A fusion scheduling method for time-sensitive stream from DetNet cross-domain to TSN

Abstract

The application relates to a fusion scheduling method for time-sensitive flow from a DetNet cross-domain to a TSN, and belongs to the technical field of long-distance time-sensitive application communication, and comprises the following steps: S1: using a network calculus curve model to depict an output cumulative function of time-sensitive flow through a DetNet scheduling mechanism; S2: using the network calculus curve model to depict an input cumulative function of the time-sensitive flow through the DetNet scheduling mechanism; S3: constructing a worst consumption delay model of the time-sensitive flow through the DetNet according to the maximum horizontal distance of the input cumulative function and the output cumulative function; and S4: strictly designing a TSN scheduling mechanism in combination with a minimum residual delay demand of the cross-domain time-sensitive flow. The application guarantees that the time-sensitive flow can be output on time according to the TSN scheduling mechanism when the time-sensitive flow is scheduled to the TSN through the DetNet, so that the time-sensitive flow can realize end-to-end deterministic transmission in a network with multiple scheduling mechanism fusions.

Description

Technical Field

[0001] This invention belongs to the field of long-distance time-sensitive application communication technology, and relates to a fusion scheduling method for time-sensitive streams from DetNet to TSN. Background Technology

[0002] With the emergence of concepts such as Industry 4.0 and 5G, the scale of networks is constantly expanding, and the requirements for deterministic transmission capabilities are also increasing. To meet the deterministic transmission needs of networks, the emergence of Time-Sensitive Networking (TSN) and Deterministic Networking (DetNet) technologies has improved the network's support for deterministic flows. TSN adopts the deterministic scheduling mechanism of IEEE 802.1Qch, and its proposed Cyclic Queueing and Forwarding (CQF) shaper can achieve deterministic scheduling for local area networks (LANs). DetNet, combining SR routing technology with the scheduling concept of CQF, proposes a deterministic scheduling scheme suitable for wide area networks (WANs), namely the Cycle Specified Queueing and Forwarding (CSQF) mechanism. In long-distance time-sensitive networks, the TSN scheduling mechanism should be applied to edge LANs, while the DetNet scheduling mechanism should be applied to core WANs. The end-to-end transmission of time-sensitive streams goes through the scheduling mechanisms of the two networks mentioned above. Therefore, TSN not only schedules data within the edge LAN, but also receives data scheduled by DetNet in the WAN. However, the scheduling rules and time slot sizes of the two technologies are inconsistent and independent of the domain. DetNet's scheduling time and time slots are more lenient than TSN's. If the time-sensitive stream takes too long to be scheduled by DetNet, or if the TSN's time slot allocation is unreasonable, the time-sensitive stream cannot be transmitted in time, resulting in increased end-to-end latency that exceeds its deadline latency requirement.

[0003] Currently, some researchers have explored the integration of TSN and DetNet technologies, but most studies focus on integrating TSN as a link layer within DetNet, neglecting the cross-domain scheduling integration of the two technologies across different network domains. Only a few researchers have investigated cross-domain scheduling mechanisms for TSN and DetNet, but these studies are often complex and fail to consider the factors influencing their mutual influence. Therefore, researching integrated scheduling mechanisms for TSN and DetNet to meet the end-to-end deterministic transmission requirements of service flows in more scenarios is worthwhile. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a fusion scheduling method for time-sensitive streams from DetNet to TSN, which integrates the TSN scheduling mechanism designed with the DetNet scheduling mechanism, ensuring that time-sensitive streams are scheduled to TSN from DetNet and output on time according to the TSN scheduling mechanism, so that time-sensitive streams can achieve end-to-end deterministic transmission in a network that integrates multiple scheduling mechanisms.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A time-sensitive stream fusion scheduling method from DetNet to TSN includes the following steps:

[0007] S1: Use the network computation curve model to characterize the output accumulation function of time-sensitive streams after passing through the DetNet scheduling mechanism;

[0008] S2: Use the network computation curve model to characterize the input accumulation function of the time-sensitive stream through the DetNet scheduling mechanism;

[0009] S3: Construct the worst-case latency model of the time-sensitive stream passing through DetNet based on the maximum horizontal distance between the input and output cumulative functions;

[0010] S4: The TSN scheduling mechanism is rigorously designed in conjunction with the minimum remaining delay requirements of cross-domain time-sensitive streams.

[0011] Furthermore, step S1, which describes the output accumulation function of the time-sensitive stream through the DetNet scheduling mechanism using a network computation curve model, specifically includes the following steps:

[0012] S11: DetNet's deterministic scheduling mechanism is CSQF, which uses three queues to alternately output time-sensitive data, with each queue having a time slot length of t. CSQF Configure node v in the DetNet network x The three time-sensitive stream scheduling queues are Q0, Q1, and Q2, and their start times are defined as follows: The closing times are respectively

[0013] S12: Set the time-sensitive flow f i The start time for transmission in the time slot corresponding to its own queue is t. b,i , represented as:

[0014]

[0015] in, Indicates flow f i The SID carried corresponds to node v x Output timeslot number at the location; This indicates that at node vx flow f i The corresponding queue is transmitting f i ;

[0016] The end time is t e,i , represented as:

[0017]

[0018] S13: Flow f i At node v x Output cumulative function Represented as:

[0019]

[0020] Where C represents the backlink transmission rate;

[0021] S14: Time-sensitive streams are stored in a high-priority queue. Considering the worst-case scenario, the remaining transmission length of low-priority streams is equal to the maximum data frame length. Therefore, the high-priority queue data frame delay forwarding time is:

[0022]

[0023] Among them, l max Indicates the maximum length of low-priority data;

[0024] Time-sensitive flow f i The time when forwarding started changed to:

[0025]

[0026] S15: Time-sensitive flow f i At node v x The output cumulative function is converted to the following table:

[0027]

[0028] Furthermore, step S2 describes using a network computation curve model to characterize the output accumulation function of the time-sensitive flow after passing through the DetNet scheduling mechanism, where the flow f... i The input accumulation function at the current node is the stream f. i The output accumulation function of the previous node includes the following steps:

[0029] S21: Flow f i At node v x The input accumulation function at point is expressed as:

[0030]

[0031] S22: Re-characterize the input accumulation function for node vx Midstream f i The input accumulator function is the sum of the input accumulator functions of all data in the same buffer queue at the same output port, expressed as:

[0032]

[0033] Among them, F x Indicates the inflow to node v x Data stream set; ε j ={0,1} represents the flow f j With flow f i Whether cached in the same queue; when ε j =1 indicates flow f j With flow f i Cached in a queue, when ε j =0 indicates flow f i With flow f i The caches are stored in different queues.

[0034] Furthermore, step S3, which involves constructing the worst-case latency model of the time-sensitive stream passing through the DetNet based on the maximum horizontal distance between the input and output cumulative functions, includes the following steps:

[0035] S31: Flow f i At node v x latency The maximum horizontal distance H(R,S) between two cumulative functions is expressed as:

[0036]

[0037] S32: Assume flow f i In the DetNet domain, a router is required. After the link is Then flow f i The worst latency after passing through the DetNet domain is:

[0038]

[0039] in, Indicates flow f i Link delay via link e.

[0040] Furthermore, in step S4, the TSN adopts a deterministic scheduling mechanism of CQF dual-queue cyclic alternation. The latency jitter of the time-sensitive stream after CQF scheduling is only related to the size of the scheduling time slot. Time slot constraints are established: the first constraint is that the time slot does not exceed the greatest common divisor of the time-sensitive stream period; the second constraint is that the latency requirement of the time-sensitive stream must be met; the third constraint is that it is not less than the time it takes for data to be sent and received in the same time slot; and the fourth constraint is that the CQF scheduling time slot must be divisible by the period.

[0041]

[0042] in, This represents the set of time-sensitive stream cycles passing through the DetNet domain; Represents the periodic set of time-sensitive streams within the TSN domain; This represents a set of time-sensitive streams processed by DetNet; Represents a stream Deadline delay requirements; Represents a stream The worst-case transmission latency after passing through DetNet; si represents the stream. The number of switches on the TSN path; Represents the set of time-sensitive streams within the TSN domain; Represents a stream Deadline delay requirements; s u Represents a stream The number of switches on the TSN path; L q B represents the length of data that the queue can buffer; B represents the transmission rate of the physical link; d hop t represents the link delay for single-hop data transmission; offset T represents the synchronization accuracy deviation between adjacent nodes. CQF This indicates that the time slot t is scheduled by an integer number of CQFs during the supercycle. CQF composition.

[0043] Furthermore, in step S4, with the objective of maximizing the success rate of time-sensitive flow scheduling, the optimal scheduling slot size is determined by combining the four established constraints. The solution steps are as follows:

[0044] S41: Based on the flow decision variable w i ∈{0,1} and time-sensitive flow f i Determine the network domain where the source and destination nodes are located. i Whether it has been scheduled by TSN, if it is a cross-domain time-sensitive flow, it is stored in the flow set F. cls If it is a time-sensitive flow within the domain, it is stored in the flow set F. ids middle;

[0045] S42: Calculate F according to the formula established in step S22. clsWorst-case latency;

[0046] S43: Obtain the upper bound of the CQF scheduling slots based on the second constraint condition.

[0047] S44: F is obtained by depth-first search. cls With F ids The longest path in the TSN is calculated, and the upper bound of the time slot is calculated in conjunction with the second constraint.

[0048] S45: Initialize the CQF queue size and calculate the minimum time slot value according to the third constraint;

[0049] S46: Use the Gurobi optimizer to perform integer planning on the number of streams that meet the latency requirements, and adjust the initial queue L in units of the maximum data frame length. q Size, return the optimal scheduling slot t CQF .

[0050] The beneficial effects of this invention are as follows: In long-distance deterministic networks, due to the involvement of multiple network domains and the different scheduling mechanisms within each domain, it is difficult to ensure end-to-end deterministic transmission of time-sensitive streams. Specifically, this invention relates to a fusion scheduling method for time-sensitive streams crossing domains from DetNet to TSN, including: using a network computation curve model to characterize the input-output accumulation function of the time-sensitive stream passing through the DetNet scheduling mechanism; constructing a worst-case latency model of the time-sensitive stream passing through DetNet based on the two functions; obtaining the minimum remaining latency requirement for the time-sensitive stream to cross domains into TSN based on the latency model; and rigorously designing the TSN scheduling mechanism and stream injection time in conjunction with the remaining time requirement of the cross-domain time-sensitive stream. This invention enables the design of a TSN scheduling mechanism that integrates DetNet scheduling, ensuring that time-sensitive streams are scheduled to TSN from DetNet and output on time according to the TSN scheduling mechanism, thus enabling end-to-end deterministic transmission of time-sensitive streams in networks with multiple fusion scheduling mechanisms.

[0051] Other advantages, objectives, and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination, or may be learned from practice of the invention. The objectives and other advantages of the invention can be realized and obtained through the following description. Attached Figure Description

[0052] To make the objectives, technical solutions, and advantages of the present invention clearer, the preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, wherein:

[0053] Figure 1 This is a diagram of a cross-domain time slot offset scheduling scenario using a deterministic network in this embodiment of the invention.

[0054] Figure 2 This is a flowchart illustrating the implementation of the cross-domain time slot offset scheduling method for deterministic networks in this embodiment of the invention.

[0055] Figure 3 This is a flowchart of the algorithm for solving the time slot offset factor in this invention. Detailed Implementation

[0056] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0057] The accompanying drawings are for illustrative purposes only and are schematic diagrams, not actual pictures. They should not be construed as limiting the invention. To better illustrate the embodiments of the invention, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual product dimensions. It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0058] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components. In the description of the present invention, it should be understood that if terms such as "upper," "lower," "left," "right," "front," and "rear" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the terms used to describe positional relationships in the drawings are only for illustrative purposes and should not be construed as limiting the present invention. For those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

[0059] The present invention is constructed as follows Figure 1The long-distance deterministic network shown consists of a core wide area network (WAN) and an edge local area network (LAN). To ensure deterministic transmission of time-sensitive streams, the WAN uses the Cycle-Specified Queueing and Forwarding (CSQF) scheduling mechanism proposed by the DetNet network, while the LAN uses the Cyclic Queueing and Forwarding (CQF) scheduling mechanism proposed by the TSN network. However, the two scheduling mechanisms differ, which introduces uncertain delays when time-sensitive streams are transmitted across domains from DetNet to TSN, making it difficult to meet the end-to-end deterministic transmission requirements.

[0060] Based on such Figure 1 In the deterministic network fusion scheduling scenario shown, this invention provides a fusion scheduling method for time-sensitive flows from DetNet to TSN across domains, such as... Figure 2 As shown, it includes the following steps:

[0061] S1. The output accumulation function of time-sensitive streams after passing through the DetNet scheduling mechanism is characterized using a network computation curve model. The construction process includes:

[0062] S101.DetNet's deterministic scheduling mechanism is CSQF, which uses three queues to alternately output time-sensitive data, with each queue corresponding to a time slot length of t. CSQF Configure node v in the DetNet network x The three time-sensitive stream scheduling queues are Q0, Q1, and Q2, and their start times are defined as follows: The closing times are respectively

[0063] S102. Set the time-sensitive flow f i The start time for transmission in the time slot corresponding to its own queue is t. b,i , represented as:

[0064]

[0065] in, Indicates flow f i The SID carried corresponds to node v x Output timeslot number at the location; This indicates that at node v x flow f i The corresponding queue is transmitting f i .

[0066] The end time is t e,i , represented as:

[0067]

[0068] S103. Flow f i At node v x Output cumulative function It can be represented as:

[0069]

[0070] Where C represents the link transmission rate.

[0071] S104. Time-sensitive streams are stored in a high-priority queue. When a large amount of data is transmitted from the buffered data of a low-priority queue at the end of the queue's open time slot, the low-priority data will occupy part of the high-priority queue's time slot due to data integrity issues, causing a delay in the actual start time of high-priority data transmission. Considering the worst-case scenario, if the remaining transmission length of the low-priority data is equal to the maximum data frame length, then the high-priority queue's data frame delay forwarding time is:

[0072]

[0073] Among them, l max This indicates the maximum length of low-priority data.

[0074] Therefore, time-sensitive flow f i The time when forwarding started changed to:

[0075]

[0076] S105. Time-sensitive flow f i At node v x The output cumulative function is converted to the following table:

[0077]

[0078] S2. The input accumulation function of the time-sensitive flow passing through the DetNet scheduling mechanism is characterized using a network computation curve model. Flow f i The input accumulation function at the current node is the stream f. i The construction process of the output accumulation function of the previous node includes:

[0079] The S201.CSQF mechanism does not require time synchronization between nodes, therefore there is a certain time skew between each node, hence the flow f i At node v x The input accumulation function at point can be expressed as:

[0080]

[0081] The S202.CSQF buffered time-sensitive stream uses three queues to schedule output data in a circular manner. Data within a single queue is output in a first-in, first-out (FIFO) manner. Therefore, traffic that enters earlier in its own queue causes subsequent traffic to wait for a queuing delay before being output. This self-queuing effect occurs because traffic from multiple different input ports converges into the same type of buffered queue at the same output port, creating a "self-queuing" situation. Since this "self-queuing" situation affects the stream's latency, the input accumulation function is redefined. For node v... x Midstream f i The input accumulator function is the sum of the input accumulator functions of all data in the same buffer queue at the same output port, and can be expressed as:

[0082]

[0083] Among them, F x Indicates the inflow node v x Data stream set; ε j ={0,1} represents the flow f j With flow f i Whether it is cached in the same queue. When ε j =1 indicates flow f j With flow f i Cached in a queue, when ε j =0 indicates flow f i With flow f i The caches are stored in different queues.

[0084] S3. Construct the worst-case latency model of the time-sensitive flow passing through DetNet based on the maximum horizontal distance between the input and output cumulative functions. The specific process includes:

[0085] S301. Flow f i At node v x latency The maximum horizontal distance H(R,S) between two cumulative functions can be expressed as:

[0086]

[0087] S302. DetNet nodes do not require time synchronization, only time slot frequency synchronization, and the links are relatively long, making link latency non-negligible. Therefore, to match the actual situation, the worst-case latency of the target flow in DetNet is calculated by summing the latency of each node. Assume flow f i In the DetNet domain, a router is required. After the link is Then flow f i The worst latency after passing through the DetNet domain is:

[0088]

[0089] in, Indicates flow f i Link delay via link e.

[0090] S4. Strictly design the TSN scheduling mechanism in combination with the minimum remaining delay requirements of cross-domain time-sensitive streams.

[0091] Specifically, TSN employs a deterministic scheduling mechanism with CQF dual-queue cyclic alternation. The latency jitter of time-sensitive streams undergoing CQF scheduling is only related to the size of the scheduling time slot. Therefore, time slot constraints are established: the first constraint is that the time slot does not exceed the greatest common divisor of the time-sensitive stream's period; the second constraint is that the latency requirements of the time-sensitive stream must be met; the third constraint is that it is not less than the time it takes for data to be sent and received within the same time slot; and the fourth constraint is that the CQF scheduling time slot must be divisible by the period.

[0092]

[0093] Where C1 represents the first constraint, This represents the set of time-sensitive stream cycles passing through the DetNet domain; C1 represents the periodic set of time-sensitive flows within the TSN domain; C2 represents the second constraint. This represents a set of time-sensitive streams processed by DetNet; Represents a stream Deadline delay requirements; Represents a stream The worst-case transmission latency after passing through DetNet; s i Represents a stream The number of switches on the TSN path; Represents the set of time-sensitive streams within the TSN domain; Represents a stream Deadline delay requirements; s u Represents a stream The number of switches on the TSN path; C3 represents the third constraint, L q B represents the length of data that the queue can buffer; B represents the transmission rate of the physical link; d hop t represents the link delay for single-hop data transmission; offset Indicates the synchronization accuracy deviation between adjacent nodes; C4 represents the fourth constraint, T CQF This indicates that the time slot t is scheduled by an integer number of CQFs during the supercycle. CQF composition.

[0094] To maximize the success rate of time-sensitive flow scheduling, the optimal scheduling slot size is determined by combining four established constraints. The solution steps are as follows: Figure 3 As shown:

[0095] S401. Based on the flow decision variable w i ∈{0,1} and time-sensitive flow f i Determine the network domain where the source and destination nodes are located. i Whether it has been scheduled by TSN, if it is a cross-domain time-sensitive flow, it is stored in the flow set F. cls If it is a time-sensitive flow within the domain, it is stored in the flow set F. ids middle;

[0096] S402. Calculate F according to the formula established in step S202. cls Worst-case latency;

[0097] S403. Obtain the upper bound of the CQF scheduling slots based on the associative constraint C2.

[0098] S404. F is obtained by depth-first search. cls With F ids Find the longest path in the TSN and calculate the upper bound of the time slot using constraint C2.

[0099] S405. Initialize the CQF queue size and calculate the minimum time slot value according to constraint C3;

[0100] S406. Use the Gurobi optimizer to perform integer planning on the number of streams that meet the latency requirements, and adjust the initial queue L in units of the maximum data frame length. q Size, return the optimal scheduling slot t CQF .

[0101] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium. When the program is executed, it can implement the steps of the method. The storage medium may be, for example, ROM / RAM, magnetic disk, optical disk, etc.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for fusing and scheduling time-sensitive streams from DetNet to TSN, characterized in that: Includes the following steps: S1: Use the network computation curve model to characterize the output accumulation function of time-sensitive streams after passing through the DetNet scheduling mechanism; S2: Use the network computation curve model to characterize the input accumulation function of the time-sensitive stream through the DetNet scheduling mechanism; S3: Construct the worst-case latency model of the time-sensitive stream passing through DetNet based on the maximum horizontal distance between the input and output cumulative functions; S4: Strictly design the TSN scheduling mechanism in combination with the minimum remaining delay requirements of cross-domain time-sensitive streams; Step S1, which describes the output accumulation function of the time-sensitive stream through the DetNet scheduling mechanism using a network computation curve model, specifically includes the following steps: S11: DetNet's deterministic scheduling mechanism is CSQF, which uses three queues to alternately output time-sensitive data. The time slot length for each queue is [missing information]. Configure nodes in the DetNet network The three time-sensitive stream scheduling queues are Q0, Q1, and Q2, and their start times are defined as follows: , , The closing times are respectively , , ; S12: Set Time-Sensitive Flow The start time of transmission in the time slot corresponding to its own queue is , is represented as: in, Represents a stream The SID carried corresponds to the node Output timeslot number at the location; Indicates at node Chuliu The corresponding queue is transmitting. ; End time is , is represented as: S13: Flow At the node Output cumulative function , is represented as: in, Indicates the intralink transmission rate; S14: Time-sensitive streams are stored in a high-priority queue. Considering the worst-case scenario, the remaining transmission length of low-priority streams is equal to the maximum data frame length. Therefore, the high-priority queue data frame delay forwarding time is: in, Indicates the maximum length of low-priority data; Time-sensitive flow The time when forwarding started changed to: S15: Time-Sensitive Flow At the node The output cumulative function is converted to the following table: Step S2 describes using a network computation curve model to characterize the output accumulation function of the time-sensitive stream after passing through the DetNet scheduling mechanism. The input accumulation function at the current node is a stream. The output accumulation function of the previous node includes the following steps: S21: Flow At the node The input accumulation function at point is expressed as: S22: Re-characterize the input cumulative function for nodes middle stream The input accumulator function is the sum of the input accumulator functions of all data in the same buffer queue at the same output port, expressed as: in, Indicates the inflow node A collection of data streams; Represents a stream With flow Whether cached in the same queue; when Time indicates flow With flow Cached in a queue, when Time indicates flow With flow Cached in different queues; Step S3, which involves constructing the worst-case latency model of the time-sensitive stream passing through the DetNet based on the maximum horizontal distance between the input and output cumulative functions, includes the following steps: S31: Flow At the node latency The maximum horizontal distance between two cumulative functions , is represented as: S32: Hypothetical Flow In the DetNet domain, a router is required. After passing through the link Then flow The worst latency after passing through the DetNet domain is: in, Represents a stream via link Link latency.

2. The time-sensitive stream fusion scheduling method from DetNet to TSN according to claim 1, characterized in that: In step S4, the TSN adopts a deterministic scheduling mechanism of CQF dual-queue cyclic alternation. The latency jitter of the time-sensitive stream after CQF scheduling is only related to the size of the scheduling time slot. Time slot constraints are established: the first constraint is that the time slot does not exceed the greatest common divisor of the time-sensitive stream period; the second constraint is that the latency requirement of the time-sensitive stream must be met; the third constraint is that it is not less than the time it takes for data to be sent and received in the same time slot; and the fourth constraint is that the CQF scheduling time slot must be divisible by the period. in, This represents the set of time-sensitive stream cycles passing through the DetNet domain; Represents the periodic set of time-sensitive streams within the TSN domain; This represents the set of time-sensitive streams processed by DetNet; Represents a stream Deadline delay requirements; Represents a stream Worst transmission latency via DetNet; Represents a stream The number of switches on the TSN path; Represents the set of time-sensitive streams within the TSN domain; Represents a stream Deadline delay requirements; Represents a stream The number of switches on the TSN path; B represents the length of data that the queue can buffer; B represents the transmission rate of the physical link. This indicates the link delay for single-hop data transmission. This indicates the synchronization accuracy deviation between adjacent nodes; This indicates that the time slots are scheduled by an integer number of CQFs during the supercycle. composition.

3. The time-sensitive stream fusion scheduling method from DetNet to TSN according to claim 2, characterized in that: In step S4, with the goal of maximizing the success rate of time-sensitive flow scheduling, the optimal scheduling slot size is determined by combining the four established constraints. The solution steps are as follows: S41: Based on flow decision variables With time-sensitive flow Determining the network domain where the source and destination nodes are located Whether it has been scheduled by TSN, if it is a cross-domain time-sensitive flow, it will be stored in the flow set. If it is a time-sensitive flow within the domain, it is stored in the flow set. middle; S42: Calculate based on the formula established in step S22 Worst-case latency; S43: Obtain the upper bound of the CQF scheduling slots based on the second constraint condition. ; S44: Obtained using depth-first search and The longest path in the TSN is used to calculate the upper bound of the time slot, combined with the second constraint. ; S45: Initialize the CQF queue size and calculate the minimum time slot value according to the third constraint; S46: Use the Gurobi optimizer to perform integer planning on the number of streams that meet the latency requirements, and adjust the initial queue in units of the maximum data frame length. Size, return the optimal scheduling slot .

Images