Device and method for performing handover in wireless communication system
The present disclosure relates to a communication technique for fusing, with an IoT technology, a 5G communication system for supporting a higher a data transmission rate than a 4G system, and a system therefor. According to various embodiments of the present disclosure, a method performed by a base station of a serving cell in a wireless communication system may comprise the steps of: transmitting configuration information for an artificial intelligence (AI)-based handover to a terminal; receiving, from the terminal, a handover request to a target cell according to the AI-based handover; and transmitting, to the terminal, a configuration message for access to the target cell, in response to the handover request, wherein the target cell is identified on the basis of a neural network (NN) configured for the AI-based handover and a measurement result of the terminal.
1. A method performed by a base station (BS) of a serving cell in a wireless communication system, the method comprising:
determining whether to perform an artificial intelligence (AI)-based handover based on a metric associated with an accuracy of the AI-based handover and a threshold;
transmitting, to a user equipment (UE), configuration information for the AI based handover;
receiving, from the UE, a handover request to a target cell according to the AI-based handover; and
transmitting, to the UE, a configuration message for access to the target cell, based on the handover request,
wherein the target cell is identified based on a neural network configured for the AI-based handover and a measurement result of the UE.
2. The method of claim 1 , wherein the configuration information further includes:
indication information indicating a performance of the AI-based handover and information associated with the neural network configured for the AI-based handover, and
wherein the information associated with the neural network includes structure information comprising a connection relation between nodes of the neural network and weight information for weights between the nodes.
3. The method of claim 2 , further comprising:
transmitting, to the UE, a scheduling message including a period of the indication information, a period of the structure information, and a period of the weight information.
4. The method of claim 1 , wherein the handover request includes an identifier of the target cell, the measurement result of the UE used for identifying the target cell, and information associated with the neural network used for identifying the target cell.
5. The method of claim 4 , further comprising:
identifying whether the handover request is valid by determining whether the identifier of the target cell matches an output value of the neural network, wherein the output value is generated based on the measurement result of the UE and the information associated with the neural network; and
in case that the handover request is valid, transmitting, to another BS of the target cell, the handover request.
6. A method performed by a user equipment (UE) in a wireless communication system, the method comprising:
determining whether to perform an artificial intelligence (AI)-based handover based on a metric associated with an accuracy of the AI-based handover and a threshold;
receiving, from a base station (BS) of a serving cell, configuration information for the AI based handover;
identifying a target cell according to the AI-based handover, based on a neural network configured for the AI-based handover and a measurement result;
transmitting, to the BS, a handover request to the target cell to the BS; and
receiving, from the BS, a configuration message for access to the target cell.
7. The method of claim 6 , wherein the configuration information further includes indication information indicating a performance of the AI-based handover and information associated with the neural network configured for the AI-based handover, and
wherein the information associated with the neural network includes structure information comprising a connection relation between nodes of the neural network and weight information for weights between the nodes.
8. The method of claim 7 , further comprising:
receiving, from the BS, a scheduling message including a period of the indication information, a period of the structure information, and a period of the weight information.
9. The method of claim 6 , wherein the handover request includes an identifier of the target cell, the measurement result of the UE used for identifying the target cell, and information associated with the neural network used for identifying the target cell.
10. The method of claim 9 , further comprising:
receiving, from the BS, feedback configuration information for learning the neural network configured for the AI-based handover;
acquiring learning data associated with the serving cell, based on the feedback configuration information; and
transmitting, to the BS of the serving cell or another BS of the target cell, the learning data.
11. A base station (BS) of a serving cell in a wireless communication system, the BS comprising:
a transceiver; and
a controller coupled with the transceiver and configured to:
determine whether to perform an artificial intelligence (AI)-based handover based on a metric associated with an accuracy of the AI-based handover and a threshold,
transmit, to a user equipment (UE), configuration information for an artificial intelligence (AI)-based handover,
receive, from the UE, a handover request to a target cell according to the AI-based handover, and
transmit, to the UE, a configuration message for access to the target cell, based on the handover request,
wherein the target cell is identified based on a neural network configured for the AI-based handover and a measurement result of the UE.
12. The BS of claim 11 , wherein the configuration information further includes indication information indicating a performance of the AI-based handover and information associated with the neural network configured for the AI-based handover, and
wherein the information associated with the neural network includes structure information comprising a connection relation between nodes of the neural network and weight information for weights between the nodes.
13. The BS of claim 12 , wherein the controller is further configured to:
transmit, to the UE, a scheduling message including a period of the indication information, a period of the structure information, and a period of the weight information.
14. The BS of claim 11 , wherein the handover request includes an identifier of the target cell, the measurement result of the UE used for identifying the target cell, and information associated with the neural network used for identifying the target cell.
15. The BS of claim 14 , wherein the controller is further configured to:
identify whether the handover request is valid by determining whether the identifier of the target cell matches a output value of the neural network, wherein the output value is generated based on the measurement result of the UE and the information associated with the neural network, and
in case that the handover request is valid, transmit, to another BS of the target cell, the handover request.
16. The method of claim 1 , wherein the metric for the accuracy of the AI-based handover comprises error information of the AI-based handover.
17. The method of claim 6 , wherein the metric for the accuracy of the AI-based handover comprises error information of the AI-based handover.
18. The BS of claim 11 , wherein the metric for the accuracy of the AI-based handover comprises error information of the AI-based handover.
19. A user equipment (UE) in a wireless communication system, the UE comprising:
a transceiver; and
a controller coupled with the transceiver, and configured to:
determine whether to perform an artificial intelligence (AI)-based handover based on a metric associated with an accuracy of the AI-based handover and a threshold,
receive, from a base station (BS) of a serving cell, configuration information for the AI-based handover,
identify a target cell according to the AI-based handover, based on a neural network configured for the AI-based handover and a measurement result,
transmit, to the BS, a handover request to the target cell, and
receive, from the BS, a configuration message for access to the target cell.
20. The UE of claim 19 ,
wherein the configuration information includes indication information indicating a performance of the AI-based handover and information associated with the neural network configured for the AI-based handover, and
wherein the information associated with the neural network includes structure information comprising a connection relation between nodes of the neural network and weight information for weights between the nodes.
21. The UE of claim 20 , wherein the controller is further configured to:
receive, from the BS, a scheduling message including a period of the indication information, a period of the structure information, and a period of the weight information.
22. The UE of claim 19 , wherein the handover request includes an identifier of the target cell, the measurement result of the UE used for identifying the target cell, and information associated with the neural network used for identifying the target cell.
23. The UE of claim 22 , wherein the controller is further configured to:
receive, from the BS, feedback configuration information for learning the neural network configured for the AI-based handover,
acquire learning data associated with the serving cell, based on the feedback configuration information, and
transmit, to the BS of the serving cell or another BS of the target cell, the learning data.
24. The UE of claim 19 , wherein the metric for the accuracy of the AI-based handover comprises error information of the AI-based handover.