WO2023116126A1

WO2023116126A1 - Time-triggered scheduling method, node, electronic device, and storage medium

Info

Publication number: WO2023116126A1
Application number: PCT/CN2022/124184
Authority: WO
Inventors: 喻敬海; 李宗辉; 段威
Original assignee: 中兴通讯股份有限公司
Priority date: 2021-12-22
Filing date: 2022-10-09
Publication date: 2023-06-29
Also published as: CN116346627A

Abstract

Provided in the present application are a time-triggered scheduling method, a node, an electronic device, and a storage medium. The method comprises: acquiring the characteristics of each service flow in a preset service flow set, the path of the service flow, and the characteristics of each preset node on the path of the service flow (110); constructing a directed graph according to the path of the service flow (120); determining the degree of urgency of the service flow according to the directed graph, the characteristics of the service flow and the characteristics of the node (130); determining a sending time of the service flow according to the directed graph and the degree of urgency of the service flow (140); and sending the sending time to the node (150).

Description

Time-triggered scheduling method, node, electronic device and storage medium

Cross References to Related Applications

This application is based on a Chinese patent application with application number 202111579523.2 and a filing date of December 22, 2021, and claims the priority of this Chinese patent application. The entire content of this Chinese patent application is hereby incorporated by reference into this application.

technical field

The present application relates to but not limited to the technical field of communication, and in particular relates to a time-triggered scheduling method, node, electronic device and storage medium.

Background technique

Time-Sensitive Networking (Time-Sensitive Networking, TSN) was proposed and standardized by IEEE 802.1TSN International Organization. It has been widely supported and recognized by industry, academia and many international organizations (including IEC, IETF, 3GPP, etc.), and it is expected to break the information network. (Information Technology, IT) and control network (Operational Technology, OT) barriers, to achieve the integration of IT and OT, has a wide range of application prospects. TSN introduces a time-triggered transmission mechanism and standardizes it as 802.1Qbv, which supports time-sensitive service flows to be sent at precise time points. Since the sending time point of the time-sensitive service flow in each device along the route is definite, the end-to-end delay of the time-sensitive service flow is also definite. Time-triggered scheduling is to schedule the sending time of each service flow in the device. It is related to factors such as network topology, routing, and end-to-end delay requirements of service flows. It is a typical set of non-deterministic polynomials (Non-deterministic Polynomial, NP ) completely problematic.

At present, the typical way to solve the time-triggered scheduling problem is to construct constraints such as end-to-end delay, non-conflict between service flows, and cache limitations, and then use a satisfiability solver to solve the problem. Although this scheduling method can traverse the entire scheduling space to It can be concluded whether it can be scheduled, but the scheduling time increases exponentially, which cannot adapt to the dynamic changes of time-sensitive business or dynamic configuration or application scenarios with strict requirements on scheduling time; Different feasible solutions may appear in each scheduling, and it is impossible to precisely control the sending time of each service flow to obtain high-quality scheduling results.

Contents of the invention

The following is an overview of the topics described in detail in this article. This summary is not intended to limit the scope of the claims.

Embodiments of the present application provide a time-triggered scheduling method, a node, an electronic device, and a storage medium.

In the first aspect, the embodiment of the present application provides a time-triggered scheduling method, which is applied to the central controller, and the method includes: obtaining the characteristics of each service flow in the preset service flow set, the path of the service flow and The characteristics of each preset node on the path of the service flow; a directed graph is constructed according to the path of the service flow, wherein the vertices of the directed graph are formed by two adjacent nodes on the path of the service flow determine the node; determine the urgency of the service flow according to the directed graph, the characteristics of the service flow, and the characteristics of the node; determine the urgency of the service flow according to the directed graph and the urgency of the service flow The sending time of the service flow; sending the sending time to the node, so that the node transmits the corresponding service flow in the service flow set according to the sending time.

In the second aspect, the present application also provides a time-triggered scheduling method applied to nodes, the method comprising: receiving the sending time from the central controller, wherein the sending time is determined by the directed graph and the urgency of the service flow It is determined that the directed graph is constructed by the path of the service flow, and the urgency of the service flow is determined by the characteristics of each service flow in the preset service flow set acquired by the central controller, the service flow The path of the flow and the characteristics of each node on the path of the service flow are determined; and the corresponding service flow in the set of service flows is transmitted according to the sending time.

In a third aspect, the present application also provides a node, including: a memory, a processor, and a computer program stored on the memory and operable on the processor, and the processor implements the second aspect above when executing the computer program The time-triggered scheduling method described above.

In a fourth aspect, the present application also provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and operable on the processor, when the processor executes the computer program, the above first The time-triggered scheduling method described in the aspect.

In the fifth aspect, the present application also provides a computer-readable storage medium, where the computer-readable storage medium stores a computer-executable program, and the computer-executable program is used to make the computer perform the above-mentioned first aspect. A trigger scheduling method, or a time-triggered scheduling method as described in the second aspect above.

Additional features and advantages of the application will be set forth in the description which follows, and, in part, will be obvious from the description, or may be learned by practice of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

Description of drawings

The accompanying drawings are used to provide a further understanding of the technical solution of the present application, and constitute a part of the specification, and are used together with the embodiments of the present application to explain the technical solution of the present application, and do not constitute a limitation to the technical solution of the present application.

FIG. 1 is a flowchart of a time-triggered scheduling method provided by an embodiment of the present application;

FIG. 2 is a flow chart of a method for determining the urgency of a service flow provided by another embodiment of the present application;

FIG. 3 is a flow chart of a method for determining the sending time of a service flow provided by another embodiment of the present application;

FIG. 4 is a flow chart of a method for determining the sending time from the total topology sequence provided by another embodiment of the present application;

FIG. 5 is a flow chart of a method for determining the sending time from the total topology sequence provided by another embodiment of the present application;

FIG. 6 is a flow chart of a method for determining the sending time of a conflicting service flow provided by another embodiment of the present application;

Fig. 7 is a schematic diagram of the time delay of each part required for calculating the urgency of the business flow provided by another embodiment of the present application;

Fig. 8 is a schematic diagram of a node connection diagram provided by another embodiment of the present application;

Fig. 9 is a schematic diagram of a directed graph provided by another embodiment of the present application;

Fig. 10 is a schematic diagram of the remaining directed graph provided by another embodiment of the present application;

Fig. 11 is a schematic diagram of a dering directed graph provided by another embodiment of the present application;

FIG. 12 is a flowchart of another method for determining the sending time of a service flow provided by another embodiment of the present application;

FIG. 13 is a flow chart of a method for initialization based on time slots provided by another embodiment of the present application;

FIG. 14 is a flowchart of a method for connecting a virtual terminal provided by another embodiment of the present application;

FIG. 15 is a schematic diagram of a sending terminal connected to a virtual terminal provided by another embodiment of the present application;

FIG. 16 is a flowchart of a time-triggered scheduling method provided by another embodiment of the present application;

Fig. 17 is a schematic diagram of implementation in 802.1Qcc provided by another embodiment of the present application;

Fig. 18 is a structural diagram of a node provided by another embodiment of the present application;

Fig. 19 is a structural diagram of an electronic device provided by another embodiment of the present application.

Detailed ways

In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the embodiments described here are only used to explain the present application, not to limit the present application.

It should be noted that although the functional modules are divided in the schematic diagram of the device, and the logical sequence is shown in the flowchart, in some cases, it can be executed in a different order than the module division in the device or the flowchart in the flowchart. steps shown or described. The terms "first", "second" and the like in the specification, claims or the above-mentioned drawings are used to distinguish similar objects, and not necessarily used to describe a specific order or sequential order.

Time-Sensitive Networking (Time-Sensitive Networking, TSN) was proposed and standardized by IEEE 802.1TSN International Organization. It has been widely supported and recognized by industry, academia and many international organizations (including IEC, IETF, 3GPP, etc.), and it is expected to break the information network. The barriers between IT and control network OT, and the integration of IT and OT, have broad application prospects. TSN introduces a time-triggered transmission mechanism and standardizes it as 802.1Qbv, which supports time-sensitive service flows to be sent at precise time points. Since the sending time point of the time-sensitive service flow in each device along the route is definite, the end-to-end delay of the time-sensitive service flow is also definite. Time-triggered scheduling is to schedule the sending time of each service flow in the device. It is related to factors such as network topology, routing, and end-to-end delay requirements of service flows. It is a typical NP-complete problem.

Aiming at the problem that the business flow scheduling is slow and the sending time of the service flow cannot be precisely regulated, the application provides a time-triggered scheduling method, node, electronic device and storage medium, the method includes: obtaining each The characteristics of the business flow, the path of the business flow, and the characteristics of each preset node on the path of the business flow; construct a directed graph according to the path of the business flow, wherein the vertices of the directed graph are composed of two adjacent nodes on the path of the business flow Determine the urgency of the service flow according to the directed graph, the characteristics of the service flow, and the characteristics of the nodes; determine the sending time of the service flow according to the urgency of the directed graph and the service flow; send the sending time to the node, So that the node transmits the corresponding service flow in the service flow set according to the sending time. According to the solution provided by the embodiment of the present application, the directed graph can be constructed through the path of the business flow, and then the urgency of the business flow can be determined. Compared with the solution method of the satisfiability solver with exponential time complexity, the directed graph and the business The urgency of the flow determines the sending time of the service flow, which can reduce the time complexity, effectively speed up the scheduling of the service flow, provide an effective guarantee for a series of functions such as online scheduling and dynamic configuration of the time-sensitive network, and can precisely control the sending of the service flow Time provides the possibility of precise control for exploring better business flow scheduling results with better service quality.

First, analyze some nouns involved in this application:

Routing refers to the network-wide process of determining the end-to-end path of a packet as it travels from source to destination.

A directed graph refers to an ordered triple (V(D), A(D), ψD), where ψD is an association function, which makes each element in A(D) (called a directed edge or arc ) corresponds to an ordered pair of elements (called vertices or points) in V(D).

In-degree refers to the sum of the number of times a point in a directed graph is the end point of an edge in the graph.

Least Common Multiple (LCM), the smallest positive integer among the common multiples of several integers is called their least common multiple.

The embodiments of the present application will be further described below in conjunction with the accompanying drawings.

As shown in FIG. 1 , FIG. 1 is a flowchart of a time-triggered scheduling method provided by an embodiment of the present application. The time-triggered scheduling method can be applied to the central controller, and the time-triggered scheduling method includes but not limited to the following steps:

Step 110, acquiring the characteristics of each service flow in the preset service flow set, the path of the service flow, and the characteristics of each preset node on the path of the service flow;

Step 120, constructing a directed graph according to the path of the service flow, wherein the vertices of the directed graph are determined by two adjacent nodes on the path of the service flow;

Step 130, determine the urgency of the service flow according to the directed graph, the characteristics of the service flow and the characteristics of the nodes;

Step 140, determine the sending time of the service flow according to the urgency of the directed graph and the service flow;

Step 150, sending the sending time to the node, so that the node transmits the corresponding service flow in the service flow set according to the sending time.

It can be understood that, according to the characteristics of the service flow and the characteristics of the nodes, the period of the service flow, the length of the packet, the end-to-end delay and the minimum forwarding delay of the service flow in the node can be obtained. Two nodes form an edge of the path of the business flow, as the vertex of the directed graph, and the two adjacent edges on the path of the business flow determine a directed edge of the directed graph, and then schedule the business according to the path of the directed graph flow, and schedule the business flow corresponding to each vertex in turn. When the in-degree of the vertex of the directed graph is greater than 1, it is determined that the business flow corresponding to the vertex conflicts, and the conflict resolution mechanism is used to calculate the conflict of each business flow. Urgency, and then sort the conflicting service flows according to the urgency, and make the sending time of the service flow with low urgency greater than the urgency under the premise of ensuring that the sending time of the later scheduled service flow is longer than that of the first scheduled service flow High service flow sending time; after the scheduling of the service flow is completed, it can ensure that any two service flows in the service flow set meet the non-conflict judgment criterion; based on this, a directed graph can be constructed through the path of the service flow to determine the service flow The urgency of the flow, compared with the satisfiability solver solution method with exponential time complexity, determines the sending time of the business flow through the directed graph and the urgency of the business flow, which can reduce the time complexity and effectively speed up the scheduling of the business flow. It provides an effective guarantee for a series of functions such as online scheduling and dynamic configuration of time-sensitive networks, and can accurately control the sending time of business flows, providing the possibility of precise control for exploring better and better service quality business flow scheduling results.

It should be noted that a node includes, but is not limited to, a sending terminal, a receiving terminal, and a switch.

It is worth noting that before scheduling the service flow, the sending terminal needs to be initialized, as follows: when the service flow f _i is sent at the sending terminal v ₀ , [v ₀ , v _x ] represents the link connecting the sending terminal, there exists a sending time

In the initialization process, the send time is set to zero, i.e.

Therefore, when any service flow in the service flow set does not conflict with other service flows, the sending time of the service flow is 0. When the service flow conflicts with other service flows, the sending time of the service flow needs to be adjusted according to the scheduling result .

It should be noted that (1) the non-conflict judgment criteria are as follows:

Two business flows f _i and f _j have no conflict on the edge [v _k , v _j ], which is equivalent to:

have

set up,

Among them, a and b are integers, respectively representing the order of service flow f _i and f _j appearing in the macro-period LCM (f _i.period , f _j .period), f _i.period is the sending period of f _i , f _j .period is the sending period of f _j ; the above inequality guarantees that there will be no conflict when the service flows f _i and f _j appear in the macro-period LCM (f _i .period, f _j .period);

(2) The conflict resolution mechanism is as follows:

Step S11: sort the n conflicting business flows according to the urgency: f ₁ .urgency＞,...,f _i .urgency＞,...,f _n .urgency; the time complexity of sorting is O(n*log(n ));

Step S12: For each flow f _i , the time when the service flow arrives at node v _k

as the benchmark, plus the minimum forwarding delay of the service flow on v _k

The initial sending time as a service flow on v _k to v _j

Right now:

The time complexity of this step is O(n);

Step S13: Starting from the service flow with the highest urgency, for each service flow f _i , use the initial sending time in step S12

As a starting point, judge whether the business flow whose urgency is higher than f _i , that is, the business flow whose subscript is smaller than i, conflicts with f _i according to the non-conflict judgment criterion;

Step S14: If there is no conflict, then i=i+1, and then return to step S13;

Step S15: If there is a conflict, the sending time of the high-urgency service flow remains unchanged, and the sending time of the low-urgency service flow _fi is:

Among them, T _w is the time window, and the time window is determined by the packet size and bandwidth of the service flow, for example, the time window is equal to the packet size of the service flow divided by the bandwidth; the sending time of the service flow _fi

Update to original sending time

Add a T _w ; in addition, if the entire time axis is divided into several time slots time_slot, the time slot is the smallest time unit for scheduling allocation, when a conflict occurs, the sending time of the business flow

Update to original sending time

Increment by 1, where,

It is determined that the sending time of the service flow f _i is greater than the sending time of the service flow with a higher degree of urgency, so as to avoid conflicts, and return to step S13;

In addition, in step S15, when using the time window, when

After searching all the time windows, it is recorded that the business flow cannot be scheduled; when time slots are used, when

search finished

After all the time slots in , record that the service flow is unschedulable, start to schedule the next service flow, that is, i=i+1 and return to step S13, or i==n, which means that all service flows have been scheduled, then jump out of the loop ;

Step S13, step S14, and step S15 are a multiple cycle. For each service flow _fi, it is necessary to judge whether it conflicts with a service flow with a higher degree of urgency. The scope of conflict judgment is the entire macrocycle of all n service flows. Therefore, the time complexity of multiple loops composed of steps S13, S14, and S15 is

It can be understood that step S15 conforms to the terminal sending time adjustment theorem, which means that at least one conflict of the service flow can be resolved by adjusting the sending time of the service flow at the sending terminal. The description of the terminal sending time adjustment theorem is as follows:

Assuming that business flows f ₁ and f ₂ collide on edge [v ₂ , v ₃ ], through scheduling, set the sending time of f ₁ and f ₂ on node v ₂ as

conflicts can be avoided, and the sending time of f ₁ and f ₂ on the sending terminal is adjusted as follows:

in,

Indicates the minimum forwarding delay for a message to be forwarded from node v _i to v _j ,

Indicates the link delay for packets sent from node v ₀ to v _j .

In practice, the characteristics of each service flow in the service flow set, the path of the service flow, and the characteristics of each preset node on the path of the service flow can be obtained from the information sent by the node, or through the user on the central controller Obtained from the setting information of .

In addition, referring to FIG. 2, in one embodiment, step 130 in the embodiment shown in FIG. 1 includes but is not limited to the following steps:

Step 210, based on the directed graph, determine the service flow, current node, and subsequent node corresponding to each vertex in the directed graph, wherein the current node is the previous one of the two adjacent nodes on the path of the service flow, and the subsequent node The node is the latter of the two adjacent nodes on the path of the service flow;

Step 220, determine the end-to-end delay of the service flow according to the directed graph, the characteristics of the service flow and the characteristics of the nodes;

Step 230, according to the characteristics of the current node, the subsequent node and the node, determine the minimum forwarding delay of the service flow;

Step 240, according to the characteristics of the directed graph and the service flow, determine the cumulative transmission delay of the service flow corresponding to the current node;

Step 250, according to the directed graph and the minimum forwarding delay, determine the minimum transmission delay of the service flow corresponding to the current node;

Step 260: Determine the urgency of the service flow according to the end-to-end delay of the service flow, the minimum forwarding delay of the service flow, the cumulative transmission delay of the service flow, and the minimum transmission delay of the service flow.

It should be noted that the calculation process of the urgency of the business flow is as follows:

Let the current node of the business flow f _i be v _k , and the subsequent node of the next hop is v _j ; according to the characteristics of the directed graph and the business flow, determine the end-to-end delay f _i .delay _endtoend of the business flow f _i ; according to The characteristics of the current node, the subsequent node and the node, determine the minimum forwarding delay of the service flow f _i forwarded from the current node v _k to the subsequent node v _j

According to the characteristics of the directed graph and the service flow, determine the cumulative transmission delay of the service flow f _i from the sending terminal to the current node v _k as

According to the directed graph and the minimum forwarding delay, determine the minimum transmission delay of the service flow f _i

Refers to the path of the service flow f _i , if the service flow f _i is at the current node v _k , if each subsequent hop is calculated according to the minimum forwarding delay, the required minimum transmission delay,

The minimum forwarding delay calculation can be reduced hop by hop through the route of the service flow f _i , and the initial value when sending the terminal is "each hop calculates the required end-to-end delay according to the minimum forwarding delay"; finally, calculate The urgency of business flow f _i on edge [v _k , v _j ], the calculation formula is:

in,

is the urgency of the service flow, f _i .delay _endtoend is the end-to-end delay of the service flow,

is the minimum forwarding delay of the service flow,

is the cumulative transmission delay of the service flow,

is the minimum transmission delay of the service flow.

It can be understood that the degree of urgency reflects the time margin that the business flow can be used for scheduling,

The smaller the value is, the more urgent it is, when

, if f _i has not reached the terminal, it means that the service flow cannot be scheduled.

In addition, referring to FIG. 3, in one embodiment, step 140 in the embodiment shown in FIG. 1 includes but is not limited to the following steps:

Step 310, topologically sort the directed graph to obtain a first topological sequence;

Step 320, when it is determined that the number of sequence points of the first topological sequence is less than the number of vertices of the directed graph, determining the remaining directed graph according to the first topological sequence and the directed graph;

Step 330, taking the service flow with the lowest degree of urgency among the service flows corresponding to each vertex in the remaining directed graph as the loop-free service flow;

Step 340, determine the de-looped directed graph according to the de-looped service flow and the remaining directed graph;

Step 350, perform topological sorting on the dering directed graph to obtain a second topological sequence;

Step 360, based on the characteristics of the service flow and the characteristics of the node, determine the sending time of the service flow according to the first topology sequence, the second topology sequence and the de-looped service flow.

It should be noted that the steps of topologically sorting a directed graph are as follows: Assume that L is a list for storing results; (1) first find a vertex with zero in-degree in the directed graph, and put the above-mentioned vertex into L; ( 2) Then delete the above-mentioned vertex and the directed edge with the above-mentioned vertex as the starting point in the directed graph; repeat (1) (2) until there is no vertex whose in-degree is zero in the directed graph; then, use L as the first A topological sequence, when the number of elements in L is the same as the total number of vertices in the directed graph, it means that there is no cycle in the directed graph, otherwise there is a cycle; if there is a cycle in the directed graph, delete the first one in the directed graph vertices in a topological sequence to obtain the remaining directed graph.

It can be understood that both the first topology sequence and the second topology sequence reflect the sequence relationship between data links, so as to determine the sequence of scheduling service flows, and use the first topology sequence to determine whether there is a loop in the directed graph. The directed graph has no loops, and the business flow scheduling can be completed only by using the first topological sequence; Then, under the joint action of the first topology sequence, the second topology sequence and the ring-free service flow, the service flow is scheduled to avoid conflicts of the service flow during transmission. The loop breaking process is as follows:

Step S31: Calculate the urgency of the service flow associated with the loop in the directed graph G'(V', E'), and use the service flow with the least urgency as the de-loop service flow, for example, f _i ;

Step S32: Record the path of f _i on the loop, and the starting point on the path is denoted as

Decrease the in-degree of nodes on the path by 1;

Repeat steps S31 and S32 until a node with an in-degree of 0 appears on the ring, at this moment the ring has been broken;

Step S33: Continue to output the topological sequence in the broken loop G'(V', E'), when the output is to the starting point of the selected service flow when the broken loop is broken, such as the node of _fi

When , restore the in-degree of the node on the path f _i , that is, add 1 to the in-degree of the node, so as to schedule the sending time of nodes along the path of f _i ;

Step S34: Since the de-loop service flow f _i is used for loop breaking processing, when scheduling the sending time of f _i in the node, the sending time of part of the service flow has been determined, so the sending time of f _i in the node will not Change the sending time point of the scheduled service flow, and only determine the sending time point with the unscheduled service flow according to the conflict resolution mechanism, and at the same time, the selected sending time point cannot conflict with the scheduled service flow;

In step S31, the maximum number of processed business flows is |F|, and the time required for sorting is O(|F|*log(|F|));

In step S32, at most all business flows are traversed, and the in-degree minus 1 operation is performed on the path, so the time complexity is O(|F|*|E|);

In step S33, it is still topological sorting, so the time complexity is O(|F|*|E|);

In step S34, scheduling is performed along the topological sequence, the length of the topological sequence is at most |E|, and the time complexity of resolving conflicts on each node is

Therefore, the time complexity of step S34 is

Therefore, the time complexity of breaking the loop is

In addition, referring to FIG. 4, in one embodiment, step 360 in the embodiment shown in FIG. 3 includes but is not limited to the following steps:

Step 410, determining the total topology sequence according to the first topology sequence, the second topology sequence and the de-looped service flow;

Step 420, traverse each sequence point in the total topology sequence according to the order of the total topology sequence, and perform scheduling processing on the service flow corresponding to the sequence point, so as to determine the sending time of the service flow.

It can be understood that, according to the sequence relationship between the data links and the urgency of the business flow, the first topological sequence, the second topological sequence and the vertices corresponding to the de-looped business flow on the remaining directed graph are connected in sequence to obtain the total topological sequence , which can effectively schedule business flows.

In addition, referring to FIG. 5, in one embodiment, step 420 in the embodiment shown in FIG. 4 includes but is not limited to the following steps:

Step 510, based on the directed graph, determine the conflicting business flow and the non-conflicting business flow from the business flow set, wherein the conflicting business flow is the business flow corresponding to the vertex whose indegree is greater than one in the directed graph, and the non-conflicting business flow is Service flows other than conflicting service flows in the set of service flows;

Step 520, traverse each sequence point in the total topology sequence according to the order of the total topology sequence, and when it is determined that the service flow corresponding to the sequence point in the total topology sequence is a conflicting service flow, based on the urgency of the service flow, the directed graph, and the service flow characteristics and node characteristics, determine the sending time of the conflicting service flow; and, when it is determined that the service flow corresponding to the sequence point in the total topology sequence is a non-conflicting service flow, set the sending time of the non-conflicting service flow to the preset initial value.

It can be understood that before traversing each sequence point in the total topology sequence in the order of the total topology sequence, it is necessary to determine whether each service flow is a conflicting service flow or a non-conflicting service flow; when scheduling a non-conflicting service flow, the The sending time of the non-conflicting service flow is set to the initial value; when the conflicting service flow is scheduled, the sending time of the conflicting service flow is adjusted according to the urgency of the service flow, the characteristics of the service flow and the characteristics of the node, so as to ensure the effective scheduling process .

In addition, referring to FIG. 6, in one embodiment, the step of determining the sending time of the conflicting service flow based on the urgency of the service flow, the characteristics of the service flow, and the characteristics of the node in the embodiment shown in FIG. 5 includes but is not limited to The following steps:

Step 610, sort the conflicting service flows based on the urgency of the service flows;

Step 620, according to the conflicting service flow, the directed graph and the characteristics of the service flow, determine the cumulative transmission delay of the conflicting service flow in each node corresponding to the conflicting service flow;

Step 630, according to the conflicting service flow, the directed graph and the characteristics of the nodes, determine the minimum forwarding delay of the conflicting service flow in each node corresponding to the conflicting service flow;

Step 640, according to the cumulative transmission delay of the conflicting service flow and the minimum forwarding delay of the conflicting service flow, determine the initial sending time of the conflicting service flow in each node corresponding to the conflicting service flow;

Step 650, determine the time window according to the characteristics of the service flow and the characteristics of the nodes;

Step 660, based on the sorting of the conflicting service flows, determine the sending time of the conflicting service flows according to the initial sending time and the time window of the conflicting service flows.

It can be understood that, when scheduling conflicting service flows, the above conflict resolution mechanism is used for scheduling processing. Assuming that there are n conflicting service flows, the n conflicting service flows are first sorted according to the urgency of the service flows:

f ₁ .urgency >,...,f _i .urgency >,...,f _n .urgency;

Then, determine the cumulative transmission delay of the conflicting traffic flow

Then determine the minimum forwarding delay of the conflicting traffic flow

Then determine the initial sending time of the conflicting traffic flow

That is, the original sending time in step S15, the calculation formula is as follows:

Then, determine the message size of the service flow according to the characteristics of the service flow, determine the bandwidth according to the characteristics of the node, divide the message size of the service flow by the bandwidth to obtain the time window T _w ;

Finally, based on the sorting of the conflicting business flows, determine the sending time of the conflicting business flows, the formula is as follows:

In the sorting of conflicting service flows, if there is a conflicting service flow with a high degree of urgency before the conflicting service flow to be processed, the initial sending time of the conflicting service flow to be processed

A time window T _w is added to update the sending time of the conflicting service flow to be processed.

Referring to FIG. 7 , FIG. 7 is a schematic diagram of time delays required for calculating the urgency of service flows according to another embodiment of the present application.

Referring to Figures 8 to 11, Figure 8 is a schematic diagram of a node connection graph provided by another embodiment of the present application, Figure 9 is a schematic diagram of a directed graph provided by another embodiment of the present application, and Figure 10 is another embodiment of the present application A schematic diagram of the remaining directed graph is provided, and FIG. 11 is a schematic diagram of a de-ringed directed graph provided by another embodiment of the present application.

It should be noted that the steps of constructing a directed graph G'(V', E') based on a business flow set F are as follows:

For each service flow f _i ∈ F, set the route as f _i .path=[[v ₀ ,v ₁ ],…,[v _k ,v _l ],[v _l ,v _m ],…,[v _{j -1} , v _j ]],

(1) Take each edge in f _i .path as a vertex in G′(V′), for example, take [v _k , v _l ] as a vertex

(2) Two adjacent edges, such as [v _k , v _l ] and [v _l , v _m ], their two vertices in G′(V′)

and

has a directed edge

The number of vertices in the directed graph G'(V', E') is O(|E|); since the two adjacent edges of each business flow have one edge in G', the directed graph G'( The number of edges in V′, E′) is O(|F|*|E|); therefore, the time complexity of traversing each business flow to construct a directed graph G′(V′, E′) is O(| F|*|E|), the time complexity of topological sorting on the directed graph G'(V', E') is O(V'+E')=O(|F|*|E|), the topology The sorted output sequence is the topological sequence, which reflects the scheduling relationship between data links. For example, two adjacent links [v _k , v _l ] and [v _l , v _m ] in f _i have There is a directed edge in the directed graph G'(V', E')

from

arrive

So in topological sort

exist

In front of , when scheduling, schedule the vertices first

reschedule vertices

It can be understood that there are 6 service flows in the node connection diagram shown in Figure 8, which are:

f ₁ =[[v ₇ ,v ₁ ],[v ₁ ,v ₂ ],[v ₂ ,v ₃ ],[v ₃ ,v ₉ ]],

f ₂ =[[v ₈ ,v ₂ ],[v ₂ ,v ₃ ],[v ₃ ,v ₄ ],[v ₄ ,v ₁₀ ]],

f ₃ =[[v ₉ ,v ₃ ],[v ₃ ,v ₄ ],[v ₄ ,v ₅ ],[v ₅ ,v ₁₁ ]],

f ₄ =[[v ₁₀ ,v ₄ ],[v ₄ ,v ₅ ],[v ₅ ,v ₆ ],[v ₆ ,v ₁₂ ]],

f ₅ =[[v ₁₁ ,v ₅ ],[v ₅ ,v ₆ ],[v ₆ ,v ₁ ],[v ₁ ,v ₇ ]],

f ₆ =[[v ₁₂ ,v ₆ ],[v ₆ ,v ₁ ],[v ₁ ,v ₂ ],[v ₂ ,v ₈ ]],

Construct the directed graph G'(V',E') shown in Figure 9 from the path of the business flow, and perform topological sorting on the directed graph G'(V',E') to obtain the first topological sequence

After the directed graph G′(V′,E′) outputs the first topology sequence, the remaining directed graph shown in Figure 10 is obtained, and the urgency of the six service flows associated with the loops in the remaining directed graph is calculated, and the urgent The service flow with the smallest degree is used as the de-ring service flow, for example, f ₁ , use the de-ring service flow f ₁ to perform ring-breaking processing on the remaining directed graph, and obtain the de-ring directed graph as shown in Figure 11, which is useful for de-ring Perform topological sorting on the graph to obtain the second topological sequence

The vertex corresponding to the ring-free traffic flow on the remaining directed graph is

Connect the vertices corresponding to the first topological sequence, the second topological sequence, and the de-looped service flow in sequence, and then determine the total topological sequence

Each sequence point in the total topology sequence is traversed according to the order of the total topology sequence, and the service flow corresponding to the sequence point is scheduled and processed to determine the sending time of the service flow.

It is worth noting that with the second topological sequence of

and

For example, since

and

at node

The backward in-degree of the output is 0, therefore,

and

There is no scheduling relationship,

it is also fine.

In addition, referring to FIG. 12 , in one embodiment, after step 310 in the embodiment shown in FIG. 3 , it also includes but is not limited to the following steps:

Step 1210, when it is determined that the number of sequence points in the first topology sequence is equal to the number of vertices in the directed graph, based on the characteristics of the service flow and the characteristics of the nodes, determine the sending time of the service flow according to the first topology sequence.

It can be understood that, when it is determined that the number of sequence points of the first topological sequence is equal to the number of vertices of the directed graph, which is equivalent to the directed graph without loops, at this moment, the first topological sequence is equivalent to the total topological sequence in step 420 , using the scheduling method in step 420, the sending time of the service flow can be determined.

In addition, referring to FIG. 13 , in one embodiment, after step 110 in the embodiment shown in FIG. 1 , it also includes but is not limited to the following steps:

Step 1310, obtain the time slot set by the user;

Step 1320, based on the time slot, initialize the characteristics of the service flow and the characteristics of the node, wherein the characteristics of the service flow include at least the period of the service flow, the length of the message and the end-to-end delay, and the characteristics of the node include at least the service in the node The minimum forwarding delay of the flow is initialized to convert the period of the service flow, the length of the packet, the end-to-end delay and the minimum forwarding delay into integer multiples of the time slot.

It can be understood that the time slot is the minimum time unit for scheduling allocation, for example, the size of the time slot is set to 1us, that is, time_slot=1us; Converted to an integer multiple of time_slot:

(1) The period of business flow: for example, 1ms, which can be divided into 1000 time_slots;

(2) The length of the message: set to L, plus 4 bytes of CRC+12 bytes of minimum inter-frame space+7 bytes of preamble+1 byte of frame start character, the actual length is L+ 24 bytes; if the port speed is 1Gbps, the number of time_slots it occupies is

in,

round up;

(3) End-to-end delay of business flow: set to delat _{end_to_end} , the number of time_slots it occupies is

in,

rounded down;

(4) The minimum forwarding delay of the service flow in the node: refers to the minimum forwarding delay required for the service flow to be forwarded from the current node to the subsequent node. The calculation is as follows: The storage delay sdelay indicates that the message is received by the switch from the first bit The time until the entire packet is stored in the switch cache, the forwarding delay fdelay represents the time from the sending time to the time when the switch sends the first bit of the packet to the link, and the link delay ldelay represents the time caused by the length of the link delay, so the minimum forwarding delay of the service flow in the node = sdelay+fdelay+ldelay, the number of time_slots occupied is

in,

Round up.

It should be noted that after the time slot is set, in step S15, if there is a conflict in the delivery of the service flows, the sending time of the service flow with a lower urgency is updated, and the formula for calculating the sending time of the service flow _fi with a lower urgency is modified for:

in,

Since the time slot is the smallest time unit for scheduling allocation, the sending time of the business flow

Update to original sending time

Increment by 1.

It is worth noting that the introduction of time slots is to simplify scheduling, because when resolving conflicts, if the business flow falls in different time slots, there will be no conflicts; if time slots are not considered, the packet needs to be considered when resolving conflicts length, the scheduling is more complex, because any overlap when sending service flow packets will cause conflicts.

In addition, referring to FIG. 14 , in one embodiment, after step 110 in the embodiment shown in FIG. 1 , it also includes but is not limited to the following steps:

Step 1410, based on the characteristics of the service flow set and the path of the service flow, use the node at the starting point of the path as the sending terminal, and determine the number of service flows corresponding to the sending terminal;

Step 1420, connecting the sending terminal to the virtual terminal, wherein the number of virtual terminals is equal to the number of service flows corresponding to the sending terminal, and the link length between the virtual terminal and the sending terminal is zero;

Step 1430, setting the sending time of the virtual terminal to a preset initial value.

And, referring to FIG. 15 , FIG. 15 is a schematic diagram of a sending terminal connected to a virtual terminal provided by another embodiment of the present application.

It should be noted that the connection to the virtual terminal is to deal with the situation that the sending terminal has multiple service flows, and the sending time of each service flow can be set to zero; if the virtual terminal is not connected, when the sending terminal sends multiple service flows, the sending If the time is set to zero, a conflict will be sent, and the conflict resolution mechanism can be applied for processing.

It can be understood that, based on the above-mentioned embodiments of the present application, the steps of the time-triggered scheduling method are as follows:

Step S151: set the size time_slot of the time slot;

Step S152: according to the size of the time_slot, convert the period of the service flow, the length of the message and the minimum forwarding delay into an integer multiple of the time_slot;

Step S153: Connect the sending terminal to the virtual terminal, and adjust the initial node of the service flow;

Step S154: traverse the route of each service flow, from the sending terminal to the receiving terminal, construct a directed graph G'(V',E') as shown in Figure 9: for example, route f _i .path=[[v ₀ , v ₁ ],...,[v _k ,v _l ],[v _l ,v _m ],...,[v _j-1 ,v _j ]], edge [v _k ,v _l ] as a vertex

Two adjacent edges [v _k , v _l ] and [v _l , v _m ] correspond to two vertices in G′(V′,E′)

and

There is a directed edge between them

Step S155: topologically sort the directed graph G'(V', E'), and output the topological sequence;

Step S156: Set the sending time of the service flow sending terminal to 0, then traverse the service flow on each edge along the topological sequence, and resolve the conflict according to the above-mentioned conflict resolution mechanism. The topological sequence ensures that when the service flow on the current edge is scheduled, these The preceding edges of the service flow have been scheduled;

Step S157: After executing step S156, if there are still unscheduled business flows, it means that there is a loop in the directed graph G'(V', E'), and the directed graph G'(V', E') needs to be broken ring processing;

Step S158: Adjust the sending time of the service flow in the sending terminal according to the terminal sending time adjustment theorem;

It can be understood that the calculation of the time complexity of the time-triggered scheduling method in the above embodiments of the present application is as follows:

Steps S151 and S152 initialize algorithm parameters, and the time complexity is constant;

Step S153 introduces a sending terminal for each service flow through the virtual terminal, and the time complexity is O(|F|);

Step S154 constructs a directed graph G'(V', E'), with a time complexity of O(|F|*|E|);

Step S155 performs topological sorting on G'(V', E'), and the time complexity is O(V'+E')=O(|F|*|E|);

Step S156 performs business flow scheduling along the topology sequence, and the time complexity is

The time complexity of step S157 breaking the loop scheduling is

Step S158 adjusts each service flow along the route at most, so the time complexity is O(|F|*|E|);

Therefore, the time complexity of the time-triggered scheduling method is

It is a polynomial time complexity. Compared with the satisfiability solver solution method with exponential time complexity, the time-triggered scheduling method in the embodiment of the present application has a lower time complexity, which effectively speeds up the scheduling of service flows.

As shown in FIG. 16 , FIG. 16 is a flowchart of a time-triggered scheduling method provided by another embodiment of the present application. The time-triggered scheduling method can be applied to nodes, and the time-triggered scheduling method includes but not limited to the following steps:

Step 1610, receiving the sending time from the central controller, wherein the sending time is determined by the directed graph and the urgency of the business flow, the directed graph is constructed by the path of the business flow, and the urgency of the business flow is obtained by the central controller determined by the characteristics of each service flow in the preset service flow set, the path of the service flow, and the characteristics of each node on the path of the service flow;

Step 1620, transmit the corresponding service flow in the service flow set according to the sending time.

It is understandable that the node will monitor the configuration information of the central controller. When the node receives the configuration information including the sending time, the node interprets and executes these configurations, and sends the service flow at a precise time point; based on this, the service flow can be passed Construct a directed graph based on the path of the business flow, and then determine the urgency of the business flow. Compared with the solution method of the satisfiability solver with exponential time complexity, the sending time of the business flow can be determined through the directed graph and the urgency of the business flow, which can reduce the Time complexity, effectively speeding up the scheduling of business flows, providing an effective guarantee for a series of functions such as online scheduling and dynamic configuration of time-sensitive networks, and being able to precisely control the sending time of business flows, providing a basis for exploring better services with better service quality Stream scheduling results provide the possibility of precise regulation.

Referring to FIG. 17 , FIG. 17 is a schematic diagram of implementation in 802.1Qcc provided by another embodiment of the present application.

It can be understood that nodes include but are not limited to sending terminals, receiving terminals, and switches; after the central controller determines the sending time of each service flow, it needs to post-process the sending time and convert it into node configuration information, through YANG/ The NETCONF protocol is configured in the node, and the node interprets and executes these configurations, and sends the service flow at a precise time point to realize the deterministic transmission of the time-sensitive network.

In addition, referring to FIG. 18 , an embodiment of the present application also provides a node.

The node includes: one or more processors and memories, and one processor and memories are taken as an example in FIG. 18 . The processor and the memory may be connected through a bus or in other ways, and connection through a bus is taken as an example in FIG. 18 .

As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs and non-transitory computer-executable programs, such as the time-triggered scheduling method applied to nodes in the above embodiments of the present application. The processor implements the time-triggered scheduling method applied to the nodes in the above embodiments of the present application by running the non-transitory software program and the program stored in the memory.

The memory may include a program storage area and a data storage area, where the program storage area may store the operating system and at least one application required by the function; the data storage area may store and execute the time-triggered scheduling method applied to the node in the above-mentioned embodiments of the present application required data etc. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory may include memory located remotely from the processor, and these remote memories may be connected to the node through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The non-transient software programs and programs required to implement the time-triggered scheduling method applied to nodes in the above-mentioned embodiments of the present application are stored in the memory. When executed by one or more processors, the implementation of the above-mentioned embodiments of the present application used The time-triggered scheduling method of a node, for example, executes steps 1610 to 1620 of the method in FIG. Determined, the directed graph is constructed by the path of the business flow, and the urgency of the business flow is determined by the characteristics of each business flow in the preset business flow set obtained by the central controller, the path of the business flow, and each It is determined by the characteristics of the node; the corresponding service flow in the service flow set is transmitted according to the sending time. Based on this, a directed graph can be constructed through the path of the business flow, and then the urgency of the business flow can be determined. Compared with the solution method of the satisfiability solver with exponential time complexity, the business can be determined through the directed graph and the urgency of the business flow. The sending time of the flow can reduce the time complexity, effectively speed up the scheduling of the business flow, and provide an effective guarantee for a series of functions such as online scheduling and dynamic configuration of the time-sensitive network. , Service flow scheduling results with better service quality provide the possibility of precise regulation.

In addition, referring to FIG. 19 , an embodiment of the present application also provides an electronic device.

The electronic device includes: one or more processors and memories, and one processor and memories are taken as an example in FIG. 19 . The processor and the memory may be connected through a bus or in other ways. In FIG. 19, connection through a bus is taken as an example.

As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs and non-transitory computer-executable programs, such as the time-triggered scheduling method applied to the central controller in the above embodiments of the present application. The processor implements the time-triggered scheduling method applied to the central controller in the above embodiments of the present application by running the non-transitory software program and the program stored in the memory.

The memory can include a program storage area and a data storage area, wherein the program storage area can store the operating system and at least one application program required by the function; the data storage area can store the time triggers applied to the central controller in the above-mentioned embodiments of the present application. The data required by the dispatch method, etc. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory may include memory located remotely from the processor, and these remote memories may be connected to the electronic device via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The non-transient software programs and programs required to implement the time-triggered scheduling method applied to the central controller in the above-mentioned embodiments of the present application are stored in the memory, and when executed by one or more processors, the above-mentioned embodiments of the present application are executed. The time-triggered scheduling method applied to the central controller, for example, executes method steps 110 to 150 in Fig. 1 described above, method steps 210 to 260 in Fig. 2 , method steps 310 to 360 in Fig. 3 , Method step 410 to step 420 in Fig. 4, method step 510 to step 520 in Fig. 5, method step 610 to step 660 in Fig. 6, method step 1210 in Fig. 12, method step 1310 to step in Fig. 13 1320, step 1410 to step 1430 of the method in FIG. 14 , the central controller obtains the characteristics of each service flow in the preset service flow set, the path of the service flow, and the characteristics of each preset node on the path of the service flow ; Construct a directed graph according to the path of the business flow, wherein the vertices of the directed graph are determined by two adjacent nodes on the path of the business flow; according to the directed graph, the characteristics of the business flow and the characteristics of the nodes, determine the Urgency; determine the sending time of the service flow according to the urgency of the directed graph and the service flow; send the sending time to the node, so that the node transmits the corresponding service flow in the service flow set according to the sending time. Based on this, a directed graph can be constructed through the path of the business flow, and then the urgency of the business flow can be determined. Compared with the solution method of the satisfiability solver with exponential time complexity, the business can be determined through the directed graph and the urgency of the business flow. The sending time of the flow can reduce the time complexity, effectively speed up the scheduling of the business flow, and provide an effective guarantee for a series of functions such as online scheduling and dynamic configuration of the time-sensitive network. , Service flow scheduling results with better service quality provide the possibility of precise regulation.

In addition, an embodiment of the present application also provides a computer-readable storage medium, the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed by a processor or a controller, for example, by the above-mentioned Execution by a processor in the embodiment of the electronic device can cause the above-mentioned processor to execute the time-triggered scheduling method applied to the central controller in the above-mentioned embodiment, for example, execute the method steps 110 to 150 in FIG. 1 described above, and FIG. Method step 210 to step 260 in 2, method step 310 to step 360 in Fig. 3, method step 410 to step 420 in Fig. 4, method step 510 to step 520 in Fig. 5, method step 610 in Fig. 6 To step 660, method step 1210 in FIG. 12, method step 1310 to step 1320 in FIG. 13, method step 1410 to step 1430 in FIG. The characteristics of the business flow, the path of the business flow, and the characteristics of each preset node on the path of the business flow; construct a directed graph according to the path of the business flow, where the vertices of the directed graph are composed of two adjacent nodes on the path of the business flow and determine; according to the directed graph, the characteristics of the service flow and the characteristics of the nodes, determine the urgency of the service flow; determine the sending time of the service flow according to the urgency of the directed graph and the service flow; send the sending time to the node, so that The node transmits the corresponding service flow in the service flow set according to the sending time; or executes the time-triggered scheduling method applied to the node in the above embodiment, for example, executes steps 1610 to 1620 of the method in Figure 16 described above, and the node receives the information from The sending time of the central controller, where the sending time is determined by the directed graph and the urgency of the business flow, the directed graph is constructed by the path of the business flow, and the urgency of the business flow is determined by the preset service obtained by the central controller The characteristics of each service flow in the flow set, the path of the service flow and the characteristics of each node on the path of the service flow are determined; the corresponding service flow in the service flow set is transmitted according to the sending time. Based on this, a directed graph can be constructed through the path of the business flow, and then the urgency of the business flow can be determined. Compared with the solution method of the satisfiability solver with exponential time complexity, the business can be determined through the directed graph and the urgency of the business flow. The sending time of the flow can reduce the time complexity, effectively speed up the scheduling of the business flow, and provide an effective guarantee for a series of functions such as online scheduling and dynamic configuration of the time-sensitive network. , Service flow scheduling results with better service quality provide the possibility of precise regulation.

The embodiment of the present application includes: obtaining the characteristics of each service flow in the preset service flow set, the path of the service flow, and the characteristics of each preset node on the path of the service flow; according to the characteristics of the service flow A path constructs a directed graph, wherein the vertices of the directed graph are determined by two adjacent nodes on the path of the service flow; according to the directed graph, the characteristics of the service flow and the nodes characteristics, determine the urgency of the service flow; determine the sending time of the service flow according to the directed graph and the urgency of the service flow; send the sending time to the node, so that the The node transmits the corresponding service flow in the service flow set according to the sending time. According to the solution provided by the embodiment of the present application, the directed graph can be constructed through the path of the business flow, and then the urgency of the business flow can be determined. Compared with the solution method of the satisfiability solver with exponential time complexity, the directed graph and the business The urgency of the flow determines the sending time of the service flow, which can reduce the time complexity, effectively speed up the scheduling of the service flow, provide an effective guarantee for a series of functions such as online scheduling and dynamic configuration of the time-sensitive network, and can precisely control the sending of the service flow Time provides the possibility of precise control for exploring better business flow scheduling results with better service quality.

Those skilled in the art can understand that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware and an appropriate combination thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit . Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). As known to those of ordinary skill in the art, the term computer storage media includes both volatile and nonvolatile media implemented in any method or technology for storage of information, such as computer readable instructions, data structures, program modules, or other data. permanent, removable and non-removable media. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cartridges, tape, magnetic disk storage or other magnetic storage devices, or can Any other medium used to store desired information and which can be accessed by a computer. In addition, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media .

The above is a description of several embodiments of the present application, but the present application is not limited to the above-mentioned embodiments. Those skilled in the art can also make various equivalent deformations or replacements without violating the spirit of the present application. Any modification or substitution is included within the scope defined by the claims of the present application.

Claims

A time-triggered scheduling method applied to a central controller, the method comprising:

Acquire the characteristics of each service flow in the preset service flow set, the path of the service flow, and the characteristics of each preset node on the path of the service flow;

Constructing a directed graph according to the path of the service flow, wherein the vertices of the directed graph are determined by two adjacent nodes on the path of the service flow;

determining the urgency of the service flow according to the directed graph, the characteristics of the service flow, and the characteristics of the node;

determining the sending time of the service flow according to the directed graph and the urgency of the service flow;

Sending the sending time to the node, so that the node transmits the corresponding service flow in the service flow set according to the sending time.
The method according to claim 1, wherein the determining the urgency of the service flow according to the directed graph, the characteristics of the service flow and the characteristics of the node comprises:

Based on the directed graph, determine the service flow, current node, and subsequent node corresponding to each vertex in the directed graph, where the current node is two adjacent nodes on the path of the service flow the previous node, and the subsequent node is the latter of the two adjacent nodes on the path of the service flow;

determining the end-to-end delay of the service flow according to the directed graph, the characteristics of the service flow and the characteristics of the node;

determining the minimum forwarding delay of the service flow according to the characteristics of the current node, the subsequent node, and the node;

determining the cumulative transmission delay of the service flow corresponding to the current node according to the directed graph and the characteristics of the service flow;

Determine the minimum transmission delay of the service flow corresponding to the current node according to the directed graph and the minimum forwarding delay;

The urgency of the service flow is determined according to the end-to-end delay of the service flow, the minimum forwarding delay of the service flow, the cumulative transmission delay of the service flow, and the minimum transmission delay of the service flow.
The method according to claim 1, wherein the determining the sending time of the service flow according to the directed graph and the urgency of the service flow comprises:

performing topological sorting on the directed graph to obtain a first topological sequence;

When it is determined that the number of sequence points of the first topological sequence is less than the number of vertices of the directed graph, determining the remaining directed graph according to the first topological sequence and the directed graph;

Taking the service flow with the lowest degree of urgency among the service flows corresponding to each vertex in the remaining directed graph as the de-loop service flow;

determining a de-looped directed graph according to the de-looped service flow and the remaining directed graph;

performing topological sorting on the de-ringed directed graph to obtain a second topological sequence;

Based on the characteristics of the service flow and the characteristics of the node, determine the sending time of the service flow according to the first topology sequence, the second topology sequence and the de-looped service flow.
The method according to claim 3, wherein, based on the characteristics of the service flow and the characteristics of the node, the determined according to the first topology sequence, the second topology sequence and the de-looped service flow The sending time of the above business flow, including:

determining a total topology sequence according to the first topology sequence, the second topology sequence and the de-looped service flow;

Traverse each sequence point in the total topology sequence according to the order of the total topology sequence, and perform scheduling processing on the service flow corresponding to the sequence point, so as to determine the sending time of the service flow.
The method according to claim 4, wherein, traversing each sequence point in the total topology sequence according to the order of the total topology sequence, and performing scheduling processing on the service flow corresponding to the sequence point, so as to determine the The sending time of the business flow, including:

Based on the directed graph, determine a conflicting service flow and a non-conflicting service flow from a set of service flows, wherein the conflicting service flow is a service flow corresponding to a vertex with an in-degree greater than one in the directed graph, and the The non-conflicting service flow is a service flow in the service flow set except the conflicting service flow;

Traverse each sequence point in the total topology sequence according to the order of the total topology sequence, and when it is determined that the service flow corresponding to the sequence point in the total topology sequence is a conflicting service flow, based on the urgency of the service flow, the According to the directed graph, the characteristics of the service flow and the characteristics of the node, determine the sending time of the conflicting service flow; and, when it is determined that the service flow corresponding to the sequence point in the total topology sequence is a non-conflicting service flow , setting the sending time of the non-conflicting service flow to a preset initial value.
The method according to claim 5, wherein the sending time of the conflicting service flow is determined based on the urgency of the service flow, the directed graph, the characteristics of the service flow and the characteristics of the node ,include:

sorting the conflicting service flows based on the urgency of the service flows;

determining the cumulative transmission delay of the conflicting service flow in each node corresponding to the conflicting service flow according to the conflicting service flow, the directed graph, and the characteristics of the service flow;

determining the minimum forwarding delay of the conflicting service flow in each node corresponding to the conflicting service flow according to the conflicting service flow, the directed graph, and the characteristics of the node;

determining the initial sending time of the conflicting service flow in each node corresponding to the conflicting service flow according to the accumulated transmission delay of the conflicting service flow and the minimum forwarding delay of the conflicting service flow;

determining a time window according to the characteristics of the service flow and the characteristics of the node;

Based on the ranking of the conflicting service flows, the sending time of the conflicting service flows is determined according to the initial sending time of the conflicting service flows and the time window.
The method according to claim 3, wherein, after the step of performing topological sorting on the directed graph to obtain the first topological sequence, further comprising:

When it is determined that the number of sequence points of the first topology sequence is equal to the number of vertices of the directed graph, based on the characteristics of the service flow and the characteristics of the node, determine the sending of the service flow according to the first topology sequence time.
The method according to claim 1, wherein said obtaining the characteristics of each service flow in the preset service flow set, the path of the service flow, and the characteristics of each preset node on the path of the service flow After the steps, also include:

Get the time slot set by the user;

Based on the time slot, initialize the characteristics of the service flow and the characteristics of the node, wherein the characteristics of the service flow include at least the period of the service flow, the length of the message and the end-to-end delay, and the node The characteristics include at least the minimum forwarding delay of the service flow in the node, and the initialization is used to convert the cycle of the service flow, packet length, end-to-end delay and minimum forwarding delay into the time Integer multiple of slots.
The method according to claim 1, wherein said obtaining the characteristics of each service flow in the preset service flow set, the path of the service flow, and the characteristics of each preset node on the path of the service flow After the steps, also include:

Based on the characteristics of the service flow set and the path of the service flow, using the node at the starting point of the path as a sending terminal, and determining the number of the service flows corresponding to the sending terminal;

Connecting the sending terminal to a virtual terminal, wherein the number of virtual terminals is equal to the number of service flows corresponding to the sending terminal, and the link length between the virtual terminal and the sending terminal is zero;

Set the sending time of the virtual terminal to a preset initial value.
A time-triggered scheduling method applied to a node, the method comprising:

receiving the sending time from the central controller, wherein the sending time is determined by a directed graph and the urgency of the service flow, the directed graph is constructed by the path of the service flow, and the urgency of the service flow Determined by the characteristics of each service flow in the preset service flow set obtained by the central controller, the path of the service flow, and the characteristics of each node on the path of the service flow;

Transmit the corresponding service flow in the service flow set according to the sending time.
A node, comprising: a memory, a processor, and a computer program stored on the memory and operable on the processor, wherein the time-triggered scheduling method according to claim 10 is implemented when the processor executes the computer program .
An electronic device, comprising: a memory, a processor, and a computer program stored on the memory and operable on the processor, wherein, when the processor executes the computer program, any one of claims 1 to 9 is realized The time-triggered scheduling method described above.
A computer-readable storage medium, wherein the computer-readable storage medium stores a computer-executable program, and the computer-executable program is used to make a computer execute the time-triggered scheduling according to any one of claims 1 to 9 method, or the time-triggered scheduling method as claimed in claim 10.