Artificial intelligence model training for idle mode assistance
A radio access network node, or nodes, may determine learning model configuration information to use to train a learning model corresponding to a user equipment in idle mode. A node may broadcast a training configuration resource indication in an information block indicative of a resource usable to broadcast a learning model training configuration or indicative of a resource usable to broadcast a training result. While idle, a user equipment may decode a training configuration according to the training configuration resource indication and perform a training action indicated in the training configuration. A learning model may be trained, based on the training action, while the user equipment is idle. While idle, the user equipment may use a model trained while the user equipment is idle to estimate a radio parameter and transmit the estimated radio parameter to a node to be used to establish a connection with the node.
1 . A method, comprising:
receiving, from a first radio access network node by a user equipment comprising at least one processor, a learning model configuration information block message comprising at least one training configuration resource indication indicative of at least one training configuration resource usable to broadcast, by the first radio access network node, a learning model training configuration;
receiving, by the user equipment, the learning model training configuration according to the at least one training configuration resource; and
decoding, by the user equipment, the learning model training configuration,
wherein the at least one training configuration resource comprises at least one time or frequency resource, and wherein the at least one training configuration resource is non-overlapping with non-training idle mode resources.
2 . The method of claim 1 , wherein the decoding of the learning model training configuration comprises blind decoding.
3 . The method of claim 1 , wherein the learning model training configuration comprises a training action indication indicative of a training action to be performed by the user equipment.
4 . The method of claim 1 , wherein the learning model training configuration comprises at least one timing advance preamble corresponding to a second radio access network node that is a neighboring radio access network node with respect to the first radio access network node, and wherein the training action comprises transmitting, to the second radio access network node, one of the at least one timing advance preamble, the method further comprising:
transmitting, by the user equipment to the second radio access network node, the one of the at least one timing advance preamble corresponding to the second radio access network node, wherein the one of the at least one timing advance preamble corresponding to the second radio access network node is usable by the second radio access network node to result in an at least one updated timing advance learning model parameter corresponding to a timing advance learning model.
5 . The method of claim 4 , wherein the learning model configuration information block message comprises a training result resource indication indicative of a training result resource usable to receive, by the user equipment, the at least one updated timing advance learning model parameter, the method further comprising:
receiving, by the user equipment via the training result resource, the at least one updated timing advance learning model parameter; and
based on the at least one updated timing advance learning model parameter, updating, by the user equipment, the timing advance learning model to result in an updated timing advance learning model.
6 . The method of claim 5 , further comprising:
based on the updated timing advance learning model, determining, by the user equipment, a timing advance corresponding to the first radio access network node with respect to the user equipment;
transmitting, by the user equipment to the first radio access network node, a connection establishment request message comprising the timing advance; and
based on the connection establishment request message, establishing, by the user equipment with the first radio access network node, a communication connection, as a result of which the user equipment is in a connected mode with respect to the first radio access network node.
7 . The method of claim 5 , further comprising:
based on the updated timing advance learning model, determining, by the user equipment, a timing advance corresponding to the second radio access network node with respect to the user equipment;
transmitting, by the user equipment to the second radio access network node, a connection establishment request message comprising the timing advance; and
based on the connection establishment request message, establishing, by the user equipment with the second radio access network node, a communication connection, as a result of which the user equipment is in connected mode with respect to the second radio access network node.
8 . A user equipment, comprising at least one processor configured to process executable instructions that, when executed by the processor, facilitate performance of operations, comprising:
receiving, from a radio access network node, a learning model configuration information block message, wherein the learning model configuration information block message comprises a training configuration resource indication indicative of at least one training configuration resource usable to receive, from the radio access network node, a learning model training configuration;
receiving the learning model training configuration according to the at least one training configuration resource;
decoding the learning model training configuration, wherein the learning model training configuration comprises a training action indication indicative of a training action to be performed by the user equipment;
performing the training action to result in a training action result; and
transmitting, to the radio access network node, the training action result,
wherein the at least one training configuration resource comprises at least one time or frequency resource, and wherein the at least one training configuration resource is non-overlapping with non-training idle mode resources.
9 . The user equipment of claim 8 , wherein the training action comprises generating a sounding reference signal to result in the training action result being a generated sounding reference signal and wherein the generated sounding reference signal is transmitted to the radio access network node, the generated sounding reference signal being usable by the radio access network node to train an uplink resource grant learning model to result in a trained uplink resource grant learning model.
10 . The user equipment of claim 9 , wherein the operations further comprise:
establishing a communication connection with the radio access network node, wherein the communication connection comprises at least one uplink resource being granted, based on the trained uplink resource grant learning model, by the radio access network node.
11 . The user equipment of claim 10 , wherein the granting of the at least one uplink resource by the radio access network node is based on excluding, by the user equipment, of transmission of a sounding reference signal after the transmitting, by the user equipment, of the generated sounding reference signal.
12 . The user equipment of claim 8 , wherein the radio access network node is a first radio access network node, wherein the user equipment performs the training action with respect to the first radio access network node to result in the training action result being a first training action result, wherein the user equipment transmits, to the first radio access network node, the first training action result, and wherein the operations further comprise:
performing, with respect to a second radio access network node that is a neighboring radio access network node with respect to the first radio access network node, the training action to result in the second training action result; and
transmitting, to the second radio access network node, the second training action result.
13 . A non-transitory machine-readable medium, comprising executable instructions that, when executed by at least one processor of a user equipment, facilitate performance of operations, comprising:
receiving, while the user equipment is idle, from a first radio access network node, a learning model configuration information block message comprising at least one training result resource usable by the user equipment to receive a training result from the first radio access network node, wherein the training result resource comprises at least one time or frequency resource, and wherein the at least one training result resource is non-overlapping with non-training idle mode resources;
receiving, while the user equipment is idle, from the first radio access network node, a learning model training configuration comprising a training action indication indicative of a training action performable by the user equipment with respect to at least the first radio access network node; and
performing, while the user equipment is idle, the training action with respect to the first radio access network node to result in a first training action result.
14 . The non-transitory machine-readable medium of claim 13 , the operations further comprising:
receiving, from the first radio access network node via the at least one training result resource, the first training action result.
15 . The non-transitory machine-readable medium of claim 13 , the operations further comprising:
performing, while the user equipment is idle, the training action with respect to a second radio access network node to result in a second training action result, wherein the second radio access network node is a neighboring radio access network node with respect to the first radio access network node; and
receiving, from the second radio access network node via the at least one training result resource, the second training action result.
16 . The non-transitory machine-readable medium of claim 13 , wherein the first training action result is to be used by the first radio access network node to update a learning model.
17 . The non-transitory machine-readable medium of claim 13 , wherein the first training action result is to be used by the user equipment to update a learning model to result in an updated learning model to be used by the user equipment.
18 . The non-transitory machine-readable medium of claim 17 , wherein the learning model is a beam selection learning model and wherein the updated learning model is an updated beam selection learning model.
19 . The non-transitory machine-readable medium of claim 18 , wherein the operations further comprise:
determining, while the user equipment is idle, with the updated beam selection learning model, a determined preferred serving beam corresponding to the first radio access network node to be used during a connection establishment corresponding to the first radio access network node;
transmitting, while the user equipment is idle, to the first radio access network node, a connection establishment message comprising a preferred serving beam indication that is indicative to the first radio access network node of the determined preferred serving beam to be used to establish a connection with the first radio access network node; and
establishing the connection with the first radio access network node, wherein the connection comprises the determined preferred serving beam, and wherein the establishing of the connection with the first radio access network node excludes beam sweeping to determine a best beam corresponding to the user equipment.
20 . The non-transitory machine-readable medium of claim 17 , wherein the learning model is a timing advance learning model, and wherein the updated learning model is an updated timing advance learning model.