Satellite-ground network time-sensitive traffic scheduling method and device based on RSMA and information age

Abstract

The invention discloses a satellite-to-ground network time-sensitive traffic scheduling method and device based on RSMA and information age, and belongs to the technical field of satellite-to-ground network communication.The method comprises the steps that satellite-to-ground communication content is divided into public streams and private streams based on an RSMA transmission mechanism; respectively calculating information age values of the public flow and the private flow in the satellite-ground network; determining an optimal scheduling strategy of the time-sensitive traffic of the satellite-ground network by adopting a multi-agent double-delay depth deterministic strategy gradient method with the aim of minimizing the weighted information age value and transmission power consumption of the time-sensitive traffic of the satellite-ground network; and synchronizing the satellite-ground network time-sensitive traffic optimal scheduling strategy to each satellite node through the inter-satellite link. By adopting the time-sensitive traffic scheduling method and device for the satellite-ground network, the low-delay and high-reliability transmission level of the time-sensitive traffic of the satellite-ground network can be improved under the constraint of limited satellite traffic scheduling capability and limited energy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of satellite-to-ground network communication, in particular to a satellite-to-ground network time-sensitive traffic scheduling method and device based on RSMA (Rate Splitting Multiple Access) and information age. BACKGROUND

[0002] In recent years, with the continuous development of satellite communication technology and the continuous improvement of networking capability, satellite-to-ground integrated network has gradually formed a communication architecture with wide area coverage and flexible access, such as shown in FIG. 1, which provides strong support for information transmission. Under this background, various time-sensitive businesses, such as industrial remote control, military strike task, emergency rescue command, etc., are expected to realize low-latency and high-reliable transmission through satellite-to-ground network. Satellite-to-ground network, with its natural advantages of wide area and mobility, is gradually becoming an important infrastructure for carrying key time-sensitive businesses, and showing broad application prospects in providing stable and predictable communication services in the global scope. Figure 2

[0003] However, when supporting time-sensitive traffic transmission, satellite-to-ground integrated network faces challenges in both latency and resources. In terms of latency, the communication node scale is large, which is easy to generate a large amount of time-sensitive data flow in a short time, while the satellite traffic scheduling capability is limited. If a large number of business flows request transmission at the same time, network congestion is easy to be caused, which leads to increased transmission delay and makes it difficult to meet the low-latency communication demand. In terms of resources, the satellite node is long-term in-orbit operation, and it is difficult to obtain and supplement energy, so the power control of the communication process is strictly required. Therefore, how to ensure the low-latency and high-reliable transmission of time-sensitive traffic under the limited satellite traffic scheduling capability and limited energy constraint is a core problem that must be solved in the actual deployment of satellite-to-ground integrated network. SUMMARY

[0004] The present application provides a satellite-to-ground network time-sensitive traffic scheduling method and device based on RSMA and information age, to at least partially solve the technical problems existing in the prior art.

[0005] To solve the above technical problems, the present application provides the following technical solutions: On the one hand, the present application provides a satellite-to-ground network time-sensitive traffic scheduling method based on RSMA and information age, which comprises: dividing satellite-to-ground communication content into public flow and private flow based on RSMA transmission mechanism; respectively calculating the information age value of the public flow and the private flow in the satellite-to-ground network; ​With the goal of minimizing the weighted information age value and transmission power consumption of time-sensitive traffic in the satellite-to-ground network, the optimal scheduling strategy for time-sensitive traffic in the satellite-to-ground network is determined by a multi-agent dual-delay deep deterministic policy gradient method under preset constraints. The optimal scheduling strategy for time-sensitive traffic in the satellite-to-ground network is synchronized to each satellite node via inter-satellite links.

[0006] Furthermore, the RSMA transmission mechanism-based division of satellite-to-ground communication content into public and private streams includes: Based on the communication requirements of the work scenario, network traffic analysis technology is used to statistically analyze the frequency distribution and service types of communication content of each node, and the satellite-to-ground communication content is divided into homogeneous traffic and heterogeneous traffic; among them, homogeneous traffic is the content requested by multiple nodes at high frequency, and heterogeneous traffic is the content requested by a single node at low frequency. Based on the RSMA transmission mechanism, homogeneous traffic from all nodes is merged and encoded into a public stream, while heterogeneous traffic is independently encoded into a private stream. The public stream uses a precoding vector that is dynamically designed based on the satellite channel state to ensure interference-free decoding at the receiver. The private stream uses a statically independent precoding vector to eliminate interference between nodes in the satellite-to-ground network. When decoding at the receiver, the public stream of multiple nodes is decoded first, followed by the private stream of a single node, thereby eliminating serial interference between the public and private streams.

[0007] Furthermore, the method for calculating the age value of the information is as follows: Record the generation timestamp of the information stream whose age value is to be calculated, and dynamically update the information age of the information stream based on the difference between the current time and the generation timestamp; The information age value is calculated based on the information age; where information age value represents the time sensitivity of information flow; and information age value increases with the information age, the larger the value, the more urgent it is to execute the transmission of the current flow.

[0008] Furthermore, the formula for calculating the value of information age based on information age is expressed as follows: in, Indicates the first Information stream received by each node The informational value of age; express Information age; This represents the business latency sensitivity coefficient; e It represents the base of a natural number.

[0009] Furthermore, the optimization objective is expressed as: wherein, is a set of precoding vectors for public flows of all satellites in the satellite-to-ground network; is a set of precoding vectors for private flows of all satellites in the satellite-to-ground network serving all nodes; is a set of rate splitting factors for allocating information rates carried by public flows and private flows; is a priority weight of the th node; is a power consumption penalty factor; is a transmit power of the th satellite; M is a total number of ground nodes; is an information age value of public flows; is an information age value of private flows; K is a total number of satellites; T is an optimization target validity time, which is usually desired to be long-term within the operation time of the satellite-to-ground network, thus represents long-term validity, while represents average within the optimization target validity time.

[0010] Further, the constraints include: the total transmission power of public flows and private flows of a satellite does not exceed a maximum transmission power threshold; the sum of transmission rates of public flows and private flows received by a node from a satellite is not less than a minimum reception rate; the ratio of transmission rates of public flows and private flows received by a node from a satellite is not less than a given threshold, and the difference between the signal-to-interference-and-noise ratios of public flows and private flows received by the node is not less than a given threshold; the sum of public information transmission interference and private information transmission interference of each node to other nodes does not exceed a maximum interference tolerance; the time sensitivity of the information age value does not exceed a maximum time sensitivity threshold.

[0011] Further, the multi-agent double-delay deep deterministic policy gradient method adopts a double-time scale framework, including high-level agents and low-level agents; wherein, the state space of the high-level agent contains the inter-satellite interference distribution, the information age value distribution of public flows and private flows of each node, the relative position of the satellite, and the traffic load distribution; the state space of the low-level agent contains the real-time channel state, the node queue state, the information age value distribution and power allocation of public flows and private flows of the th node served by the The high-level agent performs inter-satellite interference coordination in a long time scale, and the output action includes an inter-satellite interference coordination factor, a spectrum reuse factor and a satellite cooperation weight; the low-level agent performs intra-satellite rate allocation in a short time scale, and the output action includes a precoding vector and a rate splitting factor of a public flow and a private flow; wherein the rate splitting factor is used to allocate the information rate carried by the public flow and the private flow; the inter-satellite interference coordination factor is responsible for quantifying the interference suppression of the current satellite to the neighboring satellite, and then managing and controlling the harmful interference between satellites; the spectrum reuse factor is used to dynamically adjust the spatial reuse degree of the spectrum resource of the current satellite, and to balance between capacity and interference; and the satellite cooperation weight is used to dynamically adjust the cooperative transmission behavior between satellites according to the relative position and the traffic load of the satellites.

[0012] Further, the reward of the high-level agent is represented as: Wherein, represents a set of ground nodes; is a priority weight of the i-th node; is an information age value of the public flow; is an information age value of the private flow; is an interference coordination bias penalty factor; is a theoretical optimal value of the inter-satellite interference coordination factor; is a spectrum reuse incentive factor; is the inter-satellite interference coordination factor; is the spectrum reuse factor.

[0013] Further, the reward of the low-level agent is represented as: Wherein, represents a set of nodes served by the i-th satellite; is a priority weight of the i-th node; is an information age value of the public flow; is an information age value of the private flow; is a transmission power penalty factor; is a transmit power of the i-th satellite; is an unmet rate demand penalty factor; is a minimum required rate; is an actual transmission rate; represents that the sum of the values of the i-th node is summed only when the i-th node is served by the i-th satellite. ​​​​​​​​

[0014] In another aspect, the present application also provides a device for scheduling time-sensitive traffic in a satellite-ground network based on RSMA and information age, comprising: a data processing module, configured to: divide the satellite-ground communication content into public flow and private flow based on the RSMA transmission mechanism; calculate the information age value of the public flow and the private flow in the satellite-ground network respectively; a time-sensitive traffic scheduling module, configured to: determine the optimal scheduling strategy for the time-sensitive traffic in the satellite-ground network by using the multi-agent double-delay deep deterministic policy gradient method under the preset constraint condition, with the optimization target of minimizing the weighted information age value of the time-sensitive traffic in the satellite-ground network and the transmission power consumption; synchronize the optimal scheduling strategy for the time-sensitive traffic in the satellite-ground network to each satellite node through the inter-satellite link.

[0015] In another aspect, the present application also provides an electronic device comprising a processor and a memory; wherein the memory stores at least one instruction, which is loaded and executed by the processor to implement the above method.

[0016] In another aspect, the present application also provides a computer-readable storage medium, wherein the storage medium stores at least one instruction, which is loaded and executed by the processor to implement the above method.

[0017] The technical solution provided by the present application has at least the following beneficial effects: The technical solution provided by the present application combines and encodes the homogenized traffic of the satellite-ground network node into public flow and independently encodes the heterogeneous traffic into private flow according to the differentiated communication requirements through the RSMA transmission mechanism, thereby suppressing the redundant interference of homogenized content in network transmission and reducing the satellite traffic scheduling pressure. Then, the information age and its value of the public flow and the private flow are calculated respectively, the business time sensitivity requirements of the public flow and the private flow are obtained, and the multi-agent double-delay deep deterministic policy gradient method is used to minimize the weighted information age value of the time-sensitive traffic in the satellite-ground network and the transmission power consumption, so as to realize the flexible and efficient scheduling of the time-sensitive traffic in the satellite-ground network. Under the constraint of limited satellite traffic scheduling capability and limited energy, the transmission of the time-sensitive traffic with low delay and high reliability is ensured, thereby improving the time-sensitive business traffic scheduling capability of the satellite-ground integrated network. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0019] Figure 1 is an execution flow diagram of the RSMA and information age-based satellite-ground network time-sensitive flow scheduling method provided by the embodiments of the present application; Figure 2 is a satellite-ground network topology diagram; Figure 3 is a flow chart of the multi-agent double-delay deep deterministic policy gradient method provided by the embodiments of the present application; Figure 4 is a system block diagram of the electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0020] In order to make the objects, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0021] First of all, it should be noted that in the embodiments of the present application, the words such as "exemplarily", "for example" are used to represent as an example, illustration or description. Any embodiment or design scheme described as "exemplary" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the word "exemplarily" is intended to present the concept in a specific manner. In addition, in the embodiments of the present application, the meaning expressed by "and / or" can be both, or can be one of the two.

[0022] First embodiment The embodiment faces the scenario of satellite-ground network traffic transmission. In the process of implementing the satellite-ground network, in order to ensure the low-delay and high-reliability transmission of time-sensitive traffic under the constraints of limited satellite traffic scheduling capability and limited energy, meet the requirements of real-time and stability of time-sensitive services, and effectively support low-delay and reliable communication of key services, a satellite-ground network time-sensitive traffic scheduling strategy based on RSMA and information age is introduced. A satellite-ground network time-sensitive traffic scheduling method based on RSMA and information age is provided. According to the differentiated communication requirements, the homogeneous traffic of the satellite-ground network nodes is combined and encoded into a public flow by the RSMA transmission mechanism, and the heterogeneous traffic is independently encoded into a private flow, so as to suppress the redundant interference of homogeneous content in network transmission and reduce the satellite traffic scheduling pressure. Then, the information age and its value of the public flow and the private flow are calculated respectively, the service time sensitivity requirements of the public flow and the private flow are obtained, and the multi-agent double-delay deep deterministic policy gradient method is adopted to minimize the weighted information age value and transmission power consumption of the satellite-ground network time-sensitive traffic, so as to realize flexible and efficient scheduling of the satellite-ground network time-sensitive traffic. The method can be implemented by an electronic device, which can be a terminal or a server. Specifically, the execution process of the method is as shown in Figure 1 The method comprises the following steps:

[0023] S1, based on the RSMA transmission mechanism, the satellite-ground communication content is divided into a public flow and a private flow; Specifically, in the embodiment, the implementation process of S1 is as follows: S11, according to the differentiated communication requirements of the working scene, the network traffic analysis technology is used to count the frequency distribution and service type of the communication content of each node, and the satellite-ground communication content is split into homogeneous traffic and heterogeneous traffic; wherein the homogeneous traffic is the content requested by multiple nodes with high frequency, and the heterogeneous traffic is the content requested by a single node with low frequency. The specific implementation process is as follows:

[0024] For a satellite-ground communication network containing a low earth orbit satellite and a ground node, wherein the satellite set runs in an orbit with an altitude of , the position of each satellite at time is , and the satellite set contains a central satellite for implementing high-layer slow time scale actions and states, and other satellites for implementing low-layer fast time scale actions and states; in the node set , the position of each node at time is . Using the network traffic analysis technology, the satellite will analyze the communication traffic of the ground node connected to itself Break it down into homogeneous traffic and heterogeneous traffic Among them, homogeneous traffic For nodes Heterogeneous traffic compared to content frequently requested by other nodes in the network. For nodes Low-frequency content requested individually.

[0025] S12, based on the RSMA transmission mechanism, merges and encodes homogeneous traffic from all satellite-to-ground network nodes into a public stream, and independently encodes heterogeneous traffic into private streams. The public stream uses dynamically designed precoding vectors based on satellite channel conditions to ensure interference-free decoding at the receiver. The private stream uses statically designed precoding vectors to eliminate interference between nodes in the satellite-to-ground network. During decoding at the receiver, public streams from multiple nodes are decoded first, followed by private streams from a single node, thus eliminating serial interference between the public and private streams. The specific implementation process is as follows:

[0026] Based on the RSMA transmission mechanism, all nodes homogeneous traffic , Merge encoding into public flow Heterogeneous traffic , Merge encoding into a private stream . Satellite at all times The transmitted signal is:

[0027] in, Indicated by satellite The service's node set, For public stream precoding vectors, For private stream precoding vectors, This represents the number of satellite antennas. (Node) The received signal is:

[0028] in, for Satellite at all times To the node that accesses the satellite The channel vector, for Other satellites at that time To the node The channel vector, It is additive white Gaussian noise. This is the conjugate transpose operator for matrices.

[0029] For each moment Below The calculations consider both large-scale and small-scale fading in the channel between the satellite and ground nodes: In the above formula, For path loss: in, At the speed of light, For carrier frequency, for Satellite at all times To the node The instantaneous distance. Small-scale fading. Obedience to Rice's Decline:

[0030] in, Rice factor, For the line-of-sight component, For the non-line-of-sight component that follows a complex Gaussian distribution, It is an identity matrix.

[0031] Let be the phase shift factor, where This represents the phase shift caused by the Doppler effect of satellite motion. Due to its instantaneous Doppler frequency shift In an extremely short period of time ( Points earned within the specified range. The calculation is as follows:

[0032] in, For satellite Direction of motion and nodes Angle of sight For satellite At any moment The instantaneous velocity scalar relative to the ground is calculated as follows: in, It is a satellite At orbital altitude instantaneous orbital velocity at that point The gravitational constant is For the Earth's radius, It is the Earth's rotational angular velocity. It is the satellite's orbital inclination. is the geographic latitude of the ground observation point. At this time, the phase offset can be calculated as:

[0033] Node adopts a serial interference cancellation method to obtain the required public stream and private stream. Specifically, the node first decodes the public stream , eliminates it from the received signal, and then decodes the private stream . When the system bandwidth is , the node 's achievable rate of the public stream and the private stream at time are respectively:

[0034] At this time, the total achievable rate of the node is: wherein and are the rate splitting factors of the satellite's public stream and private stream to the node , used to allocate the information rate carried by the public stream and the private stream, and the sum of and is 1, is the minimum receiving rate to ensure the quality of the node's information transmission. At the same time, to ensure that the serial interference cancellation can successfully decode the public information from the private information, it is necessary to ensure that the ratio of the node's received transmission rate from the public stream to the private stream is not less than a given threshold, and the difference between the received signal-to-interference-and-noise ratio of the public stream and the private stream is not less than a given threshold. Therefore, we have:

[0035] wherein is the threshold of the ratio of the public stream and the private stream transmission rates, is the signal-to-interference-and-noise ratio threshold.

[0036] S2, respectively, calculates the information age value of the public stream and the private stream in the satellite-ground network; Specifically, in the present embodiment, the implementation process of the above S2 is as follows:​​ The generation timestamps of public and private flows are recorded separately. The information age of public and private flows is dynamically updated based on the difference between the current time and the generation timestamp, and the information age value is calculated accordingly. The information age value decreases exponentially with the increase of information age. The specific calculation method is as follows: ground nodes At any moment Time-sensitive traffic is generated Without loss of generality, It can be a public flow It can also be a private stream. ,Right now Its information value function is: in, For traffic The initial information value, This represents the latency sensitivity factor for business operations. Traffic. The arrival process follows the parameter: It follows a Poisson distribution, and its information value decreases exponentially over time. This is a decay factor that indicates the exponential decline in information value over time.

[0037] For traffic Each of its data packets At any moment The information age is defined as follows: in, For traffic In the middle, data packets The timestamp records the generation time. Node The information age is the information age of its most recently received data packet:

[0038] in, For nodes The set of data packets already received. At this point, the node... Received traffic The information age value is:

[0039] Information age value representation flow Time sensitivity A larger value indicates a higher requirement for timeliness in business operations, at which point the traffic... The more time-sensitive the data, the more quickly it needs to complete the traffic processing. The transmission.

[0040] S3, in order to minimize the weighted information age value and transmission power consumption of the satellite-ground network time-sensitive traffic, an optimal scheduling strategy of the satellite-ground network time-sensitive traffic is determined under the preset constraints by using a multi-agent double-delay deep deterministic policy gradient method; Specifically, in the embodiment, the implementation process of S3 is as follows: S31, in order to minimize the weighted information age value and transmission power consumption of the satellite-ground network time-sensitive traffic: wherein, is a public flow precoding vector set of all satellites in the satellite-ground network, is a private flow precoding vector set of all satellites in the satellite-ground network serving all nodes, is a rate splitting factor set. is a priority weight of a node is a power consumption penalty factor, is a transmission power of a satellite , , , T is an optimization target effective time, and it is usually desired that the optimization process can be effective for a long time within the running time of the satellite-ground network, so that represents long-term effectiveness, and represents an average within the optimization target effective time.

[0041] S32, constraints are set; wherein the following 5 constraints need to be met when the above optimization is performed: (1) the total transmission power of the public flow and the private flow of the satellite does not exceed the maximum transmission power threshold : (2) the sum of the transmission rate of the public flow and the transmission rate of the private flow received by the node must be greater than or equal to the minimum receiving rate of the node to ensure the quality of information transmission: (3) in order to ensure that the serial interference cancellation can successfully decode the public information from the private information, it is necessary to ensure that the ratio of the transmission rate of the public flow to the private flow received by the node is not less than a given threshold, and the difference between the signal-to-interference-and-noise ratio of the public flow and the signal-to-interference-and-noise ratio of the private flow received by the node is not less than a given threshold: ​ (4) To protect each node in the network from excessive interference from other nodes, it is necessary to ensure that the sum of the public information transmission interference and the private information transmission interference of each node to other nodes does not exceed the maximum interference tolerance : (5) To ensure the quality of service of time-sensitive business traffic, the time sensitivity of information age value does not exceed the maximum time sensitivity threshold: wherein, and are the maximum time sensitivity thresholds of public flow and private flow respectively.

[0042] S33, a multi-agent double-delay deep deterministic policy gradient method is used to solve the above complex optimization problem.

[0043] As shown in Figure 3 , the multi-agent double-delay deep deterministic policy gradient method uses a double-time scale framework; wherein the state space of the high-level agent contains: the information age value distribution of each node public flow and private flow ; the inter-satellite interference distribution : ; wherein, represents the satellite interference intensity of the satellite service to the node, and ; the relative position of the satellite , and ; the business load distribution , and .

[0044] The state space of the low-level agent contains: the real-time channel state , the node queue state , the information age value distribution of the public flow and private flow of the node served by the first satellite and the power allocation .

[0045] In addition, the high-level agent performs inter-satellite interference coordination in the long time scale, and the output action contains the inter-satellite interference coordination factor , the spectrum reuse factor , and the satellite cooperation weight ; wherein, the inter-satellite interference coordination factor is responsible for quantifying the current satellite's interference suppression strength on neighboring satellites, and then managing and controlling the harmful interference between satellites; the spectrum reuse factor is used to dynamically adjust the spatial reuse degree of the current satellite's spectrum resources, and to balance between capacity and interference; the satellite cooperation weight is used to dynamically adjust the cooperative transmission behavior between satellites according to the relative position and service load of the satellites; the calculation formulas of the parameters are as follows: wherein, represents a sigmoid function, is the maximum inter-satellite distance, is the maximum allowed inter-satellite interference threshold.

[0046] The low-level agent performs intra-satellite rate allocation in a short time scale, and outputs action The precoding vector contains public flow and private flow and , and the rate splitting factor .

[0047] Further, in order to ensure that the high-level agent action and the low-level agent action can converge as soon as possible, the high-level reward and the low-level reward are set as follows: wherein, is the theoretical optimal value of the inter-satellite interference coordination factor, is the interference coordination deviation penalty factor, and the greater the value, the more the high-level agent will tend to precise inter-satellite interference coordination when making decisions, and will sacrifice some other performance (such as spectrum reuse degree) to ensure that the interference level is in an ideal state, thereby improving system reliability. is the spectrum reuse incentive factor, and the greater the value, the more the high-level agent will tend to improve the spectrum reuse degree to improve the total capacity and spectrum efficiency of the system. is the transmission power penalty factor, and the greater the value, the more the low-level agent will tend to save power when making decisions, and adopt more energy-saving precoding and power allocation schemes, but excessive will lead to a decrease in coverage capability or transmission rate, so the rate demand unmet penalty factor is introduced to punish the situation that the actual transmission rate of the node served by the satellite cannot reach the minimum required rate , and Indicates only At that time, for each node Summing the values.

[0048] When any of the above five optimization constraints are violated during the transmission of public or private flows, the time-sensitive traffic scheduling policy update for the satellite-to-ground network is triggered. During the higher-layer policy update process, the update first occurs at the sampling time. Collect experience And put it into the high-level experience replay pool cache. , and then from Calculate the target value from the sampled batch data:

[0049] in, For high-level Critic networks, For high-level Actor networks, To explore the noise, it follows a truncated Gaussian distribution. The cutoff interval is Then, update the high-level Critic network. Parameters:

[0050] For Actor networks, the update objective is not to minimize a loss function, but to maximize an expected reward. The gradient ascent formula is as follows: Then update the high-level Actor network. : Each of the above operations After the step, update the target network: During the low-level policy update process, first at the sampling time... Collect experience And put it into the low-level experience replay pool cache. , and then from Mid-level sampling batch data. Compared to high-level updates, the target value of low-level updates depends on the actions of high-level updates, i.e.:

[0051] in, It is a low-level Critic network. It is a low-level Actor network. This represents the concatenation of action vectors. Then, the lower-level Critic network is updated. The parameters of the Actor network are as follows:

[0052] For the Actor network, similar to the high-level network, the update target is also not to minimize a loss function, but to maximize an expected return, and the gradient ascent formula is: Then the low-level Actor network is updated : After each operation step, the target network is updated: After the completion of the satellite-ground network time-sensitive traffic scheduling strategy update, the new traffic scheduling instructions are synchronized to each satellite node through the inter-satellite link, that is, the following S4 is executed.

[0053] S4, synchronizing the satellite-ground network time-sensitive traffic optimal scheduling strategy to each satellite node through the inter-satellite link.

[0054] In summary, the embodiment provides a satellite-ground network time-sensitive traffic scheduling method based on RSMA and information age, wherein the RSMA realizes power resource allocation optimization by introducing a flexible rate splitting mechanism, can combine and encode homogeneous traffic of satellite-ground network nodes into public flows, and independently encode heterogeneous traffic into private flows, thereby suppressing the redundant interference of homogeneous content in network transmission, and helping to reduce the scheduling pressure of traffic under congestion scenarios and energy constraints. The information age mechanism starts from the timeliness of information, reduces the blocking of outdated data on time-sensitive information in transmission through the information age value, ensures the priority processing of business traffic, and enhances the ability of the satellite-ground network to schedule time-sensitive traffic. Combined with the RSMA and information age mechanism, the satellite-ground network can better optimize the time-sensitive traffic scheduling process and support efficient operation of time-sensitive services under limited traffic scheduling capacity and energy constraints. Ensure low-latency and high-reliable transmission of time-sensitive traffic.

[0055] Second embodiment The embodiment provides a satellite-ground network time-sensitive traffic scheduling device based on RSMA and information age, which comprises the following modules: The data processing module is used for: Based on the RSMA transmission mechanism, the satellite-ground communication content is divided into public flows and private flows; respectively calculating the information age value of the public flows and the private flows in the satellite-ground network; The time-sensitive traffic scheduling module is used for: With the optimization target of minimizing the weighted information age value and transmission power consumption of the satellite-ground network time-sensitive traffic, an optimal scheduling strategy of the satellite-ground network time-sensitive traffic is determined under preset constraints by using a multi-agent double-delay deep deterministic policy gradient method; The optimal scheduling strategy of the satellite-ground network time-sensitive traffic is synchronized to each satellite node through an inter-satellite link.

[0056] It should be noted that the RSMA and information age based satellite-ground network time-sensitive traffic scheduling device of the present embodiment corresponds to the RSMA and information age based satellite-ground network time-sensitive traffic scheduling method of the first embodiment; the functions of each functional module in the RSMA and information age based satellite-ground network time-sensitive traffic scheduling device of the present embodiment correspond one-to-one to the process steps in the RSMA and information age based satellite-ground network time-sensitive traffic scheduling method of the first embodiment; therefore, no further description is given here.

[0057] Third embodiment The present embodiment provides an electronic device, such as Figure 4 As shown in the figure, the electronic device includes a processor and a memory; wherein the processor and the memory can be connected through a communication bus; the memory stores at least one instruction, which is loaded and executed by the processor to implement the method of the first embodiment. In addition, the electronic device can also include a transceiver, and the processor and the transceiver can be connected through a communication bus, and the transceiver is used for communication with other devices.

[0058] Next, the functions of the electronic device will be described in detail in conjunction with Figure 4 The various constituent components of the electronic device will be described in detail as follows: The processor is the control center of the electronic device. The electronic device can include multiple processors. Each of the processors can be a single-CPU or a multi-CPU. The processor can be one processor or a collective term of multiple processing elements. For example, the processor can be one or more central processing units (CPUs), other general purpose processors, application specific integrated circuits (ASICs), or one or more integrated circuits configured to implement an embodiment of the present application, such as one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor can be a microprocessor or any conventional processor, or the like. The processor can perform various functions of the electronic device by running or executing software programs stored in the memory and calling data stored in the memory.

[0059] In a specific implementation, as an embodiment, the processor can include one or more CPUs, such as CPU0 and CPU1 shown in FIG. 6, of course, this is only an exemplary description. Figure 4

[0060] The memory is used to store software programs for implementing the solution of the present application, and is controlled by the processor to perform. The specific implementation can refer to the above method embodiments, and will not be described here.

[0061] ​Optionally, the memory may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory may be integrated with the processor or exist independently, and may be accessed through the interface circuit of the electronic device ( Figure 4 (Not shown in the image) is coupled to the processor; however, this embodiment of the invention does not impose specific limitations on this.

[0062] The transceiver may include a receiver and a transmitter. Figure 4 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function. The transceiver can be integrated with the processor or exist independently, and can be connected through the interface circuit of the electronic device (…). Figure 4 (Not shown in the image) is coupled to the processor, and this embodiment of the invention does not specifically limit this.

[0063] In addition, it should be noted that, Figure 4 The structure of the electronic device shown is not intended to limit the device. Actual devices may include more or fewer components than shown, or combine certain components, or have different component arrangements. Furthermore, the technical effects achieved by this electronic device when performing the method of the first embodiment described above can be referenced to the technical effects described in the first embodiment; therefore, they will not be repeated here.

[0064] Fourth embodiment This embodiment provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by a processor to implement the method of the first embodiment described above. The computer-readable storage medium may be a ROM, random access memory, CD-ROM, magnetic tape, floppy disk, or optical data storage device, etc. The instruction stored therein can be loaded and executed by a processor in a terminal.

[0065] Moreover, it should be noted that the present application can be provided as a method, an apparatus, or a computer program product. Therefore, the embodiments of the present application can take the form of an entirely or partially hardware embodiment, an entirely or partially software embodiment, or an embodiment combining software and hardware aspects. Furthermore, when implemented in software, the embodiments of the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, a computer diskette, an optical storage medium, a magnetic storage medium, and a semiconductor memory device). The computer program product includes one or more computer instructions that when loaded and executed by a computer, cause the computer to carry out the processes or functions described in the embodiments of the present application. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable apparatus. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, such as from a website, a computer, a server, or a data center to another website, computer, server, or data center through a wired (for example, infrared, wireless, microwave, or the like) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, data center, or the like, including one or more collections of available media. The available media can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0066] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate a device that implements the flow Figure 1 The flow or the plurality of flows and / or blocks Figure 1 The device that implements the functions specified in the flow or the plurality of flows and / or blocks.

[0067] These computer program instructions can also be stored in a computer-readable storage medium that can direct the computer or other programmable data processing terminal device to work in a specific manner, so that the instructions stored in the computer-readable storage medium produce a manufactured product including instruction devices that implement the flow Figure 1 The flow or the plurality of flows and / or blocks Figure 1the functions specified in the individual block or blocks. Such computer program instructions can also be loaded into a computer or other programmable data processing devices, so that a series of operational steps are performed on the computer or other programmable devices to generate a computer-implemented process, thus the instructions executed on the computer or other programmable devices provide a process for implementing the functions specified in the flowchart block or blocks. Figure 1 the functions specified in the individual block or blocks. Such computer program instructions can also be loaded into a computer or other programmable data processing devices, so that a series of operational steps are performed on the computer or other programmable devices to generate a computer-implemented process, thus the instructions executed on the computer or other programmable devices provide a process for implementing the functions specified in the flowchart block or blocks. Figure 1 the functions specified in the individual block or blocks. Such computer program instructions can also be loaded into a computer or other programmable data processing devices, so that a series of operational steps are performed on the computer or other programmable devices to generate a computer-implemented process, thus the instructions executed on the computer or other programmable devices provide a process for implementing the functions specified in the flowchart block or blocks.

[0068] It should also be noted that, in the present document, the terms such as first and second, etc. are merely used to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article or terminal device. Without more limitations, the element defined by the statement "including a…", does not exclude the presence of other identical elements in the process, method, article or terminal device including the element. In addition, the term "and / or" is merely a description of the association relationship between the associated objects, which means that there can be three relationships, for example, A and / or B, which means that there are three cases of A alone, A and B together, and B alone, where A and B can be singular or plural. In addition, the character " / " in the present document generally represents an "or" relationship between the front and rear associated objects, but it can also represent an "and / or" relationship, which can be understood in the context before and after. "At least one" means one or more, and "multiple" means two or more. "At least one of the following" or similar expressions means any combination of these items, including single item or any combination of multiple items. For example, at least one of a, b or c can mean a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0069] In addition, it can be understood that in various embodiments of the present application, the size of the sequence number of the above processes does not mean the order of execution, and the execution order of the processes should be determined by their functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0070] Those skilled in the art can appreciate that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized in electronic hardware or in a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0071] In several embodiments provided by the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely schematic, for example, the division of functional modules / units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another device, or some features can be omitted or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms. The units described as separate components can be or can not be physically separated, and the components displayed as units can be or can not be physical units, that is, can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment. In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present, or two or more units can be integrated in one unit.

[0072] If the method is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present application. The foregoing storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0073] Finally, it should be noted that the above description is only the preferred embodiment of the application, it should be pointed out that although the preferred embodiment of the application has been described, for those skilled in the art, once the basic creative concept of the application is known, several improvements and refinements can be made without departing from the principles of the application, and these improvements and refinements should also be considered as the protection scope of the application. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the application.

Claims

1. A time-sensitive traffic scheduling method for satellite-to-ground networks based on RSMA and information age, characterized in that, The time-sensitive traffic scheduling method for satellite-to-ground networks based on RSMA and information age includes: Based on the RSMA transmission mechanism, the satellite-to-ground communication content is divided into public streams and private streams; Calculate the information age value of public and private flows in the satellite-to-ground network separately; With the goal of minimizing the weighted information age value and transmission power consumption of time-sensitive traffic in the satellite-to-ground network, the optimal scheduling strategy for time-sensitive traffic in the satellite-to-ground network is determined by a multi-agent dual-delay deep deterministic policy gradient method under preset constraints. The optimal scheduling strategy for time-sensitive traffic in the satellite-to-ground network is synchronized to each satellite node via inter-satellite links.

2. The satellite-to-ground network time-sensitive traffic scheduling method based on RSMA and information age as described in claim 1, characterized in that, The RSMA-based transmission mechanism divides satellite-to-ground communication content into public and private streams, including: Based on the communication requirements of the work scenario, network traffic analysis technology is used to statistically analyze the frequency distribution and service types of communication content of each node, and the satellite-to-ground communication content is divided into homogeneous traffic and heterogeneous traffic; among them, homogeneous traffic is the content requested by multiple nodes at high frequency, and heterogeneous traffic is the content requested by a single node at low frequency. Based on the RSMA transmission mechanism, homogeneous traffic from all nodes is merged and encoded into a public stream, while heterogeneous traffic is independently encoded into a private stream. The public stream uses a precoding vector that is dynamically designed based on the satellite channel state to ensure interference-free decoding at the receiver. The private stream uses a statically independent precoding vector to eliminate interference between nodes in the satellite-to-ground network. When decoding at the receiver, the public stream of multiple nodes is decoded first, followed by the private stream of a single node, thereby eliminating serial interference between the public and private streams.

3. The satellite-to-ground network time-sensitive traffic scheduling method based on RSMA and information age as described in claim 1, characterized in that, The method for calculating the age value of the information is as follows: Record the generation timestamp of the information stream whose age value is to be calculated, and dynamically update the information age of the information stream based on the difference between the current time and the generation timestamp; The information age value is calculated based on the information age; whereby the information age value characterizes the time sensitivity of the information flow. Furthermore, the value of information age increases with the age of the information; a higher value indicates that the current traffic transmission needs to be executed as soon as possible.

4. The time-sensitive traffic scheduling method for satellite-to-ground networks based on RSMA and information age as described in claim 3, characterized in that, The formula for calculating the value of information age based on information age is expressed as follows: in, Indicates the first Information stream received by each node The informational value of age; express Information age; Indicates the business latency sensitivity coefficient; e It represents the base of a natural number.

5. The satellite-to-ground network time-sensitive traffic scheduling method based on RSMA and information age as described in claim 2, characterized in that, The optimization objective is expressed as: in, This is the set of precoded vectors for the public flows of all satellites in the space-to-ground network; A set of precoded vectors for private streams served by all satellites and all nodes in a satellite-to-ground network; A set of rate segmentation factors used to allocate the information rates carried by public and private streams; For the first The priority weight of each node; This is the power consumption penalty factor; For the first The launch power of each satellite; M This represents the total number of ground nodes. The age value of information in public circulation; The age value of information in private streams; K Total number of satellites; T To optimize the target's effective time.

6. The satellite-to-ground network time-sensitive traffic scheduling method based on RSMA and information age as described in claim 1, characterized in that, The constraints include: The total power of the satellite's public and private streams does not exceed the maximum transmit power threshold; The sum of the satellite public stream transmission rate and private stream transmission rate received by the node is not less than the minimum receiving rate; The ratio of the transmission rate of the public stream to the private stream received by the node is not less than a given threshold, and the difference between the signal-to-interference-plus-noise ratio of the public stream and the signal-to-interference-plus-noise ratio of the private stream received by the node is not less than a given threshold. The sum of interference from each node to other nodes in public information transmission and private information transmission does not exceed the maximum interference tolerance. The time sensitivity of information age value does not exceed the maximum time sensitivity threshold.

7. The time-sensitive traffic scheduling method for satellite-to-ground networks based on RSMA and information age as described in claim 1, characterized in that, The multi-agent dual-delay deep deterministic policy gradient method employs a dual-timescale framework, comprising high-level agents and low-level agents; wherein, The state space of the high-level intelligent agent includes the distribution of inter-satellite interference, the distribution of information age value of public and private flows of each node, the relative positions of satellites, and the distribution of service load; the state space of the low-level intelligent agent includes the real-time channel state, the node queue state, and the state space of the third-level intelligent agent. The distribution of information age value and power allocation of public and private streams of each satellite service node; High-level agents perform inter-satellite interference coordination over long timescales, outputting actions including inter-satellite interference coordination factors, spectrum reuse factors, and satellite cooperation weights. Low-level agents perform intra-satellite rate allocation over short timescales, outputting actions including precoded vectors for public and private flows and rate segmentation factors. The rate segmentation factor is used to allocate the information rates carried by public and private flows. The inter-satellite interference coordination factor quantifies the current satellite's ability to suppress interference from neighboring satellites, thereby managing and controlling harmful interference between satellites. The spectrum reuse factor dynamically adjusts the spatial reuse level of current satellite spectrum resources, balancing capacity and interference. The satellite cooperation weights dynamically adjust the cooperative transmission behavior between satellites based on their relative positions and service load.

8. The satellite-to-ground network time-sensitive traffic scheduling method based on RSMA and information age as described in claim 7, characterized in that, Rewards for high-level intelligent agents Represented as: in, Represents the set of ground nodes; For the first The priority weight of each node; The age value of information in public circulation; The age value of information in private streams; A penalty factor for interference coordination deviation; This represents the theoretically optimal value for the inter-satellite interference coordination factor. This is the excitation factor for spectrum reuse; Inter-satellite interference coordination factor; This is the spectrum reuse factor.

9. The satellite-to-ground network time-sensitive traffic scheduling method based on RSMA and information age as described in claim 7, characterized in that, Rewards for low-level agents Represented as: in, Indicates by the first A set of nodes for satellite services; For the first The priority weight of each node; The age value of information in public circulation; The age value of information in private streams; This is the transmission power penalty factor; For the first The launch power of each satellite; Penalty factor for unmet rate requirements; This is the minimum required rate; This refers to the actual transmission rate. Indicates only At that time, for each node Summing the values.

10. A time-sensitive traffic scheduling device for satellite-to-ground networks based on RSMA and information age, characterized in that, The satellite-to-ground network time-sensitive traffic scheduling device based on RSMA and information age includes: The data processing module is used for: Based on the RSMA transmission mechanism, the satellite-to-ground communication content is divided into public streams and private streams; Calculate the information age value of public and private flows in the satellite-to-ground network separately; The time-sensitive traffic scheduling module is used for: With the goal of minimizing the weighted information age value and transmission power consumption of time-sensitive traffic in the satellite-to-ground network, the optimal scheduling strategy for time-sensitive traffic in the satellite-to-ground network is determined by a multi-agent dual-delay deep deterministic policy gradient method under preset constraints. The optimal scheduling strategy for time-sensitive traffic in the satellite-to-ground network is synchronized to each satellite node via inter-satellite links.

Images