Hybrid traffic transmission method and system in time-sensitive network

By using the ASAP scheduling algorithm and CQF mechanism in a time-sensitive network, combined with TAS and CQF global priority adjustment algorithm, the queuing delay problem caused by static priority allocation is solved, efficient scheduling of hybrid traffic transmission is achieved, and different services are met. Real-time and security requirements.

CN119276809AActive Publication Date: 2025-01-07SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN +1

Patent Information

Application Number
CN202411326506.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-23
Publication Date
2025-01-07
Estimated Expiration
2044-09-23

AI Technical Summary

Technical Problem

In the existing time-sensitive network, the static priority allocation strategy causes severe queuing delay and delay accumulation effects of different types of services when queue overflows, which cannot effectively meet the high real-time and security needs of different applications.

Method used

Using ASAP scheduling algorithm and CQF mechanism, combined with TAS and CQF global priority adjustment algorithm, the worst delay is calculated through directed graph model and network calculation, and priority is dynamically adjusted to ensure strict scheduling of time-triggered streams while improving audio and video bridge streams. scheduling efficiency.

Benefits of technology

It realizes flexible priority adjustment in large-scale data interaction scenarios, improves the scheduling performance and efficiency of hybrid traffic transmission, significantly improves the scheduling success rate of streams, and meets the strict delay and jitter requirements of different services.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119276809A_ABST
    Figure CN119276809A_ABST
Patent Text Reader

Abstract

The invention provides a mixed traffic transmission method and system in a time sensitive network, and relates to the technical field of mixed traffic transmission, and the method comprises the steps: constructing a TSN time sensitive network topology and a directed graph model of a time trigger flow; obtaining a TT stream set and an AVB stream set, and sorting the priorities of the TT stream set and the AVB stream set; performing preliminary scheduling on the sorted TT stream set and AVB stream set by using an ASAP scheduling algorithm, generating a time slot after the preliminary scheduling of all streams is completed, determining an initial scheduling scheme according to the time slot, and calculating the total worst end-to-end time delay of all streams in the stream set from a source node to a destination node by using network calculation; selecting the stream with the maximum priority from the AVB stream set to exchange with the stream in the TT stream set, re-scheduling, and deleting the exchanged AVB stream from the AVB stream set; and recalculating the total worst time delay until all AVB streams participate in exchange, and determining an optimal scheduling scheme. According to the invention, the scheduling efficiency of the AVB stream is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the technical field of hybrid traffic transmission, and in particular to a method and system for hybrid traffic transmission in a time-sensitive network. Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

[0003] With the continuous increase in production and demand, the requirements for real-time and deterministic information transmission are increasing. Ethernet has significant advantages in scalability and compatibility due to its high data rate and low cost, but it lacks strict quality of service (QoS) guarantees and cannot meet the needs of high real-time and security applications. Deterministic networks have strict control requirements on latency, packet loss rate and jitter in data transmission. In order to achieve low-latency deterministic transmission, the industry has proposed a variety of proprietary network protocols based on standard Ethernet. However, due to the technical incompatibility and poor interoperability of these proprietary protocols, the IEEE Time-Sensitive Networking (TSN) Working Group is committed to developing deterministic network standards to standardize the real-time and security-critical mechanisms in Ethernet, thereby achieving the coexistence of time-sensitive and non-time-sensitive flows in the same Ethernet.

[0004] TSN (Time Sensitive Networking) is an extended standard Ethernet technology with backward compatibility with standard Ethernet. In TSN (Time Sensitive Networking), mixed critical services are divided into three priority categories according to different quality of service (QoS) requirements: time-triggered (TT) services with strict timing constraints, audio-video bridging (AVB) services that require limited delay but relatively loose timing requirements, and best-effort (BE) services that do not provide timing guarantees. In order to meet these different QoS requirements, TSN configures corresponding mechanisms for each service type in the switch: TT services use queue isolation and time-aware shaper (TAS) to achieve deterministic transmission, AVB services use credit-based shaper (CBS) for rate limiting and burst-free transmission, and mixed services use preemption mechanisms to improve bandwidth utilization.

[0005] Based on these mechanisms, traffic scheduling determines the routing and timing behavior of data flows through admission control, which is the key to ensuring deterministic and real-time transmission in TSN. However, existing research mainly focuses on TT flow scheduling under the TAS mechanism, and has not yet fully covered the mixed-criticality scenario where all mechanisms coexist. In this scenario, flows are usually classified according to their associated applications. For example, control data of industrial automation and control systems (IACS) will be mapped to TT flows, while voice messages with latency and jitter requirements below 10 milliseconds will be mapped to AVB flows. After the traffic classification is completed, the corresponding flows will be cached in the predefined output port queues on the switch. According to the IEEE 802.1Qbv standard, there are eight queues on the output port of each switch, one or more of which are used for TT flows, two for AVB flows, and the rest for BE flows.

[0006] However, statically assigning flow types may lead to a cumulative delay effect for a specific type of flow when the output queue overflows. In the case of static priority assignment, if the number of application messages corresponding to the AVB flow is large, severe queuing delays or even timeouts may occur. In practical applications, different applications have different QoS requirements, and flow priorities are usually unevenly distributed. If a static priority assignment strategy is adopted, different types of services may experience significantly different delays, and some services may face severe queuing delays while other services have almost no backlog. Summary of the invention

[0007] In order to solve the above problems, the present disclosure proposes a method and system for hybrid traffic transmission in a time-sensitive network. In TSN, for the hybrid transmission of time-sensitive flows (TT flows), AVB flows, and BE flows, the CQF mechanism in the TSN system is improved, combined with TAS, and applied to the transmission of hybrid traffic, temporarily expanding the priority in large-scale data interaction scenarios, so that the scheduling efficiency of AVB flows can be improved as much as possible while the TT flows are strictly scheduled.

[0008] According to some embodiments, the present disclosure adopts the following technical solutions:

[0009] A method for transmitting mixed traffic in a time-sensitive network, comprising:

[0010] Construct TSN time-sensitive network topology and directed graph model of time-triggered flow;

[0011] Obtain TT stream sets and AVB stream sets, and sort the priorities of the TT stream sets and AVB stream sets;

[0012] The ASAP scheduling algorithm is used to perform preliminary scheduling on the sorted TT flow set and AVB flow set. After all flows are initially scheduled, time slots are generated, and the initial scheduling scheme is determined based on the time slots. The total worst delay from the source node to the destination node of all flows in the flow set is calculated using network calculations.

[0013] Select the stream with the highest priority from the AVB stream set and exchange it with the stream in the TT stream set, reschedule it and delete the exchanged AVB stream from the AVB stream set;

[0014] Recalculate the total worst delay, and determine whether the initial scheduling scheme needs to be updated based on the comparison result between the recalculated total worst delay and the previously calculated total worst delay, and repeat the flow switching step until all AVB flows have participated in the switching.

[0015] According to some embodiments, the present disclosure adopts the following technical solutions:

[0016] A mixed traffic transmission system in a time-sensitive network, comprising:

[0017] Model building module, used to build TSN time-sensitive network topology and directed graph model of time-triggered flow;

[0018] A sorting module, used for obtaining a TT stream set and an AVB stream set, and sorting the priorities of the TT stream set and the AVB stream set;

[0019] The calculation module is used to use the ASAP scheduling algorithm to perform preliminary scheduling on the sorted TT flow set and AVB flow set. After all flows are initially scheduled, time slots are generated, and the initial scheduling scheme is determined according to the time slots. The network calculation is used to calculate the total worst end-to-end delay of all flows in the flow set from the source node to the destination node.

[0020] The update module is used to select the flow with the highest priority from the AVB flow set to exchange with the flow in the TT flow set, reschedule and delete the exchanged AVB flow from the AVB flow set; recalculate the total worst delay, and determine whether the initial scheduling plan needs to be updated based on the comparison result of the recalculated total worst delay and the previously calculated total worst delay, and repeat the flow exchange steps until all AVB flows have participated in the exchange.

[0021] According to some embodiments, the present disclosure adopts the following technical solutions:

[0022] A non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, a hybrid traffic transmission method in a time-sensitive network is implemented.

[0023] According to some embodiments, the present disclosure adopts the following technical solutions:

[0024] An electronic device comprises: a processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes the method for transmitting mixed traffic in a time-sensitive network.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] The present disclosure provides a method for transmitting mixed traffic in a time-sensitive network. The ASAP scheduling algorithm is used to perform preliminary scheduling on the sorted TT flow set and AVB flow set, and the CQF mechanism is applied to the RC flow using the mixed service scheduling strategy. The CQF mechanism uses odd and even queues to cyclically receive and forward RC flows. Each service needs to be sequentially injected into different time slots after sorting. If multiple RC flows arrive at the switch at the same time and queue, only one RC flow is injected into each time slot. After all flows are scheduled, time slots are generated, and the initial scheduling scheme is determined based on the time slots. The method combines TAS and CQF to globally solve the priority adjustment problem between different traffic types, and proposes an adaptive priority adjustment algorithm. The algorithm can improve the scheduling performance by temporarily expanding the priority in large-scale data interaction scenarios, and flexibly determine the adjustment strategy, so that the scheduling efficiency of the AVB flow can be improved as much as possible while the TT flow is strictly scheduled.

[0027] The present disclosure provides a method for transmitting mixed traffic in a time-sensitive network, which comprehensively considers three indicators, namely, cycle, deadline and flow size, to prioritize TT flows, adopts a comprehensive evaluation method in mathematical modeling to comprehensively evaluate the three indicators, first homogenizes the three indicators, distinguishes extremely large indicators from extremely small indicators, the deadline of the flow is an extremely small indicator, the cycle and size of the flow are extremely large indicators, uses the extreme difference change method to standardize the data of each indicator, and after the standardization is completed, assigns weights to the evaluation indicators, sorts the TT flows according to the weights, and schedules the TT flows according to the sorting results. The flow priority sorting method proposed in the present disclosure can make the sorting of flows more reasonable, and compared with flows sorted by only a single indicator, the flow priority sorting method of the present disclosure can significantly improve the scheduling success rate of flows. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings constituting a part of the present disclosure are used to provide a further understanding of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure.

[0029] Figure 1 is a schematic diagram of a gating model according to an embodiment of the present disclosure;

[0030] Figure 2 The present invention is a flowchart of a method for transmitting mixed traffic in a time-sensitive network according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The present disclosure is further described below in conjunction with the accompanying drawings and embodiments.

[0032] It should be noted that the following detailed descriptions are all illustrative and are intended to provide further explanation of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present disclosure belongs.

[0033] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0034] Example 1

[0035] In one embodiment of the present disclosure, a method for transmitting mixed traffic in a time-sensitive network is provided, including:

[0036] Step 1: Build a directed graph model of the TSN time-sensitive network topology and time-triggered flow;

[0037] Step 2: Obtain the TT stream set and the AVB stream set, and sort the priorities of the TT stream set and the AVB stream set;

[0038] Step 3: Use the ASAP scheduling algorithm to perform preliminary scheduling on the sorted TT flow set and AVB flow set. After all flows are initially scheduled, time slots are generated, and the initial scheduling scheme is determined based on the time slots. The network calculation is used to calculate the total worst end-to-end delay of all flows in the flow set from the source node to the destination node.

[0039] Step 4: Select the flow with the highest priority from the AVB flow set and exchange it with the flow in the TT flow set, reschedule it and delete the exchanged AVB flow from the AVB flow set;

[0040] Step 5: Recalculate the total worst-case delay, and determine whether the initial scheduling plan needs to be updated based on the total worst-case delay result. Repeat the stream switching step until all AVB streams have participated in the switching.

[0041] As an embodiment, the present disclosure discloses a hybrid traffic transmission method in a time-sensitive network, and proposes a hybrid traffic scheduling method. The method combines TAS and CQF to globally solve the priority adjustment problem between different traffic types, and proposes an adaptive priority adjustment algorithm. The algorithm can improve the scheduling performance by temporarily expanding the priority in large-scale data interaction scenarios, flexibly determine the adjustment strategy, and can maximize the scheduling efficiency of AVB flows while maintaining strict scheduling of TT flows. The specific implementation process is as follows:

[0042] Step 1: Build a directed graph model of the TSN time-sensitive network topology and time-triggered flow;

[0043] Specifically, the topology of the TSN network is first modeled as a directed graph G = {V, E}. The vertex set V consists of the terminal device set ES and the switch set SW, expressed as V = ES ∪ SW. The terminal device serves as the source node and destination node of the flow, while the switch only forwards the flow. The edge set E represents the data link. The network supports full-duplex transmission, so the data link is directional. For example, two vertices v a ,v b ∈E determines the two links [v a ,v b ] and [v b ,v a ], the transmission rate of each data link is constant, denoted as l.speed.

[0044] According to different QoS requirements for data transmission, TSN flows are divided into three priorities: TT flow, AVB flow, and BE flow. Assume that the disclosure has calculated the GCL of the output port of each node in the 7 priority queues, that is, the opening and closing time of the TT service gating (called TT window). Each TT flow By the octet f i ={src,dst,prd,siz,ddl,pri,route,φ}, where src,dst are the source node and destination node of the TT flow respectively, prd is the sending period, siz defines the frame size, and ddl is the deadline. pri represents the priority of the flow, and all TT services are set to 7. route represents the transmission path, and φ represents the time slot offset, which is configured by the results of the routing algorithm and the scheduling algorithm. AVB services have the characteristics of long period, multiple data packets, and long data packets, and require a certain delay and jitter. AVB services are divided into Class A and Class B according to the minimum sending interval. Each AVB flow It is defined by an octet, similar to the TT flow. φ represents the flow injection time slot, which is different from the concept of the time slot unit in the TT wait-free scheduling mechanism. The next step is to prioritize the TT flow and the AVB flow.

[0045] Step 2: Obtain the TT stream set and the AVB stream set, and sort the priorities of the TT stream set and the AVB stream set;

[0046] Specifically, a. Sorting of TT flows: Most current flow sorting algorithms use single indicators such as cycle, deadline and flow size for sorting. Therefore, the present disclosure comprehensively considers the three indicators of cycle, deadline and flow size to sort the flows. Since the dimensions of the three indicators are not the same, the present disclosure uses the comprehensive evaluation method in mathematical modeling to comprehensively evaluate the three indicators, and finally sorts the flows according to the results.

[0047] First, the three indicators are homogenized. It is necessary to distinguish between extremely large indicators and extremely small indicators. For extremely large indicators, the larger the value, the better, while for extremely small indicators, the larger the value, the worse; this concept can be interpreted as the "urgency" of the flow, that is, the larger the value, the more urgent the corresponding situation. Under normal circumstances, the deadline of the flow is an extremely small indicator, and the period and size of the flow are extremely large indicators. After defining the extremely large indicators and extremely small indicators, use the range change method to standardize the data of each indicator, which can be expressed as follows:

[0048]

[0049] Formula (1) and (2) are the formulas for processing extremely large indicators and extremely small indicators respectively. Among them, x is the initial data, x min is the minimum value of the initial data, x max is the maximum value of the initial data, r is the range of the data, that is, x max -x min .

[0050] After the standardization process is completed, the evaluation indicators are given weights, and the formula is:

[0051]

[0052] Among them, α is the weight, r is the range of the data, that is, x max -x min , m is the number of flow indicators.

[0053] The weight of each indicator is calculated, where m is the number of indicators of the flow. Finally, the time-triggered flow is comprehensively evaluated, and the total weight of each time-triggered flow is calculated by the linear weighted comprehensive model formula.

[0054]

[0055] Among them, w is the total weight of the time-triggered flow, prd is the sending period, siz defines the frame size, and ddl is the deadline.

[0056] Based on the above, the flows can be sorted according to the weights, and the time-triggered flows (TT flows) can be scheduled according to this order.

[0057] Furthermore, b. Sorting of AVB streams: For AVB streams, the period and load of AVB streams are significantly greater than those of TT streams. The present disclosure only uses the deadline as an indicator to sort the AVB streams in ascending order. The present disclosure uses the DMS algorithm for sorting. The DMS algorithm is developed on the basis of the RMS algorithm. It weakens the restrictions on the task model in the RMS algorithm and allows the time limit of the task to be less than the period. It statically assigns priorities based on the relative deadlines of each task in the task set. When applied to stream sorting, it sorts according to the size of the stream deadline. This step generates an AVB stream set, and the streams in the stream set are sorted from small to large according to the deadline. The smaller the deadline, the higher its priority.

[0058] Step 3: Use the ASAP scheduling algorithm to perform preliminary scheduling on the sorted TT flow set and AVB flow set. After all flows are initially scheduled, time slots are generated, and the initial scheduling scheme is determined based on the time slots. The network calculation is used to calculate the total worst end-to-end delay of all flows in the flow set from the source node to the destination node.

[0059] After the sorting is completed, the TT flow and the AVB flow are initially scheduled. The present disclosure uses the ASAP algorithm to schedule the TT flow. In the ASAP algorithm, frames are scheduled sequentially at the earliest possible offset where the link on its route is idle and the queue is empty. If the frame is not assigned to the same empty queue block as it was on the previous link, the algorithm backtracks and reschedules the previous frame to the next empty queue block. If the last frame is scheduled within the deadline, the scheduling flow is successful, otherwise it fails.

[0060] The hybrid flow scheduling strategy proposed in the present disclosure applies the CQF mechanism to RC flows. Priority queues 5 and 6 are set as CQF queues for transmitting RC traffic. The CQF mechanism uses odd and even queues to cyclically receive and forward RC flows. RC flows also need to be sorted by the DMS algorithm, and each service needs to be injected into different time slots sequentially after sorting. If multiple RC flows arrive at the switch at the same time and queue, only one RC flow is injected into each time slot. In this way, RC flows in the ping-pong queue are assigned to different time slots, which prevents service congestion. Compared with using only the TAS mechanism, the hybrid service scheduling strategy reduces the fine-grained constraint differentiation of RC flows. It uses the RC flow transmission rules specified in the CQF mechanism for time slot injection, and improves the success rate of RC flow scheduling while meeting the TT flow requirements.

[0061] Step 3.1 performs preliminary scheduling on the sorted TT flows and AVB flows. The TT flows are scheduled via priority queues 1 and 2, and the AVB flows are scheduled via two CQF queues 5 and 6. The scheduling method uses the As Soon As Possible (ASAP) method.

[0062] After all flows are scheduled in step 3.2, the total delay and scheduling success of all flows are recorded.

[0063] Furthermore, after all flows are scheduled according to the ASAP method, a complete time slot table is generated based on the time slots to which the frames of all flows are assigned. This table contains which frames are transmitted on which links in each time slot. Based on the generated time slot table, the initial scheduling scheme is determined. The scheduling scheme records the frames that each link needs to transmit in each time slot.

[0064] Using network calculus to calculate the total worst end-to-end delay from the source node to the destination node of all flows in the flow set will guarantee the service time slot Offset between time slots Substituting the parameters into the service curve function, we get:

[0065] (5)

[0066] Among them, T GCL For the super cycle, is the time of streaming, The maximum waiting time for the data frame to start transmission in the current super cycle of the queue. T,L (t) Describes the conventional service curve for the fluid flow model combined with the TDMA protocol.

[0067]

[0068] Among them, C out is the link transmission rate, T is the period, and L is the transmission duration.

[0069] Taking i as the starting point, all time slots in a super period Tgcl By adding and summing, we can get the output curve of any transmission time slot i

[0070]

[0071] Among them, N m is the number of gated windows of priority queue m within a Tgcl, and its value is equal to T GCL / T m .

[0072] The arrival curve is obtained based on the transmission performance of the switch and the network calculation theory. The service curve obtained from the above Target flow rate f r The maximum delay on the queue at the kth switching node can be expressed as,

[0073]

[0074] The h(α,β) function represents the maximum horizontal deviation Dmax between two curves in network calculation.

[0075] Flow rate r In its propagation path route i The worst-case end-to-end delay on the network is obtained by summing the maximum delay of the nodes passed from its source node to its destination node and the link propagation delay.

[0076]

[0077] Among them, dst i For r i The destination node of |h| is the route r i The number of nodes on C l is the constant delay on the link. After the calculation is completed, the total end-to-end delay is recorded.

[0078] Step 4: Select the flow with the highest priority from the AVB flow set and exchange it with the flow in the TT flow set, reschedule it and delete the exchanged AVB flow from the AVB flow set;

[0079] Specifically, first select the flow with the highest priority in the AVB flow set, find the flow with the smallest deadline difference in the TT flow set for exchange, then schedule all flows, and recalculate the total worst delay according to the formula.

[0080] Step 5: Recalculate the total worst-case delay, and determine whether the initial scheduling scheme needs to be updated based on the total worst-case delay result. Repeat the stream switching step until all AVB streams have participated in the switching.

[0081] Recalculate the total worst-case delay according to formulas (5)-(9). If it is better than the previous best solution, update the current solution to the best solution. Otherwise, keep the priority of the AVB stream unchanged. Repeat the above steps until all the streams in the AVB stream set are traversed.

[0082] After the traversal is completed, the best scheduling transmission plan is generated.

[0083] Example 2

[0084] In one embodiment of the present disclosure, a hybrid traffic transmission system in a time-sensitive network is provided, including:

[0085] Model building module, used to build TSN time-sensitive network topology and directed graph model of time-triggered flow;

[0086] A sorting module, used for obtaining a TT stream set and an AVB stream set, and sorting the priorities of the TT stream set and the AVB stream set;

[0087] The calculation module is used to use the ASAP scheduling algorithm to perform preliminary scheduling on the sorted TT flow set and AVB flow set. After all flows are initially scheduled, time slots are generated, and the initial scheduling scheme is determined according to the time slots. The network calculation is used to calculate the total worst end-to-end delay of all flows in the flow set from the source node to the destination node.

[0088] The update module is used to select the flow with the highest priority from the AVB flow set to exchange with the flow in the TT flow set, reschedule and delete the exchanged AVB flow from the AVB flow set; recalculate the total worst delay, and determine whether the initial scheduling plan needs to be updated based on the comparison result of the recalculated total worst delay and the previously calculated total worst delay, and repeat the flow exchange steps until all AVB flows have participated in the exchange.

[0089] Example 3

[0090] In one embodiment of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the method for transmitting hybrid traffic in a time-sensitive network is implemented.

[0091] Example 4

[0092] In one embodiment of the present disclosure, an electronic device is provided, including: a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes the method for hybrid traffic transmission in a time-sensitive network.

[0093] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0094] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0095] Although the above describes the specific implementation methods of the present disclosure in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present disclosure. Technical personnel in the relevant field should understand that on the basis of the technical solution of the present disclosure, various modifications or variations that can be made by those skilled in the art without creative work are still within the scope of protection of the present disclosure.

Claims

1. A method for transmitting mixed traffic in a time-sensitive network, characterized in that: include: Construct TSN time-sensitive network topology and directed graph model of time-triggered flow; Obtain TT stream sets and AVB stream sets, and sort the priorities of the TT stream sets and AVB stream sets; The ASAP scheduling algorithm is used to perform preliminary scheduling on the sorted TT flow set and AVB flow set. After all flows are initially scheduled, time slots are generated, and the initial scheduling scheme is determined based on the time slots. The network calculation is used to calculate the total worst end-to-end delay of all flows in the flow set from the source node to the destination node. Select the stream with the highest priority from the AVB stream set and exchange it with the stream in the TT stream set, reschedule it and delete the exchanged AVB stream from the AVB stream set; Recalculate the total worst delay, and determine whether the initial scheduling scheme needs to be updated based on the comparison result between the recalculated total worst delay and the previously calculated total worst delay, and repeat the flow switching step until all AVB flows have participated in the switching.

2. A method for transmitting mixed traffic in a time-sensitive network according to claim 1, characterized in that: The TSN time-sensitive network topology and time-sensitive flow are obtained, and the TSN time-sensitive network topology is modeled as a directed graph model G = {V, E}. The vertex set V consists of the terminal device set ES and the switch set SW, expressed as V = ES∪SW. The terminal device serves as the source node and destination node of the flow, and the switch only forwards the flow. The edge set E represents the data link. The data link is directional and the transmission rate of each data link is constant.

3. The method for transmitting mixed traffic in a time-sensitive network according to claim 1, characterized in that: Obtain the TT flow set and the AVB flow set, first prioritize the TT flow set, and prioritize the TT flow by comprehensively considering the three indicators of period, deadline and flow size. Use the comprehensive evaluation method in mathematical modeling to comprehensively evaluate the three indicators. First, the three indicators are homogenized to distinguish between extremely large indicators and extremely small indicators. The deadline of the flow is an extremely small indicator, and the period and size of the flow are extremely large indicators. Use the extreme difference change method to standardize the data of each indicator. After the standardization is completed, assign weights to the evaluation indicators, sort the TT flows according to the weights, and schedule the TT flows according to the sorting results.

4. The method for transmitting mixed traffic in a time-sensitive network according to claim 1, characterized in that: For AVB streams, the DMS algorithm is used for priority sorting. The DMS algorithm allows the task time limit to be less than the cycle. It statically assigns priorities based on the relative deadlines of each task in the task set to generate an AVB stream set. The streams in the AVB stream set are sorted from small to large according to the deadline. The smaller the deadline, the higher the priority.

5. The method for transmitting mixed traffic in a time-sensitive network according to claim 1, characterized in that: The ASAP scheduling algorithm is used to perform preliminary scheduling on the sorted TT flow set and AVB flow set, and the CQF mechanism is applied to the RC flow using the hybrid service scheduling strategy. The CQF mechanism uses odd and even queues to cyclically receive and forward RC flows. Each service needs to be injected into different time slots sequentially after sorting. If multiple RC flows arrive at the switch at the same time and queue, only one RC flow is injected into each time slot. After all flows are scheduled, time slots are generated, and the initial scheduling plan is determined based on the time slots.

6. The method for transmitting mixed traffic in a time-sensitive network according to claim 1, characterized in that: The network calculation is used to calculate the total worst end-to-end delay of all flows in the flow set from the source node to the destination node, including: substituting the guaranteed service time slot and the offset parameters between the time slots into the service curve function, determining the starting point, adding and summing all the time slot service functions within a super period Tgcl, and obtaining the output curve of any transmission time slot, obtaining the arrival curve according to the network calculation theory, combining the arrival curve and the service curve, and calculating the maximum delay of the target flow in the queue at a certain switching node. The worst-case end-to-end delay of the flow on its propagation path is obtained by summing the maximum delay of the nodes passed from its source node to its destination node and the link propagation delay.

7. The method for transmitting mixed traffic in a time-sensitive network according to claim 1, characterized in that: The stream with the highest priority is selected from the AVB stream set to be exchanged with the stream in the TT stream set, and the AVB stream after the exchange is rescheduled and deleted from the AVB stream set, including: selecting the stream with the highest priority in the AVB stream set, finding the stream with the smallest deadline difference in the TT stream set to exchange, and then scheduling all the streams and recalculating the total worst delay. If it is better than the initial scheduling plan, the current plan is updated to the best plan. Otherwise, the priority of the AVB stream is kept unchanged, and the exchange and calculation steps are repeated until the streams in the AVB stream set are traversed.

8. A hybrid traffic transmission system in a time-sensitive network, characterized in that: Model building module, used to build TSN time-sensitive network topology and directed graph model of time-triggered flow; A sorting module, used for obtaining a TT stream set and an AVB stream set, and sorting the priorities of the TT stream set and the AVB stream set; The calculation module is used to use the ASAP scheduling algorithm to perform preliminary scheduling on the sorted TT flow set and AVB flow set. After all flows are initially scheduled, time slots are generated, and the initial scheduling scheme is determined according to the time slots. The network calculation is used to calculate the total worst end-to-end delay of all flows in the flow set from the source node to the destination node. An update module is used to select a stream with the highest priority from the AVB stream set to exchange with the stream in the TT stream set, reschedule and delete the exchanged AVB stream from the AVB stream set; Recalculate the total worst delay, and determine whether the initial scheduling scheme needs to be updated based on the comparison result between the recalculated total worst delay and the previously calculated total worst delay, and repeat the flow switching step until all AVB flows have participated in the switching.

9. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, a hybrid traffic transmission method in a time-sensitive network as described in any one of claims 1-7 is implemented.

10. An electronic device, characterized in that: include: A processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to implement a method for transmitting hybrid traffic in a time-sensitive network as described in any one of claims 1-7.

Citation Information

Patent Citations

  • Time-sensitive network hybrid flow scheduling method

    CN112291161A

  • AVB flow-aware time-sensitive flow fault-tolerant routing and scheduling method and system

    CN117640500A

  • Routing and scheduling joint optimization method and system in TSN

    CN118337714A

Cited By

  • Online reconfiguration method for time-sensitive network

    CN119865423A

  • An Online Reconfiguration Method for Time-Sensitive Networks

    CN119865423B