A Routing Method for Reliability Enhancement in a Deterministic Network

Abstract

The present invention belongs to the technical field of deterministic networks, and discloses a routing selection method for reliability enhancement in a deterministic network, including: obtaining network topology information and deterministic flow attributes, modeling the network topology as a directed graph, and defining key parameters of the deterministic flow. Then, considering the transient error probability of the link, constructing a set of minimum shortest paths that can meet the flow reliability requirements. Based on the set of minimum paths, finding all packet redundancy transmission combinations that meet the flow reliability, and combining with the cyclic queue forwarding mechanism of the deterministic network to determine the optimal combination scheme of path redundancy, transmission volume redundancy, and injection time slots. Then, calculating the optimal scheduling score of each flow and preferentially scheduling the flow with the highest score. In addition, the present invention also proposes corresponding objective functions and constraint conditions to ensure that the deterministic delay and time slot capacity requirements are met during the traffic scheduling process. The present invention can effectively improve the reliability of traffic transmission in the network and the network scheduling performance.

Description

Technical Field

[0001] The present invention belongs to the technical field of deterministic networks, and particularly relates to a routing selection method for enhancing reliability in a deterministic network. Background Art

[0002] With the rapid development of industrial Internet, intelligent manufacturing, and industry, the performance requirements of industrial networks are increasing day by day. To support real-time control and efficient collaboration, low latency, low jitter, and high reliability have become key requirements. However, the "best effort" mode of traditional Ethernet cannot provide the necessary transmission determinism and is difficult to meet strict latency and reliability standards. This uncertainty may cause production line stagnation, equipment failures, and even safety risks in industrial environments. Therefore, to meet network requirements, Deterministic Networking (DetNet) has emerged, providing predictable network behavior and ensuring reliable transmission of critical data.

[0003] Deterministic networks achieve end-to-end low latency and high reliability transmission by combining advanced network technologies. To address transient faults that may occur in the network and enhance the reliability of data transmission, the Frame Replication and Elimination for Reliability (FRER) mechanism is introduced in deterministic networks. FRER ensures that even if an error occurs on a certain path, the same data packet can still be successfully transmitted on other paths by performing redundant replication and transmission on multiple paths of the data stream, thereby improving the overall reliability of the network. This mechanism can effectively handle transient error problems such as link failures and bit errors, ensuring that data can be delivered to the destination on time and safely. By introducing FRER, deterministic networks can meet the high reliability requirements in industrial applications and avoid production failures and safety hazards caused by network transmission uncertainty.

[0004] However, although FRER can improve the reliability of the network through multi-path transmission, there are also some obvious deficiencies. First, the FRER scheme relies on redundant path transmission, which may lead to waste of network bandwidth. Especially in the case of limited network resources, this method may exacerbate network congestion. Second, FRER increases the complexity and latency of the network during the data packet replication and elimination process. Especially in large-scale networks, these operations may result in additional processing overhead. In addition, FRER cannot perform refined resource allocation for different traffic demands, lacks targeted optimization strategies, and is difficult to maintain high network efficiency in high-traffic scenarios. Summary of the Invention

[0005] The objective of the present invention is to provide a routing method with enhanced reliability in a deterministic network to solve the problems existing in the above-mentioned prior art.

[0006] To achieve the above objective, the present invention provides a routing method with enhanced reliability in a deterministic network, including:

[0007] Obtain network topology structure data and a set of deterministic flows, where the set of deterministic flows consists of several deterministic flows; construct a directed graph based on the network topology structure data, and the directed graph consists of a set of forwarding devices in the network topology and a set of links connecting the forwarding devices;

[0008] Calculate the transient failure probability of a single data packet of a deterministic flow on a link, and determine the set of minimum shortest paths that meet the flow reliability requirements based on the calculated transient failure probability;

[0009] Obtain path redundancy based on the set of minimum shortest paths and the maximum number of transmission paths of the deterministic flow, and obtain the injection time slot offset of the deterministic flow data packet on each path based on the CQF scheduling mechanism;

[0010] Determine a data packet transmission scheme combination based on the injection time slot offset, path redundancy, and transmission volume redundancy on a single path;

[0011] Calculate the optimal scheduling score of each deterministic flow based on the data packet transmission scheme combination, determine the optimal deterministic flow based on the optimal scheduling score corresponding to each deterministic flow, and schedule the optimal deterministic flow.

[0012] Optionally, the deterministic flow is specifically:

[0013] f i =(f i .S,f i .D,f i .p,f i .l,f i .d,f i .R,f i .W,f i .r)

[0014] In the formula, f i .S represents the source node of the deterministic flow f i , f i .D represents the destination node of the deterministic flow f i , f i .p represents the sending period of the deterministic flow f i , f i .l represents the length of data sent each time by the deterministic flow f i , f i.d represents the maximum end-to-end delay allowed by the deterministic flow f, f i .R represents the set of predefined routes for the deterministic flow f i , f i .R = {r1, r2, r3, …, r n} represents that the set of predefined routes consists of multiple alternative routes, r n = {e1, e2, … e l}, indicating that the alternative route consists of several loop-free forwarding links in E, f i .R is initially defined as empty, f i .W represents the maximum number of transmission paths for the deterministic flow f i , f i .r represents the minimum reliability index of the deterministic flow f i .

[0015] Optionally, calculate the transient failure probability of a single data packet of the deterministic flow on the link, specifically including:

[0016]

[0017] In the formula, is the transient failure of a single data packet of the deterministic flow f i on the path r j , λ is a constant of the hardware failure rate, l is the length of each data transmission of the deterministic flow f i , e k is any link on the path r j , lr k represents the data transmission speed of e k . is the transient failure probability of a single data packet copy of the deterministic flow f i transmitted on multiple paths of the set of predefined routes.

[0018] Optionally, determine the set of minimum shortest paths that meet the flow reliability requirements based on the calculated transient failure probability, specifically including:

[0019] Take the current shortest path where the transient failure probability of a single data packet of the deterministic flow on the link is greater than or equal to the minimum reliability index as the set of minimum shortest paths that meet the flow reliability requirements.

[0020] Optionally, the path redundancy is specifically:

[0021]

[0022] In the formula, represents selecting the path r in the set of minimum shortest paths R i ​j As for determining the transmission path of flow f i , it means not to select, f i .W is the maximum number of transmission paths of deterministic flow f i .

[0023] Optionally, the transmission volume redundancy is as follows:

[0024]

[0025] In the formula, represents the number of data packet copies of deterministic flow f j transmitted on path r i , when , When ,

[0026] Optionally, for the CQF scheduling mechanism, obtaining the injection slot offset of the deterministic flow data packet on each path specifically includes:

[0027] Based on the CQF scheduling mechanism, define the injection slot offset of the deterministic flow data packet on each path. With the goal of minimizing flow conflict, traverse all injection slot offsets and select the slot with the largest remaining network slot capacity value as the injection slot offset of the path.

[0028] Optionally, calculating the best scheduling score of each deterministic flow specifically includes:

[0029]

[0030] In the formula, Score(H i ,M i ,o i ) is the best scheduling score, α is the weight considering the maximum remaining capacity of scheduling, Res(o i ) is the maximum remaining capacity according to the combination path redundancy H i , transmission volume redundancy M i and injection slot offset o i , Cap is the maximum amount of data that can be sent in a single slot of the network, β is the weight considering the resources occupied by itself, represents the total amount of resources occupied by flow f i scheduled according to a combination H i ,M i and o i , is the number of data packet copies of flow f j transmitted on path r i , is for path rj hop count, f i .l is the length of each data transmission of flow f i , and max(F) is the maximum resource occupancy of a single flow in F.

[0031] Optionally, the scheduling of the optimal determined flow specifically includes:

[0032] Determine the constraint conditions and construct an objective function with the goal of maximizing the number of successfully scheduled network flows, and schedule the optimal determined flow based on the objective function.

[0033] Optionally, the objective function is:

[0034] max∑S i

[0035] In the formula, S i indicates whether flow f i is successfully scheduled, and S i = 1 indicates successful scheduling;

[0036] The constraint conditions include deterministic delay constraint, injection time slot constraint, and time slot capacity constraint.

[0037] The technical effect of the present invention is:

[0038] By constructing a routing selection method with reliability guarantee, the present invention significantly improves the reliability and transmission efficiency in a deterministic network, solves the problem of data loss caused by link transient failures, and ensures low delay, low jitter, and high reliability during traffic transmission. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0040] The drawings forming a part of this application are used to provide a further understanding of this application. The schematic embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation to this application. In the drawings:

[0041] Figure 1 is a flowchart of a routing selection method for enhancing reliability in a deterministic network in an embodiment of the present invention;

[0042] Figure 2 is a preliminary experimental effect diagram of a routing selection method for enhancing reliability in a deterministic network in an embodiment of the present invention. Detailed Implementation Modes

[0043] The various exemplary implementation modes of the present invention will now be described in detail. This detailed description should not be considered as a limitation on the present invention, but rather as a more detailed description of certain aspects, characteristics, and implementation schemes of the present invention.

[0044] It should be understood that the terms described in the present invention are only for describing specific implementation modes and are not used to limit the present invention. Additionally, for the numerical ranges in the present invention, it should be understood that each intermediate value between the upper and lower limits of the range is also specifically disclosed. Each intermediate value within any stated value or stated range, as well as each smaller range between any other stated value or intermediate value within the stated range, is also included in the present invention. The upper and lower limits of these smaller ranges may be independently included or excluded from the range.

[0045] Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present invention pertains. Although the present invention only describes preferred methods, any method similar or equivalent to those described herein may also be used in the implementation or testing of the present invention. All documents mentioned in this specification are incorporated by reference to disclose and describe the methods related to the said documents. In case of conflict with any incorporated document, the content of this specification shall prevail.

[0046] Without departing from the scope or spirit of the present invention, various improvements and changes can be made to the specific implementation modes of the specification of the present invention, which are obvious to those skilled in the art. Other implementation modes obtained from the specification of the present invention are obvious to those skilled in the art. The specification and examples of this application are only exemplary.

[0047] Regarding the use of "comprising", "including", "having", "containing", etc. in this article, they are all open-ended terms, meaning including but not limited to.

[0048] It should be noted that, without conflict, the embodiments and features in the embodiments of this application can be combined with each other. The following will refer to the accompanying drawings and combine with embodiments to detail this application.

[0049] Embodiment 1

[0050] As Figure 1 - Figure 2As shown in the figure, in this embodiment, a routing selection method for enhancing reliability in a deterministic network is provided, including: obtaining network topology structure data and a set of deterministic flows, where the set of deterministic flows is composed of several deterministic flows; constructing a directed graph based on the network topology structure data, where the directed graph is composed of a set of forwarding devices in the network topology and a set of links connecting the forwarding devices; calculating the transient failure probability of a single data packet of a deterministic flow on a link, and determining a set of minimum shortest paths that meet the flow reliability requirements based on the calculated transient failure probability; obtaining path redundancy based on the set of minimum shortest paths and the maximum number of transmission paths of the deterministic flow, obtaining the injection time slot offset of the deterministic flow data packet on each path based on the CQF scheduling mechanism, and determining a data packet transmission scheme combination based on the injection time slot offset, path redundancy, and transmission volume redundancy on a single path; calculating the optimal scheduling score of each deterministic flow based on the data packet transmission scheme combination, determining the optimal deterministic flow based on the optimal scheduling score corresponding to each deterministic flow, and scheduling the optimal deterministic flow.

[0051] This embodiment discloses a routing selection method for enhancing reliability in a deterministic network, aiming to solve the reliability problem caused by link transient failures. The method includes the following steps: First, obtain network topology information and the characteristic attributes of deterministic flows, model the network topology as a directed graph, and define key parameters related to deterministic flows. Next, consider the transient error probability of links and construct a set of minimum shortest paths that can meet the traffic reliability requirements. Based on this set of minimum paths, find all redundant transmission combinations that can achieve flow reliability, and combine with the cyclic queue forwarding mechanism of the deterministic network to determine the optimal combination scheme of path redundancy, transmission volume redundancy, and injection time slot. Then, calculate the optimal scheduling score of each flow and preferentially schedule the flow with the highest score. In addition, this embodiment also proposes corresponding objective functions and constraint conditions to ensure that the deterministic delay and time slot capacity requirements are met during the traffic scheduling process.

[0052] In view of this, the main purpose of this embodiment is to propose an effective routing selection method to improve the reliability in a deterministic network. The method aims to solve the network instability problem caused by link transient failures and ensure the reliable transmission and real-time performance of data streams. By optimizing the network topology model and redundant transmission strategies, network performance with low latency and high reliability is achieved, thereby providing technical support for high-demand applications such as industrial Internet. Specifically, it includes the following steps:

[0053] In the first step, obtain network topology structure information and relevant attributes of deterministic flows, and establish a corresponding mathematical model to describe the network topology and deterministic flow characteristics, specifically including:

[0054] The network topology is modeled as a directed graph G=(V, E), where V is the set of forwarding devices, and E=(e1, e2, …, eN ) is the set of links connecting forwarding devices, representing the links in the topology. There are five types of delays in the forwarding system: processing delay d proc , transmission delay d tran , propagation delay d prop , queuing delay d queue and clock synchronization delay d sync .

[0055] The set of all deterministic flows in the network is defined as F. For each deterministic flow f i , it is defined as a tuple f i = (f i .S, f i .D, f i .p, f i .l, f i .d, f i .R, f i .W, f i ). Among them, f i .S represents the source node of flow f i , f i .D represents the destination node of flow f i , f i .p represents the sending period of flow f i , f i .l represents the length of each data transmission of flow f i , f i .d represents the maximum end-to-end delay allowed for flow f, f i .R represents the set of preset routes of flow f i , f i .R = {r1, r2, r3,..., r n} represents that the set of preset routes consists of multiple alternative routes, r n = {e1, e2,... e l}, indicates that the alternative route consists of several loop-free forwarding links in E, f i .R is initially defined as empty, f i .W represents the maximum number of transmission paths of flow f i , f i .r represents the minimum reliability index of flow f i .

[0056] According to the sending periods of all flows in the flow set F, the hyper-period T C = LCM(f i .p), f i ∈ F indicates that the hyper-period is the least common multiple of all flow periods, and flow scheduling is performed in cycles of the hyper-period. Define the slot length Ts = GCD(f i .p), f i ∈F means that the slot length is the greatest common divisor of all flow periods, and the slot is the minimum time metric for flow scheduling.

[0057] In the second step, considering the transient failure probability of the link, determine the set of minimum shortest paths that meet the flow reliability requirements, specifically including

[0058] Transient failures are common failures in network communication that cause components to fail for a short time and then recover, including bit errors, temporary link failures, and temporary synchronization errors. Denote the transient failure of a single data packet of flow f i on path r j . Among them, λ is a constant representing the hardware failure rate, len is the length of each data transmission of flow f i , e k is any link on path r j , and lr k represents the data transmission speed of e k . Denote the transient failure probability of a single data packet copy of flow f i transmitted on multiple paths in the preset routing set. Find the minimum shortest routing space, that is In this embodiment, by adding the current shortest path of flow f i to R i , calculate until it is less than f i .r, then R i is a routing set composed of multiple short paths of flow f i . Using all paths in R i to transmit a single data packet copy of flow f i can ensure that the transient failure probability meets the reliability requirements of flow f i .

[0059] In the third step, based on the set of minimum paths, analyze and find all combinations of data packet redundant transmission schemes that meet the flow reliability requirements, specifically including:

[0060] According to the minimum routing space R i and the maximum number of transmission paths f i .W of flow f i , this embodiment defines path redundancy where means selecting path r i in R j as the transmission path of flow f i , means not selecting, and Indicates the flow f i The number of transmission paths is not greater than the maximum path. A single path can also transmit multiple copies of data packets. In this embodiment, multiple copies of data packets on a single path are defined as transmission volume redundancy Among them, Indicates the path r j The number of copies of the data packets of the flow f i transmitted thereon, and when When When When To meet the reliability of the flow f i It is necessary to meet It is necessary to find the possible combinations of H i and M i For H i Several combinations of are found. Among H i W of them are 1 and the rest are 0. For any H i When The smaller j is, the shorter the corresponding path r j is. According to the transient fault probability formula The shorter the path, the higher the transient fault probability. Indicates that using a single path r j to transmit copies can meet the reliability of f i From this, the maximum number of transmission copies M i and the minimum number of transmission copies M max of H min are obtained, and The combination solution of H i and M i is converted into a combinatorial bin-packing problem with upper and lower bounds. In this embodiment, the depth-first search algorithm is used to solve it.

[0061] Fourth step, combined with the circular queue forwarding mechanism of the deterministic network, from the perspective of minimizing flow conflicts, find the optimal combinations of all path redundancies, transmission volume redundancies and time slot offsets, specifically including:

[0062] According to the transmission combination, that is, the path redundancy H i and the transmission volume redundancy M i , combined with the circular queue forwarding CQF scheduling mechanism, this embodiment defines Indicates the injection time slot offset of the data packets of the flow f i on each path. Among them, Indicates data packets j injection time slot offset on the path r Indicates the path r jNot selected, no injection time slot offset. Based on the idea of minimizing flow capacity conflict, for flow f i one H i and M i combination, traverse the path r j for all possible injection time slot offsets, and select the time slot with the largest remaining network time slot capacity as the injection time slot for path r j Thus, all path redundancies, transmission volume redundancies, and offset time slot combinations of flow f i can be obtained.

[0063] Step 5, according to the path, transmission volume, and time slot offset combination, calculate the optimal scheduling scores of all flows, and preferentially schedule the flow with the highest current score, specifically including:

[0064] For a path redundancy, transmission volume redundancy, and offset time slot combination H i , M i and o i , comprehensively consider the maximum remaining network capacity after its scheduling and the amount of resources it occupies itself to calculate its scheduling score. The calculation formula is as follows:

[0065]

[0066] Among them, α is the weight considering the maximum remaining capacity of scheduling, Res(o i ) is the maximum remaining capacity according to a combination H i , M i and o i , Cap is the maximum amount of data that can be sent in a single time slot of the network, α>0 indicates that the larger the maximum remaining capacity after the scheduling of flow f i , the more beneficial it is to the scheduling of other flows; β is the weight considering the resources it occupies itself, represents the total amount of resources occupied by flow f i scheduled according to a combination H i , M i and o i . Among them, is the number of packet copies of flow f j transmitted on path r i , is the number of hops of path r j , f i .l is the length of data sent each time by flow f i , max(F) is the maximum amount of resources occupied by a single flow in F, β<0 indicates that the less total resources occupied by flow f i , the more beneficial it is to the scheduling of other flows.

[0067] The optimal scheduling score S of traffic f i ​i = max(Score(H i , M i , o i )) is the maximum score of all scheduling combinations. Each scheduling calculates the best scheduling score for all traffic flows and schedules the traffic flow with the maximum best scheduling score.

[0068] A routing selection method for reliability enhancement in a deterministic network according to this embodiment is solved by using a heuristic method based on the following optimization objectives and constraints.

[0069] The objective function is modeled as the maximum network schedulable performance. It is considered that when the number of successfully scheduled network flows is the largest, the network reaches the best scheduling performance. The objective function is expressed as:

[0070] max ΣS i

[0071] where S i indicates whether flow f i is successfully scheduled. S i = 1 means successful scheduling, otherwise.

[0072] The deterministic delay constraint is:

[0073]

[0074] where S i indicates whether flow f i is successfully scheduled, indicates selecting the path r i in R j as the transmission path of flow f i , means not selecting, indicates the injection slot offset of the data packet on path r j , indicates flow f i 's minimum routing set R i the maximum transmission delay of path r j in, indicates the hop count of path r j , T s is the slot length, f i .d is the maximum end-to-end delay allowed for flow f. This constraint means that the delay of the data packet transmitted along any path of flow f i cannot exceed the maximum delay requirement of flow f i .

[0075] Injection slot constraint:

[0076]

[0077] Among them, S i Whether to schedule flow f i is successful, indicating to select path r i in R j as the transmission path of flow f i . It means not to select, represents the injection slot offset of the data packet on path r j . represents flow f i 's minimum routing set R i the maximum transmission delay of path r j in it T s is the slot length, T c represents the hyperperiod length, f i .p is the period of flow f i . represents the last data packet of flow f i within a hyperperiod. This constraint means that for any flow f i the sum of the injection slot offset and the transmission delay cannot exceed one period, otherwise data in two hyperperiods may collide.

[0078] Slot capacity constraint:

[0079]

[0080] Among them, represents that the data packet of flow f i will be transmitted on link e j through path r k at slot t, otherwise it means no, S i whether to schedule flow f i is successful, indicating to select path r i in R j as the transmission path of flow f i . It means not to select, represents the number of copies of the data packet of flow f j transmitted on path r i , f i .l represents the length of data sent each time by flow f i . is the maximum capacity that link e k can transmit at slot t.

[0081] In this embodiment, by obtaining network topology information and deterministic flow attributes, modeling the network topology as a directed graph, and defining the key parameters of deterministic flows. Then, considering the transient error probability of links, constructing a set of minimum shortest paths that can meet the flow reliability requirements. Based on the set of minimum paths, finding all combinations of packet redundant transmissions that satisfy flow reliability, and combining with the circular queue forwarding mechanism of the deterministic network to determine the optimal combination scheme of path redundancy, transmission volume redundancy, and injection time slots. Then, calculating the optimal scheduling score for each flow and preferentially scheduling the flow with the highest score. In addition, this embodiment also proposes corresponding objective functions and constraint conditions to ensure that the deterministic delay and time slot capacity requirements are met during the traffic scheduling process. This embodiment can effectively improve the reliability of traffic transmission in the network and the network scheduling performance.

[0082] As described above, the foregoing is only a preferred specific embodiment of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed in the present application should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A routing method for reliability enhancement in a deterministic network, characterized in that, Including: Obtain network topology structure data and a set of deterministic flows, where the set of deterministic flows is composed of several deterministic flows; construct a directed graph based on the network topology structure data, and the directed graph is composed of a set of forwarding devices in the network topology and a set of links connecting the forwarding devices; Calculate the transient failure probability of a single data packet of a deterministic flow on a link, and determine the set of minimum shortest paths that meet the flow reliability requirements based on the calculated transient failure probability; Obtain path redundancy based on the set of minimum shortest paths and the maximum number of transmission paths of the deterministic flow, and obtain the injection slot offset of the deterministic flow data packet on each path based on the CQF cyclic queuing and forwarding scheduling mechanism; Determine the data packet transmission scheme combination based on the injection slot offset, path redundancy, and transmission volume redundancy on a single path; Calculate the best scheduling score of each deterministic flow based on the data packet transmission scheme combination, determine the optimal deterministic flow based on the best scheduling score corresponding to each deterministic flow, and schedule the optimal deterministic flow.

2. The reliability-enhanced routing method in a deterministic network according to claim 1, wherein The deterministic flow is specifically: f i = (f i .S, f i .D, f i .p, f i .l, f i .d, f i .R, f i .W, f i .r) where f i .S represents the source node of the deterministic flow f i .D represents the destination node of the deterministic flow f i .p represents the sending period of the deterministic flow f i .l represents the length of data sent each time for the deterministic flow f i .d represents the maximum allowed end-to-end delay of the deterministic flow f i .R represents the preset routing set of the deterministic flow f i .R = {r1, r2, r3,..., r i} represents that the preset routing set consists of multiple alternative routes, and r i = {e1, e2,... e i}, i .R is initially defined as empty, E is the set of links connecting forwarding devices, and f i .W represents the maximum number of transmission paths of the deterministic flow f i .r represents the minimum reliability index of the deterministic flow f n .r represents the minimum reliability index of the deterministic flow f n = {e1, e2,... e l}, indicates that the alternative route consists of several loop-free forwarding links in E, and f i .R is initially defined as empty, E is the set of links connecting forwarding devices, and f i .W represents the maximum number of transmission paths of the deterministic flow f i .r represents the minimum reliability index of the deterministic flow f i .r represents the minimum reliability index of the deterministic flow f i .r represents the minimum reliability index of the deterministic flow f 3. A routing method for reliability enhancement in a deterministic network according to claim 1, characterized in that, Calculating the transient failure probability of a single data packet of a deterministic flow on a link specifically includes: In the formula, is the deterministic flow f i The transient fault of a single data packet on path r j where λ is a constant of the hardware failure rate, l is the length of each data transmission of the deterministic flow f i and e k is any link on path r j denoted as lr k and the data transmission speed of e k is is the transient fault probability of a single data packet copy of the deterministic flow f i transmitted on multiple paths in the preset routing set.

4. A routing method for reliability enhancement in a deterministic network according to claim 1, characterized in that The determining the set of minimum shortest paths that meet the flow reliability requirements based on the calculated transient failure probability specifically includes: Taking the current shortest path where the transient failure probability of a single data packet of the deterministic flow on the link is greater than or equal to the minimum reliability index as the minimum shortest path that meets the flow reliability requirements.

5. A routing method for enhancing reliability in a deterministic network according to claim 1, characterized in that The path redundancy is specifically: In the formula, represents selecting the set R of the minimum shortest paths i the path r in j as the transmission path for determining the flow f i , means not selecting, f i .W is the maximum number of transmission paths of the deterministic flow f i .

6. The reliability-enhanced routing method in a deterministic network according to claim 1, wherein The transmission volume redundancy is specifically: In the formula, represents the deterministic flow f j transmitted on the path r i in terms of the number of packet copies, when and when while and when 7. A routing method for reliability enhancement in a deterministic network according to claim 1, characterized in that, The obtaining the injection slot offset of the deterministic flow data packet on each path based on the CQF scheduling mechanism specifically includes: Based on the CQF scheduling mechanism, define the injection slot offset of the deterministic flow data packet on each path. Taking the minimization of flow conflict as the goal, traverse all injection slot offsets, and select the slot with the largest remaining network slot capacity value as the injection slot offset of the path.

8. The routing method for reliability enhancement in a deterministic network according to claim 1, wherein The calculating the best scheduling score of each deterministic flow specifically includes: Where Score(H i , M i , o i ) is the optimal scheduling score, α is the weight considering the maximum remaining capacity of the scheduling, Res(o i ) is the maximum remaining capacity according to the redundancy of a combined path H i , transmission volume redundancy M i and injection time slot offset o i , Cap is the maximum amount of data that can be sent in a single time slot of the network, β is the weight considering the resources occupied by itself, represents the total amount of resources occupied by the flow f i scheduled according to a combination H i , M i and o i , is the number of packet copies of the flow f j transmitted on the path r i , is the number of hops of the path r j , f i .l is the length of data sent each time by the flow f i , max(F) is the maximum amount of resources occupied by a single flow in F, and F is the set of flows.​ 9. A routing method for reliability enhancement in a deterministic network according to claim 1, wherein The scheduling the optimal deterministic flow specifically includes: Determine the constraint conditions and construct an objective function with the goal of maximizing the number of successfully scheduled flows in the network. Schedule the optimal deterministic flow based on the objective function.

10. A routing method for reliability enhancement in a deterministic network according to claim 9, characterized in that, The objective function is: max∑S i where S i represents whether the flow f i is successfully scheduled. S i = 1 indicates successful scheduling; The constraint conditions include deterministic delay constraint, injection slot constraint, and slot capacity constraint.

Images