE trajectory prediction model in the target UE.
23. The system of claim 22 , wherein each network node of the at least one network node comprises processing circuitry configured to cause the network node to perform at least one of the downloading, receiving, and using.