An end-to-end reliable routing method and system for error-oriented networks

Abstract

This invention discloses an end-to-end reliable routing method and system for error-prone networks. Under the current network topology of the error-prone network, a randomized shortest main path from the source node to the destination node is generated. The randomized shortest main path is divided into multiple sub-segments based on hop count, and relay nodes for each sub-segment are determined. For each sub-segment, the forwarding range of data packets within that sub-segment is planned. A set of neighboring nodes is selected centered on a node on the main path of that sub-segment, and the union of these nodes is taken as the corridor area for that sub-segment. Only nodes within this corridor area are allowed to participate in data packet forwarding for that sub-segment. Port-directed probabilistic forwarding is performed within the corridor area. When a relay node in a sub-segment receives a data packet for the first time, it triggers the data packet forwarding relay for the next sub-segment. This invention enables routing to improve reliability while effectively controlling the overhead of parallel forwarding.

Description

Technical Field

[0001] This invention relates to the field of satellite network communication technology, and specifically to an end-to-end reliable routing method and system for error-prone networks, and more particularly to an end-to-end reliable routing method and system for low-Earth orbit satellite networks in error-prone environments. Background Technology

[0002] Low Earth Orbit (LEO) satellites offer advantages such as global coverage and low propagation latency, making them suitable for broadband access, emergency communications, and communications in extreme environments. However, in actual operation, LEO satellite networks face continuous challenges from the harsh space environment and interference: for example, high-energy solar particles, cosmic rays, and trapped particles in radiation belts can induce single-event effects in onboard electronic devices, leading to bit flips, processing anomalies, or payload degradation, resulting in satellite node failures, link-end equipment malfunctions, or link establishment failures. Strong sunlight and space electromagnetic disturbances can also cause blinding or increased bit error rates in inter-satellite laser links, causing random switching between available and unavailable states. These node failures and random link interruptions make it difficult for end-to-end communication paths to remain consistently available, especially in multi-hop, long-path transmissions.

[0003] In such error-prone environments, traditional unicast routing relies on acknowledgment and retransmission mechanisms to improve data delivery success rates, but at the cost of significant end-to-end latency and resource overhead. While flooding routing can improve data reachability, it generates a large number of redundant packet forwardings, consuming valuable link resources. Therefore, in the absence of stable paths and global network state information, designing an efficient and reliable routing mechanism that balances reachability, latency, and forwarding overhead has become a pressing challenge.

[0004] Currently, existing research has proposed methods for link availability modeling and network connectivity assessment in faulty network environments to analyze the connectivity characteristics of satellite networks under different damage conditions. However, designing end-to-end reliable routing strategies based on such models remains challenging. Existing reliable transmission schemes (such as acknowledgment retransmission unicast, multipath routing, and area-restricted flooding) either sacrifice latency or waste significant resources, lacking fine-grained control over redundancy. Therefore, a new routing mechanism is needed that can fully utilize link models and connectivity information while adaptively controlling redundancy through parameterized forwarding strategies, achieving an adjustable performance trade-off. Summary of the Invention

[0005] To address the reliability requirements of unstable links, this invention provides an end-to-end reliable routing method and system for error-prone networks. This invention employs a parameterized end-to-end controlled diffusion reliable routing mechanism, combining parallel packet forwarding within sub-segments, forwarding area constraints, and port-directed probabilistic forwarding. This allows routing to improve reliability while effectively controlling the overhead of parallel forwarding. A deduplication mechanism is also introduced within each sub-segment to suppress loop propagation and further limit redundancy overhead.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: An end-to-end reliable routing method for error-prone networks includes the following steps: Step S100: Under the current network topology of the error network, generate a randomized shortest main path from the source node to the destination node; Step S200: Divide the randomized shortest main path into multiple sub-segments according to the number of hops, and determine the relay node of each sub-segment; Step S300: For each sub-segment, plan the forwarding range of data packets within the sub-segment, select a set of neighboring nodes centered on the nodes on the main path of the sub-segment, and take the union of the set as the corridor area of ​​the sub-segment. Only nodes within the corridor area are allowed to participate in the forwarding of data packets in the sub-segment. Step S400: Perform port-oriented probabilistic forwarding within the corridor area: For each sub-segment, pre-determine the relay node for that sub-segment, where the relay node is the end node on the main path of that sub-segment; each forwarding node located within the corridor area of ​​that sub-segment determines its orientation port set based on its position relative to the relay node of its own sub-segment, where the orientation port is the port direction that makes the forwarding node closer to the current sub-segment relay node in both the row and column directions; Step S500: When a relay node of a certain sub-segment receives the data packet for the first time, it triggers the relay of data packet forwarding for the next sub-segment; if the current sub-segment is not the last sub-segment, the relay node is used as the starting forwarding node for the next sub-segment to continue propagating the data packet; if the current sub-segment is the last sub-segment and the relay node is the destination node, the end-to-end transmission of the data packet is completed; wherein, a deduplication mechanism is implemented during the data packet forwarding process of each sub-segment, and the nodes participating in the deduplication judgment include forwarding nodes and relay nodes, and for the same data packet in the same sub-segment, each node performs a forwarding action only once.

[0007] Further, in step S100, under the current network topology of the error network, a randomized shortest main path from the source node to the destination node is generated. Specifically, a breadth-first search algorithm is used to search for the shortest hop path from the source node to the destination node under the current network topology of the error network. When performing the breadth-first search, the traversal order of the adjacent nodes of each node is randomized. Finally, one shortest path is randomly obtained from all the shortest paths, and the shortest path is taken as the randomized shortest main path.

[0008] Further, in step S200, the selection of the number of sub-segments is as follows: let the number of hops on the main path from the source node to the destination node be H, given the constraint interval of the segment length, select the minimum number of sub-segments K, so that the main path is divided into K segments and the number of hops in each segment falls within the constraint interval of the segment length. The end node of each sub-segment is determined as the relay node of that sub-segment and serves as the starting forwarding node of the next sub-segment.

[0009] Furthermore, in step S300, the construction of the corridor area is specifically as follows: Let the first... The set of main path nodes corresponding to each sub-segment is: ,in, No. Each node on the main path of each sub-segment For the first The number of main path nodes contained in each sub-segment; with any node Expand in both row and column directions from the center. The side length formed by the jump The square neighborhood is defined as a set ,in, Let the width be the corridor width; then the first... Corridor area of ​​each segment Defined as the union of the square neighborhoods of all nodes on the main path segment: .

[0010] Further, in step S400, each forwarding node located within the corridor area of ​​the sub-segment determines its orientation port set based on its position relative to the relay node of its sub-segment. The orientation port is the port direction that makes the forwarding node closer to the current relay node in both the row and column directions. Specifically: when there is displacement between the forwarding node and the relay node in the row direction, the orientation port set includes port directions that reduce the absolute value of the row direction displacement; when there is displacement between the forwarding node and the relay node in the column direction, the orientation port set includes port directions that reduce the absolute value of the column direction displacement; when there is displacement in both the row and column directions, the orientation port set includes both of the above port directions; the non-orienting port set is defined as all port directions other than the orientation ports and the incoming port; when a port belongs to the orientation port set, it is forwarded with a first forwarding probability. A forwarding attempt is performed on the packet; when the port belongs to the non-directing port set, a second forwarding probability is used. Perform a forwarding attempt on the packet; and prohibit backoff forwarding via the port from which it originated.

[0011] Further, in the port orientation probabilistic forwarding described in step S400: for ports belonging to the orientation port set, a first forwarding probability is used. Perform a forwarding attempt on the packet; for ports belonging to the non-direction port set, with a second forwarding probability. Perform a forwarding attempt on the data packet; and satisfy the following conditions: .

[0012] Furthermore, the width of the corridor First forwarding probability Second forwarding probability and the number of sub-segments The parameter configuration table is determined by looking up the parameter configuration table, which is compiled from several simulation results for different network sizes and different network error scenarios.

[0013] Further, in step S500, the triggering condition for forwarding relay is: when the relay node of a certain sub-segment receives the data packet for the first time, the first round of the relay of that sub-segment is recorded, and the relay node is used as the starting forwarding node of the next sub-segment to initiate the data packet forwarding relay.

[0014] Furthermore, the deduplication mechanism stipulates that: for the same data packet within the same sub-segment, each node shall perform a forwarding action at most once; when the node receives a copy of the data packet carrying the same data packet identifier and the same sub-segment identifier for the second or subsequent time within the same sub-segment, it shall not forward it again; since a node may be in the corridor area set of two sub-segments at the same time, when the node receives a copy of the data packet carrying the same data packet identifier but a different sub-segment identifier, it is allowed to perform a forwarding action again within the corresponding sub-segment.

[0015] An end-to-end reliable routing system for error-prone networks includes: The first module is used to generate a randomized shortest main path from the source node to the destination node under the current network topology of the error network. The second module is used to divide the randomized shortest main path into multiple sub-segments according to the number of hops, and to determine the relay node of each sub-segment. The third module is used to plan the forwarding range of data packets within each sub-segment. It selects a set of neighboring nodes centered on the nodes on the main path of the sub-segment, and takes the union of these nodes as the corridor area of ​​the sub-segment. Only nodes within the corridor area are allowed to participate in the forwarding of data packets in the sub-segment. The fourth module is used to perform port-oriented probabilistic forwarding within the corridor area: For each sub-segment, the relay node of the sub-segment is pre-determined, and the relay node is the end node of the sub-segment on the main path of the sub-segment; each forwarding node located within the corridor area of ​​the sub-segment determines the oriented port set according to its position relative to the relay node of its own sub-segment, and the oriented port is the port direction that makes the forwarding node closer to the current sub-segment relay node in the row and column directions; The fifth module is used to trigger the relay of data packet forwarding for the next sub-segment when the relay node of a certain sub-segment first receives the data packet; if the current sub-segment is not the last sub-segment, the relay node is used as the starting forwarding node for the next sub-segment to continue propagating the data packet; if the current sub-segment is the last sub-segment and the relay node is the destination node, the end-to-end transmission of the data packet is completed; wherein, a deduplication mechanism is implemented during the data packet forwarding process of each sub-segment, and the nodes participating in the deduplication judgment include forwarding nodes and relay nodes, and for the same data packet in the same sub-segment, each node performs a forwarding action only once.

[0016] Compared with the prior art, the present invention has the following beneficial technical effects: First, this invention spatially constrains the diffusion range by combining segment indirect force with forwarding area restrictions, thus limiting redundant forwarding to a local area related to end-to-end transmission. This significantly reduces resource consumption caused by invalid diffusion across the entire network while ensuring end-to-end reliability.

[0017] Second, this invention controls the forwarding direction and intensity through port-oriented probabilistic forwarding, making data packets more inclined to advance along the direction of relay nodes. Under the premise of meeting the target reachability, it effectively reduces the first-delivery delay and reduces the overhead of repeated forwarding caused by blind flooding.

[0018] Third, by parametrically designing key parameters such as corridor width, number of sub-segments, and port forwarding probability, this invention enables flexible configuration based on link availability and service reliability requirements, achieving an adjustable trade-off between reachability, latency, and overhead, and is suitable for end-to-end reliable transmission scenarios in low-Earth orbit satellite networks under error environments. Attached Figure Description

[0019] The accompanying drawings are provided to further understand the invention and constitute a part of this invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0020] Figure 1 This is a schematic diagram of the sub-segment corridor area planning according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the node port forwarding probability configuration according to an embodiment of the present invention; Figure 3This is a schematic diagram of inter-segment forwarding of data packets according to an embodiment of the present invention; Figure 4 This is a flowchart of the method of the present invention. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0023] Example 1 This invention provides an end-to-end reliable routing method for error-prone networks, such as... Figure 4 As shown, it includes the following steps: Step S100: Generate the main path from the source node to the destination node based on the positions of the source node and the destination node and the network topology information of the error network; Step S200: Divide the main path into multiple sub-segments according to the number of hops, and determine the last node of each sub-segment as a relay node; Step S300: For the i-th sub-segment, construct a corridor region centered on all nodes in that sub-segment: specifically, expand the neighborhood centered on each main path node according to the set corridor width, and use the union of these neighborhoods as the corridor region of the i-th sub-segment. Only nodes located within this corridor region are allowed to participate in packet forwarding for that sub-segment; Step S400: Perform port-oriented probabilistic forwarding within the corridor area: Each forwarding node determines the oriented port set based on its row and column displacement relative to the current sub-segment relay node. For ports belonging to the oriented port set, data packets are forwarded with a higher probability; for non-oriented ports, data packets are forwarded with a lower probability; at the same time, backhaul through the incoming port is prohibited, thereby guiding data packets to spread towards the relay node. Step S500: When a relay node of a certain segment receives a data packet for the first time, it triggers the data packet forwarding relay of the next segment, and in the next round, it uses the relay node as the starting point of the next segment to initiate data packet forwarding.

[0024] In addition, a deduplication mechanism is implemented within each sub-segment: each node performs a forwarding action on the same data packet at most once within the same sub-segment to prevent loop propagation and redundant forwarding; if a node is located in the corridor area of ​​two sub-segments at the same time, when it receives different sub-segment copies of the same data packet, it forwards it only once within each sub-segment.

[0025] Example 2 An end-to-end reliable routing method for error-prone networks includes the following steps: Step S100: Under the current network topology of the error network, generate a randomized shortest main path from the source node to the destination node; Specifically, the breadth-first search algorithm is used to search for the shortest path from the source node to the destination node on the current network topology of the error network. When performing the breadth-first search, the traversal order of the adjacent nodes of each node is randomized. Finally, one shortest path is randomly obtained from all the shortest paths and is taken as the randomized shortest main path.

[0026] Step S200: Divide the randomized shortest main path into multiple sub-segments according to the number of hops, and determine the relay node of each sub-segment; Specifically, let H be the number of hops on the main path from the source node to the destination node. Given a constraint range for the length of a sub-segment, select the minimum number of sub-segments K such that the main path is divided into K segments and the number of hops in each segment falls within the constraint range for the length of the sub-segment. The end node of each sub-segment is determined as the relay node of that sub-segment and serves as the starting forwarding node for the next sub-segment.

[0027] Step S300: For each sub-segment, plan the forwarding range of data packets within the sub-segment, select a set of neighboring nodes centered on the nodes on the main path of the sub-segment, and take the union of the set as the corridor area of ​​the sub-segment. Only nodes within the corridor area are allowed to participate in the forwarding of data packets in the sub-segment. Specifically, the construction of the corridor area is as follows: Let the first... The set of main path nodes corresponding to each sub-segment is: ,in, No. Each node on the main path of each sub-segment For the first The number of main path nodes contained in each sub-segment; with any node Expand in both row and column directions from the center. The side length formed by the jump The square neighborhood is defined as a set ,in, Let the width be the corridor width; then the first... Corridor area of ​​each segment Defined as the union of the square neighborhoods of all nodes on the main path segment: .

[0028] Step S400: Perform port-oriented probabilistic forwarding within the corridor area: For each sub-segment, pre-determine the relay node for that sub-segment, where the relay node is the end node on the main path of that sub-segment; each forwarding node located within the corridor area of ​​that sub-segment determines its orientation port set based on its position relative to the relay node of its own sub-segment, where the orientation port is the port direction that makes the forwarding node closer to the current sub-segment relay node in both the row and column directions; Specifically, when the forwarding node and the relay node are displaced in the row direction, the oriented port set includes port directions that reduce the absolute value of the row direction displacement; when the forwarding node and the relay node are displaced in the column direction, the oriented port set includes port directions that reduce the absolute value of the column direction displacement; when there is displacement in both the row and column directions, the oriented port set includes both of the above port directions; the non-oriented port set is defined as all port directions other than the oriented ports and the incoming port; when a port belongs to the oriented port set, it is forwarded with a first forwarding probability. A forwarding attempt is performed on the packet; if the port does not belong to the set of facing ports, a second forwarding probability is used. Perform a forwarding attempt on the packet; and prohibit backoff forwarding via the port from which it originated.

[0029] Step S500: When a relay node of a certain sub-segment receives the data packet for the first time, it triggers the data packet forwarding relay of the next sub-segment. The triggering condition for the forwarding relay is as follows: when a relay node of a certain sub-segment receives the data packet for the first time, the first arrival round of the relay for that sub-segment is recorded, and the relay node is used as the starting forwarding node of the next sub-segment to initiate the data packet forwarding relay; if the current sub-segment is not the last sub-segment, the relay node is used as the starting forwarding node of the next sub-segment to continue propagating the data packet; if the current sub-segment is the last sub-segment and the relay node is the destination node, the end-to-end transmission of the data packet is completed; wherein, a deduplication mechanism is implemented during the data packet forwarding process of each sub-segment, and the nodes include forwarding nodes and relay nodes. For the same data packet in the same sub-segment, each node performs a forwarding action only once; Specifically, the deduplication mechanism stipulates that: for the same data packet within the same sub-segment, each node performs a forwarding action at most once; when the node receives a copy of the data packet carrying the same data packet identifier and the same sub-segment identifier for the second or more times within the same sub-segment, it will no longer forward it; since a node may be in the corridor area set of two sub-segments at the same time, when the node receives a copy of the data packet carrying the same data packet identifier but a different sub-segment identifier, it is allowed to perform a forwarding action again within the corresponding sub-segment.

[0030] Furthermore, for ports belonging to the aforementioned oriented port set, with a first forwarding probability Perform a forwarding attempt on the packet; for ports belonging to the non-direction port set, with a second forwarding probability. Perform a forwarding attempt on the data packet; and satisfy the following conditions: .

[0031] Example 3 like Figure 1 As shown, in an example mesh, given a source node and a destination node (e.g., the source node is located at (3,3), and the destination node is located at (15,15)), step S100 is first executed to generate the main path from the source node to the destination node. The main path is generated using a randomized shortest main path method, such as... Figure 1 The dark implementation from the source node to the destination node is shown in the image.

[0032] Next, step S200 is executed to divide the main path into sub-segments and determine relay nodes. The current main path has a hop count of H=24. Within the given segment length constraint range, it is divided as evenly as possible into multiple sub-segments. The end node of each sub-segment is determined as the relay node for that segment, and this relay node serves as the starting point for the next sub-segment. Figure 3Taking the example shown, the main path is divided into segments at two nodes. The first segment is (3,3)~(7,7), the second segment is (7,7)~(15,7), and the third segment is (15,7)~(15,15), with each segment having a length of 8 jumps. The first segment uses (7,7) as the relay node, and the next relay is initiated immediately after (7,7) is reached.

[0033] Then, step S300 is executed to construct a forwardable corridor region for each sub-segment. Taking nodes (3,3) to (7,7) in the first segment as an example, Figure 1 The area enclosed by the dashed line is the union of the regions constructed by the first segment node in the main path. Data packets marked with the first segment are only allowed to be forwarded and propagated within this region.

[0034] Next, step S400 is executed to perform port-oriented probabilistic forwarding within the corridor area. For example... Figure 2 As shown, nodes B and C currently hold a data packet and are ready to forward it. This data packet was forwarded from node A in the previous time step. For nodes B and C, the port of the relay node (7,7) heading towards the current sub-segment uses the first forwarding probability. Except for the port facing node A, the remaining ports all use the second forwarding probability. Forward data packets.

[0035] When a sub-segment relay node receives a data packet, it executes step S500 to immediately begin relaying the next sub-segment. For example... Figure 3 As shown, the relay node D(7,7) of the first segment receives the data packet, and at the current moment changes the sub-segment ID in the data packet to the sub-segment ID of the second segment, and forwards it out according to the port probability in step S400.

[0036] Follow the steps above until the entire network finishes forwarding the data packet, at which point this routing transmission will terminate.

[0037] The end-to-end reliable routing system includes a parameter configuration table (Table 1) for retrieving key parameters during use. Based on the current network error scenario, service preferences, and target performance requirements, the system retrieves the corridor width, first forwarding probability, second forwarding probability, and number of segments from the routing table. Table 2 shows the correlation between each key parameter and target performance metrics, including reachability, total forwarding cost, and end-to-end latency. This is used to determine the direction of parameter adjustment when a direct query in Table 1 is not possible. Table 1 contains recommended parameter configurations derived from extensive simulation experiments on different network error scenarios and corresponding target performance, allowing for direct querying of recommended parameter configurations under given conditions.

[0038] In use, for example in , In error-prone environments, where a reachability of at least 99.9% is required, the corresponding configuration can be directly obtained by referring to Table 2: corridor width set to 4, port forwarding probability... Set to 0.98, Setting it to 0.30, the segmentation method divides the main path into segments with a maximum segment length of 15 hops. With this configuration, reachability can be guaranteed with the least possible packet forwarding overhead.

[0039] In most usage scenarios, the error environment and corresponding reachability requirements cannot be directly matched to those in Table 1. It is necessary to combine the correlation between the various indicators and parameters given in Table 2, refer to the approximate parameter configuration range provided in Table 2, and then conduct simulations on the obtained parameter configurations. Finally, the best-performing set of parameters from the simulation results is selected as the chosen configuration. For example, the current error environment is... , It is necessary to ensure that the data packet reachability is not less than 98.0%, and the minimum distance between the source node and the destination node is... Jump. To quickly obtain the parameter combination that meets the requirements, please refer to Table 1. The corresponding balanced configurations for moderate and minor damage scenarios, combined with Table 2, allow for simulations of the ranges of parameters in these two rows, thus obtaining the corresponding parameter combinations through a small number of simulations.

[0040] More generally, to further reduce the manual intervention required for table lookups and simulations, a neural network model can be constructed and trained based on a large amount of simulation data, selecting parameter combinations that meet the constraints and exhibit superior overall performance. This neural network model takes the shortest path length between the source and destination nodes, network error scenarios, and target performance as inputs, and outputs recommended key parameter combinations, including corridor width, port forwarding probability, and segment partitioning method.

[0041] Table 1

[0042] Table 2

[0043] Example 4 The present invention also provides an end-to-end reliable routing system for error-prone networks, comprising: The first module is used to generate a randomized shortest main path from the source node to the destination node under the current network topology of the error network. The second module is used to divide the randomized shortest main path into multiple sub-segments according to the number of hops and determine the relay node of each sub-segment. The third module is used to plan the forwarding range of data packets within each sub-segment. It selects a set of neighboring nodes centered on the nodes on the main path of the sub-segment, and takes the union of these nodes as the corridor area of ​​the sub-segment. Only nodes within the corridor area are allowed to participate in the forwarding of data packets in the sub-segment. The fourth module is used to perform port-oriented probabilistic forwarding within the corridor area: For each sub-segment, the relay node of the sub-segment is pre-determined, and the relay node is the end node of the sub-segment on the main path of the sub-segment; each forwarding node located within the corridor area of ​​the sub-segment determines the oriented port set according to its position relative to the relay node of its own sub-segment, and the oriented port is the port direction that makes the forwarding node closer to the current sub-segment relay node in the row and column directions; The fifth module is used to trigger the relay of data packet forwarding for the next sub-segment when the relay node of a certain sub-segment first receives the data packet; if the current sub-segment is not the last sub-segment, the relay node is used as the starting forwarding node for the next sub-segment to continue propagating the data packet; if the current sub-segment is the last sub-segment and the relay node is the destination node, the end-to-end transmission of the data packet is completed; wherein, a deduplication mechanism is implemented during the data packet forwarding process of each sub-segment, the nodes include forwarding nodes and relay nodes, and for the same data packet in the same sub-segment, each node performs a forwarding action only once.

[0044] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0045] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0046] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0047] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0048] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit its scope of protection. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that after reading the present invention, they can still make various changes, modifications or equivalent substitutions to the specific implementation of the invention, but these changes, modifications or equivalent substitutions are all within the scope of protection of the pending claims of the invention.

Claims

1. An end-to-end reliable routing method for an error-oriented network, characterized by, Includes the following steps: Step S100: Under the current network topology of the error network, generate a randomized shortest main path from the source node to the destination node; Step S200: Divide the randomized shortest main path into multiple sub-segments according to the number of hops, and determine the relay node of each sub-segment; Step S300: For each sub-segment, plan the forwarding range of data packets within the sub-segment, select a set of neighboring nodes centered on the nodes on the main path of the sub-segment, and take the union of the set as the corridor area of ​​the sub-segment. Only nodes within the corridor area are allowed to participate in the forwarding of data packets in the sub-segment. Step S400: Perform port-oriented probabilistic forwarding within the corridor area: For each sub-segment, pre-determine the relay node for that sub-segment, where the relay node is the end node on the main path of that sub-segment; each forwarding node located within the corridor area of ​​that sub-segment determines its orientation port set based on its position relative to the relay node of its own sub-segment, where the orientation port is the port direction that makes the forwarding node closer to the current sub-segment relay node in both the row and column directions; Step S500: When a relay node in a certain sub-segment receives the data packet for the first time, it triggers the data packet forwarding relay of the next sub-segment; If the current sub-segment is not the last sub-segment, the relay node is used as the starting forwarding node for the next sub-segment to continue propagating the data packet; if the current sub-segment is the last sub-segment and the relay node is the destination node, the end-to-end transmission of the data packet is completed; wherein, a deduplication mechanism is implemented during the forwarding of data packets in each sub-segment, and the nodes participating in the deduplication judgment include forwarding nodes and relay nodes, and for the same data packet in the same sub-segment, each node performs a forwarding action only once.

2. The end-to-end reliable routing method for error-oriented networks according to claim 1, characterized in that, Step S100 generates a randomized shortest main path from the source node to the destination node under the current network topology of the error network. Specifically, it uses a breadth-first search algorithm to search for the shortest hop path from the source node to the destination node under the current network topology of the error network. When performing the breadth-first search, the traversal order of the adjacent nodes of each node is randomized. Finally, a shortest path is randomly obtained from all the shortest paths and is taken as the randomized shortest main path.

3. The end-to-end reliable routing method for error-oriented networks according to claim 1, characterized in that, In step S200, the selection of the number of sub-segments is as follows: Let the number of hops on the main path from the source node to the destination node be H. Given the constraint interval of the segment length, select the minimum number of sub-segments K so that the main path is divided into K segments and the number of hops in each segment falls within the constraint interval of the segment length. The end node of each sub-segment is determined as the relay node of that sub-segment and serves as the starting forwarding node of the next sub-segment.

4. The end-to-end reliable routing method for error-oriented networks according to claim 3, characterized in that, In step S300, the construction of the corridor area is specifically as follows: Let the first... The set of main path nodes corresponding to each sub-segment is: ,in, No. Each node on the main path of each sub-segment For the first The number of main path nodes contained in each sub-segment; with any node Expand in both row and column directions from the center. The side length formed by the jump The square neighborhood is defined as a set ,in, Let the width be the corridor width; then the first... The corridor area of ​​each segment Defined as the union of the square neighborhoods of all nodes on the main path segment: .

5. The end-to-end reliable routing method for error-oriented networks according to claim 4, characterized in that, In step S400, each forwarding node located within the corridor area of ​​the sub-segment determines its orientation port set based on its position relative to the relay node of its sub-segment. The orientation port is the port direction that makes the forwarding node closer to the current relay node in both the row and column directions. Specifically: when there is displacement between the forwarding node and the relay node in the row direction, the orientation port set includes the port direction that reduces the absolute value of the row direction displacement; when there is displacement between the forwarding node and the relay node in the column direction, the orientation port set includes the port direction that reduces the absolute value of the column direction displacement; when there is displacement in both the row and column directions, the orientation port set includes both of the above port directions; the non-orienting port set is defined as all port directions other than the orientation ports and the incoming port; when a port belongs to the orientation port set, it is forwarded with a first forwarding probability. A forwarding attempt is performed on the packet; when the port belongs to the non-directing port set, a second forwarding probability is used. Perform a forwarding attempt on the data packet; And prohibit backoff forwarding via the port from which the signal originates.

6. The end-to-end reliable routing method for error-prone networks according to claim 5, characterized in that, In the probabilistic forwarding of the port orientation of step S400: for the ports belonging to the set of oriented ports, with a first forwarding probability performing a forwarding attempt on the data packet; for the ports belonging to the set of non-oriented ports, with a second forwarding probability performing a forwarding attempt on the data packet; and satisfying .

7. The end-to-end reliable routing method for error-oriented networks according to claim 5, characterized in that, The corridor width , the first forwarding probability , the second forwarding probability , and the number of subsegments are determined by looking up a parameter configuration table, which is obtained by sorting simulation results for different network scales and different network error scenarios.

8. The end-to-end reliable routing method for error-oriented networks according to claim 1, characterized in that, In step S500, the trigger condition for forwarding relay is: when the relay node of a certain sub-segment receives the data packet for the first time, the first round of the relay of that sub-segment is recorded, and the relay node is used as the starting forwarding node of the next sub-segment to initiate the data packet forwarding relay.

9. The end-to-end reliable routing method for error-oriented networks according to claim 1, characterized in that, The deduplication mechanism stipulates that for the same data packet within the same sub-segment, each node shall perform a forwarding action at most once; when the node receives a copy of the same data packet with the same data packet identifier and the same sub-segment identifier for the second or subsequent time within the same sub-segment, it shall not forward it again; since a node may be in the corridor area set of two sub-segments at the same time, when the node receives a copy of the same data packet with the same data packet identifier but a different sub-segment identifier, it is allowed to perform a forwarding action again within the corresponding sub-segment.

10. An end-to-end reliable routing system for an error prone network, characterized by, include: The first module is used to generate a randomized shortest main path from the source node to the destination node under the current network topology of the error network. The second module is used to divide the randomized shortest main path into multiple sub-segments according to the number of hops, and to determine the relay node of each sub-segment. The third module is used to plan the forwarding range of data packets within each sub-segment. It selects a set of neighboring nodes centered on the nodes on the main path of the sub-segment, and takes the union of these nodes as the corridor area of ​​the sub-segment. Only nodes within the corridor area are allowed to participate in the forwarding of data packets in the sub-segment. The fourth module is used to perform port-oriented probabilistic forwarding within the corridor area: For each sub-segment, the relay node of the sub-segment is pre-determined, and the relay node is the end node of the sub-segment on the main path of the sub-segment; each forwarding node located within the corridor area of ​​the sub-segment determines the oriented port set according to its position relative to the relay node of its own sub-segment, and the oriented port is the port direction that makes the forwarding node closer to the current sub-segment relay node in the row and column directions; The fifth module is used to trigger the relay of data packet forwarding to the next segment when the relay node of a certain segment receives the data packet for the first time. If the current sub-segment is not the last sub-segment, the relay node is used as the starting forwarding node for the next sub-segment to continue propagating the data packet; if the current sub-segment is the last sub-segment and the relay node is the destination node, the end-to-end transmission of the data packet is completed; wherein, a deduplication mechanism is implemented during the forwarding of data packets in each sub-segment, and the nodes participating in the deduplication judgment include forwarding nodes and relay nodes, and for the same data packet in the same sub-segment, each node performs a forwarding action only once.

Images