VoLTE/VoNR performance optimization for a cellular communication system

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

a transceiver configured to receive, from a user equipment (UE), uplink (UL) signals; and

a processor operably coupled to the transceiver, the processor configured to:

identify first and second parameters based on a measurement period of the UL signals, wherein the measurement period comprises a first time period and a second time period,

determine, based on the first and second parameters, a first UL power control parameter corresponding to the first time period and a second UL power control parameter corresponding to the second time period, wherein the first time period is longer than the second time period, and

update the first UL power control parameter based on the first time period and the second UL power control parameter based on the second time period, the first UL power control parameter being updated using an objective function value comprising a rejection rate of a service being served between the UE and the BS, and a normalization factor for a signal to interference and noise ratio (SINR) and a mean opinion source value (MOS) associated with UE capability,

wherein the transceiver is further configured to transmit, to the UE, the updated first and second UL power control parameters for a UL transmit power of the UE.

2 . The BS of claim 1 , wherein:

the first parameter includes at least one of a reference signal received power (RSRP), the SINR, and a channel throughput;

the second parameter includes at least one of a rank indicator (RI), a precoding matrix indicator (PMI), a channel quality indicator (CQI), and a sounding reference signal (SRS);

the first UL power control parameter includes a power of physical uplink shared channel (Po_PUSCH) and a pathloss correction factor (α); and

the second UL power control parameter includes information for a close loop portion of subframe-level power control (f(i)).

3 . The BS of claim 1 , wherein the processor is further configured to use a first deep reinforcement learning (DRL) algorithm to determine the first UL power control parameter and a second DRL algorithm to determine the second UL power control parameter.

4 . The BS of claim 3 , wherein:

the first parameter includes a long-term rewarded parameter associated with the UE for the first time period; and

the processor is further configured to identify, based on the first parameter, the first UL power control parameter using the first DRL algorithm.

5 . The BS of claim 4 , wherein:

the second parameter is an instantaneous rewarded parameter associated with the UE for the second time period; and

the processor is further configured to identify, based om the first UL power control parameter and the second parameter, the second UL power control parameter using the second DRL algorithm.

6 . The BS of claim 1 , wherein the processor is further configured to update the first UL power control parameter using the objective function value given by:

O

=

MOS

avg

C

MOS

-

Rate

rej

+

UL

⁢

_

⁢

SINR

avg

C

SINR

,

where:

MOS avg is an average mean opinion source (MOS) value for each UE supporting a voice over long-term evolution (VoLTE) capability,

C MOS is a normalization factor for MOS,

Rate rej is a VoLTE rejection rate,

UL_SINR avg is an average uplink SINR value for each UE supporting the VoLTE capability, and

C SINR is the normalization factor for the SINR.

7 . The BS of claim 1 , wherein, to identify the first UL power control parameter, the processor is further configured to use a power control algorithm to:

initialize four points based on an initially decided range of the first UL power control parameter;

identify best three points in a set among the four points;

determine a centroid value of the set as a new parameter for the first UL power control parameter as a new search point; and

identify a number of searches based on a predetermined search number and a predetermined stopping condition.

8 . The BS of claim 1 , wherein, to identify the first UL power control parameter, the processor is further configured to use a power control algorithm to:

initialize a default point as a starting parameter for the first UL power control parameter;

identify a search direction in which an objective value increases;

randomly identify a neighbor point when a direction is not identified for the objective value to increase; and

continue a search operation until a stopping condition is satisfied with a predefined condition.

9 . The BS of claim 1 , wherein:

the processor is further configured to identify the second UL power control parameter based on neural network processing of the second parameter and reward calculation information received from the UE; and

the transceiver is further configured to transmit, to the UE, the second UL power control parameter.

10 . A method of base station (BS) in a wireless communication system, the method comprising:

receiving, from a user equipment (UE), uplink (UL) signals;

identifying first and second parameters based on a measurement period of the UL signals, wherein the measurement period comprises a first time period and a second time period;

determining, based on the first and second parameters, a first UL power control parameter corresponding to the first time period and a second UL power control parameter corresponding to the second time period, wherein the first time period is longer than the second time period;

updating the first UL power control parameter based on the first time period and the second UL power control parameter based on the second time period, wherein the first UL power control parameter is updated using an objective function value comprising a rejection rate of a service being served between the UE and the BS, and a normalization factor for a signal to interference and noise ratio (SINR) and a mean opinion source value (MOS) associated with UE capability; and

transmitting, to the UE, the updated first and second UL power control parameters for a UL transmit power of the UE.

11 . The method of claim 10 , wherein:

the first parameter includes at least one of a reference signal received power (RSRP), the SINR, and a channel throughput;

the second parameter includes at least one of a rank indicator (RI), a precoding matrix indicator (PMI), a channel quality indicator (CQI), and a sounding reference signal (SRS);

the first UL power control parameter includes a power of physical uplink shared channel (Po_PUSCH) and a pathloss correction factor (α); and

the second UL power control parameter includes information for a close loop portion of subframe-level power control (f(i)).

12 . The method of claim 10 , further comprising using a first deep reinforcement learning (DRL) algorithm to determine the first UL power control parameter and a second DRL algorithm to determine the second UL power control parameter.

13 . The method of claim 12 , further comprising:

identifying, based on the first parameter, the first UL power control parameter using the first DRL algorithm,

wherein the first parameter includes a long-term rewarded parameter associated with the UE for the first time period.

14 . The method of claim 13 , further comprising:

identifying, based on the first UL power control parameter and the second parameter, the second UL power control parameter using the second DRL algorithm,

wherein the second parameter is an instantaneous rewarded parameter associated with the UE for the second time period.

15 . The method of claim 10 , further comprising updating the first UL power control parameter using the objective function value given by:

O

=

MOS

avg

C

MOS

-

Rate

rej

+

UL

⁢

_

⁢

SINR

avg

C

SINR

,

where:

MOS avg is an average mean opinion source (MOS) value for each UE supporting a voice over long-term evolution (VoLTE) capability,

C MOS is a normalization factor for MOS,

Rate rej is a VoLTE rejection rate,

UL_SINR avg is an average uplink SINR value for each UE supporting the VoLTE capability, and

C SINR is the normalization factor for the SINR.

16 . The method of claim 10 , further comprising, for identifying the first UL power control parameter using a power control algorithm:

initializing four points based on an initially decided range of the first UL power control parameter;

identifying best three points in a set among the four points;

determining a centroid value of the set as a new parameter for the first UL power control parameter as a new search point; and

identifying a number of searches based on a predetermined search number and a predetermined stopping condition.

17 . The method of claim 10 , further comprising, to identify the first UL power control parameter using a power control algorithm:

initializing a default point as a starting parameter for the first UL power control parameter;

identifying a search direction in which an objective value increases;

randomly identifying a neighbor point when a direction is not identified for the objective value to increase; and

continuing a search operation until a stopping condition is satisfied with a predefined condition.

18 . The method of claim 10 , further comprising:

identifying the second UL power control parameter based on neural network processing of the second parameter and reward calculation information received from the UE; and

transmitting, to the UE, the second UL power control parameter.

19 . A non-transitory computer-readable medium comprising program code, that when executed by at least one processor, causes an electronic device to:

identify first and second parameters based on a measurement period of received uplink (UL) signals, wherein the measurement period comprises a first time period and a second time period;

determine, based on the first and second parameters, a first UL power control parameter corresponding to the first time period and a second UL power control parameter corresponding to the second time period, wherein the first time period is longer than the second time period;

update the first UL power control parameter based on the first time period and the second UL power control parameter based on the second time period, wherein the first UL power control parameter is updated using an objective function value comprising a rejection rate of a service being served between a user equipment (UE) and a base station, and a normalization factor for a signal to interference and noise ratio (SINR) and a mean opinion source value (MOS) associated with UE capability; and

transmit, the UE, the updated first and second UL power control parameters for a UL transmit power of the UE.

20 . The non-transitory computer-readable medium of claim 19 , wherein:

the first parameter includes at least one of a reference signal received power (RSRP), the SINR, and a channel throughput;

the second parameter includes at least one of a rank indicator (RI), a precoding matrix indicator (PMI), a channel quality indicator (CQI), and a sounding reference signal (SRS);

the first UL power control parameter includes a power of physical uplink shared channel (Po_PUSCH) and a pathloss correction factor (α); and

the second UL power control parameter includes information for a close loop portion of subframe-level power control (f(i)).