Cross-domain network traffic scheduling method, apparatus and device, and computer program product

Abstract

The invention discloses a cross-domain network traffic scheduling method, device and equipment, and a computer program product. The method comprises the following steps: receiving a data packet of a sending end; based on a preset cross-domain traffic scheduling model, the data packet is controlled to be transmitted among the first TSN network domain, the cellular network domain and the second TSN network domain in sequence, the data packet finally enters a receiving end, and the preset cross-domain traffic scheduling model is realized based on a predefined cooperative gating strategy. The cross-domain traffic scheduling model based on the collaborative gating strategy is adopted to control network data transmission, jitter of the whole network is reduced, the deterministic performance of the network is optimized, coordination limitation of a frequency spectrum and an operator is eliminated, the applicability and stability of the network are enhanced, complex parameter calculation and optimization mechanisms are not needed, the calculation complexity is reduced, and the network performance is improved. And the real-time performance and the response speed of the system are improved. And a dynamic gating mechanism is adopted, so that the transmission time can be flexibly adjusted, the network state is dynamically adapted, and diversified network communication requirements are met.

Description

Technical Field

[0001] The present application relates to the field of network transmission technology, and in particular to a method, apparatus and device, and computer program product for cross-domain network traffic scheduling. Background Art

[0002] Delay jitter is a key metric for evaluating network quality, and its performance is directly related to the quality of network services. Latency refers to the time it takes for a message or packet to travel from one end of the network to the other. Variations in this delay are called jitter, primarily caused by varying queuing times for successive packets within a service flow. This is the single most significant issue affecting service quality, and different service types have varying jitter tolerance thresholds.

[0003] A key factor in the development of emerging industries lies in achieving network deterministic guarantees for service flow transmission latency, jitter, and zero packet loss. However, actual industrial scenarios are very complex, characterized by a large number of service flows, widely varying traffic characteristics, and deep integration of heterogeneous networks. In view of these characteristics, achieving network deterministic guarantees for a large number of heterogeneous multi-domain network scenarios in complex industries requires focusing on the adaptation of a large number of time-sensitive service flows to deterministic resources, the mixed deterministic co-network scheduling of differentiated service flows, and the end-to-end deterministic guarantees across heterogeneous converged networks. It is of great significance to reduce delay and jitter indicators through specific technical means in heterogeneous multi-domain networks to achieve end-to-end deterministic guarantees.

[0004] In recent years, researchers have proposed a variety of effective methods from various perspectives, including time synchronization, spectrum sharing, congestion control, reinforcement learning, time slot allocation, and deep learning. These studies have not only achieved breakthroughs in theory, but also demonstrated significant performance improvements in practical applications.

[0005] However, although the above methods have made significant progress in reducing delay jitter and improving network performance, each method still has certain problems from the technical, operational and cost perspectives, such as insufficient accuracy of delay jitter compensation, poor real-time performance, low system stability and high cost. Summary of the Invention

[0006] The embodiments of the present application provide a cross-domain network traffic scheduling method, apparatus and equipment, and a computer program product to reduce the delay jitter of cross-domain network transmission and improve the stability of network transmission.

[0007] The embodiments of this application adopt the following technical solutions:

[0008] In a first aspect, an embodiment of the present application provides a traffic scheduling method for a cross-domain network, wherein the cross-domain network is composed of a first TSN network domain, a cellular network domain, and a second TSN network domain. The traffic scheduling method for the cross-domain network includes:

[0009] Receive data packets from the sender;

[0010] Based on a preset cross-domain traffic scheduling model, the data packet is controlled to be transmitted in sequence between the first TSN network domain, the cellular network domain and the second TSN network domain, and the data packet finally enters the receiving end. The preset cross-domain traffic scheduling model is implemented based on a predefined collaborative gating strategy.

[0011] Optionally, the first TSN network domain is deployed at the transmitting end, the second TSN network domain is deployed at the receiving end, and the data packet received at the transmitting end includes:

[0012] receiving the data packet from the sending end through the first TSN network domain;

[0013] The controlling, based on a preset cross-domain traffic scheduling model, to sequentially transmit the data packet among the first TSN network domain, the cellular network domain, and the second TSN network domain, and allowing the data packet to finally enter the receiving end includes:

[0014] Based on the preset cross-domain traffic scheduling model, the collaborative gating strategy configured in the first TSN network domain is used to control the data packet from entering the cellular network domain;

[0015] After the data packet is transmitted in the cellular network domain, based on the preset cross-domain traffic scheduling model, the collaborative gating strategy configured in the second TSN network domain is used to control the release of the data packet and allow the data packet to enter the receiving end.

[0016] Optionally, the preset cross-domain traffic scheduling model is constructed in the following form:

[0017] determining a variable delay within the cellular network domain;

[0018] The variable delay within the cellular network domain is compensated using a controllable adaptive compensation delay to obtain a compensated end-to-end target delay, wherein the controllable adaptive compensation delay is implemented based on a predefined collaborative gating strategy to keep the compensated end-to-end target delay constant.

[0019] Optionally, the predefined collaborative gating strategy includes a gating period, where the gating period refers to the entire time process for the data packet to be transmitted to the receiving end through the inter-domain network, and the gating period is determined by:

[0020] determining a network quality of the cellular network domain;

[0021] The gating period is set according to the network quality of the cellular network domain.

[0022] Optionally, the controlling the data packet to enter the cellular network domain by using the collaborative gating strategy configured in the first TSN network domain based on the preset cross-domain traffic scheduling model includes:

[0023] When the data packet enters the first TSN network, determining the gating state of the first TSN network domain according to the collaborative gating strategy configured in the first TSN network domain;

[0024] If the gating state of the first TSN network domain is closed, controlling the data packet to wait in the first TSN network domain until the gating state of the first TSN network domain is open;

[0025] If the gating state of the first TSN network domain is open, the data packet is transmitted to the cellular network domain through the first TSN network domain.

[0026] Optionally, the controlling the release of the data packet based on the preset cross-domain traffic scheduling model and utilizing the collaborative gating strategy configured in the second TSN network domain to allow the data packet to enter the receiving end includes:

[0027] When the data packet enters the second TSN network, determining the gating state of the second TSN network domain according to the collaborative gating strategy configured in the second TSN network domain;

[0028] If the gating state of the second TSN network domain is closed, controlling the data packet to wait in the second TSN network domain until the gating state of the second TSN network domain is open;

[0029] If the gating state of the second TSN network domain is open, the data packet is transmitted to the receiving end through the second TSN network domain.

[0030] Optionally, the predefined cooperative gating strategy is implemented based on a time-aware shaper.

[0031] In a second aspect, an embodiment of the present application further provides a traffic scheduling device for a cross-domain network, wherein the cross-domain network is composed of a first TSN network domain, a cellular network domain, and a second TSN network domain, and the traffic scheduling device for the cross-domain network includes:

[0032] A receiving unit, configured to receive data packets from a sending end;

[0033] A cross-domain transmission control unit is used to control the transmission of the data packet in sequence between the first TSN network domain, the cellular network domain and the second TSN network domain based on a preset cross-domain traffic scheduling model, and to enable the data packet to finally enter the receiving end. The preset cross-domain traffic scheduling model is implemented based on a predefined collaborative gating strategy.

[0034] In a third aspect, an embodiment of the present application further provides a device, including:

[0035] A processor; and a memory arranged to store computer-executable instructions, wherein when the executable instructions are executed, the processor executes any of the aforementioned cross-domain network traffic scheduling methods.

[0036] In a fourth aspect, an embodiment of the present application further provides a computer program product, comprising a computer program / instruction, which, when executed by a processor, implements any of the aforementioned cross-domain network traffic scheduling methods.

[0037] At least one of the above-mentioned technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: the traffic scheduling method of the cross-domain network in the embodiment of the present application, the cross-domain network is composed of a first TSN network domain, a cellular network domain and a second TSN network domain, and the data packet of the sending end is first received; then based on the preset cross-domain traffic scheduling model, the data packet is controlled to be transmitted in sequence between the first TSN network domain, the cellular network domain and the second TSN network domain, and the data packet finally enters the receiving end, and the preset cross-domain traffic scheduling model is implemented based on a predefined collaborative gating strategy. The traffic scheduling method of the cross-domain network in the embodiment of the present application adopts a cross-domain traffic scheduling model implemented based on a collaborative gating strategy to control network data transmission, reduces the jitter of the overall network, optimizes the deterministic performance of the network, gets rid of the spectrum and operator coordination restrictions, enhances the network applicability and stability, and does not require complex parameter calculation and optimization mechanisms, reduces the computational complexity, and improves the real-time performance and response speed of the system. A dynamic gating mechanism is adopted to flexibly adjust the transmission time, dynamically adapt to the network status, and meet diverse network communication needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0039] Figure 1 A flow chart of a method for cross-domain network traffic scheduling in an embodiment of the present application;

[0040] Figure 2 This is a flow chart of traffic scheduling in a cross-domain network according to an embodiment of the present application;

[0041] Figure 3 A schematic diagram of a gating cycle in an embodiment of the present application;

[0042] Figure 4 This is a schematic diagram of the structure of a traffic scheduling device for a cross-domain network in an embodiment of the present application;

[0043] Figure 5 This is a structural diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0044] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0045] The following describes in detail the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0046] Currently, various methods and technologies for reducing delay jitter have been proposed in the prior art, mainly including:

[0047] (1) Network time synchronization and compensation technology

[0048] In complex network topologies, the Precision Time Protocol (PTP) network timing technology is often used for time synchronization. However, the asymmetry of its two-way delay measurement can lead to delay jitter. To address this, researchers have proposed a network delay optimization and compensation method. By correcting delay asymmetry and optimizing jitter, this method significantly improves network time synchronization accuracy, thereby enhancing network performance.

[0049] (2) Spectrum Sharing in Wireless Networks

[0050] Wireless network spectrum resources are limited, making spectrum sharing an effective means of reducing latency and jitter. Research has shown that by sharing spectrum from licensed networks, the spectrum bandwidth of wireless networks can be expanded, thereby reducing data transmission latency and jitter. This study uses stochastic geometry and queuing theory to analyze the impact of spectrum sharing on latency performance and validates the effectiveness of spectrum sharing in reducing latency and jitter through Monte Carlo simulation.

[0051] (3) Improvement of congestion control algorithm

[0052] Traditional congestion control algorithms perform poorly in complex network environments, especially when faced with severe latency jitter. The Bottleneck Bandwidth and Round-Trip (BBR) algorithm offers a new approach to congestion control by fully utilizing bandwidth while ensuring low latency. However, the BBR algorithm still has shortcomings in wireless networks, such as insufficient sensitivity to latency jitter. To address these issues, researchers have proposed an improved BBR algorithm that optimizes the congestion window by incorporating the mean and standard deviation of the Round-Trip Time (RTT), thereby increasing the transmission rate when latency jitter is severe.

[0053] (4) Reinforcement learning and network optimization

[0054] Reinforcement learning shows great potential for optimizing network latency and jitter. By using a Markov model to learn and reinforce network states, researchers have proposed a reinforcement learning-based approach to optimizing end-system access latency and jitter. This approach optimizes the objective function of the reinforcement learning model to train model parameters that adapt to dynamic network environments, effectively reducing latency and jitter.

[0055] (5) Time slot allocation optimization

[0056] In complex communication scenarios such as tactical data links, traditional fixed time slot allocation methods can easily lead to resource waste and degraded communication performance. Researchers have proposed a dynamic time slot optimization scheme by combining the CNN-Res LSTM time slot demand prediction model with the AWPSO-SAA time slot allocation algorithm. This scheme predicts node communication needs and combines particle swarm optimization and simulated annealing algorithms to achieve efficient and stable time slot allocation, significantly reducing latency jitter.

[0057] (6) Network modeling based on deep learning

[0058] Network modeling is fundamental to optimizing network performance. Researchers have proposed DWNet (Deeper and Wider Networks), a heterogeneous network modeling method based on graph neural networks (GNNs). By introducing deeper message passing and extensive feature fusion, DWNet can more accurately predict end-to-end latency and jitter in the network. Experimental results show that the model exhibits stronger generalization capabilities when dealing with unseen network topologies.

[0059] Although the above methods have made significant progress in reducing latency jitter and improving network performance, they still have some limitations:

[0060] (1) Network time synchronization technology (such as PTP) provides time information through a timing server. This method has the following problems:

[0061] 1) Network delay: When a timing server provides time information to other devices through the network, network delay can lead to inaccurate time synchronization between devices. This delay can be especially noticeable in large-scale networks.

[0062] 2) Complexity of delay and jitter compensation. In complex network topologies, the asymmetry of two-way delay measurement may lead to insufficient accuracy of delay and jitter compensation.

[0063] (2) Although spectrum sharing technology can optimize spectrum resource utilization, it faces the following challenges:

[0064] 1) Insufficient spectrum sensing accuracy. Complex wireless environments may lead to inaccurate channel state information, thus affecting the efficiency of spectrum allocation.

[0065] 2) Multipath propagation and interference management are complex. In multi-user scenarios, multipath propagation of signals may lead to spectrum usage conflicts, increasing the complexity of interference management.

[0066] 3) Cross-operator coordination is difficult. In cross-operator spectrum sharing, the lack of a unified coordination mechanism may lead to interference problems and affect system stability.

[0067] (3) Although improved congestion control algorithms (such as BBR) have optimized network performance to a certain extent, the following problems still exist:

[0068] 1) Insufficient adaptability to dynamic network environments. In a network environment with severe delay jitter, the improved BBR algorithm may still not be able to completely avoid congestion.

[0069] 2) Increased computational complexity: Introducing more parameters and optimization mechanisms may increase the computational complexity of the algorithm and affect real-time performance.

[0070] (4) Although the optimization method based on reinforcement learning performs well in dynamic network environments, it also has the following disadvantages:

[0071] 1) Long training time: Reinforcement learning models require a lot of time to train, especially in complex network environments.

[0072] 2) Sensitivity to environmental changes. Reinforcement learning models are sensitive to changes in the network environment and may require frequent retraining to adapt to new network states.

[0073] (5) Although time slot allocation optimization methods (such as TDMA time slot allocation) can improve resource utilization efficiency, they also have the following limitations:

[0074] 1) Delay and jitter issues: Time division multiplexing (TDM) technology may introduce delay and jitter because the time slots of different signals may have delay differences.

[0075] 2) Insufficient flexibility in resource allocation. In a dynamic network environment, a fixed time slot allocation method may be difficult to adapt to rapidly changing communication needs.

[0076] (6) Deep learning models (such as DWNet) perform well in network modeling, but they also have the following disadvantages:

[0077] 1) Large data requirements: Deep learning models usually require a large amount of labeled data for training, and the cost of data acquisition and labeling is high.

[0078] 2) High computing resource requirements: The training and inference processes require a large amount of computing resources, especially high-performance hardware such as GPUs or TPUs.

[0079] 3) Poor model interpretability. Deep learning models are often regarded as "black boxes" and their decision-making process is difficult to explain. This is an important problem in some applications with high interpretability requirements.

[0080] 4) Overfitting risk: Deep learning models are prone to overfitting on small sample data, resulting in insufficient generalization ability.

[0081] Based on this, the embodiment of the present application provides a method for traffic scheduling across domain networks, such as Figure 1 As shown, a flow chart of a traffic scheduling method for a cross-domain network in an embodiment of the present application is provided, wherein the cross-domain network is composed of a first TSN network domain, a cellular network domain and a second TSN network domain.

[0082] The cross-domain network is mainly divided into the sending end, TSN (Time-Sensitive Networking Domain) domain, transition network domain (i.e. cellular network domain), receiving end, time server and controller. The TSN network domain includes TSN switches, TSN gateways and other devices, which can be specifically divided into the first TSN network domain deployed for the sending end and the second TSN network domain deployed for the receiving end. The network domain connected in the middle can be a wired domain or a wireless domain. The time server can provide accurate time information for many devices in the TSN domain. According to the delay, jitter and other information of the overall network, the controller configures the corresponding gating strategy for the TSN switches at both ends. Through the mutual cooperation of the gating strategies of the TSN switches at both ends, the delay and jitter performance of the overall network can be optimized.

[0083] Specifically, the cross-domain network traffic scheduling method of the embodiment of the present application includes at least the following steps S110 to S120:

[0084] Step S110: receiving a data packet from the sending end.

[0085] Step S120, based on a preset cross-domain traffic scheduling model, controls the data packet to be transmitted in sequence between the first TSN network domain, the cellular network domain and the second TSN network domain, and makes the data packet finally enter the receiving end, and the preset cross-domain traffic scheduling model is implemented based on a predefined collaborative gating strategy.

[0086] Combine Figure 2 , provides a schematic diagram of a cross-domain network traffic scheduling process in an embodiment of the present application. During cross-domain network traffic scheduling, the first TSN network domain first receives data packets sent by the sender. These data packets carry various information and may come from sensors, control systems, and other devices in the Industrial Internet. They are the basic units of information transmission in the network.

[0087] The preset cross-domain traffic scheduling model is implemented based on a predefined collaborative gating strategy (CGS). This collaborative gating strategy can be divided into the collaborative gating strategy for the ingress TSN domain (CGS-I) and the collaborative gating strategy for the egress TSN domain (CGS-E), which work together to control the transmission of data packets.

[0088] Transmission in the First TSN Domain: Once packets enter the first TSN domain, CGS-I takes over. It acts as a traffic shaper, regulating upstream traffic to a more predictable pattern. Modeled as a time-aware shaper, it shapes the incoming traffic, precisely controlling the timing of packet entry into the cellular domain and strictly limiting the characteristics of traffic entering the cellular domain.

[0089] Transmission in the cellular network domain: After being processed in the first TSN domain, data packets enter the cellular network domain. The time-varying nature of wireless transmission latency in the cellular network domain is a key factor affecting end-to-end determinism. However, through the preceding traffic shaping and subsequent collaborative gating strategies, this uncertainty can be addressed to a certain extent.

[0090] After leaving the cellular network domain, packets enter the secondary TSN network domain. CGS-E and CGS-I work closely together to release packets at the scheduled time, absorbing latency variations introduced by upstream traffic. It buffers early packets and calculates release times based on relevant formulas to ensure that packets arrive at the receiver according to the scheduled time sequence. Furthermore, based on the traffic arrival curve, it calculates parameters such as the maximum backlog safety limit to ensure stable and deterministic packet transmission.

[0091] The data packet arrives at the receiving end: After being transmitted and controlled by the above three network domains, the data packet finally reaches the receiving end, completing the traffic scheduling process of the entire cross-domain network.

[0092] The cross-domain network traffic scheduling method of the present application embodiment uses a cross-domain traffic scheduling model based on a collaborative gating strategy to control network data transmission, reducing overall network jitter, optimizing network deterministic performance, breaking away from spectrum and operator coordination restrictions, enhancing network applicability and stability, and eliminating the need for complex parameter calculation and optimization mechanisms, reducing computational complexity and improving the system's real-time performance and response speed. A dynamic gating mechanism is used to flexibly adjust transmission time and dynamically adapt to network status, meeting diverse network communication needs.

[0093] In some embodiments of the present application, the first TSN network domain is deployed at the sending end, and the second TSN network domain is deployed at the receiving end, and the receiving of the data packet from the sending end includes: receiving the data packet from the sending end through the first TSN network domain; based on the preset cross-domain traffic scheduling model, controlling the data packet to be transmitted in sequence between the first TSN network domain, the cellular network domain and the second TSN network domain, and making the data packet finally enter the receiving end includes: based on the preset cross-domain traffic scheduling model, using the collaborative gating strategy configured in the first TSN network domain to control the data packet to enter the cellular network domain; after the data packet is transmitted in the cellular network domain, based on the preset cross-domain traffic scheduling model, using the collaborative gating strategy configured in the second TSN network domain to control the release of the data packet, and making the data packet enter the receiving end.

[0094] Continue to refer Figure 2 In the data packet reception phase, the first TSN network domain (represented as TSN1) deployed at the sending end receives the data packets sent by the sending end. Next, the data packet transmission control phase begins. Based on the preset cross-domain traffic scheduling model, the collaborative gating strategy configured in the first TSN network domain is used to control the data packets. This collaborative gating strategy adjusts the upstream traffic to a more predictable pattern and accurately controls the time when the data packet enters the cellular network domain. For example, by setting the relevant parameters of the time-aware shaper, the traffic characteristics entering the cellular domain are strictly restricted.

[0095] After a packet completes transmission within the cellular network domain, its release is controlled again based on a pre-defined cross-domain traffic scheduling model and a coordinated gating strategy configured in the second TSN network domain (represented as TSN2) deployed at the receiving end. This strategy releases packets at a predetermined time, absorbing latency variations introduced by upstream traffic and ensuring that packets arrive at the receiving end according to the predetermined time sequence by, for example, buffering early packets.

[0096] By deploying TSN network domains at both the transmitter and receiver ends and configuring collaborative gating strategies, this approach leverages a cross-domain traffic scheduling model to achieve stable data packet transmission across the cross-domain network. This effectively addresses the uncertainties of cellular network domains, reduces end-to-end latency variations, improves network determinism, and meets the needs of time-sensitive applications. It also offers advantages such as direct control, explainable decisions, and adaptability to dynamic networks.

[0097] In some embodiments of the present application, the preset cross-domain traffic scheduling model is constructed in the following form: determining the variable delay within the cellular network domain; using a controllable adaptive compensation delay to compensate for the variable delay within the cellular network domain to obtain a compensated end-to-end target delay, and the controllable adaptive compensation delay is implemented based on a predefined collaborative gating strategy to keep the compensated end-to-end target delay constant.

[0098] The time-varying nature of wireless transmission delay in cellular networks is far greater than that of wired networks. Standard TSN traffic shaping mechanisms, such as TAS and ATS, primarily control traffic scheduling within a single TSN domain and are unable to guarantee end-to-end determinism in converged networks that include cellular domains with unpredictable delay characteristics. To effectively connect non-deterministic cellular links between deterministic TSN domains and isolate the impact of cellular network delay variations, the end-to-end delay variation optimization problem is formulated as follows:

[0099] Given an arrival curve α in The input traffic flow described by (t) must sequentially traverse TSN1, the cellular network domain, and TSN2. The variable delay introduced by the cellular network is in, is a known lower bound on the variable delay, is the known upper limit of variable delay. By coordinating the egress gating strategies of TSN1 and TSN2, a cross-domain scheduling mechanism is formed to minimize the end-to-end delay variation. e2e The goal is to make the end-to-end delay D of any packet p e2e (p) remains constant:

[0100]

[0101] Among them, t arrival_A (p) is the time when data packet p arrives at TSN1, t release_C (p) is the time when it is finally released from TSN2, is the predefined target delay.

[0102] Latency variation stems from the unpredictability of packet arrival times. The goal of cross-domain traffic scheduling is to logically transform a non-deterministic network domain with time-varying latency into a deterministic channel with constant latency. By actively controlling the release time of packets at key network nodes, irregular traffic can be shaped into a predictable pattern, effectively mitigating variations. It can be divided into two parts: the uncontrollable variable delay D in the cellular network domain Cellular (p) and controllable adaptive compensation delay W comp (p). This relationship can be expressed as:

[0103]

[0104] Regardless of D Cellular How (p) fluctuates within its range, W comp (p) will be adjusted accordingly to keep the sum of the two constant. In this way, the scheduling mechanism absorbs the unevenness of the packet sequence in the time dimension by introducing controllable delay, and finally achieves deterministic sequence balance. To ensure the feasibility of this mechanism, the compensation delay W comp (p) must be non-negative. Therefore, the following feasibility conditions must be met:

[0105]

[0106] By building a cross-domain traffic scheduling model and using the adaptive compensation delay generated by the collaborative gating strategy to effectively balance the variable delay in the cellular network domain, the fluctuation of the end-to-end delay is significantly reduced, the delay is kept constant, and the certainty and stability of network transmission are greatly improved. It provides a reliable network environment for time-sensitive applications and enhances the network's adaptability to complex dynamic environments.

[0107] In some embodiments of the present application, the predefined collaborative gating strategy includes a gating period, which refers to the entire time process for the data packet to be transmitted to the receiving end through the cross-domain network, and the gating period is determined by: determining the network quality of the cellular network domain; and setting the gating period according to the network quality of the cellular network domain.

[0108] In the embodiment of the present application, the predefined collaborative gating strategy includes the key element of gating period. Gating period refers to the entire time process of data packets being transmitted to the receiving end through the cross-domain network, such as Figure 3 As shown, a schematic diagram of a gating cycle in an embodiment of the present application is provided. The determination process is as follows:

[0109] First, we need to accurately determine the network quality of the cellular network domain. As an intermediate, non-deterministic wireless network domain, the cellular network domain's latency characteristics vary with wireless channel conditions and are subject to known lower and upper bounds. Through extensive measurement and analysis methods, we can determine the latency distribution of the cellular network domain.

[0110] Next, the gating period is set based on the obtained cellular network domain network quality. Generally, the gating period is set to the maximum normal latency of the intermediate network domain. For example, if measurement and analysis reveal that the maximum latency of the intermediate network domain under normal circumstances is 5ms, the gating period can be initially set to 5ms. Alternatively, based on the network's latency distribution, the gating period can be set to a certain percentage of the maximum latency, such as 90% of the maximum latency, to increase redundancy and ensure more stable data packet transmission.

[0111] At the same time, frame replication technology is used to avoid occasional high latency situations. When high latency is detected, data packets are replicated and sent through different paths to ensure that at least one data packet arrives on time. During the gating cycle, the gating of TSN1 and TSN2 operates according to the preset switching time. Figure 3 As shown in the figure, in the initial state (1), the gates of TSN1 and TSN2 are both in the closed state; when the preset opening time (2) is reached, the gate of TSN1 is opened, and the data packet can enter the intermediate network domain through TSN1 and reach TSN2 after transmission; when the preset gate opening time (4) of TSN2 is reached, the data packet can be transmitted to the receiving end through TSN2, thereby realizing the orderly transmission of data packets in the cross-domain network.

[0112] By rationally setting gating periods based on cellular network quality and utilizing frame replication technology, we effectively address the uncertainty of intermediate network domains. This makes data packet transmission across cross-domain networks more orderly and stable, reduces network jitter, and improves network transmission certainty. This provides more reliable network support for various applications and helps meet the requirements for data transmission stability and timeliness in different scenarios.

[0113] In some embodiments of the present application, the control of the data packet entering the cellular network domain based on the preset cross-domain traffic scheduling model and the use of the collaborative gating strategy configured in the first TSN network domain includes: when the data packet enters the first TSN network, determining the gating state of the first TSN network domain according to the collaborative gating strategy configured in the first TSN network domain; if the gating state of the first TSN network domain is closed, controlling the data packet to wait in the first TSN network domain until the gating state of the first TSN network domain is open; if the gating state of the first TSN network domain is open, transmitting the data packet to the cellular network domain through the first TSN network domain.

[0114] When a data packet enters the first TSN network, the gating status of the first TSN network domain is determined based on the coordinated gating policy configured in the first TSN network domain. This determination is based on the rules and parameters preset in the coordinated gating policy, combined with multiple factors such as the current network operating status.

[0115] If the gating state of the first TSN network domain is determined to be closed, the data packet will not be able to immediately pass through the first TSN network domain to the cellular network domain. In this case, the data packet will wait in the first TSN network domain. During the waiting process, the system will continuously monitor the gating state until the gating state of the first TSN network domain changes to open.

[0116] Once the gating state of the first TSN network domain becomes open, the data packet is allowed to pass through the first TSN network domain and is transmitted to the cellular network domain, continuing its transmission journey in the cross-domain network. For example, in the diagram, when the data packet arrives at TSN1, if the TSN1 gating is in the closed state (such as stage (1)), the data packet will wait in TSN1; when the gating is opened (such as stage (2)), the data packet can enter the intermediate network domain through TSN1.

[0117] The coordinated gating strategy of the first TSN network domain enables precise control over data packets entering the cellular network domain. This control method effectively coordinates the transmission timing of data packets, preventing them from entering the cellular network domain out of order when gating is not enabled, thereby reducing the possibility of network congestion. It also helps ensure that data packets are transmitted according to a predetermined time sequence, improving the orderliness and stability of network transmission. This lays the foundation for deterministic transmission across the entire cross-domain network, enabling the network to better adapt to complex and changing communication environments and meet the requirements of various applications for stable and reliable data transmission.

[0118] In some embodiments of the present application, based on the preset cross-domain traffic scheduling model, the collaborative gating strategy configured in the second TSN network domain is used to control the release of the data packet and allow the data packet to enter the receiving end, including: when the data packet enters the second TSN network, the gating state of the second TSN network domain is determined according to the collaborative gating strategy configured in the second TSN network domain; if the gating state of the second TSN network domain is closed, the data packet is controlled to wait in the second TSN network domain until the gating state of the second TSN network domain is open; if the gating state of the second TSN network domain is open, the data packet is transmitted to the receiving end through the second TSN network domain.

[0119] When a data packet is transmitted from the cellular network domain to the second TSN network, the gating status of the second TSN network domain is determined based on the coordinated gating strategy configured in the second TSN network domain. This determination process comprehensively considers various parameters preset in the coordinated gating strategy and the current real-time status of the network.

[0120] If the gate state of the second TSN network domain is determined to be closed, the data packet will not be able to immediately pass through the second TSN network domain to the receiver. In this case, the data packet will wait in the second TSN network domain. During this waiting period, the system will continue to monitor the gate state until the gate state of the second TSN network domain changes to open.

[0121] Once the gate of the second TSN network domain is turned on, the data packet is allowed to pass through the second TSN network domain and be transmitted to the receiving end. For example, referring to the schematic diagram, when a data packet arrives at TSN2, if the gate of TSN2 is closed at this time, the data packet needs to wait in TSN2; when the gate is turned on, the data packet can pass through TSN2 smoothly to the receiving end.

[0122] Leveraging the collaborative gating strategy of the second TSN network domain, precise control is achieved over the release and entry of data packets into the receiving end. This control method effectively ensures that data packets arrive at the receiving end at the appropriate time, avoiding network issues that could arise from data packets arriving too early or too late. It also further enhances the determinism and stability of network transmission, making traffic scheduling across the entire cross-domain network more organized and adaptable to complex and changing network environments, providing reliable support for various applications with strict time requirements for data transmission.

[0123] In some embodiments of the present application, the predefined cooperative gating strategy is implemented based on a time-aware shaper.

[0124] The cellular network domain is a non-deterministic wireless network domain in the middle. Its delay characteristics are a key factor affecting end-to-end determinism. The transmission delay of data packet p in the cellular network domain is defined as D Cellular (p). This delay varies with wireless channel conditions and is bounded by a known lower bound and upper limit The constraints satisfy:

[0125]

[0126] Considering the service rate of the cellular network domain, the minimum guaranteed service rate is defined as R Cellular According to network calculus theory, the worst-case service capacity β of the cellular network domain is Cellular (t), can be modeled as:

[0127]

[0128] Where [x] + =max(0,x).

[0129] The ingress TSN domain is the collaborative gating strategy of TSN1 (CGS-I): CGS-I is configured in the first TSN network domain and acts as a traffic shaper to adjust the upstream traffic to a more predictable pattern, thereby accurately controlling the time when the data packet enters the cellular domain. Its operation can be modeled as a time-aware shaper (σ s , ρ s ), where σ s =B(maximum burst size), ρ s =B / P, where P is the scheduling period.

[0130] For the α in (t) The arrival curve of the output flow of the constrained input flow after CGS-I shaping It can be expressed as:

[0131]

[0132] The parameter constraints are as follows:

[0133] σ out =B, (7)

[0134]

[0135] Among them, ∧ is the minimum operator. Therefore, the traffic characteristics entering the cellular domain are strictly restricted to:

[0136]

[0137] The collaborative gating strategy (CGS-E) of the egress TSN domain, i.e. TSN2: CGS-E strictly cooperates with CGS-I and is configured in the second TSN network domain. release_C (p) Release packet p to absorb the delay variation introduced by the upstream:

[0138]

[0139] in, Indicates the target delay for the cross-domain segment. To release packets at the target time, CGS-E must buffer early arriving packets. The maximum required compensation delay This can be formally derived using the supremum and infimum operators:

[0140]

[0141] Traffic leaving TSN1 is affected by When the flow is limited by β Cellular (t) (see Equation 5) modeling the cellular network domain, the burstiness of traffic arriving at TSN2 increases. Its new arrival curve It can be more strictly limited to:

[0142]

[0143] in, Therefore, a safe upper bound on the maximum backlog is It can be calculated as:

[0144]

[0145] σ′ out and Substituting the expression into , and combining formulas (7) and (8), we can get:

[0146]

[0147] When the endpoint is a periodic traffic source and the data transmission time is fixed, the traffic characteristics entering the cellular network domain can be directly expressed as the arrival curve of the source traffic:

[0148] α src (t)=σ src +ρ src t, (15)

[0149] Therefore, formula (14) can be simplified as:

[0150]

[0151] By ensuring that all successfully arriving packets are processed at the precise target time, the final output traffic generated by CGS-E is exactly consistent with the intended schedule.

[0152] The coordinated gating strategy implemented with a time-aware shaper effectively addresses the issue of non-deterministic latency within the cellular network domain. CGS-I shapes traffic to strictly limit the characteristics of traffic entering the cellular domain. Combined with CGS-E, packets are released at predetermined times and latency variations are absorbed. This results in more orderly packet transmission, reduced end-to-end latency variation, and improved network transmission determinism, providing stable and reliable data transmission across cross-domain networks.

[0153] The embodiment of the present application also provides a cross-domain network traffic scheduling device 400, such as Figure 4 As shown, a schematic structural diagram of a traffic scheduling device for a cross-domain network in an embodiment of the present application is provided. The cross-domain network is composed of a first TSN network domain, a cellular network domain, and a second TSN network domain. The traffic scheduling device 400 for the cross-domain network includes: a receiving unit 410 and a cross-domain transmission control unit 420, wherein:

[0154] The receiving unit 410 is configured to receive a data packet from a transmitting end;

[0155] The cross-domain transmission control unit 420 is used to control the transmission of the data packet in sequence between the first TSN network domain, the cellular network domain and the second TSN network domain based on a preset cross-domain traffic scheduling model, and to enable the data packet to finally enter the receiving end. The preset cross-domain traffic scheduling model is implemented based on a predefined collaborative gating strategy.

[0156] In some embodiments of the present application, the first TSN network domain is deployed at the sending end, and the second TSN network domain is deployed at the receiving end. The receiving unit 410 is specifically used to: receive the data packet from the sending end through the first TSN network domain; the cross-domain transmission control unit 420 is specifically used to: based on the preset cross-domain traffic scheduling model, use the collaborative gating strategy configured in the first TSN network domain to control the data packet to enter the cellular network domain; after the data packet is transmitted in the cellular network domain, based on the preset cross-domain traffic scheduling model, use the collaborative gating strategy configured in the second TSN network domain to control the release of the data packet and allow the data packet to enter the receiving end.

[0157] In some embodiments of the present application, the preset cross-domain traffic scheduling model is constructed in the following form: determining the variable delay within the cellular network domain; using a controllable adaptive compensation delay to compensate for the variable delay within the cellular network domain to obtain a compensated end-to-end target delay, and the controllable adaptive compensation delay is implemented based on a predefined collaborative gating strategy to keep the compensated end-to-end target delay constant.

[0158] In some embodiments of the present application, the predefined collaborative gating strategy includes a gating period, which refers to the entire time process for the data packet to be transmitted to the receiving end through the cross-domain network, and the gating period is determined by: determining the network quality of the cellular network domain; and setting the gating period according to the network quality of the cellular network domain.

[0159] In some embodiments of the present application, the cross-domain transmission control unit 420 is specifically used to: when the data packet enters the first TSN network, determine the gating state of the first TSN network domain according to the collaborative gating strategy configured in the first TSN network domain; if the gating state of the first TSN network domain is closed, control the data packet to wait in the first TSN network domain until the gating state of the first TSN network domain is open; if the gating state of the first TSN network domain is open, transmit the data packet to the cellular network domain through the first TSN network domain.

[0160] In some embodiments of the present application, the cross-domain transmission control unit 420 is specifically used to: when the data packet enters the second TSN network, determine the gating state of the second TSN network domain according to the collaborative gating strategy configured in the second TSN network domain; if the gating state of the second TSN network domain is closed, control the data packet to wait in the second TSN network domain until the gating state of the second TSN network domain is open; if the gating state of the second TSN network domain is open, transmit the data packet to the receiving end through the second TSN network domain.

[0161] In some embodiments of the present application, the predefined cooperative gating strategy is implemented based on a time-aware shaper.

[0162] It can be understood that the above-mentioned cross-domain network traffic scheduling device can implement the various steps of the cross-domain network traffic scheduling method provided in the aforementioned embodiment. The relevant explanations of the cross-domain network traffic scheduling method are applicable to the cross-domain network traffic scheduling device and will not be repeated here.

[0163] Figure 5 This is a schematic diagram of the structure of a device in the embodiment of the present application. Figure 5 As shown, the device includes one or more processors (or processing units), may further include one or more memories coupled to the processors, and may further include a communication module coupled to the processors.

[0164] The communication module can be used to communicate with other devices or apparatuses, such as sending or receiving data and / or signals. The communication module can include at least one communication module for communication. The communication module can include any interface necessary for communicating with other devices. Exemplarily, the communication module can be a transceiver, circuit, bus, module, or other type of communication module.

[0165] The processor may include, but is not limited to, at least one of the following: a general-purpose computer, a special-purpose computer, a microcontroller, a digital signal processor (DSP), or one or more of a controller-based multi-core controller architecture. A device may have multiple processors, such as application-specific integrated circuit chips, which are time-slave to a clock synchronized with a main processor.

[0166] The memory may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, at least one of the following: read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, hard disk, compact disc (CD), digital video disc (DVD), or other magnetic storage and / or optical storage. Examples of volatile memories include, but are not limited to, at least one of the following: random access memory (RAM), or other volatile memories that do not persist during a power outage.

[0167] A computer program includes computer-executable instructions that are executed by an associated processor. The program may be stored in ROM. The processor may perform any suitable actions and processes by loading the program into RAM.

[0168] The possible implementation of the present application can be realized by means of a program, so that the communication device can perform any process discussed in the above embodiments. The possible implementation of the present application can also be realized by hardware or by a combination of software and hardware.

[0169] In some embodiments, the program may be tangibly contained in a computer-readable storage medium that may be included in the device (such as in a memory) or other storage device accessible by the device. The program may be loaded from the computer-readable storage medium into RAM for execution. The computer-readable storage medium may include any type of tangible non-volatile memory, such as ROM, EPROM, flash memory, hard disk, CD, DVD, etc.

[0170] The present application also provides a computer-readable storage medium having computer instructions or program codes stored thereon, which, when executed by a processor, causes the processor to perform the methods and functions described in any of the above embodiments. A computer-readable medium may be any tangible medium containing or storing a program for or related to an instruction execution system, apparatus, or device. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. Computer-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any suitable combination thereof. The computer-readable storage medium may be any available medium that a computer can access, or a data storage device such as a server or data center that includes one or more available media integrated therein. More detailed examples of computer-readable storage media include electrical connections with one or more wires, magnetic media (e.g., magnetic disks, floppy disks, hard disks, tapes, magnetic storage devices), optical media (e.g., optical storage devices, DVDs), semiconductor media (e.g., solid-state drives), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), or any suitable combination thereof.

[0171] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The embodiments of the present application also provide at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes one or more computer-executable instructions, such as instructions included in a program module, which are executed in a device on a real or virtual processor of the target to perform the processes, methods and functions involved in any of the above embodiments. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. 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. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) method.

[0172] The present application also provides a computer program product, including a computer program or instructions, which, when run on a computer, causes the computer to perform the processes, methods, and functions in the above-described embodiments. Typically, a program module includes routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. In various embodiments, the functions of the program modules can be combined or divided between program modules as needed. The machine executable instructions for the program modules can be executed in local or distributed devices. In distributed devices, the program modules can be located in local and remote storage media.

[0173] In general, various embodiments of the present application can be implemented in hardware or dedicated circuits, software, logic, or any combination thereof. Some aspects can be implemented in hardware, while other aspects can be implemented in firmware or software, which can be executed by a controller, microprocessor, or other computing device. Although various aspects of the embodiments of the present disclosure are shown and described as block diagrams, flow charts, or using some other graphical representation, it should be understood that the blocks, devices, systems, techniques, or methods described herein can be implemented as, by way of non-limiting example, hardware, software, firmware, dedicated circuits or logic, general-purpose hardware or a controller or other computing device, or some combination thereof.

[0174] It should be noted that although the embodiments of the present application are described above in conjunction with the accompanying drawings, the above embodiments are not independent of each other, and they can also be combined to obtain other embodiments. The methods, situations, categories, and divisions of the embodiments in the embodiments of the present application are only for the convenience of description and should not constitute special limitations. The features of the various methods, categories, situations, and embodiments can be combined with each other when they are logical. The various embodiments of the present application can be combined arbitrarily to achieve different technical effects. The embodiments of the present application no longer list various combinations.

[0175] In addition, although the operations of the method of the present disclosure are described in a particular order in the accompanying drawings, this does not require or imply that these operations must be performed in this particular order, or that all the operations shown must be performed to achieve the desired result. On the contrary, the steps depicted in the flowchart can change the order of execution. Additionally or alternatively, certain steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps. It should also be noted that the features and functions of two or more devices according to the present disclosure can be embodied in one device. Conversely, the features and functions of a device described above can be further divided into being embodied by multiple devices.

[0176] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0177] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A traffic scheduling method for a cross-domain network, characterized in that: The cross-domain network is composed of a first TSN network domain, a cellular network domain, and a second TSN network domain. The traffic scheduling method of the cross-domain network includes: Receive data packets from the sender; Based on a preset cross-domain traffic scheduling model, the data packet is controlled to be transmitted in sequence between the first TSN network domain, the cellular network domain and the second TSN network domain, and the data packet finally enters the receiving end. The preset cross-domain traffic scheduling model is implemented based on a predefined collaborative gating strategy.

2. The cross-domain network traffic scheduling method according to claim 1, characterized in that: The first TSN network domain is deployed at the transmitting end, the second TSN network domain is deployed at the receiving end, and the data packet of the receiving and transmitting end includes: receiving the data packet from the sending end through the first TSN network domain; The controlling, based on a preset cross-domain traffic scheduling model, to sequentially transmit the data packet among the first TSN network domain, the cellular network domain, and the second TSN network domain, and allowing the data packet to finally enter the receiving end includes: Based on the preset cross-domain traffic scheduling model, the collaborative gating strategy configured in the first TSN network domain is used to control the data packet from entering the cellular network domain; After the data packet is transmitted in the cellular network domain, based on the preset cross-domain traffic scheduling model, the collaborative gating strategy configured in the second TSN network domain is used to control the release of the data packet and allow the data packet to enter the receiving end.

3. The cross-domain network traffic scheduling method according to claim 1, characterized in that: The preset cross-domain traffic scheduling model is constructed as follows: determining a variable delay within the cellular network domain; The variable delay within the cellular network domain is compensated using a controllable adaptive compensation delay to obtain a compensated end-to-end target delay, wherein the controllable adaptive compensation delay is implemented based on a predefined collaborative gating strategy to keep the compensated end-to-end target delay constant.

4. The cross-domain network traffic scheduling method according to claim 1, characterized in that: The predefined collaborative gating strategy includes a gating period, which refers to the entire time process of transmitting the data packet to the receiving end through the cross-domain network. The gating period is determined by: determining a network quality of the cellular network domain; The gating period is set according to the network quality of the cellular network domain.

5. The cross-domain network traffic scheduling method according to claim 2, characterized in that: The controlling the data packet to enter the cellular network domain by utilizing the collaborative gating strategy configured in the first TSN network domain based on the preset cross-domain traffic scheduling model includes: When the data packet enters the first TSN network, determining the gating state of the first TSN network domain according to the collaborative gating strategy configured in the first TSN network domain; If the gating state of the first TSN network domain is closed, controlling the data packet to wait in the first TSN network domain until the gating state of the first TSN network domain is open; If the gating state of the first TSN network domain is open, the data packet is transmitted to the cellular network domain through the first TSN network domain.

6. The cross-domain network traffic scheduling method according to claim 2, characterized in that: The controlling the release of the data packet based on the preset cross-domain traffic scheduling model and utilizing the collaborative gating strategy configured in the second TSN network domain to allow the data packet to enter the receiving end includes: When the data packet enters the second TSN network, determining the gating state of the second TSN network domain according to the collaborative gating strategy configured in the second TSN network domain; If the gating state of the second TSN network domain is closed, controlling the data packet to wait in the second TSN network domain until the gating state of the second TSN network domain is open; If the gating state of the second TSN network domain is open, the data packet is transmitted to the receiving end through the second TSN network domain.

7. The cross-domain network traffic scheduling method according to any one of claims 1 to 6, characterized in that: The predefined cooperative gating strategy is implemented based on a time-aware shaper.

8. A traffic scheduling device for a cross-domain network, characterized in that: The cross-domain network is composed of a first TSN network domain, a cellular network domain, and a second TSN network domain. The traffic scheduling device of the cross-domain network includes: A receiving unit, configured to receive data packets from a sending end; A cross-domain transmission control unit is used to control the transmission of the data packet in sequence between the first TSN network domain, the cellular network domain and the second TSN network domain based on a preset cross-domain traffic scheduling model, and to enable the data packet to finally enter the receiving end. The preset cross-domain traffic scheduling model is implemented based on a predefined collaborative gating strategy.

9. A device comprising: processor; and a memory arranged to store computer-executable instructions, wherein when the executable instructions are executed, the processor executes the cross-domain network traffic scheduling method according to any one of claims 1 to 7.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the cross-domain network traffic scheduling method according to any one of claims 1 to 7 is implemented.

Images