Apparatus and method for load balancing in wireless communication system

A base station (BS) in a wireless communication system, the BS comprising:

• a transceiver;
• a memory storing one or more instructions;
• and
• at least one processor connected with the transceiver and configured to execute the one or more instructions stored in the memory to:
• obtain information about the BS based on a measurement report received from one or more user equipments (UEs) in coverage of the BS, the BS transmitting a signal with at least preset power to the one or more UEs,
• based on the information about the BS, transmit first information about a relation between the BS and the one or more UEs to a reinforcement learning apparatus,
• receive, from the reinforcement learning apparatus, priority information comprising a handover order or handover weights associated with a plurality of BSs, wherein the priority information is determined by the reinforcement learning apparatus based on a number of UEs on which handover is to be performed from among UEs served by the BS, and
• perform a handover procedure with at least one UE by transmitting the priority information to the at least one UE.

An operating method of a reinforcement learning apparatus in a wireless communication system, the operating method comprising:

• receiving, from each of a plurality of base stations (BSs), first information about a relation between a corresponding (BS) and one or more user equipments (UEs) in coverage of the BS;
• determining, based on the first information received from each of the plurality of BSs, a number of UEs on which handover is to be performed from among UEs served by a corresponding BS;
• and
• transmitting, to each of the plurality of BSs, priority information comprising a handover order or handover weights associated with the plurality of BSs, wherein the priority information is determined by the reinforcement learning apparatus based on the number of UEs on which handover is to be performed.

An operating method of a base station (BS) in a wireless communication system, the operating method comprising:

• obtaining information about the BS based on a measurement report received from one or more user equipments (UE) in coverage of the BS, the BS transmitting a signal with at least preset power to the one or more UEs;
• based on the information about the BS, transmitting first information about a relation between the BS and the one or more UEs to a reinforcement learning apparatus;
• receiving, from the reinforcement learning apparatus, priority information comprising a handover order or handover weights associated with a plurality of BSs, wherein the priority information is determined by the reinforcement learning apparatus based on a number of UEs on which handover is to be performed from among UEs served by the BS;
• and
• performing a handover procedure with at least one UE by transmitting the priority information to the one UE.