Deterministic time delay transmission method and device, electronic equipment and storage medium

Abstract

The invention provides a deterministic time delay transmission method, relates to the technical field of communication, and particularly relates to a deterministic time delay transmission method and device, electronic equipment and a storage medium. According to the specific implementation scheme, the method comprises the following steps: acquiring an accumulated data arrival amount, an accumulated network service amount and an accumulated data departure amount of a base station buffer area to obtain total time delay; based on the total time delay, obtaining a probability boundary of initial deterministic time delay; and adjusting the probability boundary of the preliminary deterministic time delay according to the maximum transmission rate of the user and the probability density function of the signal-to-noise ratio of the user to obtain the final probability boundary of the deterministic time delay.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technologies, and in particular to a deterministic delay transmission method, device, electronic device, and storage medium. Background Art

[0002] In many communication scenarios, such as the Industrial Internet of Things, data transmission requires deterministic latency, not just extremely low latency. Currently, many communication solutions only optimize the communication resources required by multiple sensors in wireless control systems to ensure deterministic transmission of short data packets, or optimize joint scheduling algorithms for latency-sensitive services. None of these solutions ensure the determinism of transmission latency. Summary of the Invention

[0003] The present disclosure provides a deterministic delay transmission method, device, electronic device, and storage medium for solving at least one of the above technical problems.

[0004] According to one aspect of the present disclosure, a deterministic delay transmission method is provided, comprising:

[0005] Obtain the cumulative data arrival volume, cumulative network service volume, and cumulative data departure volume of the base station buffer to obtain the total delay;

[0006] Based on the total delay, obtaining a preliminary probability bound of the deterministic delay;

[0007] The preliminary probability boundary of the deterministic time delay is adjusted according to the probability density function of the user's maximum transmission rate and the user's signal-to-noise ratio to obtain a final probability boundary of the deterministic time delay.

[0008] According to one aspect of the present disclosure, a deterministic delay transmission device is provided, comprising:

[0009] The total delay module is used to obtain the cumulative data arrival, cumulative network service volume and cumulative data departure of the base station buffer to obtain the total delay;

[0010] A preliminary determination module, configured to obtain a preliminary probability boundary of a deterministic time delay based on the total time delay;

[0011] The final determination module is used to adjust the probability boundary of the preliminary deterministic time delay according to the probability density function of the user's maximum transmission rate and the user's signal-to-noise ratio to obtain the final probability boundary of the deterministic time delay.

[0012] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0013] at least one processor; and

[0014] a memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the above-mentioned service information transmission method.

[0016] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the above-mentioned service information transmission method.

[0017] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, which implements the above-mentioned service information transmission method when executed by a processor.

[0018] It should be understood that the contents described in this section are not intended to represent the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0020] Figure 1 1 is a flow chart of a deterministic delay transmission method provided by the first embodiment of the present disclosure;

[0021] Figure 2 This is a flow chart of the reinforcement learning part of the deterministic time-delay transmission provided by the first embodiment of the present disclosure;

[0022] Figure 3 2 is a schematic structural diagram of a deterministic time-delay transmission device provided in a second embodiment of the present disclosure;

[0023] Figure 4 is a block diagram of an electronic device for implementing an embodiment of the present disclosure. DETAILED DESCRIPTION

[0024] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0025] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.

[0026] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0027] The terminology used herein is for describing particular embodiments only and is not intended to limit the present disclosure.As used herein, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0028] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted as having an idealized or overly formal meaning unless expressly defined as such herein.

[0029] The deterministic delay transmission method disclosed herein can be executed by an electronic device such as a terminal device or a server. The terminal device may be an in-vehicle device, user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, an in-vehicle device, a wearable device, or the like. The method can be implemented by a processor invoking computer-readable program instructions stored in a memory. Alternatively, the deterministic delay transmission method provided herein can be executed by a server.

[0030] It should be noted that the following transmitting elements can be of various types. This article uses a super intelligent surface (RIS) transmitting element as an example for illustration. Furthermore, the number of base stations in this application can be multiple or one. For ease of explanation, this article assumes that the number of base stations is 1. In the following formula, m represents the number of base stations, and the subscript of m can be omitted when m=1.

[0031] Based on this, the communication system includes multiple RIS transmitting elements, N transmitting elements are used to reflect the received signal while changing the signal phase, and K users can receive signals from the base station via direct and reflected wireless links, respectively, where N is an integer greater than 1 and K is an integer greater than or equal to 1. Modeling this communication system yields the following representation:

[0032] Represents the vector of the signal sent by the base station, where s k Represents the data sent to user k. All signals are normalized signals, that is, they satisfy E{|s k | 2}=1;p krepresents the transmission power of the base station to the kth user. Therefore, the received signal of the kth user can be expressed as: The direct link is modeled as a Rayleigh channel (i.e., the channel gain from the base station to the user) h d,k ~CN(0,β d,k ), K = {1, 2, ..., K}, the indirect channel with RIS is modeled as a Rice fading channel, and the link between the base station and the RIS (i.e., the channel gain from the base station to the transmitting element) is expressed as The link between RIS and user k (i.e., the channel gain from the transmitting element to the user) is expressed as The mean is 0 and the variance is The complex Gaussian white noise is a preset value.

[0033] Based on the above, in some examples, the user's signal-to-noise ratio is determined based on the channel gain from the base station to the user, the channel gain from the base station to the transmitting element, the channel gain from the transmitting element to the user, the phase shift matrix of the transmitting element, the preset complex Gaussian white noise amount, and the transmission power from the base station to the user.

[0034] Specifically, the signal-to-noise ratio of user k is determined according to the following method:

[0035]

[0036] Among them, Θ is the phase shift matrix of the transmitting element, defined as the diagonal matrix Wherein N={1,2,...,N}, N is the number of elements of the transmitting element.

[0037] Based on the above, in some examples, the maximum transmission rate is determined as follows:

[0038] Determine the signal-to-noise ratio, channel block length, channel dispersion, and preset transmission error probability to obtain the maximum transmission rate.

[0039] In short packet transmission, the transmission block length and transmission error probability are not negligible. According to the finite block length (FBL) theory, for the Gaussian white noise (AWGN) channel, when the coding block length (CBL) is n k , the transmission error probability is ε e The approximate expression of the maximum transmission rate of mobile users is:

[0040]

[0041] Medium M k Indicates the number of information bits that can be transmitted, n k =W k ×T is the channel block length, where the transmission duration T is fixed, γ krepresents the signal-to-noise ratio shown in formula (1), Q -1 (·) is the inverse function. Define a Define channel dispersion as Based on the above, (2.1) can be simplified as:

[0042]

[0043] Based on the above, in some examples, the signal-to-noise ratio probability density function is determined as follows:

[0044] The probability density function is obtained according to the first large-scale fading coefficient of the channel from the base station to the user, the second large-scale fading coefficient of the channel from the base station to the transmitting element and its first Ricean factor, the third large-scale fading coefficient of the channel from the transmitting element to the user and its second Ricean factor, and the signal-to-noise ratio factor.

[0045] Specifically, the cumulative distribution function of the signal-to-noise ratio obeys the form of the Marcum-Q function, based on which the probability density function is obtained as follows:

[0046]

[0047] where υ k =|f g,k H Θg r | 2 , β g,k ,β r ,β d,k They represent the first large-scale fading coefficient of the channel from the base station to the user, the second large-scale fading coefficient of the channel from the base station to the transmitting element and its first Ricean factor, and the third large-scale fading coefficient of the channel from the transmitting element to the user and its second Ricean factor, respectively. K g,k and K r represents the first Rician factor and the second Rician factor. And when ρ→∞, Substituting 1 into (3) yields the final expression of (3).

[0048] This method will be described with reference to the accompanying drawings, taking the above communication system as an example.

[0049] In the first embodiment of the disclosure, see Figure 1 , Figure 1 A flowchart of a deterministic delay transmission method provided by the first embodiment of the present disclosure is shown. The method is applied at the transmitting end and includes the following steps:

[0050] S101: Obtain the cumulative amount of data arrival, the cumulative amount of network service, and the cumulative amount of data departure in the base station buffer to obtain the total delay.

[0051] S102: Based on the total delay, obtain a preliminary probability bound of the deterministic delay.

[0052] S103 : Adjust the preliminary probability boundary of the deterministic delay according to the probability density function of the user's maximum transmission rate and the user's signal-to-noise ratio to obtain the final probability boundary of the deterministic delay.

[0053] The method provided by the present disclosure can accurately obtain the deterministic delay of the data transmission process, thereby effectively optimizing the performance of the communication system based on the deterministic delay, for example, allocating bandwidth and transmitting power based on the deterministic delay, and adjusting the phase shift of the transmitting element.

[0054] Regarding S101, in some examples, S101 includes:

[0055] Sub-step 1: converting the cumulative data arrival amount, cumulative network service amount and cumulative data departure amount in the bit domain into the cumulative data arrival amount, cumulative network service amount and cumulative data departure amount in the exponential domain;

[0056] Sub-step 2: Determine a first operator based on the cumulative data arrival amount and the cumulative data service amount in the exponential domain format, and determine the total delay according to the first operator, the cumulative data arrival amount in the exponential domain format, and the cumulative network service amount.

[0057] In bit domain form, during the duration (t1, t2), the cumulative data arrival amount, cumulative network service amount, and cumulative data departure amount of the base station buffer are defined as follows:

[0058]

[0059]

[0060]

[0061] Arrival process m,k (i) describes the number of bits entering the transmit buffer in time slot i, s m,k (i) indicates service progress, leaving process d m,k (i) is given as the number of bits leaving the queue, which is equal to the number of bits that successfully reach the receiver. Then, the total delay at time t is expressed as:

[0062] T m,k (t)=inf{u≥0:A m,k (0,t)≤D m,k (0,t+u)} (4.1)

[0063] To facilitate analysis, the cumulative data arrival, cumulative network service, and cumulative data departure of the base station buffer in bit domain form are converted into exponential domain form. Based on this, in sub-step 1, the cumulative data arrival, cumulative network service, and cumulative data departure in exponential domain form are expressed as follows:

[0064]

[0065]

[0066]

[0067] Based on this, in sub-step 2, the symbol % is used to represent the first operator (a deconvolution operator), then Among them, α represents the arrival process, β represents the service process, and the total delay at time t is specifically:

[0068] T m,k (t)=inf{u≥0:A m,k %S m,k (t+u,t)≤1} (4.1)

[0069] For S102, stochastic network calculus (SNC) is a network performance analysis tool often used to analyze network performance boundaries. It transforms complex network systems into easily analyzable models, providing probabilistic quality of service (QoS) assurance. This approach takes into account factors such as the self-similarity and random burstiness of data traffic in real networks, as well as channel fading in network systems. It allows the network to violate performance boundaries with a certain probability, thus guaranteeing the stochastic QoS of the entire service system. Compared to deterministic network calculus, it can significantly improve network resource utilization. In this example, S102 uses SNC to analyze total latency.

[0070] In some examples, S102 includes:

[0071] Sub-step 1: Analyze the total delay based on Markov inequality and moment generating function to obtain a preliminary probability bound for the deterministic delay.

[0072] Specifically, the moment bound can be obtained from the Markov inequality, and for any s>0, the Markov inequality is obtained: Where a is the total delay (4.1) and X is the intermediate variable.

[0073] The moment generating function is Substituting the moment generating function into the above Markov inequality, the Markov inequality can be rewritten as:

[0074] Pr(X≥a)≤a -s M X(1+s) (5.1).

[0075] From (5.1), we can perform an analysis based on deterministic delay, that is, the probability that the delay falls within the specified time window. When a=1,

[0076] and When , T is the subscript form of the total delay mentioned above. Then the sub-step is always, and the probability bound of the preliminary deterministic delay is expressed as:

[0077]

[0078] The above 5.2 is a process of gradually scaling the probability to obtain the probability boundary.

[0079] Furthermore, in some examples, after sub-step 1 of S102, S102 further includes:

[0080] Sub-step 2: Convert the preliminary probability bound of deterministic delay into the probability bound of deterministic delay in the form of steady-state kernel function.

[0081] According to (5.2), and Represent the probability bounds (upper and lower bounds, respectively) of the deterministic delay in the form of a steady-state kernel function.

[0082] Regarding S103, in some examples, S103 includes:

[0083] Sub-step 1: Determine a second operator based on the upper bound of the Mellin transform of the moment generating function, and substitute the second operator into the probability bound of the deterministic delay in the form of a steady-state kernel function to obtain a new probability bound of the deterministic delay in the form of a steady-state kernel function. The new probability bound of the deterministic delay in the form of a steady-state kernel function includes the Mellin transform corresponding to the cumulative data arrival amount and the Mellin transform corresponding to the cumulative network service amount.

[0084] Specifically, the upper bound of the Mellin transform based on the moment generating function determines the second operator (a deconvolution operator) to be expressed as:

[0085]

[0086] Where s>0, so the probability bound based on deterministic delay can be calculated from the Mellin transform of the data arrival process and the service process.

[0087] Based on (6.1) and substituting the probability bound of the deterministic delay in the form of the steady-state kernel function, the probability bound of the deterministic delay in the form of the steady-state kernel function is determined as:

[0088]

[0089] and,

[0090]

[0091] Sub-step 2: Substitute the number of data packets arriving at the base station buffer in each time slot and the data size of each data packet into the Mellin transform of the cumulative data arrival amount to obtain the final Mellin transform of the cumulative data arrival amount.

[0092] Among them, (6.2) and (6.2) The Mellin transform representing the final cumulative data arrival amount (i.e., the data arrival process) is specifically:

[0093]

[0094] The number of data packets arriving at the base station buffer in each time slot is represented by λ k , the data size of each data packet is expressed as x bits.

[0095] Sub-step three: Substitute the maximum transmission rate into the Mellin transform of the cumulative network service volume to obtain the final Mellin transform of the cumulative network service volume.

[0096] Based on the maximum transmission rate (2.2), let The Mellin transform representing the cumulative network service volume (i.e., service process) is expressed as:

[0097]

[0098]

[0099] in, And s>0.

[0100] Sub-step 4: Obtain the final probability bound of the deterministic delay based on the probability density function, the Mellin transform of the final cumulative data arrival volume, and the Mellin transform of the final cumulative network service volume.

[0101] Substituting the probability density function represented by (3), the Mellin transform of the final cumulative data arrival volume represented by (6.4), and the Mellin transform of the final cumulative network service volume represented by (6.5)-(6.6) into (6.2) and (6.3), combined with (5.2), we obtain the final probability bound of deterministic delay:

[0102]

[0103] In some examples, after S103, the method further includes:

[0104] Step 1: Determine the bandwidth allocation of multiple users, the base station's transmit power for multiple users, and the phase shift matrix of the transmit element based on the probability bound of the deterministic delay.

[0105] Since the phase shift matrix at the transmitting element is continuous, while the transmitting power and bandwidth allocation at the base station are discrete, it is difficult to combine the two aspects for optimization in the related art. The present disclosure determines the deterministic delay and can jointly optimize the transmitting element, transmitting power and bandwidth allocation based on the deterministic delay to obtain better communication quality.

[0106] In some examples, step 1 can be performed in a model-free manner. For example, the problem of optimizing bandwidth allocation, transmit power, and phase shift matrices can be written as:

[0107]

[0108]

[0109]

[0110]

[0111]

[0112]

[0113] Among them, the first constraint C 12.2 is the constraint of deterministic delay, the second constraint C 12.3 is the maximum transmit power constraint of the base station, and the third constraint C 12.4 The fourth constraint C is the total system bandwidth allocation constraint. 12.5 is the phase shift constraint of the emitting element.

[0114] For some examples, see Figure 2 , step 1 can be carried out in a model manner. Taking the reinforcement learning model as an example, a reinforcement learning model with a mixed action space is adopted, and the probability boundary of the deterministic delay obtained above is used as the reward function (i.e., the optimization target) of the reinforcement learning model for optimization, which can solve the joint problem.

[0115] Specifically, step one includes:

[0116] S201. Input a reinforcement learning model according to current channel state parameters to obtain a current communication control action that matches the current channel state parameters, wherein the communication control action includes at least one of the following: a bandwidth allocation action for multiple users in the current time slot, a transmission power allocation action for multiple users by the base station, and a phase shift matrix of a transmitting element.

[0117] S202: Execute the current communication control action to obtain a new channel state parameter and a first reward parameter, wherein the reward parameter is determined according to a probability boundary of a final deterministic delay.

[0118] S203: Determine a first loss value based on the first reward parameter, the new channel state parameter, and the current channel state.

[0119] S204: Train the reinforcement learning model according to the first loss value.

[0120] S201-S204 describe the training process of the reinforcement learning model.

[0121] Among them, reinforcement learning models can include DQN (Deep Q-Network), SAC (Soft Actor Critic), PPO (Proximal Policy Optimization), etc.

[0122] First, a reinforcement learning environment is defined based on the reinforcement learning model of the transmitting element, base station and user (user terminal), which includes two intelligent agents: the base station and the transmitting element.

[0123] The state space S of the reinforcement learning model l : The environmental state of the kth user at time slot t is the channel state information, the maximum and minimum delay requirements of each user (user terminal), and the action selected by the user at the previous moment.

[0124] The action space A of the reinforcement learning model l :

[0125] Discrete communication control actions: bandwidth allocation actions for multiple users in the current time slot, and base station transmission power allocation actions for multiple users;

[0126] Continuous communication control actions: The phase shift matrix of the transmitting element. The phase shift at the transmitting element serves as a continuous action space. Since neural networks can only accept real numbers, not complex numbers, when constructing the action space, if complex numbers are involved, the real and imaginary parts are used as independent input ports. Therefore, the phase shift matrix is separated into real and imaginary parts as inputs.

[0127] The reward function r of the reinforcement learning model l : The probability boundary of the final deterministic delay; the first reward parameter based on maximizing the requirements of deterministic delay transmission for different user terminals is the optimization goal.

[0128] In reinforcement learning, the interaction between the environment and the agent is as follows: the agent obtains a state S from the environment t Then, select the best action a according to the strategy πt , and execute this action in the environment to generate a new state S t+1 and reward r t The above is a cycle. The reinforcement learning process is to repeat this cycle, allowing the agent to continuously optimize its own strategy, ultimately learning the optimal strategy to maximize the cumulative reward. In other words, based on channel state information, the maximum and minimum delay requirements of each user (user terminal), and the user's action selection at the previous moment, the communication control action is obtained. The goal is to obtain the optimal transmission delay based on the probability bound of the final deterministic delay. Decisions are continuously optimized to learn better communication control actions.

[0129] In disclosing the second embodiment, see Figure 3 , for Figure 1 , Figure 2 The following is a structural diagram of a deterministic delay transmission device 30 provided in the second embodiment of the present disclosure. The device includes:

[0130] The total delay module 301 is used to obtain the cumulative data arrival amount, cumulative network service amount and cumulative data departure amount of the base station buffer to obtain the total delay;

[0131] A preliminary determination module 302 is configured to obtain a preliminary probability boundary of a deterministic delay based on the total delay;

[0132] The final determination module 303 is configured to adjust the probability boundary of the preliminary deterministic delay according to the probability density function of the user's maximum transmission rate and the user's signal-to-noise ratio to obtain the final probability boundary of the deterministic delay.

[0133] In some examples, the total delay module is specifically configured to:

[0134] Converting the cumulative data arrival amount, the cumulative network service amount and the cumulative data departure amount in the bit domain into the cumulative data arrival amount, the cumulative network service amount and the cumulative data departure amount in the exponential domain;

[0135] A first operator is determined based on the cumulative data arrival amount and the cumulative data departure amount in the exponential domain format, and a total delay is determined according to the first operator, the cumulative data arrival amount and the cumulative network service amount in the exponential domain format.

[0136] In some examples, the preliminary determination module is specifically configured to:

[0137] The total delay is analyzed based on Markov inequality and moment generating function, and a preliminary probability bound of deterministic delay is obtained.

[0138] In some examples, the preliminary determination module is further configured to:

[0139] The preliminary probability bound of deterministic delay is converted into the probability bound of deterministic delay in the form of steady-state kernel function.

[0140] In some examples, the finalization module is specifically configured to:

[0141] Determine a second operator based on the upper bound of the Mellin transform of the moment generating function, substitute the second operator into the probability bound of the deterministic delay in the form of a steady-state kernel function, and obtain a new probability bound of the deterministic delay in the form of a steady-state kernel function, wherein the new probability bound of the deterministic delay in the form of a steady-state kernel function includes the Mellin transform corresponding to the cumulative data arrival amount and the Mellin transform corresponding to the cumulative network service amount;

[0142] Substituting the number of data packets arriving at the base station buffer in each time slot and the data size of each data packet into the Mellin transform of the cumulative data arrival amount to obtain the final Mellin transform of the cumulative data arrival amount;

[0143] Substituting the maximum transmission rate into the Mellin transform of the cumulative network service volume to obtain the final Mellin transform of the cumulative network service volume;

[0144] According to the probability density function, the Mellin transform of the final cumulative data arrival volume and the Mellin transform of the final cumulative network service volume, the probability bound of the final deterministic delay is obtained.

[0145] In some examples, the signal-to-noise ratio of the final determination module is determined as follows:

[0146] The user's signal-to-noise ratio is determined based on the channel gain from the base station to the user, the channel gain from the base station to the transmitting element, the channel gain from the transmitting element to the user, the phase shift matrix of the transmitting element, the preset amount of complex Gaussian white noise, and the base station's transmit power to the user.

[0147] In some examples, the maximum transmission rate of the finalization module is determined as follows:

[0148] Determine the signal-to-noise ratio, channel block length, channel dispersion, and preset transmission error probability to obtain the maximum transmission rate.

[0149] In some examples, the probability density function of the final determination module is determined as follows:

[0150] The probability density function is obtained according to the first large-scale fading coefficient of the channel from the base station to the user, the second large-scale fading coefficient of the channel from the base station to the transmitting element and its first Ricean factor, the third large-scale fading coefficient of the channel from the transmitting element to the user and its second Ricean factor, and the signal-to-noise ratio factor.

[0151] In some examples, the apparatus further includes:

[0152] The allocation module is used to determine the bandwidth allocation of multiple users, the transmission power of the base station for multiple users and the phase shift matrix of the transmission element according to the probability boundary of the deterministic delay.

[0153] In some examples, the allocation module is specifically configured to:

[0154] Inputting a reinforcement learning model according to current channel state parameters to obtain a current communication control action that matches the current channel state parameters, wherein the communication control action includes at least one of the following: a bandwidth allocation action for multiple users in a current time slot, a transmit power allocation action for multiple users by a base station, and a phase shift matrix of a transmitting element;

[0155] Executing the current communication control action to obtain a new channel state parameter and a first reward parameter, wherein the reward parameter is determined according to a probability bound of a final deterministic delay;

[0156] Determine a first loss value based on the first reward parameter, the new channel state parameter, and the current channel state;

[0157] The reinforcement learning model is trained based on the first loss value.

[0158] In the technical solutions disclosed herein, the acquisition, storage, and application of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0159] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0160] Figure 4 A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0161] like Figure 4As shown, the device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access memory (RAM) 403. Various programs and data required for the operation of the device 400 can also be stored in the RAM 403. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0162] Various components in device 400 are connected to I / O interface 405, including an input unit 406, such as a keyboard, mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a magnetic disk, optical disk, etc.; and a communication unit 409, such as a network card, modem, wireless communication transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0163] The computing unit 401 can be a variety of general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as the deterministic delay transmission method. For example, in some embodiments, the deterministic delay transmission method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 408. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the deterministic delay transmission method described above can be performed. Alternatively, in other embodiments, the computing unit 401 can be configured to perform the deterministic delay transmission method in any other appropriate manner (e.g., by means of firmware).

[0164] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system comprising at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0165] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0166] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0167] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0168] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0169] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0170] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0171] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A deterministic delay transmission method, comprising: Obtain the cumulative data arrival volume, cumulative network service volume, and cumulative data departure volume of the base station buffer to obtain the total delay; Based on the total delay, obtaining a preliminary probability bound of the deterministic delay; The preliminary probability boundary of the deterministic time delay is adjusted according to the probability density function of the user's maximum transmission rate and the user's signal-to-noise ratio to obtain a final probability boundary of the deterministic time delay.

2. The method according to claim 1, wherein The step of obtaining the cumulative amount of data arriving, the cumulative amount of network service, and the cumulative amount of data leaving the base station buffer to obtain the total delay includes: Converting the cumulative data arrival amount, the cumulative network service amount and the cumulative data departure amount in the bit domain into the cumulative data arrival amount, the cumulative network service amount and the cumulative data departure amount in the exponential domain; A first operator is determined based on the cumulative data arrival amount and the cumulative data service amount in the exponential domain format, and the total delay is determined according to the first operator, the cumulative data arrival amount and the cumulative network service amount in the exponential domain format.

3. The method according to claim 1, wherein The obtaining of a preliminary probability bound of the deterministic delay based on the total delay includes: The total delay is analyzed based on Markov inequality and moment generating function to obtain the probability boundary of the preliminary deterministic delay.

4. The method according to claim 3, wherein after calculating the total delay based on the Markov inequality and the moment generating function to obtain the preliminary probability bound of the deterministic delay, obtaining the preliminary probability bound of the deterministic delay based on the total delay further comprises: The preliminary probability bound of the deterministic time delay is converted into a probability bound of the deterministic time delay in the form of a steady-state kernel function.

5. The method according to claim 4, wherein The step of adjusting the preliminary probability boundary of the deterministic delay according to the probability density function of the user's maximum transmission rate and the user's signal-to-noise ratio to obtain the final probability boundary of the deterministic delay includes: Determining a second operator based on an upper bound of the Mellin transform of the moment generating function, and substituting the second operator into the probability bound of the deterministic delay in the steady-state kernel function form to obtain a new probability bound of the deterministic delay in the steady-state kernel function form, wherein the new probability bound of the deterministic delay in the steady-state kernel function form includes a Mellin transform corresponding to the cumulative data arrival amount and a Mellin transform corresponding to the cumulative network service amount; Substituting the number of data packets arriving at the base station buffer in each time slot and the data size of each data packet into the Mellin transform of the cumulative data arrival amount to obtain a final Mellin transform of the cumulative data arrival amount; Substituting the maximum transmission rate into the Mellin transform of the accumulated network service volume to obtain a final Mellin transform of the accumulated network service volume; The probability boundary of the final deterministic delay is obtained according to the probability density function, the Mellin transform of the final cumulative data arrival amount, and the Mellin transform of the final cumulative network service amount.

6. The method according to any one of claims 1 to 6, wherein: The signal-to-noise ratio is determined as follows: The signal-to-noise ratio of the user is determined based on the channel gain from the base station to the user, the channel gain from the base station to the transmitting element, the channel gain from the transmitting element to the user, the phase shift matrix of the transmitting element, the preset complex Gaussian white noise amount, and the transmitting power from the base station to the user.

7. The method according to any one of claims 1 to 6, wherein: The maximum transmission rate is determined as follows: The signal-to-noise ratio, channel block length, channel dispersion, and a preset transmission error probability are determined to obtain the maximum transmission rate.

8. The method according to any one of claims 1 to 7, wherein: The probability density function is determined as follows: The probability density function is obtained according to the first large-scale fading coefficient of the channel from the base station to the user, the second large-scale fading coefficient of the channel from the base station to the transmitting element and its first Ricean factor, the third large-scale fading coefficient of the channel from the transmitting element to the user and its second Ricean factor, and the signal-to-noise ratio factor.

9. The method according to any one of claims 1 to 8, wherein: After adjusting the preliminary probability boundary of the deterministic delay according to the probability density function of the user's maximum transmission rate and the user's signal-to-noise ratio to obtain the final probability boundary of the deterministic delay, the method further includes: Bandwidth allocation for multiple users, transmit power for multiple users by the base station, and a phase shift matrix of a transmit element are determined according to the probability bound of the deterministic time delay.

10. The method according to claim 9, wherein: The determining, according to the probability bound of the deterministic time delay, bandwidth allocation for multiple users, transmit power of a base station for multiple users, and a phase shift matrix of a transmitting element includes: Inputting a reinforcement learning model according to current channel state parameters to obtain a current communication control action that matches the current channel state parameters, wherein the communication control action includes at least one of the following: a bandwidth allocation action for multiple users in a current time slot, a transmit power allocation action for multiple users by a base station, and a phase shift matrix of a transmitting element; executing the current communication control action to obtain a new channel state parameter and a first reward parameter, wherein the reward parameter is determined according to a probability bound of the final deterministic delay; Determine a first loss value based on the first reward parameter, the new channel state parameter, and the current channel state; The reinforcement learning model is trained according to the first loss value.

11. A deterministic delay transmission device, comprising: The total delay module is used to obtain the cumulative data arrival, cumulative network service volume and cumulative data departure of the base station buffer to obtain the total delay; A preliminary determination module, configured to obtain a preliminary probability boundary of a deterministic time delay based on the total time delay; The final determination module is used to adjust the probability boundary of the preliminary deterministic time delay according to the probability density function of the user's maximum transmission rate and the user's signal-to-noise ratio to obtain the final probability boundary of the deterministic time delay.

12. The device according to claim 11, wherein The total delay module is specifically used for: Converting the cumulative data arrival amount, the cumulative network service amount and the cumulative data departure amount in the bit domain into the cumulative data arrival amount, the cumulative network service amount and the cumulative data departure amount in the exponential domain; A first operator is determined based on the cumulative data arrival amount and the cumulative data service amount in the exponential domain format, and the total delay is determined according to the first operator, the cumulative data arrival amount and the cumulative network service amount in the exponential domain format.

13. The device according to claim 11, wherein The preliminary determination module is specifically used for: The total delay is analyzed based on Markov inequality and moment generating function to obtain the probability boundary of the preliminary deterministic delay.

14. The device according to claim 13, wherein The preliminary determination module is further configured to: The preliminary probability bound of the deterministic time delay is converted into a probability bound of the deterministic time delay in the form of a steady-state kernel function.

15. The device according to claim 14, wherein The final determination module is specifically used for: Determining a second operator based on an upper bound of the Mellin transform of the moment generating function, and substituting the second operator into the probability bound of the deterministic delay in the steady-state kernel function form to obtain a new probability bound of the deterministic delay in the steady-state kernel function form, wherein the new probability bound of the deterministic delay in the steady-state kernel function form includes a Mellin transform corresponding to the cumulative data arrival amount and a Mellin transform corresponding to the cumulative network service amount; Substituting the number of data packets arriving at the base station buffer in each time slot and the data size of each data packet into the Mellin transform of the cumulative data arrival amount to obtain a final Mellin transform of the cumulative data arrival amount; Substituting the maximum transmission rate into the Mellin transform of the accumulated network service volume to obtain a final Mellin transform of the accumulated network service volume; The probability boundary of the final deterministic delay is obtained according to the probability density function, the Mellin transform of the final cumulative data arrival amount, and the Mellin transform of the final cumulative network service amount.

16. The device according to any one of claims 11 to 15, wherein: The signal-to-noise ratio of the final determination module is determined according to the following method: The signal-to-noise ratio of the user is determined based on the channel gain from the base station to the user, the channel gain from the base station to the transmitting element, the channel gain from the transmitting element to the user, the phase shift matrix of the transmitting element, the preset complex Gaussian white noise amount, and the transmitting power from the base station to the user.

17. The device according to any one of claims 11 to 16, wherein: The maximum transmission rate of the final determination module is determined according to the following method: The signal-to-noise ratio, channel block length, channel dispersion, and a preset transmission error probability are determined to obtain the maximum transmission rate.

18. The device according to any one of claims 11 to 17, wherein: The probability density function of the final determination module is determined according to the following method: The probability density function is obtained according to the first large-scale fading coefficient of the channel from the base station to the user, the second large-scale fading coefficient of the channel from the base station to the transmitting element and its first Ricean factor, the third large-scale fading coefficient of the channel from the transmitting element to the user and its second Ricean factor, and the signal-to-noise ratio factor.

19. The device according to any one of claims 11 to 18, wherein: The device further comprises: An allocation module is configured to determine bandwidth allocation for multiple users, transmit power for the multiple users, and a phase shift matrix of a transmitting element of a base station according to a probability boundary of the deterministic delay.

20. The device according to claim 19, wherein The allocation module is specifically used for: Inputting a reinforcement learning model according to current channel state parameters to obtain a current communication control action that matches the current channel state parameters, wherein the communication control action includes at least one of the following: a bandwidth allocation action for multiple users in a current time slot, a transmit power allocation action for multiple users by a base station, and a phase shift matrix of a transmitting element; executing the current communication control action to obtain a new channel state parameter and a first reward parameter, wherein the reward parameter is determined according to a probability bound of the final deterministic delay; Determine a first loss value based on the first reward parameter, the new channel state parameter, and the current channel state; The reinforcement learning model is trained according to the first loss value.

21. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 11.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-11.

23. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 11.

Images