Cross-node deep learning methods of selecting machine learning modules in wireless communication systems
A method of wireless communication is performed by a user equipment (UE). The method receives, from a network, a configuration for a decision making module. The method also executes the decision making module to determine a selection parameter for a configuration of at least one machine learning module. The method selects the configuration of the at least one machine learning module based on the selection parameter. Further, the method reports, to the network, a decision resulting from executing the decision making module.
1. A method of wireless communication by a user equipment (UE), comprising:
receiving, from a network, a configuration for a decision making module;
executing the decision making module to determine a selection parameter from a plurality of selection parameters for configuring the at least one machine learning module;
configuring the at least one machine learning module in accordance with the selection parameter; and
reporting, to the network, a decision resulting from executing the decision making module.
2. The method of claim 1 , in which wherein the reporting further comprises reporting inputs to the decision making module and performance data associated with the decision.
3. The method of claim 1 , wherein the decision making module comprises a reinforcement learning module.
4. The method of claim 1 , wherein the configuration of the at least one machine learning module comprises an indication of which of the at least one machine learning module to select.
5. The method of claim 1 , wherein the configuration of the at least one machine learning module comprises a selection of module parameters for the at least one machine learning module.
6. The method of claim 1 , wherein the selecting the configuration includes downloading a new machine learning module to replace the at least one machine learning module, or downloading a new set of parameters for the at least one machine learning module.
7. The method of claim 1 , wherein the configuration of the at least one machine learning module is in accordance with at least one of a location of the UE, channel conditions experienced by the UE, and mobility of the UE.
8. The method of claim 1 , further comprising receiving a first set of reference signals in response to the decision having a first value and receiving a second, different set of reference signals in response to the decision having a second, different value.
9. The method of claim 1 , further comprising receiving a configuration for the at least one machine learning module.
10. The method of claim 1 , wherein the executing the decision making module is based on in accordance with receiving a signal from the network.
11. The method of claim 10 , wherein the signal from the network comprises a reference signal.
12. The method of claim 1 , further comprising executing the at least one machine learning module in accordance with the configuration selected for the at least one machine learning module.
13. A method of wireless communication, by a network device, comprising:
transmitting, to a user equipment (UE), a configuration for a decision making module;
receiving, from the UE, a decision resulting from the UE executing the decision making module to determine a selection parameter from a plurality of selection parameters for configuring at least one UE machine learning module; and
transmitting, to the UE, signaling in accordance with the decision received from the UE.
14. The method of claim 13 , wherein the signaling comprises a first set of reference signals in response to the decision having a first value and a second, different set of reference signals in response to the decision having a second, different value.
15. The method of claim 13 , further comprising:
requesting the UE to report an input and an output of the decision making module, and performance data associated with the output of the decision making module;
training the decision making module in accordance with the input, the output, and the performance data; and
transmitting, to the UE, updates to the decision making module, in accordance with the training.
16. The method of claim 13 , further comprising transmitting, to the UE, a signal for executing the decision making module.
17. The method of claim 16 , in which wherein the signal comprises a reference signal.
18. An apparatus for a user equipment (UE) for wireless communication, comprising:
a memory; and
at least one processor coupled to the memory, the at least one processor configured to:
receive, from a network, a configuration for a decision making module;
execute the decision making module to determine a selection parameter from a plurality of selection parameters for configuring at least one machine learning module;
to configure the at least one machine learning module in accordance with the selection parameter; and
report, to the network, a decision resulting from executing the decision making module.
19. The apparatus of claim 18 , wherein the at least one processor is further configured to report inputs to the decision making module and performance data associated with the decision.
20. The apparatus of claim 18 , wherein the decision making module comprises a reinforcement learning module.
21. The apparatus of claim 18 , wherein the configuration of the at least one machine learning module comprises an indication of which of the at least one machine learning module to select.
22. The apparatus of claim 18 , wherein the configuration of the at least one machine learning module comprises a selection of module parameters for the at least one machine learning module.
23. The apparatus of claim 18 , wherein in which the at least one processor is further configured to select the configuration by downloading a new machine learning module to replace the at least one machine learning module, or downloading a new set of parameters for the at least one machine learning module.
24. The apparatus of claim 18 , wherein the configuration of the at least one machine learning module is in accordance with at least one of a location of the UE, channel conditions experienced by the UE, and mobility of the UE.
25. The apparatus of claim 18 , wherein the at least one processor is further configured to receive a first set of reference signals in response to the decision having a first value and receiving a second, different set of reference signals in response to the decision having a second, different value.
26. The apparatus of claim 18 , wherein the at least one processor is further configured to receive a configuration for the at least one machine learning module.
27. The apparatus of claim 18 , wherein the at least one processor is further configured to execute the decision making module in accordance with receiving a signal from the network.
28. The apparatus of claim 27 , wherein the signal from the network comprises a reference signal.
29. The apparatus of claim 18 , wherein the at least one processor is further configured to execute the at least one machine learning module in accordance with the configuration selected for the at least one machine learning module.
30. An apparatus for a network device for wireless communication, comprising:
a memory; and
at least one processor coupled to the memory, the at least one processor configured to:
transmit, to a user equipment (UE), a configuration for a decision making module;
receive, from the UE, a decision resulting from the UE executing the decision making module to determine a selection parameter from a plurality of selection parameters for configuring at least one UE machine learning module; and
transmit, to the UE, signaling in accordance with the decision received from the UE.