Cross-domain fusion scheduling method for time-sensitive flow from DetNet to TSN

Abstract

The invention relates to a fusion scheduling method of a time-sensitive stream from a DetNet domain to a TSN, which belongs to the technical field of long-distance time-sensitive application communication, and comprises the following steps: S1, depicting an output accumulation function of the time-sensitive stream passing through a DetNet scheduling mechanism by using a network calculation curve model; s2, describing an input accumulation function of the time-sensitive flow passing through a DetNet scheduling mechanism by using a network calculation curve model; s3, according to the maximum horizontal distance between the input accumulation function and the output accumulation function, constructing a worst consumption time delay model when the time-sensitive current passes through the DetNet; and S4, strictly designing a TSN scheduling mechanism in combination with the minimum residual delay demand of the cross-domain time-sensitive flow. According to the invention, when the time-sensitive flow is scheduled to the TSN through the DetNet, the time-sensitive flow can be output on time according to a TSN scheduling mechanism, so that the time-sensitive flow can realize end-to-end deterministic transmission in a network in which a plurality of scheduling mechanisms are fused.

Description

Technical Field

[0001] The present invention belongs to the technical field of long-distance time-sensitive application communication, and relates to a fusion scheduling method for time-sensitive flows from DetNet to TSN across domains. Background Art

[0002] With the introduction of concepts such as Industry 4.0 and the fifth generation mobile networks (5G), the scale of networks continues to expand while the requirements for deterministic transmission capabilities are becoming higher and higher. In order to meet the deterministic transmission requirements of the network, the emergence of Time Sensitive Network (TSN) and Deterministic Network (DetNet) technologies has improved the network's ability to support deterministic flows. The deterministic scheduling mechanism adopted by TSN is IEEE 802.1Qch. The proposed Cyclic Queueing and Forwarding (CQF) shaper can realize deterministic scheduling of local area networks, while DetNet combines SR routing technology with the scheduling idea of ​​CQF to propose a deterministic scheduling scheme suitable for wide area networks, namely the Cycle Specified Queueing and Forwarding (CSQF). In long-distance time-sensitive networks, the edge local area network should apply the TSN scheduling mechanism, while the core wide area network should apply the DetNet scheduling mechanism. The end-to-end transmission of time-sensitive flows will go through the scheduling mechanisms of the above two networks. Therefore, TSN not only schedules data in the edge LAN, but also receives data scheduled by the wide area network DetNet. However, the scheduling rules and time slot sizes of the two technologies are inconsistent and independent of the domain. The scheduling time and scheduling time slot of DetNet are looser than those of TSN. If the time-sensitive flow takes too long to be scheduled by DetNet, the TSN scheduling time slot allocation is unreasonable, resulting in the inability to transmit the time-sensitive flow in time, causing the end-to-end delay to increase, exceeding its deadline delay requirement.

[0003] At present, some researchers have explored the integration technology of TSN and DetNet, but most of them consider TSN technology as the integration of DetNet link layer, and do not involve the integration of cross-domain scheduling technology of the two technologies in different network domains. At present, only a few researchers have studied the cross-domain scheduling mechanism of TSN and DetNet, but the research method is relatively complex and does not consider the factors affecting each other. Therefore, it is worthwhile to study the integration scheduling mechanism of TSN and DetNet to meet the end-to-end deterministic transmission requirements of business flows in more scenarios. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a fusion scheduling method for time-sensitive flows from DetNet to TSN across domains, to realize the TSN scheduling mechanism integrated with the DetNet scheduling mechanism design, to ensure that the time-sensitive flows can be output on time according to the TSN scheduling mechanism when they are scheduled from DetNet to TSN, so that the time-sensitive flows can achieve end-to-end deterministic transmission in a network where multiple scheduling mechanisms are integrated.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] A fusion scheduling method for time-sensitive flows from DetNet to TSN across domains includes the following steps:

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

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

[0009] S3: Construct the worst consumption delay model of time-sensitive flow through DetNet based on the maximum horizontal distance between the input cumulative function and the output cumulative function;

[0010] S4: Strictly design the TSN scheduling mechanism based on the minimum residual latency requirement of cross-domain time-sensitive flows.

[0011] Furthermore, the output cumulative function of the time-sensitive flow through the DetNet scheduling mechanism is described by using the network calculation curve model in step S1, which specifically includes the following steps:

[0012] S11: DetNet’s deterministic scheduling mechanism is CSQF, which uses three queues to output time-sensitive data in a cyclic alternating manner. The time slot length corresponding to each queue is t CSQF , set the node v in the DetNet network x The three time-sensitive flow scheduling queues are Q0, Q1, and Q2, and the start times are defined as The closing times are

[0013] S12: Setting time-sensitive flow i The start time of transmission in the time slot corresponding to the own queue is t b,i , expressed as:

[0014]

[0015] in, Represents the flow f i The SID carried corresponds to the node v x The output time slot number at Indicates that at node vx Flow i The corresponding queue is transmitting f i ;

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

[0017]

[0018] S13: Flow i At node v x Output accumulation function It is expressed as:

[0019]

[0020] Where C represents the link transmission rate;

[0021] S14: The time-sensitive flow is stored in the high-priority queue. Considering the worst case, the remaining transmission length of the low-priority queue is the maximum data frame length, and the delay forwarding time of the high-priority queue data frame is:

[0022]

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

[0024] Time Sensitivity Flow i The time to start forwarding changes to:

[0025]

[0026] S15: Time Sensitivity i At node v x The output cumulative function is converted into:

[0027]

[0028] Furthermore, in step S2, the network calculation curve model is used to characterize the output cumulative function of the time-sensitive flow through the DetNet scheduling mechanism, and the flow f i The input accumulation function at the current node is the flow f i The output accumulation function of the previous node specifically includes the following steps:

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

[0030]

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

[0032]

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

[0034] Further, step S3 constructs the worst consumption delay model of the time-sensitive flow through DetNet according to the maximum horizontal distance between the input cumulative function and the output cumulative function, including the following steps:

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

[0036]

[0037] S32: Assume that the flow f i In the DetNet domain, it needs to pass through a router Through the link Then flow f i The worst latency through the DetNet domain is:

[0038]

[0039] in, Represents the flow f i Link delay through link e.

[0040] Further, in step S4, TSN adopts a deterministic scheduling mechanism of CQF dual queue cyclic alternation. The delay jitter of the time-sensitive flow after CQF scheduling is only related to the size of the scheduling time slot; establish time slot constraints, the first constraint is that the time slot does not exceed the greatest common divisor of the time-sensitive flow cycle, the second constraint is that the time-sensitive flow delay requirement needs to be met, the third constraint is not less than the time for data to be sent to the receiver in the same time slot, and the fourth constraint is that the CQF scheduling time slot must be divisible by the super period:

[0041]

[0042] in, represents the set of time-sensitive flow cycles passing through the DetNet domain; Represents the periodic set of the time-sensitive flow set in the TSN domain; Represents the set of time-sensitive flows passing through DetNet; Representation Flow The deadline delay requirement; Representation Flow The worst transmission delay through DetNet; si represents the flow The number of switches on the TSN path; Represents the set of time-sensitive flows in the TSN domain; Representation Flow The deadline delay requirement; s u Representation Flow The number of switches on the TSN path; L q Indicates the length of the queue that can cache data; B indicates the sending rate of the physical link; d hop represents the link delay of single-hop data transmission; t offset Indicates the synchronization accuracy deviation between adjacent nodes; T CQF Indicates that the super period consists of an integer number of CQF scheduling time slots t CQF composition.

[0043] Further, in step S4, the optimal scheduling time slot size is solved by combining the four established constraints with the goal of maximizing the scheduling success rate of the time-sensitive flow. The solving steps are:

[0044] S41: According to the flow decision variable w i ∈{0,1} and time-sensitive flow f i The network domain where the source and destination nodes are located is determined by f 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 consumption delay;

[0046] S43: Obtaining the upper bound of the CQF scheduling time slot based on the second constraint condition

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

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

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

[0050] The beneficial effects of the present invention are as follows: in a long-distance deterministic network, since multiple network domains are involved and the scheduling mechanisms in each domain are different, it is difficult to ensure the end-to-end deterministic transmission of time-sensitive flows. Specifically, it relates to a fusion scheduling method for time-sensitive flows from DetNet to TSN across domains, including using a network calculation curve model to characterize the input-output cumulative function of the time-sensitive flow through the DetNet scheduling mechanism; constructing a worst-case consumption delay model for the time-sensitive flow through DetNet based on the two functions; obtaining the minimum remaining delay requirement for the time-sensitive flow to enter TSN across domains based on the delay model; strictly designing the TSN scheduling mechanism and the flow injection time in combination with the remaining time requirement of the cross-domain time-sensitive flow; the present invention can realize the design of a TSN scheduling mechanism that integrates DetNet scheduling, ensuring that the time-sensitive flow can be output on time according to the TSN scheduling mechanism when it is scheduled from DetNet to TSN, so that the time-sensitive flow can achieve end-to-end deterministic transmission in a network where multiple scheduling mechanisms are integrated.

[0051] Other advantages, objectives and features of the present invention will be described in the following description to some extent, and to some extent, will be obvious to those skilled in the art based on the following examination and study, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be described in detail below in conjunction with the accompanying drawings, wherein:

[0053] Figure 1 is a cross-domain time slot offset scheduling scenario diagram of a deterministic network used in an embodiment of the present invention;

[0054] Figure 2 is an implementation flow chart of a method for cross-domain time slot offset scheduling in a deterministic network in an embodiment of the present invention;

[0055] Figure 3 It is a flow chart of the algorithm for solving the time slot offset factor of the present invention. DETAILED DESCRIPTION

[0056] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways 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 only illustrate the basic concept of the present invention in a schematic manner, and the following embodiments and features in the embodiments can be combined with each other without conflict.

[0057] Among them, the drawings are only used for illustrative explanations, and they only represent schematic diagrams rather than actual pictures, and should not be understood as limitations on the present invention. In order to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of actual products. For those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.

[0058] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right", "front", "rear", etc. indicate the orientation or position relationship, they are based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation. Therefore, the terms describing the position relationship in the drawings are only used for illustrative purposes and cannot be understood as limiting the present invention. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0059] The present invention is constructed as Figure 1The long-distance deterministic network shown in the figure is composed of a core wide area network and an edge local area network. To ensure the deterministic transmission of time-sensitive flows, the wide area network adopts the Cycle Specified Queueing and Forwarding (CSQF) scheduling mechanism proposed by the DetNet network, and the local area network adopts the cyclic queueing and forwarding (CQF) scheduling mechanism proposed by the TSN network. However, the two scheduling mechanisms are different, which leads to the introduction of uncertain delays when time-sensitive flows are transmitted across domains from DetNet to TSN, making it difficult to meet the end-to-end deterministic transmission requirements.

[0060] Based on Figure 1 The present invention provides a method for fusion scheduling of time-sensitive flows from DetNet to TSN across domains, such as Figure 2 As shown, the following steps are included:

[0061] S1. The network calculation curve model is used to characterize the output accumulation function of the time-sensitive flow through the DetNet scheduling mechanism. The construction process includes:

[0062] S101.DetNet’s deterministic scheduling mechanism is CSQF, which uses three queues to output time-sensitive data alternately in a loop. The time slot length corresponding to each queue is t CSQF , set the node v in the DetNet network x The three time-sensitive flow scheduling queues are Q0, Q1, and Q2, and the start times are defined as The closing times are

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

[0064]

[0065] in, Represents the flow f i The SID carried corresponds to the node v x The output time slot number at Indicates that at node v x Flow i The corresponding queue is transmitting f i .

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

[0067]

[0068] S103. Flow i At node v x Output accumulation function It can be expressed as:

[0069]

[0070] Where C represents the link transmission rate.

[0071] S104. The time-sensitive flow is stored in the high-priority queue. When the cached data of the low-priority queue transmits a large data at the end of the queue opening time slot, due to the integrity of the transmitted data, the low-priority data will occupy part of the high-priority queue time slot, resulting in a delay in the actual start of transmission of the high-priority data. Considering the worst case, the remaining transmission length of the low-priority queue is the maximum data frame length, then the delay forwarding time of the high-priority queue data frame is:

[0072]

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

[0074] Therefore, time-sensitive flow i The time to start forwarding changes to:

[0075]

[0076] S105. Time Sensitivity Flow i At node v x The output cumulative function is converted into:

[0077]

[0078] S2. Use the network calculation curve model to characterize the input accumulation function of the time-sensitive flow through the DetNet scheduling mechanism. i The input accumulation function at the current node is the flow f i The output accumulation function of the previous node is constructed by:

[0079] S201.CSQF mechanism does not require time synchronization of each node, so there is a certain time deviation between each node, then the flow f i At node v x The input cumulative function at can be expressed as:

[0080]

[0081] S202.CSQF caches the three queues of time-sensitive flows in a circularly open manner to schedule output data, while the data in a single queue is output in a first-in, first-out manner. Therefore, the first-in traffic in the queue itself will cause the later-in traffic to wait for a queuing delay before it can be output. The impact of the traffic in the queue itself is that the traffic from multiple different input ports converges into the same cache queue of the same output port, resulting in a "self-queuing" waiting situation. Since the "self-queuing" situation will affect the delay of the flow, the input cumulative function is re-characterized. For node v x Midstream f i The input cumulative function of is the sum of all data input cumulative functions in the same cache queue of the same output port, which can be expressed as:

[0082]

[0083] Among them, F x Indicates the inflow node v x The data stream set of ε j ={0,1} represents the flow f j With flow i Whether to cache in the same queue. j =1 indicates flow f j With flow i Cache in a queue, when ε j =0 indicates flow f i With flow i Cache in different queues.

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

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

[0086]

[0087] S302. DetNet nodes do not need time synchronization, only time slot frequency synchronization, and the link is long, so the link delay cannot be ignored. Therefore, in order to match the actual situation, the worst delay of the target flow in DetNet is calculated by accumulating and summing the delay of a single node. Assume that flow f i In the DetNet domain, it needs to pass through a router Through the link Then flow f i The worst latency through the DetNet domain is:

[0088]

[0089] in, Represents the flow f i Link delay through link e.

[0090] S4. Strictly design the TSN scheduling mechanism based on the minimum residual delay requirement of cross-domain time-sensitive flows.

[0091] Specifically, TSN adopts a deterministic scheduling mechanism of CQF dual queue cyclic alternation. The delay jitter of the time-sensitive flow after CQF scheduling is only related to the size of the scheduling time slot. Therefore, the time slot constraints are established. The first constraint is that the time slot does not exceed the greatest common divisor of the time-sensitive flow cycle, the second constraint is that the time-sensitive flow delay requirement must be met, the third constraint is not less than the time it takes for data to be sent to the receiver in the same time slot, and the fourth constraint is that the CQF scheduling time slot must be divisible by the super cycle:

[0092]

[0093] Among them, C1 represents the first constraint, represents the set of time-sensitive flow cycles passing through the DetNet domain; represents the periodic set of the time-sensitive flow set in the TSN domain; C2 represents the second constraint, Represents the set of time-sensitive flows passing through DetNet; Representation Flow The deadline delay requirement; Representation Flow Worst transmission delay through DetNet;s i Representation Flow The number of switches on the TSN path; Represents the set of time-sensitive flows in the TSN domain; Representation Flow The deadline delay requirement; s u Representation Flow The number of switches on the TSN path; C3 represents the third constraint, L q Indicates the length of the queue that can cache data; B indicates the sending rate of the physical link; d hop represents the link delay of single-hop data transmission; t offset represents the synchronization accuracy deviation between adjacent nodes; C4 represents the fourth constraint, T CQF Indicates that the super period consists of an integer number of CQF scheduling time slots t CQF composition.

[0094] With the goal of maximizing the scheduling success rate of time-sensitive flows, the optimal scheduling time slot size is solved by combining the 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 The network domain where the source and destination nodes are located is determined by f 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 consumption delay;

[0097] S403. Obtain the upper bound of the CQF scheduling time slot according to the combined constraint C2

[0098] S404. Obtain F by depth-first search cls With F ids The longest path in TSN, combined with constraint C2 to calculate the upper bound of the time slot

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

[0100] S406. Use the Gurobi optimizer to perform integer programming on the number of flows that meet the delay requirements, and adjust the initial queue L in units of the maximum data frame length. q size, returns the optimal scheduling time slot t CQF .

[0101] A person skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing related hardware through a program. The program can be stored in a computer-readable storage medium. When the program is executed, the steps of the method can be implemented. The storage medium, such as ROM / RAM, a disk, an optical disk, etc.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution, which should be included in the scope of the claims of the present invention.

Claims

1. A fusion scheduling method for time-sensitive flows from DetNet to TSN across domains, characterized by: The following steps are involved: S1: Use the network calculation curve model to characterize the output accumulation function of the time-sensitive flow through the DetNet scheduling mechanism; S2: Use the network calculation curve model to characterize the input accumulation function of the time-sensitive flow through the DetNet scheduling mechanism; S3: Construct the worst consumption delay model of time-sensitive flow through DetNet based on the maximum horizontal distance between the input cumulative function and the output cumulative function; S4: Strictly design the TSN scheduling mechanism based on the minimum residual latency requirement of cross-domain time-sensitive flows.

2. The method for cross-domain fusion scheduling of time-sensitive flows from DetNet to TSN according to claim 1 is characterized in that: Step S1 uses a network calculation curve model to characterize the output cumulative function of the time-sensitive flow through the DetNet scheduling mechanism, which specifically includes the following steps: S11: DetNet’s deterministic scheduling mechanism is CSQF, which uses three queues to output time-sensitive data in a cyclic alternating manner. The time slot length corresponding to each queue is t CSQF , set the node v in the DetNet network x The three time-sensitive flow scheduling queues are Q0, Q1, and Q2, and the start times are defined as The closing times are S12: Setting time-sensitive flow i The start time of transmission in the time slot corresponding to the own queue is t b,i , expressed as: in, Represents the flow f i The SID carried corresponds to the node v x The output time slot number at Indicates that at node v x Flow i The corresponding queue is transmitting f i ; The end time is t e,i , expressed as: S13: Flow i At node v x Output accumulation function It is expressed as: Where C represents the link transmission rate; S14: The time-sensitive flow is stored in the high-priority queue. Considering the worst case, the remaining transmission length of the low-priority queue is the maximum data frame length, and the delay forwarding time of the high-priority queue data frame is: Among them, l max Indicates the maximum length of low priority data; Time Sensitivity Flow i The time to start forwarding changes to: S15: Time Sensitivity i At node v x The output cumulative function is converted into a table:

3. The method for cross-domain fusion scheduling of time-sensitive flows from DetNet to TSN according to claim 2, characterized in that: Step S2 uses the network calculation curve model to characterize the output cumulative function of the time-sensitive flow through the DetNet scheduling mechanism, flow f i The input accumulation function at the current node is the flow f i The output accumulation function of the previous node specifically includes the following steps: S21: Flow i At node v x The input cumulative function at is expressed as: S22: Re-characterize the input cumulative function, for node v x Midstream f i The input cumulative function of is the sum of all data input cumulative functions in the same cache queue of the same output port, expressed as: Among them, F x Indicates the inflow node v x The data stream set; ε j ={0,1} represents the flow f j With flow i Whether to cache in the same queue; when ε j =1 indicates flow f j With flow i Cache in a queue, when ε j =0 indicates flow f i With flow i Cache in different queues.

4. The method for cross-domain fusion scheduling of time-sensitive flows from DetNet to TSN according to claim 3 is characterized in that: Step S3 constructs the worst consumption delay model of the time-sensitive flow through DetNet according to the maximum horizontal distance between the input cumulative function and the output cumulative function, including the following steps: S31: Flow i At node v x Delay is the maximum horizontal distance H(R,S) between two cumulative functions, expressed as: S32: Assume that the flow f i In the DetNet domain, it needs to pass through a router Through the link Then flow f i The worst latency through the DetNet domain is: in, Represents the flow f i Link delay through link e.

5. The method for cross-domain fusion scheduling of time-sensitive flows from DetNet to TSN according to claim 4, characterized in that: In step S4, TSN adopts a deterministic scheduling mechanism of CQF dual queue cyclic alternation. The delay jitter of the time-sensitive flow after CQF scheduling is only related to the size of the scheduling time slot; establish time slot constraints, the first constraint is that the time slot does not exceed the greatest common divisor of the time-sensitive flow cycle, the second constraint is that the time-sensitive flow delay requirement must be met, the third constraint is not less than the time for data to be sent to the receiver in the same time slot, and the fourth constraint is that the CQF scheduling time slot must be divisible by the super cycle: in, represents the set of time-sensitive flow cycles passing through the DetNet domain; Represents the periodic set of the time-sensitive flow set in the TSN domain; Represents the set of time-sensitive flows passing through DetNet; Represents the flow f i cls The deadline delay requirement; Represents the flow f i cls Worst transmission delay through DetNet;s i Represents the flow f i cls The number of switches on the TSN path; Represents the set of time-sensitive flows in the TSN domain; Representation Flow The deadline delay requirement; s u Representation Flow The number of switches on the TSN path; L q Indicates the length of the queue that can cache data; B indicates the sending rate of the physical link; d hop represents the link delay of single-hop data transmission; t offset Indicates the synchronization accuracy deviation between adjacent nodes; T CQF Indicates that the super period consists of an integer number of CQF scheduling time slots t CQF composition.

6. The method for cross-domain fusion scheduling of time-sensitive flows from DetNet to TSN according to claim 5, characterized in that: In step S4, the optimal scheduling time slot size is solved by combining the four established constraints with the goal of maximizing the scheduling success rate of the time-sensitive flow. The solution steps are: S41: According to the flow decision variable w i ∈{0,1} and time-sensitive flow f i The network domain where the source and destination nodes are located is determined by f 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; S42: Calculate F according to the formula established in step S22 cls Worst consumption delay; S43: Obtaining the upper bound of the CQF scheduling time slot based on the second constraint condition S44: Get F by depth-first search cls With F ids The longest path in TSN, and the upper bound of the time slot is calculated in combination with the second constraint S45: Initialize the CQF queue size and calculate the minimum time slot value according to the third constraint condition; S46: Use the Gurobi optimizer to perform integer programming on the number of flows that meet the latency requirements, and adjust the initial queue L in units of the maximum data frame length. q size, returns the optimal scheduling time slot t CQF .

Images