KR20230097696A - Rate-splitting multiple access method for the base station with limited energy supply to maximize the sum rate based on deep reinforcement learning - Google Patents

Abstract

According to an embodiment of the present invention, a transmission rate division multiple access method for maximizing an aggregate transmission rate of a base station having limited energy supply includes determining a first transmit power based on information of the base station in a first state; dividing data to be transmitted to a plurality of terminals into shared and private messages, and encoding the shared and private messages into shared and private streams, respectively; performing power allocation and beamforming design for each of the coded shared and private streams within the determined transmission power; transmitting the data to the plurality of terminals and receiving a sum transmission rate; and determining a second transmit power based on the received sum rate and the base station information in the second state. Accordingly, in an embodiment of the present invention, the base station determines the transmission power by using deep reinforcement learning based on the sum rate and base station state information received from the plurality of terminals, and uses an optimization technique within the determined transmission power. By designing power allocation and beamforming for each of the coded shared and private streams, a base station with limited energy supply can efficiently use the supplied energy to suit changing external energy and communication channel conditions.

Description

Rate-splitting multiple access method for the base station with limited energy supply to maximize the sum rate based on deep reinforcement learning}

The present invention relates to a rate division multiple access method for maximizing the sum rate in a base station with limited energy supply, and more specifically, to optimize power allocation and beamforming design in a transmitter using deep reinforcement learning and optimization techniques. , a rate division multiple access method for maximizing the sum rate in a communication environment where energy supply is limited.

Since the advent of LTE-based 4G mobile communication, MIMO (Multiple Input Multiple Output) technology using multiple antennas has become a core technology that is essential for mobile communication. Recently, MIMO technology has been developed into Massive MIMO, etc., and theoretically, infinite antennas are considered. In addition, in wireless LAN, MIMO technology has been spread starting with 802.11n, and all recently released wireless LANs adopt MIMO technology as a standard. MIMO) technology has emerged.

Multi-user MIMO technology can simultaneously support services to multiple users in the same frequency band using multiple antennas in one base station, thereby increasing the efficiency of the radio band. Despite these advantages, since one base station uses multiple antennas to provide services to multiple users, there is a problem of inter-user interference. Since it changes rapidly, it is practically impossible to obtain accurate channel information for all users, and thus signal interference between service users is unavoidable.

Rate-Splitting Multiple Access (RSMA) is a non-orthogonal multi-user access technology that has excellent performance and robustness in a multi-user and multi-antenna communication environment and is capable of supporting multiple users in a variety of channel environments. . This rate division multiple access technology has strengths compared to existing multiple access technologies in terms of energy and frequency band efficiency and robustness against inaccurate channel state information. On the other hand, the transmission rate division multiple access technology so far uses a base station with no limit on transmission power to obtain the maximum sum transmission rate in preparation for changing channel state information in an environment where the base station can provide services to users with a certain transmission power. has been developed to provide

In 6G, a next-generation mobile communication technology that uses a high-frequency band (mmWave) with strong linearity, the importance of a mobile base station using a drone-type base station platform, an unmanned aerial vehicle system, is gradually emerging. Since the high frequency band utilizes a wider bandwidth than the existing frequency band, it is suitable for transmitting large amounts of data, but is relatively vulnerable to radio wave shadowing due to its strong linearity. The importance of small cells is increasing. Since the mobile base station is supplied with energy through external energy such as solar energy and RF signal due to limited transmission power, it is possible to provide reliable service to the user by using it efficiently and appropriately for the communication channel condition. However, it is difficult to efficiently use the energy supplied appropriately to the changing external energy and communication channel conditions. Accordingly, in the transmission rate division multiple access method for maximizing the sum transmission rate of a base station with limited energy supply, a multiple access method capable of efficiently using the energy supplied appropriately to the changing external energy and communication channel conditions is required.

The present invention is to solve the problems of the prior art as described above, and a base station with limited energy supply that allows the base station to efficiently use energy supplied appropriately for changing external energy and communication channel conditions maximizes the sum transmission rate. It is to provide a rate division multiple access method to perform.

According to a first aspect of the present invention, a rate division multiple access method for maximizing the sum transmission rate of a base station with limited energy supply includes determining a first transmit power based on information of the base station in a first state; dividing data to be transmitted to a plurality of terminals into shared and private messages, and encoding the shared and private messages into shared and private streams, respectively; performing power allocation and beamforming design for each of the coded shared and private streams within the determined transmission power; transmitting the data to the plurality of terminals and receiving a sum transmission rate; and determining a second transmission power based on the received sum rate and the base station information in a second state.

A base station using rate division multiple access for maximizing a sum rate in a communication environment in which energy supply is limited according to a second feature of the present invention includes a transceiver for transmitting and receiving signals to and from a plurality of terminals; a processor connected to the transceiver and controlling an operation of the base station; and a memory, wherein the processor determines a first transmit power based on the base station information in a first state; dividing data to be transmitted to the plurality of terminals into shared and personal messages, and encoding the shared and personal messages into shared and personal streams, respectively; performing power allocation and beamforming design for each of the coded shared and private streams within the determined transmit power; transmitting the data to the plurality of terminals and receiving a sum transmission rate; and determining a second transmit power based on the received sum rate and the base station information in the second state.

In order to provide transmission rate division multiple access for maximizing the sum transmission rate in a communication environment with limited energy supply according to the third aspect of the present invention, a program of instructions executable by a digital processing device is tangibly implemented, and the digital processing device The recording medium, which can be read by , is characterized in that a program for executing the transmission rate division multiple access method according to the first aspect of the present invention in a computer is recorded.

The rate division multiple access method for maximizing the sum rate of a base station with limited energy supply according to an embodiment of the present invention provides the following effects.

The base station determines the transmission power using deep reinforcement learning based on the sum transmission rate and base station state information received from the plurality of terminals, and allocates power to each of the coded shared and private streams using an optimization technique within the determined transmission power And by designing beamforming, a base station with limited energy supply can efficiently use the supplied energy to suit the changing external energy and communication channel conditions.

The above effect is a greater advantage when the base station is a mobile base station inevitably limited in energy supply, and such a mobile base station plays a role in connecting cells to cells, making it easier to secure network connectivity, It is possible to support services even in areas where communication is restricted because there is no existing base station.

By using rate-division multiple access technology, it is possible to provide reliable services to users using the same frequency band even if channel state information of users is not accurately known in a multi-user MIMO environment.

1 is a flowchart of a rate division multiple access method for maximizing a sum rate based on deep reinforcement learning in a base station with limited energy supply according to an embodiment of the present invention.
2 is a block diagram illustrating a base station using rate division multiple access for maximizing the sum rate in a communication environment where energy supply is limited according to an embodiment of the present invention.
FIG. 3 is a diagram schematically illustrating a series of processes in which a rate division multiple access method for maximizing the sum rate is performed by a base station with limited energy supply according to an embodiment of the present invention.
4 is a graph comparing performance of multiple access technologies including rate division multiple access technology according to an embodiment of the present invention.
5 is a graph comparing performance of multiple access technologies including rate division multiple access technology using deep reinforcement learning in a communication environment where energy supply is limited according to an embodiment of the present invention.

Hereinafter, the present invention will be described in detail with reference to examples and drawings. However, the following description is not intended to limit the present invention to specific embodiments, and in describing the present invention, if it is determined that the detailed description of related known technologies may obscure the gist of the present invention, the detailed description will be omitted. .

In embodiments of the present invention, a base station generally refers to a fixed station that communicates with a wireless device, but may have mobility, and may be replaced by terms such as eNB (evolved-NodeB) and BTS (base transceiver system). there is.

In addition, in embodiments of the present invention, a terminal may be fixed or mobile, and may include a user equipment (UE), a mobile station (MS), a subscriber station (SS), and a mobile subscriber station (MSS). Mobile Subscriber Station), Mobile Terminal, or Advanced Mobile Station (AMS).

1 is a flow chart of a rate division multiple access method for maximizing the sum transmission rate of a base station with limited energy supply according to an embodiment of the present invention, and FIG. It is a block diagram showing a base station using rate division multiple access for maximizing the sum rate in a communication environment.

Referring to FIG. 1, a rate division multiple access method 100 for maximizing the sum rate of a base station 200 with limited energy supply according to an embodiment of the present invention is based on the base station information in the first state Determining a first transmit power (110); Dividing data to be transmitted to a plurality of terminals 300 into shared and personal messages, and encoding the shared and personal messages into shared and personal streams (120); performing power allocation and beamforming design for each of the coded shared and private streams within the determined transmit power (130); transmitting the data to the plurality of terminals 300 and receiving a sum transmission rate (140); and determining (150) a second transmit power based on the received sum rate and the base station information in the second state.

Referring to FIG. 2, a base station 200 using rate division multiple access for maximizing a sum rate based on deep reinforcement learning in a communication environment with limited energy supply according to an embodiment of the present invention includes a plurality of terminals. a transceiver 210 for transmitting and receiving signals with the field 300; a processor 220 connected to the transceiver 210 and controlling an operation of the base station 200; and a memory 230, wherein the processor 220 includes an operation 110 of determining a first transmission power based on the base station information in a first state; dividing data to be transmitted to the plurality of terminals 300 into shared and personal messages, and encoding the shared and personal messages into shared and personal streams (120); performing power allocation and beamforming design for each of the coded shared and private streams within the determined transmit power (130); an operation 140 of transmitting the data to the plurality of terminals 300 and receiving a sum transmission rate; and an operation 150 of determining a second transmit power based on the received sum rate and the base station information in the second state.

The base station 200 determines transmission power based on base station status information. In one embodiment of the present invention, the state information of the base station may include the amount of energy harvested in the base station, the amount of energy stored in the base station, and channel information fed back from a plurality of communicating terminals 300. .

The determination of the transmit power is performed by the processor 220 of the base station 200 receiving state information of the base station through the transceiver 210 and the memory 230 and performing a deep reinforcement learning algorithm.

In an embodiment of the present invention, the deep reinforcement learning algorithm is a machine learning-based model and may be a reinforcement learning-based model. Reinforcement learning-based models can be continuously or periodically updated as they learn without manager intervention.

In the reinforcement learning-based model, an agent takes an action from the environment, and accordingly, a reward and a state are given to the agent, and the agent is selected so that the reward is the largest. It can be a training model. A model based on reinforcement learning may be classified into a model using a model-based algorithm or a model using a model-free algorithm, depending on whether an agent has prior knowledge.

Deep reinforcement learning is an algorithm that uses a deep neural network to solve a problem in a continuous and complex state space and action space like a real environment using reinforcement learning as described above. In an embodiment of the present invention, the agent is a base station, the environment is a rate division multiple access communication environment with limited energy supply, the action is transmission from the base station to the user, the compensation is the sum transmission rate, the state is the amount of energy harvested, and the base station It can be set based on the amount of stored energy and channel information fed back from a plurality of communicating terminals.

In an embodiment of the present invention, a deep reinforcement learning algorithm used to determine transmission power may be a soft actor critic (SAC) algorithm.

The base station 200 divides data to be transmitted to a plurality of terminals 300 into two types, a common message and a private message, using rate division multiple access technology. A shared message is encoded into one shared stream using a codebook shared by all users, which can be decoded by all users. A personal message is encoded into a personal stream through a codebook that only a specific user corresponding to each message has, and can be decoded only by the specific user.

The user decrypts the shared stream and obtains the portion of the shared message that corresponds to his/her own message. In addition, the shared stream is removed from the received signal through successive interference cancellation (SIC). The sequential interference cancellation technique is used to simultaneously process multiple received signals at the receiver side. This technique allows a receiver to process a signal using a difference in signal strength among target signals. That is, the receiver decodes the stronger signal, first extracts the stronger signal from the superimposed signal, and then removes the weaker signal from the remaining signals.

After removing the shared stream, the user has only interference caused by the personal stream corresponding to other users, and treats it as noise to decode the desired personal stream. Through decoding of a shared stream and a private stream using the sequential interference cancellation technique, each user can obtain an original message corresponding to himself/herself.

Therefore, the base station multicasts a part of the message to be transmitted to the users by utilizing the shared message in a situation where the channel state information of the users to be provided with service is not accurately known (eg, due to quantization error, channel state change, etc.) (multicast) to minimize signal interference between adjacent users.

The base station performs power allocation and beamforming design for one shared stream using a precoder to transmit the divided message to multiple users, and power allocation and beamforming for each individual stream. Do a foam design. In this case, power allocation and beamforming design of shared streams and power allocation of individual streams correspond to non-convex problems.

Convex problems have one minimum (global minimum) or one maximum (global maximum), so it is relatively easy to calculate them, but in the case of a non-convex problem, such as a cubic equation, additional Since it has a local minimum and a local maximum, it is relatively difficult to calculate the minimum or maximum value. For example, in a non-convex problem, when solving a problem using methods such as gradient descent, which is a representative method for solving convex problems, it does not converge to the minimum or maximum value, but falls into the minimum or maximum value, There may be cases where the desired minimum or maximum value cannot be calculated.

Accordingly, in an embodiment of the present invention, power allocation and beamforming design for each of the coded shared and private streams are preferentially performed using a zero-forcing technique. In addition, power allocation of personal streams, power allocation of shared streams, and beamforming design of shared streams may be performed using an optimization algorithm.

In an embodiment of the present invention, an optimization algorithm used for power allocation of a personal stream, power allocation of a shared stream, and beamforming design of a shared stream may be a sequential least squares programming (SLSQP) algorithm.

In an embodiment of the present invention, the SLSQP algorithm simplifies power allocation of private streams, power allocation of shared streams, and beamforming design of shared streams, approximates the objective function with a convex quadratic equation, calculates the next point, and predicts the next point again. It is possible to optimally solve a non-convex/non-linear problem by repeating a series of processes of performing the same method and solving the problem.

In an embodiment of the present invention, the SLSQP algorithm is a constraint condition that the base station cannot set the power allocation higher than the transmit power determined as a result of deep reinforcement learning with respect to power allocation of the personal stream and the shared stream, and all desired transmission It operates under the upper and lower limit conditions that the sum of the power allocation ratios of messages must be less than or equal to 1, and regarding the beamforming design of the shared stream, the square of the L2 norm of the normalized beamforming vector of the shared stream must be less than or equal to 1 operate under the conditions

FIG. 3 is a diagram schematically illustrating a series of processes in which a rate division multiple access method for maximizing the sum rate is performed by a base station with limited energy supply according to an embodiment of the present invention.

Referring again to FIG. 2 together with FIG. 3 , the base station 200 includes a transceiver 210 , a processor 220 and a memory 230 . The processor 220 may be configured to implement the procedures and/or methods proposed in the present invention. The memory 230 is connected to the processor 220 and stores various information related to the operation of the processor 220 . The transceiver 210 is connected to the processor 220 and communicates with the plurality of terminals 300 to transmit and/or receive radio signals.

In FIG. 3, B _i is the amount of energy stored in the base station in the ith step, E _i is the amount of energy harvested in the ith step, and h _i is the channel state to be fed back to the base station by a plurality of terminals in the ith step. Information H _i represents channel state information fed back by the base station from a plurality of terminals in the i-th step, and e _i represents channel state information loss occurring in the i-th step.

In one embodiment of the present invention, the base station 200 may transmit data to a plurality of terminals 300 and receive the sum data rate 10 . In addition, transmission power may be determined again based on the received sum rate 10 and base station information 20 in the next state.

Referring to FIG. 3, base station information 20 in the next state includes the amount of energy stored in the base station at the i-th step (B _i ), the amount of energy harvested at the ith step (E _i ), and the i-th step. This is information including the feedback received channel information state (H _i ).

A deep reinforcement learning algorithm may be used to determine the transmission power, and in an embodiment of the present invention, the deep reinforcement learning algorithm may be a soft actor critic (SAC) algorithm 30 .

The base station 200 determines transmission power to be used based on the amount of energy stored in the base station, the amount of harvested energy, and the state of channel information received as feedback. Thereafter, the base station 200 receives the sum transmission rate 10 from the communication environment (ie, the plurality of terminals 300) as a reward, evaluates the action performed, and at the same time receives base station information 20 of the next state. do. Referring to this, the agent can determine the optimal transmission power by repeating a series of learning processes in a direction that can receive a larger reward.

In this case, the amount of energy stored in the base station must satisfy certain conditions, and the amount of energy stored in the base station is b1 and b2 step by step, max b is the maximum amount of energy that can be stored in the base station, p is the transmit power, and transmission If the time is T and the amount of harvested energy is E, the conditions are as follows.

b2 = m(b1, p, E) = min(max b, b1-pT+E)

Therefore, in one embodiment of the present invention, the amount of energy stored in the base station in the second state is: (a) the amount of maximum energy that the base station can hold, (b) the amount of energy stored in the base station in the first state The amount of energy obtained by subtracting the product of the determined transmit power in the first state and the time at which the data is transmitted, and adding the amount of energy harvested to the base station in the second state, in the case of (a) and (b), the smaller energy can be determined by the amount of

The transmit power 40 determined again through the soft actor critic (SAC) algorithm 30, which is a deep reinforcement learning algorithm, is used to design power allocation and beamforming for each of the shared and private streams encoded in the i-th step, and these operations In the performance of SLSQP (sequential least squares programming) algorithm 50, which is an optimization technique, is used, and data is transmitted to a plurality of terminals 300, which are a plurality of users, by using an optimal precoder in the i-th step. .

Then, the base station 200 receives the new sum rate from the plurality of terminals 300 as a reward and evaluates the action performed. As described above, the rate division multiple access method for maximizing the sum rate repeatedly can be performed

In one embodiment of the present invention, a base station in a communication environment where energy supply is limited may be a mobile base station. The drone-type base station platform makes it easier to secure network connectivity by serving as a link between cells, and enables service to be supported even in areas where communication is restricted because base stations do not exist. In addition, by raising the height of the base station to secure the maximum line of sight, it is possible to compensate for weaknesses in high-frequency band communication such as shadowing, and to provide continuous service even when the existing base station is destroyed due to natural disasters. this is possible

Since the mobile base station receives energy through external energy such as solar energy and RF signal due to limited transmission power, it is possible to provide reliable service to the user by using it efficiently and appropriately for the communication channel condition. The sum transmission rate according to the present invention Through the transmission rate division multiple access method for maximizing, it is possible to efficiently use energy supplied appropriately to changing external energy and communication channel conditions.

In the following, 1) performance comparison of rate division multiple access technology and other multiple access technologies, and 2) performance comparison of rate division multiple access technology and other multiple access technologies using deep reinforcement learning in a communication environment with limited energy supply. The experimental process and results are explained in detail.

4 is a graph comparing performance of multiple access technologies including rate division multiple access technology according to an embodiment of the present invention, and FIG. 5 is deep reinforcement learning in a communication environment with limited energy supply according to an embodiment of the present invention. This is a graph comparing the performance of multiple access technologies including this utilized rate division multiple access technology.

The simulation environment for the experiment is a communication environment in which a mobile base station provides services to multiple users after receiving external energy as much as the battery's chargeable capacity with a 50% probability through energy harvesting. In this case, the user completely knows the channel state information, and in the process of feeding it back to the base station, loss of channel state information occurs due to quantization errors, rapid changes in channel state, and the like. Accordingly, the base station receives incomplete channel state information as feedback.

In the graphs of FIGS. 4 and 5, the x-axis is the number of learning iterations, and 100 steps were set to 1 iteration in the simulation process. The y-axis is a relative measure of the performance evaluated by the learned agent for the specified verification environment every 1000 steps. Here, step means interaction between agent and environment.

The verification environment was set identically to the learning environment. The mobile base station is optimally configured under the same configuration of the amount of energy harvested, the amount of energy remaining in the battery, and the feedback channel information after receiving external energy as much as the battery's chargeable capacity with a 50% probability through energy harvesting. Determines the transmit power of the system to provide services to multiple users. Then, it receives a reward from the environment, i.e., the sum rate. For clearer visualization in performance comparison, the reward received from the environment was multiplied by 1/10000 to calculate the value and set to be shown on the y-axis of the graph, and the verification model was set constant to ensure the consistency of the evaluation process.

Referring back to FIG. 4 , the following four cases were compared. Equal (Equal Power Allocation Precoder) Greedy, WF (Water Filling Precoder) Greedy, SLSQP Greedy (when the base station recognizes that the incomplete channel status information it has received is incomplete), SLSQP Greedy (no-info σ _e ) ( When the base station recognizes that the incomplete channel state information it has received is complete).

Greedy means that deep reinforcement learning is not applied. That is, when the base station harvests energy, it is a case in which all of the harvested energy is used as soon as it is harvested without considering the harvested energy, the amount of energy remaining in the battery, and feedback channel information.

SLSQP Greedy and SLSQP Greedy (no-info σ _e ) are the results of using rate-division multiple access technology that divides messages into private messages and shared messages and transmits them together. Equal Greedy and WF Greedy do not divide messages into private messages and shared messages. It is a general multiple access technology that transmits messages only in a unicast method without

Through the experimental results of FIG. 4, it can be seen that the transmission rate division multiple access technology that transmits a message by dividing it into a personal message and a shared message shows superior performance in terms of the sum transmission rate compared to other multiple access technologies that do not use a shared message. .

Referring back to FIG. 5 , the following 8 cases were compared. SAC+SLSQP, SAC+SLSQP(no-info σ _e ), SAC+WF, SAC+Equal, Equal Greedy, WF Greedy, SLSQP Greedy, SLSQP Greedy(no-info σ _{e )} .

Through the experimental results of FIG. 5, it can be confirmed that the results of the 4 cases using deep reinforcement learning in the energy harvesting environment show superior performance in terms of sum transmission rate compared to the results of the 4 cases without using deep reinforcement learning. there is. In addition, comparing each Greedy case under the same conditions with respect to the case using deep reinforcement learning, it can be confirmed that the rate division multiple access technology shows superior performance compared to other multiple access technologies that do not use shared messages. Therefore, it can be seen that the transmission rate division multiple access method for maximizing the transmission rate based on deep reinforcement learning considering energy harvesting according to the present invention shows superior performance compared to existing multiple access technologies under the same communication environment.

As described above, the rate division multiple access method for maximizing the sum rate by a base station with limited energy supply according to an embodiment of the present invention is based on the sum rate and base station status information received by the base station from a plurality of terminals. Determining the transmission power using deep reinforcement learning, and using an optimization technique within the determined transmission power to design power allocation and beamforming for each coded shared and private stream, thereby changing external energy and communication in a base station with limited energy supply It provides an effect that can efficiently use the energy supplied to suit the channel state.

An embodiment according to the present invention may be implemented by various means, for example, hardware, firmware, software, or a combination thereof. In the case of hardware implementation, one embodiment of the present invention provides one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), FPGAs ( field programmable gate arrays), processors, controllers, microcontrollers, microprocessors, etc.

In the case of implementation by firmware or software, an embodiment of the present invention may be implemented in the form of a module, procedure, or function that performs the functions or operations described above. The software codes may be stored in a memory unit and driven by a processor. The memory unit may be located inside or outside the processor and exchange data with the processor by various means known in the art.

Meanwhile, the embodiments of the present invention can be implemented as computer readable codes in a computer readable recording medium. The computer-readable recording medium includes all types of recording devices in which data that can be read by a computer system is stored.

Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc., and implementation in the form of a carrier wave (for example, transmission over the Internet) include In addition, the computer-readable recording medium may be distributed to computer systems connected through a network, so that computer-readable codes may be stored and executed in a distributed manner. In addition, functional programs, codes, and code segments for implementing the present invention can be easily inferred by programmers in the technical field to which the present invention belongs.

As various modifications may be made to the configurations and methods described and illustrated herein without departing from the scope of the present invention, all matter contained in the above detailed description or shown in the accompanying drawings is illustrative and not intended to limit the present invention. It is not. Accordingly, the scope of the present invention is not limited by the above-described exemplary embodiments, and should be defined only in accordance with the following claims and equivalents thereof.

10: sum transmission rate of step i-1 20: base station state information of step i
30: SAC algorithm 40: determined transmission power of step i
50: SLSQP algorithm 200: base station
210: transceiver 220: processor
230: memory 300: user terminals

Claims (15)

In a rate division multiple access method for a base station with limited energy supply to maximize the sum rate,
determining a first transmission power based on the base station information in a first state;
dividing data to be transmitted to a plurality of terminals into shared and private messages, and encoding the shared and private messages into shared and private streams, respectively;
performing power allocation and beamforming design for each of the coded shared and private streams within the determined transmission power;
transmitting the data to the plurality of terminals and receiving a sum transmission rate; and
determining a second transmit power based on the received sum rate and the base station information in a second state;
Rate division multiple access method comprising a. According to claim 1,
Power allocation and beamforming design for each of the encoded shared and private streams are performed first using a zero-forcing technique, and power allocation and beamforming design of the private streams are performed first. The transmission rate division multiple access method, characterized in that the power allocation of the stream and the beamforming design of the shared stream are performed using a first optimization algorithm. According to claim 2,
The first optimization algorithm is a rate division multiple access method, characterized in that the SLSQP (sequential least squares programming) algorithm. According to claim 1,
The base station information in the first and second states includes an amount of energy harvested in the base station, an amount of energy stored in the base station, and channel information fed back from the plurality of terminals,
The transmission power is determined by using a second deep reinforcement learning algorithm. According to claim 4,
The amount of energy stored in the base station in the second state is
(a) the maximum amount of energy that can be possessed by the base station;
(b) subtracting the product of the determined transmission power in the first state and the time at which the data is transmitted from the amount of energy stored in the base station in the first state, and adding the amount of energy harvested in the base station in the second state amount of energy;
The transmission rate division multiple access method, characterized in that the determination is made with the smaller amount of energy among (a) and (b). According to claim 4,
The second deep reinforcement learning algorithm is a rate division multiple access method, characterized in that the soft actor critic (SAC) algorithm. According to claim 1,
The rate division multiple access method, characterized in that the base station is a mobile base station. In a base station using rate division multiple access for maximizing the sum rate in a communication environment where energy supply is limited,
Transmitting and receiving unit for transmitting and receiving signals with a plurality of terminals;
a processor connected to the transceiver and controlling an operation of the base station; and a memory;
the processor,
determining a first transmit power based on the base station information in a first state;
dividing data to be transmitted to the plurality of terminals into shared and personal messages, and encoding the shared and personal messages into shared and personal streams, respectively;
performing power allocation and beamforming design for each of the coded shared and private streams within the determined transmit power;
transmitting the data to the plurality of terminals and receiving a sum transmission rate; and
determining a second transmit power based on the received sum rate and the base station information in a second state;
A base station that performs According to claim 8,
Power allocation and beamforming design for each of the encoded shared and private streams are performed first using a zero-forcing technique, and power allocation and beamforming design of the private streams are performed first. The base station, characterized in that the power allocation of the stream and the beamforming design of the shared stream are performed using a first optimization algorithm. According to claim 9,
The base station, characterized in that the first optimization algorithm is a sequential least squares programming (SLSQP) algorithm. According to claim 8,
The base station information in the first and second states includes an amount of energy harvested in the base station, an amount of energy stored in the base station, and channel information fed back from the plurality of terminals,
The base station, characterized in that the determination of the transmission power is performed using a second deep reinforcement learning algorithm. According to claim 11,
The amount of energy stored in the base station in the second state is
(a) the maximum amount of energy that can be possessed by the base station;
(b) subtracting the product of the determined transmission power in the first state and the time at which the data is transmitted from the amount of energy stored in the base station in the first state, and adding the amount of energy harvested in the base station in the second state amount of energy;
A base station, characterized in that determined by the smaller amount of energy among (a) and (b). According to claim 11,
The base station, characterized in that the second deep reinforcement learning algorithm is a soft actor critic (SAC) algorithm. According to claim 8,
The base station is characterized in that the base station is a mobile base station. A recording medium in which a program of instructions executable by a digital processing device is tangibly implemented to provide transmission rate division multiple access for maximizing the sum transmission rate in a communication environment where energy supply is limited, and which can be read by the digital processing device as,
A computer-readable recording medium on which a program for executing the method of any one of claims 1 to 7 is recorded on a computer.

Images