Electronic device and method for providing scheduling information based on learning in wireless communication system
An electronic device may include a storage device and at least one processor, wherein the at least one processor may obtain environmental information from a radio access network (RAN) to store the environmental information in the storage device, identify at least one first configuration value for scheduling a radio resource from the obtained environmental information, based on a learning model generated based on previously obtained environmental information, compare the first configuration value with at least one threshold value, adjust the first configuration value to a second configuration value, and transmit the adjusted second configuration value to the RAN.
1 . An electronic device comprising:
memory storing instructions and comprising a storage device; and
at least one processor,
wherein the instructions when executed by the at least one processor, cause the electronic device to:
obtain, from a radio access network (RAN), environmental information corresponding to each of at least one parameter associated with the RAN,
store the environmental information in the storage device,
identify at least one first configuration value for scheduling a radio resource from the obtained environmental information, based on a learning model generated based on previously obtained environmental information,
determine at least one threshold value based on at least one previously obtained value of the at least one first configuration value,
compare the at least one first configuration value with the at least one threshold value, respectively,
adjust, based on a result of the comparison of the at least one first configuration value with the at least one threshold value, the at least one first configuration value to at least one second configuration value, and
transmit the at least one second configuration value to the RAN.
2 . The electronic device of claim 1 , wherein the environmental information comprises state information, and
wherein the state information comprises at least one of information indicating a throughput for at least one user equipment (UE) connected to the RAN or information indicating a modulation and coding scheme (MCS) for the at least one UE.
3 . The electronic device of claim 1 , wherein the environmental information comprises reward information, and
wherein the reward information comprises at least one of delay information about at least one user equipment (UE) connected to the RAN or information indicating a cumulative transport block size (TBS) for the at least one UE.
4 . The electronic device of claim 1 , wherein the at least one first configuration value comprises information related to radio resource allocation for a plurality of user equipments (UEs) connected to the RAN.
5 . The electronic device of claim 4 , wherein the information related to the radio resource allocation comprises information corresponding to at least one parameter for allocating the radio resource, based on proportional fairness (PF).
6 . The electronic device of claim 5 , wherein the at least one parameter for allocating the radio resource, based on the PF, the radio resource comprises at least one of a parameter corresponding to an increase in fairness, a parameter corresponding to an increase in throughput, or a parameter corresponding to a number of sub-bands allocable within a configured time period.
7 . The electronic device of claim 1 , wherein the learning model comprises at least one of a reinforcement learning model, a supervised learning model, an unsupervised learning model, or a semi-supervised learning model.
8 . The electronic device of claim 1 ,
wherein the at least one second configuration value is determined within a configured range from the first threshold value.
9 . The electronic device of claim 8 , wherein the at least one threshold value comprises a second threshold value corresponding to an initial configuration value, and
wherein the at least one second configuration value is determined within a configured range from the second threshold value.
10 . The electronic device of claim 1 , wherein the instructions when executed by the at least one processor, further cause the electronic device to use the at least one second configuration value as data of the learning model.
11 . An electronic device comprising:
memory storing instructions and comprising a storage device; and
at least one processor,
wherein the instructions when executed by the at least one processor, cause the electronic device to:
obtain, from a radio access network (RAN), environmental information corresponding to each of at least one parameter associated with the RAN,
identify at least one first configuration value for scheduling a radio resource from the obtained environmental information, based on a learning model generated based on previously obtained environmental information,
determine at least one threshold value based on at least one previously obtained value of the at least one first configuration value,
compare the at least one first configuration value with the at least one threshold value, respectively,
adjust, based on a result of the comparison of the at least one first configuration value with the at least one threshold value, the at least one first configuration value to at least one second configuration value,
store the at least one second configuration value in the storage device, and
input, into the learning model, the at least one second configuration value as data of the learning model.
12 . The electronic device of claim 11 , wherein the instructions when executed by the at least one processor, further cause the electronic device to transmit, to the RAN, the at least one first configuration value.
13 . The electronic device of claim 11 , wherein the environmental information comprises state information, and
wherein the state information comprises at least one of information indicating a throughput for at least one user equipment (UE) connected to the RAN or information indicating a modulation and coding scheme (MCS) for the at least one UE.
14 . The electronic device of claim 11 , wherein the environmental information comprises reward information, and
wherein the reward information comprises at least one of delay information about at least one user equipment (UE) connected to the RAN or information indicating a cumulative transport block size (TBS) for the at least one UE.
15 . The electronic device of claim 11 , wherein the learning model comprises at least one of a reinforcement learning model, a supervised learning model, an unsupervised learning model, or a semi-supervised learning model.
16 . A method of operating an electronic device for providing scheduling information by learning in a wireless communication system, the method comprising:
obtaining, from a radio access network (RAN), environmental information corresponding to each of at least one parameter associated with the RAN;
identifying at least one first configuration value for scheduling a radio resource from the obtained environmental information, based on a learning model generated based on previously obtained environmental information;
determining at least one threshold value based on at least one previously obtained value of the at least one first configuration value;
comparing the at least one first configuration value with the at least one threshold value, respectively;
adjusting, based on a result of the comparing of the at least one first configuration value with the at least one threshold value, the at least one first configuration value to at least one second configuration value; and
inputting, into the learning model, the at least one second configuration value as data of the learning model.
17 . The method of claim 16 , further comprising:
transmitting the at least one first configuration value to the RAN.
18 . The method of claim 16 , wherein the environmental information comprises state information, and
wherein the state information comprises at least one of information indicating a throughput for at least one user equipment (UE) connected to the RAN or information indicating a modulation and coding scheme (MCS) for the at least one UE.
19 . The method of claim 16 , wherein the environmental information comprises reward information, and
wherein the reward information comprises at least one of delay information about at least one user equipment (UE) connected to the RAN or information indicating a cumulative transport block size (TBS) for the at least one UE.
20 . The method of claim 16 , wherein the learning model comprises at least one of a reinforcement learning model, a supervised learning model, an unsupervised learning model, or a semi-supervised learning model.