A time-sensitive traffic routing method and system for intersecting redundant paths

Abstract

The application provides a time-sensitive traffic routing method and system of intersecting redundant paths, the method comprising: acquiring all paths of the same traffic and its multiple copies transmitted from a sending node to a target receiving node, and constructing a directed graph containing nodes and edges between adjacent nodes on all paths; finding all shortest paths by using a single-source shortest path algorithm, and constructing a preliminary shortest path set; calculating average delay differences at all intersecting nodes according to the proximity of the center points and lengths of all intersecting paths; updating weights in a preset round, screening out a best path set in the preliminary shortest path set based on each round of weights by using a K-shortest path algorithm and a preset delay difference threshold; and performing topology optimization on multiple intersecting paths with edge overlap in the best path set, and calculating the reliability of the optimized entire network structure. The application can reduce the packet burst problem of redundant paths and improve network reliability.

Description

Technical Field

[0001] This invention relates to the field of Internet technology, and in particular to a time-sensitive traffic routing method and system for intersecting redundant paths. Background Technology

[0002] In fields such as autonomous driving, telemedicine, and industrial manufacturing, end-to-end latency and reliability of traffic are crucial and have a decisive impact on network quality of service. The IEEE 802.1CB Frame Replication and Deletion (FRER) protocol transmits copies of the same traffic through multiple redundant paths to ensure reliable transmission of time-sensitive streams. Based on FRER, each data packet is assigned a sequence number before transmission and is copied into multiple copies at the sending end, which are then sent to the receiving end through multiple redundant paths. At the receiving end, a sequence number checking mechanism eliminates duplicate data packets, ensuring that each data packet is processed only once at the receiving end. Through this mechanism, the FRER protocol effectively improves network reliability and provides deterministic transmission services.

[0003] However, on the one hand, the arrival times of replica streams on different redundant paths in FRER may differ, leading to packet bursts at nodes with limited packet elimination capabilities. This can overload the nodes, causing data delays and impacting network stability. On the other hand, unexpected packet elimination may occur at the intersection of different redundant paths before duplicate data packets reach the receiver, thus affecting the high reliability guarantee provided by the FRER mechanism.

[0004] Existing technologies alleviate node overload by expanding node buffers, but they do not fundamentally solve the packet bursting problem and cannot adapt to dynamic changes in the network environment. Furthermore, existing time-sensitive traffic routing methods for intersecting paths lack clear reliability assessments and still fail to address the packet bursting problem in intersecting paths. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a time-sensitive traffic routing method for intersecting redundant paths to eliminate or improve the shortcomings of existing time-sensitive traffic routing methods for intersecting redundant paths, which cannot solve the problems of packet bursts and unexpected data packet elimination, thus affecting network reliability.

[0006] One aspect of the present invention provides a time-sensitive traffic routing method for intersecting redundant paths, the method comprising the following steps:

[0007] Obtain all paths of the same traffic and its multiple replicas from the sending node to the target receiving node, and construct a directed graph containing the nodes on all paths and the edges between adjacent nodes;

[0008] The single-source shortest path algorithm is used to find all paths from the sending node to the target receiving node that do not pass through duplicate nodes, and a preliminary shortest path set is constructed.

[0009] Obtain all intersecting paths in the initial shortest path set, and calculate the average time delay difference at all intersecting nodes based on the similarity of the center points and lengths of all intersecting paths;

[0010] A weight is assigned to each edge of the directed graph, and the weight is adjusted according to the bandwidth utilization of the corresponding edge and the number of intersecting nodes. Based on the current weight, a preset number of shortest paths are selected from the initial shortest path set using the K shortest path algorithm. Based on the average delay difference at the intersecting nodes, the delay difference of multiple intersecting paths with intersecting nodes in the preset number of shortest paths is calculated, and path groups of multiple intersecting paths with a delay difference greater than a preset delay difference threshold are filtered out to form the optimal path set.

[0011] With the goal of minimizing the number of intersecting nodes, the weights are updated in a preset number of rounds based on the bandwidth utilization of the edges of the directed graph; in each round of updates, based on the weights updated in this round, the optimal path set in the initial shortest path set is selected using the K shortest path algorithm and the preset delay difference threshold.

[0012] For multiple intersecting paths with overlapping edges in the optimal path set, perform topology optimization and retain only one of the paths.

[0013] The reliability of the entire optimized network structure is calculated based on the packet loss rate of each path in the optimized optimal path set.

[0014] Output the optimized set of best paths and the reliability of the entire network structure.

[0015] In some embodiments of the present invention, the time delay difference at the intersecting nodes is calculated as follows:

[0016]

[0017] Where S represents the set of all intersecting paths, This indicates how close the interval center points of any two paths in the set of intersecting paths S are. This indicates how similar the interval lengths of any two paths in the set of intersecting paths S are. This indicates that the numerical value is normalized.

[0018] In some embodiments of the present invention, the reliability of the optimized entire network structure is calculated based on the packet loss rate of each path in the optimized optimal path set. Specific methods include:

[0019] Calculate the probability that no packet loss occurs on each path in the optimized best path set;

[0020] The probability of transmitting data without packet loss at least one path in the optimal path set is calculated using the inclusion-exclusion principle, and this probability is used as the reliability of the optimized network structure.

[0021] In some embodiments of the present invention, the formula for calculating the reliability of the optimized overall network structure is as follows:

[0022]

[0023] Among them, P(A) i ) represents the probability that no packet loss will occur on a certain path.

[0024] In some embodiments of the present invention, a method for topology optimization of multiple intersecting paths with overlapping edges in the optimal path set includes:

[0025] For paths that overlap in the optimal path set, only the path with the largest number of hops after the intersecting node is retained to optimize the optimal path set.

[0026] In some embodiments of the present invention, the single-source shortest path algorithm includes: a greedy algorithm or a dynamic programming algorithm.

[0027] In some embodiments of the present invention, the single-source shortest path algorithm is the Bellman-Ford algorithm.

[0028] Another aspect of the present invention provides a time-sensitive traffic routing system with intersecting redundant paths, including a processor, a memory, and a computer program stored in the memory, the processor being configured to execute the computer program, and when the computer program is executed, the system performing the steps of the method as described in any of the preceding claims.

[0029] Another aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method as described in any of the preceding claims.

[0030] Another aspect of the present invention provides a computer program product comprising a computer program that, when executed by a processor, implements the steps of the method as described in any of the preceding claims.

[0031] The beneficial effects of the present invention are at least as follows:

[0032] This invention provides a time-sensitive traffic routing method and system for intersecting redundant paths. The method includes: acquiring all paths along which the same traffic and its multiple copies are transmitted from a sending node to a target receiving node; constructing a directed graph containing nodes on all paths and edges between adjacent nodes; using a single-source shortest path algorithm to find all shortest paths and constructing a preliminary shortest path set; calculating the average delay difference at all intersecting nodes based on the proximity of the center points and lengths of all intersecting paths; updating the weights in a preset number of rounds with the objective of minimizing the number of intersecting nodes; and, based on the weights in each round, using a K-shortest path algorithm and a preset delay difference threshold to select the optimal path set from the preliminary shortest path set; performing topology optimization on multiple intersecting paths with overlapping edges in the optimal path set; and calculating the reliability of the entire optimized network structure. This invention considers the packet elimination problem caused by intersecting nodes of redundant paths and can reduce packet bursting problems of redundant paths, thereby improving network reliability.

[0033] Additional advantages, objects, and features of the invention will be set forth in part in the description which follows, and will also become apparent in part to those skilled in the art upon studying the description, or may be learned by practice of the invention. The objects and other advantages of the invention can be realized and obtained by means of the structures specifically pointed out in the description and drawings.

[0034] Those skilled in the art will understand that the objectives and advantages achievable with the present invention are not limited to those specifically described above, and that the above and other objectives achievable with the present invention will become clearer from the following detailed description. Attached Figure Description

[0035] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, are not intended to limit the scope of the invention. In the drawings:

[0036] Figure 1 This is a flowchart of a time-sensitive traffic routing method for intersecting redundant paths according to an embodiment of the present invention.

[0037] Figure 2 This is a framework diagram of the BJOR algorithm in another embodiment of the present invention.

[0038] Figure 3 This is a schematic diagram of a topology optimization strategy in another embodiment of the present invention. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the embodiments and accompanying drawings. Here, the illustrative embodiments and descriptions of this invention are used to explain the invention, but are not intended to limit the invention.

[0040] It should also be noted that, in order to avoid obscuring the invention with unnecessary details, only the structures and / or processing steps closely related to the solution according to the invention are shown in the accompanying drawings, while other details that are not closely related to the invention are omitted.

[0041] It should be emphasized that the term "including / comprises" as used herein refers to the presence of a feature, element, step, or component, but does not exclude the presence or addition of one or more other features, elements, steps, or components.

[0042] It should also be noted that, unless otherwise specified, the term "connection" in this article can refer not only to a direct connection, but also to an indirect connection involving an intermediary.

[0043] In the following description, embodiments of the invention will be illustrated with reference to the accompanying drawings. In the drawings, the same reference numerals represent the same or similar parts, or the same or similar steps.

[0044] The IEEE 802.1CB Frame Replication and Cancellation (FRER) protocol transmits copies of the same traffic through multiple redundant paths to ensure reliable transmission of time-sensitive streams. Intersecting redundant paths refer to multiple redundant paths used in network transmission to ensure reliable data transmission, where at least two paths intersect at some point or on some links. When multiple paths intersect, packets may be unexpectedly canceled before reaching the receiver. Furthermore, the FRER mechanism may also cause packet bursts at the receiver, both of which affect network reliability.

[0045] To address the above problems, one embodiment of the present invention proposes a time-sensitive traffic routing method for intersecting redundant paths, such as... Figure 1 As shown, the method includes the following steps S101 to S108:

[0046] Step S101: Obtain all paths of the same traffic and its multiple replicas from the sending node to the target receiving node, and construct a directed graph containing the nodes on all paths and the edges between adjacent nodes.

[0047] Step S102: Use the single-source shortest path algorithm to find all paths from the sending node to the target receiving node that do not pass through duplicate nodes, and construct a preliminary shortest path set.

[0048] Step S103: Obtain all intersecting paths in the initial shortest path set, and calculate the average time delay difference at all intersecting nodes based on the similarity of the center points and lengths of all intersecting paths.

[0049] Step S104: Assign weights to each edge of the directed graph. The weights are adjusted based on the bandwidth utilization of the corresponding edge and the number of intersecting nodes. Based on the current weights, use the K shortest path algorithm to select a preset number of shortest paths from the initial shortest path set. Based on the average delay difference at the intersecting nodes, calculate the delay difference of multiple intersecting paths with intersecting nodes in the preset number of shortest paths. Filter out all path groups with multiple intersecting paths in the preset number of shortest paths that are greater than the preset delay difference threshold to form the optimal path set.

[0050] Step S105: With the goal of minimizing the number of intersecting nodes, update the weights in a preset number of rounds based on the bandwidth utilization of the edges of the directed graph; in each round of update, based on the weights updated in this round, use the K shortest path algorithm and a preset time delay difference threshold to select the best path set in the initial shortest path set.

[0051] Step S106: Perform topology optimization on multiple intersecting paths with overlapping edges in the optimal path set, and retain only one of the paths.

[0052] Step S107: Calculate the reliability of the entire optimized network structure based on the packet loss rate of each path in the optimized optimal path set.

[0053] Step S108: Output the optimized set of best paths and the reliability of the entire network structure.

[0054] In a directed graph, nodes represent devices in the network (such as routers and switches), while edges represent connections between these devices and the direction of data transmission, thus illustrating the communication paths and traffic directions of the network structure.

[0055] The edge weights are adjusted based on the bandwidth utilization of the corresponding edge and the number of intersecting nodes. The K shortest path algorithm tends to select the path with the smaller total weight to achieve more efficient data transmission.

[0056] The single-source shortest path algorithm uses a directed graph to find all possible paths from the source node (sender node) to the target node (receiver node). This can be implemented using graph traversal algorithms such as Depth-First Search (DFS) and Breadth-First Search (BFS). Then, all independent paths (i.e., paths that do not share any edges) are selected from the found paths; these paths together form a complete path set.

[0057] The formula for calculating the time delay difference of multiple intersecting paths with intersecting nodes in the preset number of shortest paths, based on the average time delay difference at intersecting nodes, is as follows:

[0058]

[0059] This calculation takes into account that there may be multiple intersecting nodes in the path group of multiple intersecting paths, and that different paths may also intersect at the receiving end (denoted by L).

[0060] Among them, topology optimization for multiple intersecting paths with overlapping edges in the optimal path set is to reduce redundant path branches, thereby reducing intersecting nodes, which in turn reduces the possibility of packet elimination at intersecting nodes and lowers the failure rate.

[0061] The reliability of the entire network structure refers to the network's ability to continue to operate normally within a specific period of time. It is usually used to measure a network system's ability to maintain its service functions and performance when it encounters failures, attacks, or other uncertainties.

[0062] In some embodiments, the time delay difference at intersecting nodes is calculated as follows:

[0063]

[0064] Where S represents the set of all intersecting paths, This indicates how close the interval center points of any two paths in the set of intersecting paths S are. This indicates how similar the interval lengths of any two paths in the set of intersecting paths S are. This indicates that the numerical value is normalized.

[0065] Specifically, this method assumes that path delay is an inherently known property, and that the delay of each edge (consisting of two nodes) is a uniformly distributed interval [d, D], such as [1ms, 3ms], indicating that the delay experienced by the data packet at these two nodes is uniformly distributed between 1ms and 3ms.

[0066]

[0067]

[0068] This calculation method borrows from similarity measures in statistics, but it is the first attempt of its kind in the field of network reliability analysis. Considering that the intersection of any two paths in a path group will generate packet bursts, this calculation method uses... Perform numerical normalization. Model calculation results. The closer a value is to 1, the greater the difference in latency between the paths in the set of intersecting paths, and the greater the possibility of packet bursts.

[0069] In some embodiments, the reliability of the optimized network structure is calculated based on the packet loss rate of each path in the optimized optimal path set. Specific methods include:

[0070] Calculate the probability that no packet loss occurs on each path in the optimized best path set;

[0071] The probability of transmitting data without packet loss at least one path in the optimal path set is calculated using the inclusion-exclusion principle, and this probability is used as the reliability of the optimized network structure.

[0072] In some embodiments, the formula for calculating the reliability of the optimized overall network structure is:

[0073]

[0074] Among them, P(A) i ) represents the probability that no packet loss will occur on a certain path.

[0075] In some embodiments, a method for topology optimization of multiple intersecting paths with overlapping edges in the optimal path set includes:

[0076] For paths that overlap in the optimal path set, only the path with the largest number of hops after the intersecting node is retained to optimize the optimal path set.

[0077] Furthermore, for topology optimization of multiple intersecting paths with overlapping edges in the optimal path set, the branch with the best network condition can be selected by monitoring the network status of multiple branches of the overlapping path.

[0078] In some embodiments, the single-source shortest path algorithm includes a greedy algorithm or a dynamic programming algorithm.

[0079] In some embodiments, the single-source shortest path algorithm is the Bellman-Ford algorithm.

[0080] Another embodiment of the present invention provides a time-sensitive traffic routing method and system for intersecting redundant paths. The technical solution can be summarized as follows: First, based on packet bursting phenomena at intersecting nodes, this solution proposes a delay difference model and defines a metric to quantify the delay differences of different time-sensitive flows. Second, to address the unexpected packet cancellation caused by intersecting nodes, this solution designs a reliability calculation model to more accurately assess network reliability. Based on the above two models, the BJOR (Bubble and Intersecting Node Optimization) algorithm is proposed. Simulation results show that, under network topologies with varying connectivity, BJOR significantly reduces the probability of packet bursting and effectively improves network reliability compared to other existing algorithms.

[0081] Unlike existing methods, the technical solution in this embodiment considers the path delay differences on different redundant paths and also takes into account the impact of intersecting nodes in redundant paths on network reliability. Through optimization of calculation methods and path selection, the paths planned by this solution for time-sensitive flows have a lower probability of packet bursts and higher network reliability. Specifically, this solution solves the following technical problems:

[0082] 1. The path delay difference metric is proposed to effectively quantify the probability of packet bursts at each intersecting node.

[0083] 2. A reliability calculation model for intersecting paths is proposed. The minimal path set is used to calculate the reliability of the optimized topology, which ensures more accurate network reliability calculation.

[0084] 3. A packet burst and intersection node optimization algorithm (BJOR) was designed, which takes into account both path delay differences and the number of intersection nodes, reducing the probability of packet bursts while improving network reliability.

[0085] like Figure 2 As shown, the BJOR algorithm mainly consists of four steps: delay difference measurement, network reliability calculation, network weight update and feedback, and routing result output. In the delay difference model, the scheme calculates the potential packet burst probability at intersecting nodes based on path groups and delivers the calculated delay difference to the controller. In the reliability calculation model, the scheme first performs topology optimization on intersecting redundant paths to obtain a more accurate reliability calculation result, which is then delivered to the controller. The controller compares the path delay difference obtained during the routing process with a predetermined threshold. If it does not meet the requirements, the routing policy is updated and recalculated. At the same time, the controller updates the weights of each path in the network, so that other traffic tends to choose non-intersecting redundant paths. Finally, the BJOR algorithm outputs the routing result and reliability to the user side. Based on the two models designed in the scheme, BJOR provides low burstiness and high reliability guarantees for routing under intersecting redundant path conditions.

[0086] Specifically, the design scheme of the delay difference model is as follows:

[0087] To effectively address packet burst issues at their root, this solution takes a routing approach to avoid excessive delay differences among multiple redundant paths. Therefore, a delay difference model is designed. This model uses parameters... Quantization at a certain intersection node v i The time delay difference of different redundant paths.

[0088] In this model, the time delay of each path is in the interval [range missing]. For a given node with uniform internal distribution and different combinations of redundant paths in the input model, the following formula is used to calculate the time delay difference between different redundant paths.

[0089]

[0090] Among them, in the model and These represent the similarity between the midpoints of any two paths in the intersecting path set S and the similarity between their interval lengths, respectively. This calculation method borrows from similarity measures in statistics, but it is the first attempt of its kind in the field of network reliability analysis. Considering that the intersection of any two paths in the path group will produce packet bursts, the model uses... Perform numerical normalization. Model calculation results. The closer a value is to 1, the greater the difference in latency between the paths in the set of intersecting paths, and the greater the possibility of packet bursts.

[0091] Specifically, the design scheme of the reliability calculation model is as follows:

[0092] (1) Design of topology optimization strategy: Considering that intersecting nodes can lead to the unexpected elimination of data packets and reduce the performance of redundant networks, the results obtained by performing reliability calculations based on the original topology will no longer be accurate. In order to solve this problem, this scheme will perform topology optimization on the redundant path group input to the reliability calculation model at the intersecting nodes.

[0093] like Figure 3 As shown, the topology optimization strategy retains only one path with the maximum hop count after intersecting nodes. The maximum hop count refers to the number of intermediate nodes (routers or switches) that a data packet passes through in the network.

[0094] Since the optimized topology retains the path with the highest hop count, the calculation of this model is equivalent to finding a reliability lower bound, ensuring the network transmission performance in the worst case, that is, the actual reliability of the network is always greater than or equal to the calculated reliability.

[0095] (2) Reliability calculation based on minimum path set theory:

[0096] The reliability model references the concept of a minimum path set to calculate the reliability of the optimized network topology. A minimum path set is the set of all possible shortest paths from the sender to the receiver in the network that do not involve duplicate nodes or links; it is a single-source shortest path algorithm. The model first determines the set of independent paths from the sender to the receiver, then calculates the probability of no packet loss on each path in the independent path set, and combines this with the inclusion-exclusion principle (a mathematical method for calculating the size of the union or intersection of multiple sets) to calculate the reliability of data transmission in the case that at least one redundant path has no packet loss, which is then considered as the network reliability. This reliability model uses P(R) to represent network reliability, and its calculation formula is shown below:

[0097]

[0098] Among them, P(A) i The probability that a redundant path will not experience packet loss is represented by the number 1. The reliability model is based on this method and can effectively take into account the influence of intersecting nodes in the reliability calculation. By combining the independence between paths and the unexpected elimination of data packets, the overall reliability of the network can be evaluated more intuitively.

[0099] Specifically, the design scheme of the Packet Burst and Intersection Node Optimization Algorithm (BJOR) is as follows:

[0100] (1) Algorithm Flow Design: Based on the characteristics of intersecting redundant paths and the shortcomings of existing technologies, and combining the aforementioned delay difference model and reliability calculation model, this scheme designs the BJOR algorithm. Its core is to ensure that the delay difference between paths is minimized while simultaneously minimizing the number of intersecting nodes in the redundant path set. Specifically, the optimization objective of BJOR is:

[0101] min∑ v∈P |J v |,

[0102] |δ P |≤Φ,

[0103] Among them, |J v | represents the number of intersecting nodes in the entire network, |δ P | represents the average delay difference of all intersecting nodes along the path from the sender to the receiver, and Φ is a user-input threshold. The closer Φ is to 0, the stricter the user's requirements are regarding the possibility of data packet bursts.

[0104] Based on the above ideas, the BJOR algorithm designed in this model includes the following steps: First, an algorithm for calculating the single-source shortest path (such as the Bellman-Ford algorithm) is used to find the initial path in the directed path graph G(V,E) input by the user, and it is added to the path set P. Next, the k-shortest-paths algorithm is used to generate k paths that meet the user's requirements as candidate paths. Each path is then checked to see if it meets the latency difference threshold Φ. Paths that meet the conditions are added to the path set P, ultimately resulting in a complete set of paths that meet the requirements.

[0105] (2) Design of the weight update function:

[0106] In the BJOR algorithm, a weight update function is used to continuously update the topology for route selection. The scheme dynamically updates the weights of edges in the graph based on bandwidth utilization and the number of intersecting nodes. The specific weight update rules include: the bandwidth weight of an edge is adjusted according to bandwidth usage, while the weight of an edge connected to an intersecting node is increased by the user-input parameter ω (the larger ω is, the stricter the requirement for the number of intersecting nodes), thereby reducing the probability of these edges in subsequent path selection.

[0107] In summary, the technical solution of this embodiment can bring the following effects:

[0108] (1) Achieving path delay consistency control and reducing packet burst risk: This solution uses a delay difference model to accurately quantify the delay difference of different redundant paths at intersecting nodes and uses this indicator in the path selection process. Unlike traditional methods that rely solely on cache expansion, BJOR actively avoids path combinations with large delay differences during path planning, effectively reducing packet bursts at intersecting nodes and ensuring the stability of data transmission from the root, making it suitable for scenarios with high real-time requirements.

[0109] (2) Effectively reduce the number of intersecting nodes and improve the reliability of redundant paths: This scheme considers both the delay difference and the number of intersecting nodes during the path selection process, and prioritizes non-intersecting paths through a weight update mechanism. This approach not only reduces the packet elimination problem caused by the number of intersecting nodes, but also calculates the reliability of the optimized topology through the minimum path set theory, making the redundant paths more reliable, thus meeting the requirements of high-reliability application scenarios.

[0110] (3) Dynamic weight adjustment mechanism to reduce algorithm complexity: The weight update function designed in this invention dynamically adjusts the path based on bandwidth utilization and the number of intersecting nodes, avoiding complex network calculation processes and realizing a path selection strategy with low computational overhead. This simplified calculation method enables BJOR to perform well in environments with high real-time requirements, and can respond quickly under constantly changing network conditions, further improving the guarantee capability of network service quality.

[0111] In summary, this invention provides a time-sensitive traffic routing method and system for intersecting redundant paths. The method includes: acquiring all paths for the same traffic and its multiple copies transmitted from the sending node to the target receiving node; constructing a directed graph containing nodes on all paths and edges between adjacent nodes; using a single-source shortest path algorithm to find all shortest paths and constructing a preliminary shortest path set; calculating the average latency difference at all intersecting nodes based on the proximity of the center points and lengths of all intersecting paths; updating the weights in a preset number of rounds with the goal of minimizing the number of intersecting nodes; and, based on the weights in each round, using a K-shortest path algorithm and a preset latency difference threshold to select the optimal path set from the preliminary shortest path set; performing topology optimization on multiple intersecting paths with overlapping edges in the optimal path set, and calculating the reliability of the entire optimized network structure. This invention effectively reduces the number of intersecting nodes and improves the reliability of redundant paths. By employing a weight update function to dynamically adjust paths based on bandwidth utilization and the number of intersecting nodes, it avoids complex network calculation processes and achieves a low-computational-overhead path selection strategy. Ultimately, this effectively reduces packet bursts at intersecting nodes, ensuring data transmission stability from the root and making it suitable for scenarios with high real-time requirements.

[0112] Corresponding to the above method, the present invention also provides a system comprising a computer device including a processor and a memory, wherein the memory stores computer instructions, and the processor is configured to execute the computer instructions stored in the memory, wherein when the computer instructions are executed by the processor, the system implements the steps of the method as described above.

[0113] This invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the aforementioned edge computing server deployment method. The computer-readable storage medium can be a tangible storage medium, such as random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, floppy disks, hard disks, removable storage disks, CD-ROMs, or any other form of storage medium known in the art.

[0114] Those skilled in the art will understand that the exemplary components, systems, and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software, or a combination of both. Whether implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention. When implemented in hardware, it can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this invention are programs or code segments used to perform the desired tasks. The programs or code segments can be stored in a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried in a carrier wave.

[0115] It should be clarified that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of the present invention.

[0116] In this invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with or in place of features of other embodiments.

[0117] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, various modifications and variations of the embodiments of the present invention are possible. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method of time sensitive traffic routing of intersecting redundant paths, characterized by, The method comprises the following steps: Obtaining all paths of the same flow and its multiple copies transmitted from a sending node to a target receiving node, and constructing a directed graph containing edges between nodes and adjacent nodes on all paths; Finding all paths between the sending node and the target receiving node without passing through repeated nodes by using a single-source shortest path algorithm, and constructing a preliminary shortest path set; Obtaining all intersecting paths in the preliminary shortest path set, and calculating average time delay difference at all intersecting nodes according to the proximity of the center point and length of all intersecting paths; Configuring a weight for each edge of the directed graph, adjusting the weight according to the bandwidth utilization and the number of intersecting nodes of the corresponding edge, screening out a preset number of shortest paths in the preliminary shortest path set by using a K-shortest path algorithm according to the current weight, calculating time delay difference of multiple intersecting paths in the preset number of shortest paths that have intersecting nodes according to the average time delay difference at the intersecting nodes, and screening out path groups of all multiple intersecting paths greater than a preset time delay difference threshold in the preset number of shortest paths to form a best path set; Updating the weight based on the bandwidth utilization of the edge of the directed graph for a preset number of rounds with the minimum number of intersecting nodes as the target, and screening out the best path set in the preliminary shortest path set based on the weight of the current round of update by using the K-shortest path algorithm and the preset time delay difference threshold in each round of update; Topologically optimizing multiple intersecting paths with edge overlap in the best path set, and retaining only one path among them; Calculating the reliability of the optimized entire network structure based on the packet loss rate of each path in the optimized best path set; Outputting the optimized best path set and the reliability of the entire network structure.

2. The time-sensitive traffic routing method of intersecting redundant paths according to claim 1, characterized in that, The calculation formula of the time delay difference at the intersecting nodes is: where S denotes a set of all intersecting paths, denotes closeness of interval center points of any two paths in the set S of intersecting paths, denotes closeness of interval lengths of any two paths in the set S of intersecting paths, denotes normalizing the logarithmic values.

3. The time-sensitive traffic routing method of intersecting redundant paths of claim 1, wherein, The specific method for calculating the reliability of the optimized entire network structure based on the packet loss rate of each path in the optimized best path set comprises: Calculating the probability that each path in the optimized best path set does not occur packet loss; Calculating the probability that data is transmitted without packet loss by at least one path in the best path set by using the inclusion-exclusion principle as the reliability of the optimized entire network structure.

4. The time-sensitive traffic routing method of intersecting redundant paths according to claim 3, wherein, The calculation formula for calculating the reliability of the optimized entire network structure is: where P(A i ) denotes the probability that no packet loss occurs on a certain path.

5. The time-sensitive traffic routing method of intersecting redundant paths of claim 1, wherein, The method for topologically optimizing multiple intersecting paths with edge overlap in the best path set comprises: Retaining only the path with the largest number of hops after the intersecting nodes for the overlapping paths in the best path set to optimize the best path set.

6. The time-sensitive traffic routing method of intersecting redundant paths of claim 1, wherein, The single-source shortest path algorithm comprises a greedy algorithm or a dynamic programming algorithm.

7. The time-sensitive traffic routing method of intersecting redundant paths of claim 1, wherein, The single-source shortest path algorithm is a Bellman-Ford algorithm.

8. A time sensitive traffic routing system of intersecting redundant paths comprising a processor, a memory and a computer program stored on the memory, characterized in that, The processor is configured to execute the computer program, and when the computer program is executed, the system implements the steps of the method according to any one of claims 1 to 7.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method according to any one of claims 1 to 7.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method according to any one of claims 1 to 7.

Images