A dynamic routing and traffic balancing method and system for a regionalized network topology

Abstract

The application relates to a dynamic routing and traffic balancing method and system of a regionalized network topology, the method comprising the following steps: dividing a satellite network into multiple partitions, and allocating a core node for traffic scheduling and routing calculation to each partition; each core satellite node responds to each traffic demand, adjusts bandwidth and traffic distribution in each partition through a multi-anchor segment routing method and a preset linear programming model; and each satellite node dynamically adjusts the routing of each traffic demand through a probability forwarding scheduling method based on a geometric topology according to the relative position of the satellite node and a target node. The application realizes low delay, high bandwidth utilization, load balancing and efficient fault recovery of the satellite network through network partitioning, a multi-anchor segment routing method and probability forwarding based on a geometric topology.

Description

Technical Field

[0001] This invention belongs to the field of satellite network technology, and particularly relates to routing optimization and traffic engineering technology for low Earth orbit satellite networks, especially to a dynamic routing and traffic balancing method and system for regionalized network topology. Background Technology

[0002] Low Earth Orbit (LEO) satellite networks have become an important part of the global communications field with technological advancements and the rapid development of LEO satellite constellations. LEO satellites offer advantages such as low latency, high bandwidth, and wide coverage, providing high-quality communication services to users worldwide. Especially in future 6G and Internet of Things (IoT) applications, LEO satellite networks hold immense potential. However, due to the high dynamism of satellite networks, their large constellation size, and the frequent changes in inter-satellite links, traditional routing and traffic management methods face significant challenges.

[0003] First, the link states in the LEO satellite network are constantly changing. Due to the rapid movement of satellites, the communication links between satellites are constantly changing. This highly dynamic network topology makes it difficult for traditional static routing algorithms (such as the shortest path algorithm) or topology-based algorithms to adapt, especially when dealing with large-scale traffic and high-frequency topology changes. Existing methods cannot meet the requirements of low latency, high bandwidth utilization, and load balancing.

[0004] Secondly, most existing routing algorithms rely on the global network state and static topology, ignoring real-time network changes. When faced with sudden traffic surges, link failures, and congestion, traditional algorithms cannot quickly adjust routing paths, leading to a significant decline in network performance and potentially causing service interruptions or unavailability. For example, many shortest-path-based routing algorithms, while providing theoretically optimal path selection, often fail to adapt quickly to dynamic changes in network topology, resulting in high computational complexity and response latency. Furthermore, they cannot rapidly perform dynamic route switching when links fail.

[0005] Furthermore, traffic engineering (TE) techniques have been widely applied in satellite networks in recent years to optimize traffic allocation and improve network bandwidth utilization. However, existing TE methods often suffer from high computational complexity and slow convergence when dealing with the high dynamic characteristics and bursty traffic in LEO satellite networks, especially in large-scale satellite network topologies where traditional TE methods struggle to achieve real-time and fast traffic optimization. In addition, most existing TE algorithms rely on complex models and calculations, often requiring significant computational resources, thus failing to meet the requirements of real-time and efficient traffic scheduling in satellite networks.

[0006] Although some studies have proposed adaptive routing algorithms and fault recovery mechanisms to improve the fault tolerance and resilience of satellite networks, these methods still face many challenges. Most existing adaptive routing algorithms assume that the network state is relatively stable and usually require global route recalculation for the entire network. This not only incurs high computational overhead but may also lead to significant latency, especially in dynamically changing network environments, making it difficult to achieve real-time fault recovery and traffic load balancing.

[0007] To address the above issues, existing research mainly focuses on the following directions: On the one hand, dynamic routing methods based on traffic prediction have been proposed, aiming to optimize routing paths based on network traffic prediction information. However, this method has poor adaptability under dynamic topology and requires a large amount of computation. On the other hand, for the fault recovery problem in satellite networks, distributed routing algorithms based on region partitioning have been proposed, which can make local route adjustments in certain situations. However, these methods still have certain limitations in large-scale networks, especially in their inability to efficiently cope with large-scale faults and dynamic traffic fluctuations. Summary of the Invention

[0008] To address the issues of link failures, traffic congestion, and uneven load distribution in large-scale satellite networks, a first aspect of this invention provides a dynamic routing and traffic balancing method for regionalized network topologies, comprising: dividing the satellite network into multiple partitions and allocating core nodes for traffic scheduling and route calculation to each partition; each core satellite node responding to each traffic demand by adjusting the bandwidth and traffic allocation within each partition using a multi-anchor segment routing method and a preset linear programming model; and each satellite node dynamically adjusting the route for each traffic demand based on its relative position to the target node using a probabilistic forwarding scheduling method based on geometric topology.

[0009] In some embodiments of the present invention, adjusting the bandwidth and traffic allocation within each partition using a multi-anchor segment routing method and a preset linear programming model includes: decomposing each traffic demand into multiple sub-flows, with each sub-flow scheduling traffic through multiple anchor nodes; and adjusting the bandwidth and traffic allocation within each partition based on a preset linear programming model.

[0010] In some embodiments of the present invention, the preset linear programming model is determined by the following method: constructing an objective function based on maximizing link utilization; using the total traffic size, the ratio of the total traffic size to the capacity of each link, and the non-negativity of traffic allocation as constraints; and constructing a linear programming model based on the objective function and the constraints.

[0011] In some embodiments of the present invention, the method of dynamically adjusting the routing of nodes in each partition through the probabilistic forwarding scheduling method based on geometric topology includes: constructing a topology graph of partition nodes; obtaining the current coordinates and next-hop area landmark coordinates of each node in the partition based on the topology graph; and calculating the upward forwarding probability and the rightward forwarding probability respectively based on the current coordinates and next-hop area landmark coordinates of each node in the partition, according to the shortest path principle.

[0012] In some embodiments of the present invention, the method further includes: when a link failure or network congestion occurs in a partition, a greedy routing algorithm and a preset source routing table are used to perform local path adjustment on the path of the faulty area.

[0013] Furthermore, the local path adjustment of the path in the fault area using a greedy routing algorithm and a preset source routing table includes: replanning the path in the fault area using a greedy routing algorithm; each satellite node writing a candidate path into the packet header based on the preset source routing table; and subsequent satellite nodes obtaining the routing information of the next-hop satellite through the packet header.

[0014] A second aspect of the present invention provides a dynamic routing and traffic balancing system for a regionalized network topology, comprising: a partitioning module for dividing a satellite network into multiple partitions and allocating core nodes for traffic scheduling and route calculation to each partition; a first adjustment module for each core satellite node to respond to each traffic demand by adjusting the bandwidth and traffic allocation within each partition using a multi-anchor segment routing method and a preset linear programming model; and a second adjustment module for each satellite node to dynamically adjust the routing of each traffic demand based on its relative position to the target node using a probabilistic forwarding scheduling method based on geometric topology.

[0015] Furthermore, the first adjustment module includes: a decomposition unit, used to decompose each traffic demand into multiple sub-flows, each sub-flow scheduling traffic through multiple anchor nodes; and an adjustment unit, used to adjust the bandwidth and traffic allocation within each partition based on a preset linear programming model.

[0016] A third aspect of the present invention provides an electronic device comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the dynamic routing and traffic balancing method for regionalized network topology provided in the first aspect of the present invention.

[0017] In a fourth aspect, the present invention provides a computer-readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the dynamic routing and traffic balancing method for regionalized network topology provided in the first aspect of the present invention.

[0018] The beneficial effects of this invention are:

[0019] This invention proposes a lightweight routing optimization method that combines regional partitioning and traffic engineering. By dividing the satellite network into multiple management zones and employing multi-anchor segment routing and probabilistic forwarding mechanisms, it can effectively achieve dynamic traffic scheduling and rapid fault recovery, optimize load distribution, and improve bandwidth utilization, thereby enhancing the overall performance and reliability of the LEO satellite network. Attached Figure Description

[0020] Figure 1 This is a basic flowchart illustrating the dynamic routing and traffic balancing method for regionalized network topology in some embodiments of the present invention.

[0021] Figure 2 This is a schematic diagram of a LEO satellite network in some embodiments of the present invention;

[0022] Figure 3 This is a schematic diagram of low-orbit constellation partitioning in some embodiments of the present invention;

[0023] Figure 4 This is a schematic diagram of a segmented routing algorithm in some embodiments of the present invention;

[0024] Figure 5 This is a schematic diagram of a probabilistic forwarding algorithm in some embodiments of the present invention;

[0025] Figure 6 This is a schematic diagram of the flow band region in some embodiments of the present invention;

[0026] Figure 7 This is a schematic diagram of hierarchical partitioning and local segment routing in some embodiments of the present invention;

[0027] Figure 8 This is a schematic diagram of the structure of a dynamic routing and traffic balancing device for a regionalized network topology in some embodiments of the present invention.

[0028] Figure 9 This is a schematic diagram of the structure of an electronic device in some embodiments of the present invention. Detailed Implementation

[0029] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0030] refer to Figure 1 and Figure 2In a first aspect of the present invention, a dynamic routing and traffic balancing method for a regionalized network topology is provided, comprising: S100. Dividing a satellite network into multiple partitions and allocating a core node for traffic scheduling and route calculation to each partition; S200. Each core satellite node responds to each traffic demand by adjusting the bandwidth and traffic allocation within each partition using a multi-anchor segment routing method and a preset linear programming model; S300. Each satellite node dynamically adjusts the route for each traffic demand based on its relative position to the target node using a probabilistic forwarding scheduling method based on geometric topology.

[0031] refer to Figure 2 In step S100 of some embodiments of the present invention, the satellite network is divided into multiple partitions, and a core node for traffic scheduling and routing calculation is assigned to each partition;

[0032] Specifically, assuming the LEO satellite network is a large distributed network, the network is divided into... The system comprises several regions, each with multiple satellites. Each region serves as a management unit and is designated with a landmark node. As the core node and communication hub of this partition, the entire satellite network is abstracted into a skeleton diagram composed of landmark nodes through this partitioning method, denoted as […]. ,in Represents a set of regions. This represents the set of communication links between regions. A schematic diagram of the partitioned structure is shown below. Figure 3 As shown.

[0033] Based on this, we treat the region as a whole and select the sum of the bandwidth that all satellites within the region can accommodate as the load for that region. Here, we assume that the bandwidth that each satellite can accommodate is equal and is... Specifically, let each region... The load is:

[0034] ,

[0035] in, Indicates the area The number of satellites within the region. To the area Link The maximum flow capacity is defined as:

[0036] ,

[0037] This definition ensures that the capacity of any communication link will not exceed the total bandwidth load of any area in its connected region.

[0038] This regional division allows each part of the network to be managed independently, thereby reducing the complexity of overall network routing calculations. Each region acts as an aggregate entity, managing its own traffic scheduling and routing, and communicating only with representative nodes in neighboring regions. Nodes within a region forward data to their representative nodes according to pre-defined rules, ensuring even traffic distribution and balanced network load.

[0039] In the skeleton diagram model, we considered Each flow tunnel. Source satellite and target satellite Composition, with corresponding traffic requirements The main goal of traffic tunneling planning is to achieve overall network load balancing by evenly distributing communication load across different areas, thereby preventing overload of specific links and alleviating performance bottlenecks.

[0040] Therefore, in step S200 of some embodiments of the present invention, adjusting the bandwidth and traffic allocation within each partition using the multi-anchor segment routing method and the preset linear programming model includes:

[0041] S201. Decompose each traffic demand into multiple sub-flows, and schedule traffic for each sub-flow through multiple anchor nodes; S202. Adjust the bandwidth and traffic allocation within each partition based on a preset linear programming model.

[0042] Specifically, assuming each flow tunnel Total flow is Then divide it into Servings, each serving has a volume of [missing information]. Each piece of traffic will be forwarded along a different set of anchor points. Specifically, for a traffic tunnel... and the established anchor point group We can determine an independent path. For a path This represents a communication link between two areas. Passing traffic It can be calculated using the following formula:

[0043] ,

[0044] in, For indicator functions, when the path Includes links hour, ,otherwise This formula indicates that the link The total traffic on the link is the sum of the traffic allocated to all paths through that link.

[0045] To achieve optimal load balancing, a linear programming model can be used to minimize the maximum utilization of links in the network.

[0046] Therefore, refer to Figure 4 In step S200 of some embodiments of the present invention, the preset linear programming model is determined by the following method: S203. Construct an objective function based on maximizing link utilization; S204. Use the total traffic size, the ratio of the total traffic size to the capacity of each link, and the non-negativity of traffic allocation as constraints; S205. Construct a linear programming model based on the objective function and the constraints.

[0047] Specifically, the model can be represented as:

[0048] ;

[0049]

[0050] (1)

[0051] (2)

[0052] ;(3)

[0053] in, To pass through the path The amount of traffic forwarded For link capacity, This is the upper limit for link utilization. Constraint (1) ensures that the total traffic of each traffic tunnel is satisfied; Constraint (2) limits the total traffic on each link to no more than a certain percentage of its capacity. The load is multiplied by 100 to achieve load balancing; constraint (3) ensures the non-negativity of traffic distribution. By solving this linear programming model, traffic can be effectively distributed to each path, ensuring load balancing and efficient resource utilization in the network.

[0054] Specifically, for a set of anchor points, data packets are first forwarded along the source node region towards the anchor point region, with the entry and exit directions perpendicular. Routing follows the shortest path principle, meaning forwarding occurs along the rectangular boundary formed by the two nodes. Theoretically, there are two optimal paths for forwarding along the bounding box. Because the entry and exit directions are perpendicular, the vector... The first anchor point uniquely determines the path of all subsequent nodes. Vector subsequent nodes The decision was made and Segment routing.

[0055] For example, the key code for the region-based multi-anchor segment routing method (MN-ACSR) is as follows:

[0056] Divide the satellite network into regional sets And identify the landmark nodes of the area. ;

[0057] Initialize skeleton link Determine link capacity ;

[0058] Building a skeleton diagram ;

[0059] for to do:

[0060] Location source / target area landmark: , ,

[0061] Generate candidate anchor set ,

[0062] Construct a linear programming model,

[0063] Solving for and ;

[0064] for to do:

[0065] The landmark group corresponding to the anchor point is obtained through the anchor point forwarding rules. ,

[0066] Initialize the current node ;

[0067] for to do:

[0068] ,

[0069] end for;

[0070] end for;

[0071] end for.

[0072] By incorporating a software-defined networking (SDN) architecture, MN-ACSR can monitor network status in real time and dynamically adjust anchor point selection and traffic allocation strategies to adapt to dynamic changes in network topology and traffic demands. This dynamic management mechanism not only improves the overall performance and reliability of the network but also enhances the system's robustness under high load and failure conditions, thereby significantly improving the resource utilization efficiency and overall performance of low Earth orbit (LEO) satellite networks.

[0073] In the traffic engineering section, this invention proposes a multi-anchor segment routing method (MN-ACSR) based on region partitioning. The algorithm pseudocode is shown in Algorithm 1. This method decomposes each traffic demand into multiple sub-flows and schedules the traffic through different anchor nodes. Each sub-flow is transmitted on different paths, which are calculated through optimization to achieve load balancing and bandwidth maximization.

[0074] To further optimize traffic scheduling, this disclosure introduces a probabilistic mechanism within the region. However, due to the cumulative effect of probabilistic forwarding, links near the rectangular region boundary may experience greater traffic load, leading to high traffic concentration. To mitigate this phenomenon, this application employs a forwarding probabilistic scheduling method based on geometric topology characteristics to balance traffic distribution.

[0075] refer to Figure 5 and Figure 6 In step S300 of some embodiments of the present invention, the dynamic adjustment of the routing of nodes within each partition using the probabilistic forwarding scheduling method based on geometric topology includes:

[0076] S301. Construct a topology graph of the partition nodes;

[0077] S302. Based on the topology graph, obtain the current coordinates of the nodes in each partition and the coordinates of the next-hop area landmark;

[0078] S303. Based on the current coordinates of the node in each partition and the coordinates of the next-hop area landmark, calculate the upward forwarding probability and the rightward forwarding probability respectively using the shortest path principle.

[0079] Specifically, each satellite dynamically calculates its forwarding probability based on its relative position to the target node, as shown in Algorithm 2. Specifically, assume the satellite is currently located at coordinates... Next jump area landmark Located at coordinates According to the probabilistic forwarding principle, satellite nodes will forward data in two directions based on the shortest path principle. The probability of forwarding upward is... and the probability of forwarding to the right They are respectively:

[0080] ,

[0081] When a data packet enters the next region, if the satellite is located at the boundary, the forwarding probability will be recalculated based on the new satellite coordinates. Assume the current boundary satellite coordinates are... The coordinates of the next jump area landmark are The forwarding probability from the current region to the next region is:

[0082] .

[0083] For example, the reference code for the forwarding probability scheduling method (Adaptive Forwarding) based on geometric topology characteristics is as follows:

[0084] Input: Skeleton diagram Current node Next jump landmark .

[0085] Output: Updated node ,

[0086] Calculate the relative coordinate difference:

[0087] ;

[0088] Determine the forwarding direction:

[0089] if then:

[0090] Sure Axis Neighbor Satellites and y-axis neighbor satellites ,

[0091] Calculate probability weights:

[0092] ,

[0093] Probabilistically forward data packets to two neighboring satellites until the data packets reach the region boundary;

[0094] else:

[0095] Directly towards the target landmark Forward until the data packet reaches the area boundary;

[0096] end if;

[0097] return the updated current node.

[0098] It's understandable that traffic will form a divergent band-shaped area. This method distributes traffic more evenly within the band between the source and sink. The larger the band, the wider the traffic distribution area, and the better the load balancing effect. Compared to traditional single-path routing schemes, probabilistic forwarding effectively ensures even traffic distribution across each link and allows for individual optimization for different traffic tunnels, thus avoiding mutual interference between traffic tunnels and link congestion.

[0099] Meanwhile, the probabilistic forwarding mechanism eliminates the need for frequent path determination requests from the controller, making path selection more efficient and real-time. This routing method significantly improves the efficiency of traffic forwarding within the region and the overall system performance.

[0100] When link failures or network congestion occur, local path adjustment strategies are required.

[0101] Therefore, refer to Figure 7 In some embodiments of the present invention, the steps further include: step S400. When a link failure or network congestion occurs in a partition, the path of the faulty area is locally adjusted by using a greedy routing algorithm and a preset source routing table.

[0102] Specifically, given our satellite cluster partitioning strategy, each region can be considered a "black box" to other regions, meaning other regions do not need to know the current traffic distribution and satellite load status. This partitioning strategy simplifies the complexity of routing planning and enables local path optimization. Especially when traffic congestion or failure occurs in a certain region, we only need to optimize the paths in that region, rather than replanning the entire network. This significantly reduces computational complexity and avoids the performance loss that might result from global path recalculation.

[0103] After traffic congestion or link failure information is reported to the ground controller, the controller quickly identifies the affected area and re-plans routes for that area. At this time, probabilistic multipath routing is temporarily disabled, and a more precise greedy routing algorithm is used instead, such as... Algorithms are used to optimize traffic paths. This strategy allows traffic to precisely avoid faulty areas or congestion points, ensuring that traffic can bypass problem areas more effectively and reduce network load.

[0104] Because probabilistic multipath routing is used, the original data packets could not predict which specific satellites they would be forwarded to the next regional boundary. To address this issue, the ground station pre-calculates and stores all possible paths from the source satellite to the next regional landmark based on the current congestion situation, and stores these calculation results in the relevant boundary satellites. When a data packet arrives at a boundary satellite, the satellite reads its stored routing path, writes this routing path information into the packet header, and then forwards the data packet to the next-hop satellite.

[0105] Furthermore, we introduce the principle of source routing tables. In this routing method, every satellite can potentially act as a source satellite. Specifically, when a source satellite performs path calculation, it writes the calculated routing table into the packet header. Subsequent satellites can then read the header information to obtain the location of the next-hop satellite. In this way, each satellite can automatically select a path based on the header information, ensuring that packets are forwarded smoothly along the predetermined path. This continues until the packet reaches the boundary satellite of the next region, at which point that boundary satellite becomes the new source satellite, and similar routing calculations are performed. Once the packet reaches the boundary of the next region, the probabilistic multipath routing mechanism restarts, and subsequent traffic forwarding reverts to a probabilistic forwarding principle. Through this dynamic routing adjustment mechanism, we can respond quickly to link failures or congestion issues, effectively allocate traffic, and maintain network stability and efficiency while minimizing computational overhead.

[0106] It is understood that, through the above methods, this invention can achieve low latency, high bandwidth utilization, load balancing, and efficient fault recovery in large-scale, dynamically changing LEO satellite networks. The strategy of regional partitioning and local path adjustment demonstrates better adaptability and efficiency in network scale and dynamic environments.

[0107] Example 2

[0108] refer to Figure 8 In a second aspect, the present invention provides a dynamic routing and traffic balancing system 1 for regionalized network topology, comprising: a partitioning module 11 for dividing a satellite network into multiple partitions and allocating core nodes for traffic scheduling and route calculation to each partition; a first adjustment module 12 for each core satellite node to respond to each traffic demand by adjusting the bandwidth and traffic allocation within each partition through a multi-anchor segment routing method and a preset linear programming model; and a second adjustment module 13 for each satellite node to dynamically adjust the routing of each traffic demand based on its relative position to the target node through a probabilistic forwarding scheduling method based on geometric topology.

[0109] Furthermore, the first adjustment module 12 includes: a decomposition unit, used to decompose each traffic demand into multiple sub-flows, each sub-flow scheduling traffic through multiple anchor nodes; and an adjustment unit, used to adjust the bandwidth and traffic allocation within each partition based on a preset linear programming model.

[0110] Example 3

[0111] refer to Figure 9 In a third aspect, the present invention provides an electronic device comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the dynamic routing and traffic balancing method for regionalized network topology of the first aspect of the present invention.

[0112] Electronic device 500 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from storage device 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of electronic device 500. The processing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. An input / output (I / O) interface 505 is also connected to bus 504.

[0113] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, hard disks; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 9 An electronic device 500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 9 Each box shown can represent a device or multiple devices as needed.

[0114] Specifically, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by a processing device 501, it performs the functions defined in the methods of embodiments of this disclosure. It should be noted that the computer-readable medium described in embodiments of this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0115] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more computer programs, which, when executed by the electronic device, cause the electronic device to:

[0116] Computer program code for performing the operations of embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, C++, and Python—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0117] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0118] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. 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 dynamic routing and traffic balancing method for regionalized network topology, characterized in that, include: The satellite network is divided into multiple partitions, and a core node is assigned to each partition for traffic scheduling and routing calculation. Each core satellite node responds to each traffic demand by adjusting the bandwidth and traffic allocation within each partition using a multi-anchor segment routing method and a pre-defined linear programming model. Each satellite node dynamically adjusts the route for each traffic demand based on its relative position to the target node using a probabilistic forwarding scheduling method based on geometric topology: constructing a topology map of the partition nodes; Based on the topology graph, obtain the current coordinates of the node in each partition and the coordinates of the next-hop area landmark. Based on the current coordinates of the node within each partition and the coordinates of the next-hop area landmark, the upward forwarding probability and the rightward forwarding probability are calculated respectively using the shortest path principle.

2. The dynamic routing and traffic balancing method for regionalized network topology according to claim 1, characterized in that, The method of adjusting bandwidth and traffic allocation within each partition using a multi-anchor segment routing method and a preset linear programming model includes: Each traffic demand is broken down into multiple sub-flows, and each sub-flow schedules traffic through multiple anchor nodes; Based on a pre-defined linear programming model, the bandwidth and traffic allocation within each partition are adjusted.

3. The dynamic routing and traffic balancing method for regionalized network topology according to claim 1, characterized in that, The preset linear programming model is determined by the following method: Based on maximizing link utilization, an objective function is constructed. The constraints are the total traffic volume, the ratio of the total traffic volume to the capacity of each link, and the non-negativity of traffic allocation. Based on the objective function and the constraints, a linear programming model is constructed.

4. The dynamic routing and traffic balancing method for regionalized network topology according to claim 1, characterized in that, Also includes: When a link failure or network congestion occurs in a partition, a greedy routing algorithm and a preset source routing table are used to adjust the path in the faulty area locally.

5. The dynamic routing and traffic balancing method for regionalized network topology according to claim 4, characterized in that, The step of adjusting the local paths in the fault area using a greedy routing algorithm and a preset source routing table includes: The path to the faulty area is replanned using a greedy routing algorithm; Based on the preset source routing table, each satellite node writes the candidate path into the packet header; Subsequent node satellites obtain the routing information of the next-hop satellite through the packet header.

6. A dynamic routing and traffic balancing system for a regionalized network topology, characterized in that, include: The partitioning module is used to divide the satellite network into multiple partitions and assign a core node for traffic scheduling and routing calculation to each partition; The first adjustment module is used by each core satellite node to respond to each traffic demand by adjusting the bandwidth and traffic allocation within each partition through a multi-anchor segment routing method and a preset linear programming model. The second adjustment module is used by each satellite node to dynamically adjust the route of each traffic demand based on its relative position with the target node, using a probabilistic forwarding scheduling method based on geometric topology: constructing a topology map of the partition nodes; Based on the topology graph, obtain the current coordinates and next-hop area landmark coordinates of the nodes in each partition; based on the current coordinates and next-hop area landmark coordinates of the nodes in each partition, calculate the upward forwarding probability and the rightward forwarding probability respectively according to the shortest path principle.

7. The dynamic routing and traffic balancing system for regionalized network topology according to claim 6, characterized in that, The first adjustment module includes: The decomposition unit is used to decompose each traffic demand into multiple sub-flows, and each sub-flow schedules traffic through multiple anchor nodes. The adjustment unit is used to adjust the bandwidth and traffic allocation within each partition based on a preset linear programming model.

8. An electronic device, comprising: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the dynamic routing and traffic balancing method for a regionalized network topology as described in any one of claims 1 to 5.

9. A computer-readable medium having a computer program stored thereon, wherein, When the computer program is executed by the processor, it implements the dynamic routing and traffic balancing method for regionalized network topology as described in any one of claims 1 to 5.

Images