A low earth orbit satellite congestion control method based on artificial immune algorithm

Abstract

The application discloses a low-orbit satellite congestion control method based on an artificial immune algorithm, which comprises the following steps: a satellite node periodically monitors the occupancy rate of an output queue in each direction, when congestion is detected, the satellite generates a congestion warning packet as an antigen and sends it to a directly adjacent node; the adjacent node receiving the congestion warning packet finds a matching item of an affected destination node in a historical memory cell library through the similarity between the current scene and the historical record, as the routing strategy of the destination node; when no match is found, the optimal bypass strategy is determined based on the direction of the congestion link and the position information of the satellite; the satellite comprehensively evaluates the generated control strategy within a time window; when the affinity continues to fail to reach a threshold, the satellite continuously monitors the queue occupancy rate change trend, and when it is found that a continuous multiple periods show an upward trend, the shunt proportion is increased; the application improves the response speed of the congestion control, network performance and service quality.

Description

Technical Field

[0001] This invention relates to the field of satellite communication network technology, and specifically to a low-orbit satellite congestion control method based on an artificial immune algorithm. Background Technology

[0002] With the continued growth of global communication demands, low-Earth orbit (LEO) satellite networks, with their advantages of low latency and wide coverage, are becoming a key component of next-generation communication systems. However, as satellite networks expand and traffic surges, network congestion is becoming increasingly prominent, severely impacting service quality and user experience.

[0003] Traditional terrestrial network congestion control methods are no longer suitable for low-Earth orbit (LEO) satellite networks. This is mainly because LEO satellite networks have the following unique characteristics: First, the high-speed movement of satellite nodes leads to dynamic changes in network topology; second, the limited bandwidth and high transmission latency of inter-satellite links place higher demands on congestion control; and finally, the limited computing and storage resources of satellite nodes make it difficult to support complex control algorithms.

[0004] Currently, most existing satellite network congestion control schemes employ simple routing bypass strategies, directly diverting traffic entirely to alternative paths when link congestion is detected. While simple to implement, this method has serious drawbacks: firstly, the lack of a reasonable traffic scheduling mechanism easily leads to the spread of congestion problems throughout the network; secondly, the complete bypass strategy often significantly increases transmission latency and reduces network resource utilization. More importantly, these methods cannot learn from historical experience and are ill-equipped to cope with dynamic changes in network conditions.

[0005] Furthermore, existing congestion control schemes often overlook the physical characteristics of low-Earth orbit satellite networks, particularly the link instability issues in special environments such as polar regions. Due to the significant convergence characteristics of satellite orbits in the vicinity of the polar regions, the relative motion between adjacent satellites is more intense. Coupled with the impact of harsh weather conditions, traditional congestion control strategies are unable to guarantee the stable operation of the network.

[0006] Based on the above problems, there is an urgent need for an intelligent control strategy that can fully consider the characteristics of low-Earth orbit satellite networks, effectively control network congestion, and maintain network stability. This strategy should possess adaptive learning capabilities, able to acquire knowledge from historical experience and make timely adjustments based on dynamic changes in the network state. Simultaneously, it must consider the network's physical characteristics and resource constraints to ensure the practicality and reliability of the control strategy. Summary of the Invention

[0007] To address the congestion control problem in low-Earth orbit (LEO) satellite networks, this invention provides a congestion control method for LEO satellites based on an artificial immune algorithm. By introducing the adaptive mechanism of the biological immune system into the congestion control process and combining it with a gridded routing framework, this invention offers a novel solution for intelligent congestion control in LEO satellite networks. This solution not only effectively alleviates network congestion but also possesses learning and adaptive capabilities, improving the network's service quality and resource utilization, thus laying the foundation for building a more efficient and reliable satellite communication network.

[0008] This invention discloses a low-Earth orbit satellite congestion control method based on an artificial immune algorithm, comprising:

[0009] Step 1: Map the satellites of the low-Earth orbit constellation to virtual grid coordinates using a gridding method;

[0010] Step 2: Based on the constructed grid framework, satellite nodes periodically monitor the occupancy rate of output queues in each direction; when congestion is detected, the satellite node generates a congestion warning packet and sends it to its immediate neighboring nodes.

[0011] Step 3: The neighboring nodes that receive the congestion warning packet analyze the set of affected destination nodes according to their own forwarding needs, and search for matching items of affected destination nodes in the historical memory cell library based on the similarity between the current scene and the historical records; when a memory cell with similarity exceeding the threshold is found, the alternative paths and diversion ratio stored therein are directly applied as the routing strategy for the affected nodes; otherwise, the antibody generation process in step 4 is triggered.

[0012] Step 4: Based on the congestion information obtained in Step 3, the satellite first analyzes the directional characteristics of the congested links and, combined with the location information in Step 1, determines the optimal detour strategy. After determining the alternative paths, the satellite sets an initial diversion threshold and generates a random number between [0,1] for each data packet to be forwarded to make a diversion decision, thereby achieving balanced distribution of traffic.

[0013] Step 5: Based on the control strategy generated in Step 4, the satellite performs a comprehensive evaluation within the time window [t0, t0+Δt]. When the affinity continues to exceed the threshold, the strategy information is passed to Step 7 for storage; otherwise, it proceeds to Step 6 for optimization.

[0014] Step 6: For strategies with insufficient affinity in Step 5, the satellite continuously monitors the trend of queue occupancy. When an upward trend is found for several consecutive cycles, the diversion ratio is increased. The optimized strategy is re-entered into Step 5 for evaluation until the expected performance requirements are met.

[0015] Step 7: The satellite stores the high-performance strategy from Step 5 as an effective antibody in the memory cell bank in the form of a quadruple.

[0016] As a further improvement of the present invention, step 1 specifically includes:

[0017] Each satellite node is mapped to virtual grid coordinates (x, y) according to its orbital plane number i and satellite number j, through the following mapping relationship; where,

[0018] x = i (i ∈ [0, N-1])

[0019] y=(j+i×δ)mod M(j∈[0,M-1])

[0020] In the formula, δ is the phase offset between adjacent orbital planes. The low-Earth orbit constellation consists of N orbital planes, with M satellites evenly distributed on each orbital plane.

[0021] As a further improvement of the present invention, in step 2, three levels of congestion are set: idle state: output queue occupancy rate ρ < 50%, mild congestion: 50% ≤ ρ < 75%, and severe congestion: ρ ≥ 75%.

[0022] As a further improvement of the present invention, in step 3, the similarity between the current scene and the historical records is calculated using the Jaccard coefficient:

[0023]

[0024] In the formula, D is the set of affected nodes stored in the history memory cell, and D′ is the affected destination node;

[0025] When a memory cell with a similarity exceeding the threshold θ is found, its stored alternative paths and diversion ratios are directly applied; otherwise, the antibody generation process in step 4 is triggered.

[0026] As a further improvement of the present invention, in step 4, the method for determining the optimal detour strategy includes:

[0027] For congested links in the east-west direction, the satellite compares the row coordinates of the current node and the target node: if the target node is above, it chooses to detour northward; if it is below, it chooses to detour southward.

[0028] For congested links in the north-south direction, the route is detoured to the east or west based on the difference in column coordinates.

[0029] As a further improvement of the present invention, in step 5, the affinity calculation formula is as follows:

[0030] Affinity(Ab)=w1×ΔρR+w2×ηT+w3×(1-ρmax)

[0031] In the formula, ΔρR=(ρ(t0)-ρ(t0+Δt)) / ρ(t0) represents the relative reduction in queue occupancy, ηT=T(t0+Δt) / T(t0) represents the throughput maintenance rate, ρmax represents the maximum queue occupancy within the window, and the weighting coefficients satisfy w1+w2+w3=1.

[0032] As a further improvement of the present invention, in step 6, when an upward trend is found for three consecutive cycles, the diversion ratio p is adjusted to p_new = p_current + 5%.

[0033] As a further improvement of the present invention, in step 6, in order to ensure network stability, the satellite sets upper and lower thresholds for the offloading ratio: the lower limit of 20% ensures the basic utilization rate of the main path, and the upper limit of 80% prevents the alternative path from being overloaded; when the offloading ratio reaches the threshold, the satellite locks the current configuration for at least 100 time units to avoid network oscillations caused by frequent adjustments.

[0034] As a further improvement of the present invention, in step 7, the satellite stores the high-performance strategy from step 5 into the memory cell bank in the form of a quadruple MC = (L, A, S, D), where L is the congested link identifier, A is the set of alternative paths determined in step 4, S is the final optimized diversion ratio, and D is the set of affected destination nodes obtained from step 3.

[0035] As a further improvement of the present invention, in step 7, the satellite performs a cleanup every preset time unit to evaluate the usage frequency of memory cells and remove memory cells that have been used zero times in the most recent evaluation period. When a new congestion scenario occurs, the satellite prioritizes calculating the Jaccard similarity with the stored memory cells. When a memory cell with a similarity exceeding the threshold is found, its stored control strategy is directly reused to achieve a rapid response to recurring congestion.

[0036] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0037] 1. This invention is based on a gridded routing framework and employs a virtual grid mapping strategy to simplify complex physical topologies into regular structures, significantly reducing the complexity of routing calculations. Particularly in handling link instability issues in polar regions, it achieves efficient and reliable path selection through a location-aware mechanism.

[0038] 2. This invention is similar to the working mechanism of a biological immune system, but unlike traditional immune algorithms, it employs a lightweight control mechanism that significantly reduces control overhead through local control and targeted propagation. Simultaneously, the optimized gradual adjustment strategy avoids drastic network fluctuations, making the solution more suitable for deployment on resource-constrained satellite nodes.

[0039] 3. This invention adds adaptive learning capabilities to satellite networks, but this process is transparent to other parts of the network and does not require changes to the existing network architecture, thus exhibiting excellent deployability. Through the memory cell mechanism, the system can quickly learn from historical experience, significantly improving the response speed to recurring congestion.

[0040] 4. Existing satellite network congestion control strategies mostly employ complete bypass schemes, which, while simple to implement, often lead to a severe waste of network resources. In contrast, this invention dynamically adjusts traffic allocation through an intelligent traffic splitting mechanism, ensuring both the rational utilization of congested links and preventing network instability. Especially when handling sudden traffic surges, the gradual adjustment strategy can better maintain network stability.

[0041] In summary, this invention has significant advantages over existing technologies in terms of routing efficiency, resource utilization, network stability, and control overhead, providing an innovative solution for the intelligent management of large-scale satellite networks. Attached Figure Description

[0042] Figure 1 This is a flowchart of the low-orbit satellite congestion control method based on artificial immune algorithm in this invention.

[0043] Figure 2 This is a schematic diagram of a satellite congestion link in this invention.

[0044] Figure 3 This is a schematic diagram of the artificial immune algorithm for traffic diversion processing of congested links in this invention.

[0045] Figure 4 This is a flowchart of antibody generation in this invention. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0047] The present invention will now be described in further detail with reference to the accompanying drawings:

[0048] This invention provides a low-Earth orbit satellite congestion control method based on an artificial immune algorithm. By establishing a gridded routing framework and combining it with a biological immune mechanism, it can effectively solve the performance bottleneck problem faced by traditional satellite network congestion control, improve the congestion control response speed, and enhance the network's service quality and resource utilization.

[0049] Existing satellite network congestion control methods have several limitations: First, traditional methods often employ passive response strategies, lacking the ability to predict congestion and resulting in delayed responses; second, the current full traffic switching scheme is too simplistic and crude, as suddenly shifting all traffic to backup paths can easily trigger network instability and chain reactions; third, existing methods often fail to fully consider the special regional effects in satellite networks, such as the orbital convergence characteristics in polar regions; and finally, these methods lack the necessary learning capabilities, failing to learn from historical congestion events and requiring the re-execution of the entire decision-making process even when facing similar congestion scenarios.

[0050] In this invention, an efficient grid mapping mechanism is first designed based on the physical characteristics of the satellite constellation. Since LEO satellite constellations are typically deployed in polar orbits, consisting of multiple orbital planes with several satellites evenly distributed on each plane, forming a regular network structure, this physical topology is mapped to a virtual grid structure. Each satellite node can quickly determine its position in the grid based on its orbital plane number and satellite number, thus significantly simplifying the routing calculation process.

[0051] When the system detects that the queue occupancy rate of a certain link exceeds a preset threshold, it considers a congestion state to have occurred. At this time, the congested node generates a Congestion Warning Packet (CWP) containing the congested link identifier and status information, which is sent as an antigen to neighboring nodes. Neighboring nodes receiving the CWP first analyze the set of affected destination nodes, and then search for similar historical congestion scenarios in their memory cell database. Through similarity calculation based on the Jaccard coefficient, if a memory cell with a similarity exceeding the threshold is found, the node can directly reuse the stored control strategy to achieve a rapid response to congestion.

[0052] For newly emerging congestion patterns, the system triggers an antibody generation process. Based on the grid structure and target node locations, the system first determines appropriate detour directions and generates a set of alternative paths. Then, a random decision-making mechanism is used to distribute data packets, ensuring both priority use of the main path and balanced traffic distribution. During the control process, the system continuously evaluates the effectiveness of the strategy, and when the affinity does not meet expectations, it optimizes the control strategy through gradual parameter adjustments. This closed-loop immune response mechanism ensures both the real-time performance and effectiveness of congestion control, while continuously learning and optimizing to improve the system's adaptability.

[0053] The main contents of this invention include:

[0054] 1. Mesh-based routing and geolocation awareness mechanism: An efficient mapping scheme based on the physical network to the virtual mesh is constructed, mapping the orbital numbers of satellite nodes to two-dimensional mesh coordinates, significantly simplifying routing calculations. Through a dynamic location mapping algorithm, the system can calculate the geolocation of satellite nodes in real time and accurately identify special areas such as polar convergence zones. Based on this, an adaptive path selection strategy considering geolocation is designed, which effectively avoids transmission problems caused by unstable links in polar regions by prioritizing links pointing towards the equator.

[0055] 2. Congestion Control Strategy Based on Artificial Immune Algorithm: A complete congestion control framework is designed by introducing a biological immune system mechanism. Through a multi-level congestion state identification mechanism based on queue occupancy rate, the system can accurately quantify the congestion level of links and promptly notify relevant nodes. Using congestion state as the antigen and control strategy as the antibody, a random decision-making mechanism dynamically adjusts the traffic allocation ratio, avoiding network oscillations caused by complete detours in traditional solutions. Simultaneously, a progressive optimization mechanism based on the trend of queue occupancy rate changes is designed to achieve dynamic adjustment of the strategy.

[0056] 3. Immune Memory and Learning Mechanism: A comprehensive immune memory mechanism was designed, storing key information such as congestion link identifiers, alternative paths, diversion ratios, and impact ranges through memory cell structures. A similarity calculation method based on the Jaccard coefficient can quickly identify similar congestion scenarios, enabling efficient reuse of historical experience. A dynamic update mechanism continuously evaluates and optimizes control strategies, coupled with a storage management strategy based on usage frequency and success rate, ensuring efficient utilization of memory resources and significantly improving system response speed.

[0057] The low-Earth orbit satellite network congestion control method based on artificial immune algorithm proposed in this invention has significant advantages in the field of modern satellite communication. It can effectively improve the service quality and resource utilization efficiency of the network and is applicable to multiple application scenarios such as next-generation low-Earth orbit satellite constellation systems, space backbone networks, and space-ground integrated networks. The application of this method is expected to achieve widespread application and commercial value in the field of on-board networks.

[0058] Specifically:

[0059] like Figure 1 As shown, this invention provides a low-Earth orbit satellite congestion control method based on an artificial immune algorithm, comprising:

[0060] Step 1, Mesh routing mapping:

[0061] Based on the physical characteristics of LEO satellite constellations, a virtual mesh structure is constructed. Since LEO constellations typically employ polar orbit deployment, consisting of N orbital planes, with M satellites evenly distributed across each plane, forming a regular network structure. Each satellite node is mapped to virtual mesh coordinates (x, y) according to its orbital plane number i and satellite number j, through the following mapping relationship; where,

[0062] x = i (i ∈ [0, N-1])

[0063] y=(j+i×δ)mod M(j∈[0,M-1])

[0064] In the formula, δ is the phase offset between adjacent orbital planes.

[0065] Meanwhile, satellite nodes calculate their geographical location (longitude σs, latitude φs) in real time using a dynamic position mapping algorithm, and determine whether they are in a high-latitude region (|φ|>65°) based on the location information. When located in a high-latitude region, the satellite will prioritize data forwarding via links pointing towards the equator to avoid the instability of links in polar regions.

[0066] Step 2, Antigen Recognition and Response:

[0067] Based on the mesh routing framework constructed in step 1, satellite nodes periodically monitor the occupancy rate ρi(t) of the output queues in each direction, and set three congestion levels: idle (ρ<50%), mild congestion (50%≤ρ<75%), and severe congestion (ρ≥75%). When congestion is detected (reaching mild or severe congestion), the satellite node generates a congestion warning packet (CWP), which contains a link identifier (Link_ID) and a link state (Link_State); and sends it only to directly adjacent nodes.

[0068] Step 3, Memory Cell Matching:

[0069] The neighboring node that receives the CWP first analyzes the set of affected destination nodes D' based on its own forwarding needs, then searches for matches in the memory cell bank, and calculates the similarity between the current scene and the historical records using the Jaccard coefficient:

[0070]

[0071] In the formula, D represents the set of affected nodes stored in the historical memory cell. When a memory cell with a similarity exceeding the threshold θ (e.g., 0.8) is found, its stored alternative paths and diversion ratios are directly applied; otherwise, the antibody generation process in step 4 is triggered.

[0072] Step 4, Antibody generation:

[0073] Based on the congestion information obtained in step 3, the satellite first analyzes the directional characteristics of the congested links and, combined with the location information in step 1, determines the optimal detour strategy. For congested links in the horizontal direction (east-west), the satellite compares the row coordinates of the current node and the target node: when the target node is above, it chooses to detour north; when it is below, it chooses to detour south. For congested links in the vertical direction (north-south), it chooses to detour east or west based on the difference in column coordinates. After determining the alternative paths, the satellite sets an initial diversion threshold of 0.7, meaning that 70% of the traffic remains on the main path and 30% of the traffic is forwarded through the alternative paths. For each data packet to be forwarded, a random number between [0,1] is generated for diversion decision-making to achieve balanced traffic distribution.

[0074] Step 5, Affinity Calculation and Evaluation:

[0075] Based on the control strategy generated in step 4, the satellite performs a comprehensive evaluation within the time window [t0, t0+Δt]. When the affinity consistently exceeds a threshold (e.g., 0.75), the strategy information is passed to step 7 for storage; otherwise, it proceeds to step 6 for optimization. The affinity calculation formula is as follows:

[0076] Affinity(Ab)=w1×ΔρR+w2×ηT+w3×(1-ρmax)

[0077] In the formula, ΔρR=(ρ(t0)-ρ(t0+Δt)) / ρ(t0) represents the relative reduction in queue occupancy, ηT=T(t0+Δt) / T(t0) represents the throughput maintenance rate, ρmax represents the maximum queue occupancy within the window, and the weighting coefficients satisfy w1+w2+w3=1.

[0078] Step 6, Antibody Optimization:

[0079] For the strategy with insufficient affinity in step 5, the satellite adopts a gradual optimization scheme. By continuously monitoring the trend of queue occupancy, when an upward trend is detected for three consecutive cycles, the offloading ratio p is adjusted to p_new = p_current + 5%. To ensure network stability, the satellite sets upper and lower thresholds for the offloading ratio: a lower limit of 20% to ensure basic utilization of the main path, and an upper limit of 80% to prevent excessive load on alternative paths. When the offloading ratio reaches the threshold, the satellite locks the current configuration for at least 100 time units to avoid network oscillations caused by frequent adjustments. The optimized strategy is then re-evaluated in step 5 until the expected performance requirements are met.

[0080] Step 7, Memory Cell Renewal:

[0081] The satellite stores the high-performance strategy from step 5 into a memory cell repository in the form of a quadruple MC = (L, A, S, D), where L is the congested link identifier, A is the set of alternative paths determined in step 4, S is the final optimized diversion ratio, and D is the set of affected destination nodes obtained from the analysis in step 3. The satellite performs a cleanup every 1000 time units, evaluating the usage frequency of memory cells and removing those that have been used zero times in the most recent evaluation period. When a new congestion scenario occurs, the satellite prioritizes calculating the Jaccard similarity with the stored memory cells. When a memory cell with a similarity greater than 0.8 is found, its stored control strategy is directly reused to achieve a rapid response to recurring congestion.

[0082] Example:

[0083] This invention provides a low-Earth orbit satellite congestion control method based on an artificial immune algorithm, comprising:

[0084] S1, Mesh-based route mapping:

[0085] Based on the physical characteristics of LEO satellite constellations, a virtual mesh structure is constructed. Since LEO constellations typically employ polar orbit deployment, consisting of N orbital planes, with M satellites evenly distributed across each plane, forming a regular network structure. Each satellite node is mapped to virtual mesh coordinates (x, y) according to its orbital plane number i and satellite number j, through the following mapping relationship; where,

[0086] x = i (i ∈ [0, N-1])

[0087] y=(j+i×δ)mod M(j∈[0,M-1])

[0088] In the formula, δ is the phase offset between adjacent orbital planes.

[0089] Meanwhile, satellite nodes calculate their geographical location (longitude σs, latitude φs) in real time using a dynamic position mapping algorithm, and determine whether they are in a high-latitude region (|φ|>65°) based on the location information. When located in a high-latitude region, the satellite will prioritize data forwarding via links pointing towards the equator to avoid the instability of links in polar regions.

[0090] S2, Antigen Recognition and Response:

[0091] like Figure 2As shown, when satellite node S(4,5) periodically monitors and discovers that the occupancy rate of its westward output queue is continuously rising, reaching 80% at time t1, exceeding the severe congestion threshold (75%), it immediately triggers the congestion response mechanism. At this time, S(4,5) generates a congestion warning packet (CWP) containing the congested link identifier "S(4,5)-S(4,4)" and the link status "CONGESTED", and sends the CWP to its three directly adjacent nodes: northward neighbor S(3,5), eastward neighbor S(4,6), and southward neighbor S(5,5). Based on the directed propagation mechanism, these neighboring nodes will not continue to spread the information to other nodes after receiving the CWP, effectively avoiding unnecessary control overhead.

[0092] S3, Memory Cell Matching:

[0093] Upon receiving the CWP, the neighboring node immediately begins congestion handling. Taking node S(3,5) as an example, this node first checks all data packets that need to be forwarded through the S(4,5)-S(4,4) link, and through analysis, determines the set of affected destination nodes D' = {S(4,3),S(4,2),S(3,3),S(3,2)}. Subsequently, S(3,5) searches its memory cell library for similar historical congestion scenarios and finds a memory cell instance containing a congested link identifier, a set of alternative paths {S(3,4)}, a main path traffic ratio of 0.7, and a set of historically affected nodes {S(4,3),S(4,2),S(3,3)}. The calculated Jaccard similarity is 0.85, exceeding the preset threshold of 0.8. Therefore, as... Figure 3 As shown, S(3,5) directly reuses the control strategy stored in the memory cell, sets S(3,4) as the alternative next hop, and performs flow splitting at a ratio of 70% / 30%. The dashed arrows in the figure indicate the direction of flow splitting.

[0094] S4, Antibody generation:

[0095] Taking another neighboring node S(4,6) as an example, since the satellite failed to find any historical records with similarity exceeding the threshold in the memory cell bank, a new control strategy needs to be generated. First, the satellite analyzed the characteristics of the congested link S(4,5)-S(4,4), confirming that it is a westward link, and identified that the affected destination node set {S(4,2),S(4,1)} is located on the same horizontal plane as the current node. Based on the grid routing rules, the satellite selected an alternative path to the north: S(4,6)-S(3,6)-S(3,5)-S(3,4). At the same time, an initial diversion threshold of 0.8 was set, and a random decision mechanism was used for traffic allocation: when the random number r≤0.8, the data packet is forwarded through the main path (via S(4,5)); when r>0.8, it is forwarded through the alternative path (via S(3,6)). The entire antibody generation process is as follows. Figure 4 As shown.

[0096] S5. Affinity Assessment:

[0097] After determining the control strategy, S(4,6) comprehensively evaluated the strategy's effectiveness within the time window [t0, t0+100]. The satellite recorded detailed changes in performance indicators: queue occupancy decreased from an initial 80% to 65%, but peaked at 82% at time t0+10; throughput decreased from an initial 100Mbps to 85Mbps. Substituting these data into the affinity calculation formula Affinity(Ab)=w1×ΔρR+w2×ηT+w3×(1-ρmax), where the weighting coefficients were set to w1=0.5 and w2=w3=0.25 respectively, the calculated affinity was 0.35. Since this value was lower than the preset threshold of 0.75, the satellite immediately entered the antibody optimization phase.

[0098] S6, Antibody Optimization:

[0099] To address the low affinity, the satellite optimized the control strategy for the S(4,6) nodes. Analysis revealed that queue occupancy rates increased by 78%, 79%, and 80% over three consecutive detection cycles. The satellite adopted a gradual optimization strategy, reducing the main path's offloading ratio from 80% to 75%. In the new evaluation cycle [t1, t1+100], all performance indicators significantly improved: queue occupancy rate decreased to 58%, throughput remained at 90 Mbps, and the maximum queue occupancy rate was only 75%. The recalculated affinity improved to 0.81, exceeding the preset threshold, indicating that the optimized strategy achieved the expected results.

[0100] S7, Memory Cell Renewal:

[0101] Finally, node S(4,6) stores the optimized control strategy into the database as a memory cell, fully recording information such as the congested link identifier "S(4,5)-S(4,4)", the alternative path set {S(3,6)-S(3,5)-S(3,4)}, the optimized traffic splitting ratio of 0.75, and the set of affected destination nodes {S(4,2),S(4,1)}. It also initializes the usage frequency (1 time) statistics. This new memory cell will participate in the evaluation over the next 1000 time units. If it is not used during this period, it will be removed from the memory bank during the next cleanup, thus ensuring the efficient utilization of memory resources.

[0102] This invention presents a congestion control strategy for low-Earth orbit satellite networks based on an artificial immune algorithm. In this strategy, the physical topology of satellite nodes is mapped onto a virtual mesh structure. When congestion is detected, the system transmits congestion information as an antigen to neighboring nodes. Through a memory cell matching mechanism, the system can quickly reuse historical successful experiences; for new congestion scenarios, the diversion strategy is dynamically adjusted through antibody generation and optimization processes. This adaptive control scheme based on an immune mechanism ensures both rapid response to congestion and improved network performance through continuous learning and optimization, effectively solving the congestion control problem in satellite networks.

[0103] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A low-Earth orbit satellite congestion control method based on an artificial immune algorithm, characterized in that, include: Step 1: Map the satellites of the low-Earth orbit constellation to virtual grid coordinates using a gridding method; Step 2: Based on the constructed grid framework, satellite nodes periodically monitor the occupancy rate of output queues in each direction; when congestion is detected, the satellite node generates a congestion warning packet and sends it to its immediate neighboring nodes. Step 3: The neighboring nodes that receive the congestion warning packet analyze the set of affected destination nodes according to their own forwarding needs, and search for matching items of affected destination nodes in the historical memory cell library by the similarity between the current scene and the historical records; when a memory cell with similarity exceeding the threshold is found, the alternative paths and diversion ratio stored in it are directly applied as the routes for the affected nodes. Otherwise, the antibody generation process in step 4 will be triggered; Step 4: Based on the congestion information obtained in Step 3, the satellite first analyzes the directional characteristics of the congested links and, combined with the location information in Step 1, determines the optimal detour strategy. After determining the alternative paths, the satellite sets an initial diversion threshold and generates a random number between [0,1] for each data packet to be forwarded to make a diversion decision, thereby achieving a balanced distribution of traffic; this routing strategy is like an antibody against an antigen. Step 5: Based on the control strategy generated in Step 4, the satellite performs a comprehensive evaluation within the time window [t0, t0+Δt]; calculates the affinity based on the queue occupancy rate; when the affinity continuously exceeds the threshold, the strategy information is passed to Step 7 for storage; otherwise, proceed to Step 6 for optimization. Step 6: For strategies with insufficient affinity in Step 5, the satellite continuously monitors the trend of queue occupancy. When an upward trend is found for several consecutive cycles, the diversion ratio is increased. The optimized strategy is re-entered into Step 5 for evaluation until the expected performance requirements are met. Step 7: The satellite stores the high-performance strategy from Step 5 as an effective antibody in the memory cell bank in the form of a quadruple.

2. The low-orbit satellite congestion control method as described in claim 1, characterized in that, Step 1 specifically includes: Each satellite node is mapped to virtual grid coordinates (x, y) according to its orbital plane number i and satellite number j, through the following mapping relationship; where, x = i (i ∈ [0, N-1]) y=(j+i×δ)mod M(j∈[0,M-1]) In the formula, δ is the phase offset between adjacent orbital planes. The low-Earth orbit constellation consists of N orbital planes, with M satellites evenly distributed on each orbital plane.

3. The low-orbit satellite congestion control method as described in claim 1, characterized in that, In step 2, three congestion levels are set: idle state: output queue occupancy ρ < 50%, mild congestion: 50% ≤ ρ < 75%, and severe congestion: ρ ≥ 75%.

4. The low-orbit satellite congestion control method as described in claim 1, characterized in that, In step 3, the similarity between the current scene and the historical records is calculated using the Jaccard coefficient: In the formula, D is the set of affected nodes stored in the history memory cell, and D' is the affected destination node; When a memory cell with a similarity exceeding the threshold θ is found, its stored alternative paths and splitting ratios are directly applied. Otherwise, the antibody generation process in step 4 will be triggered.

5. The low-orbit satellite congestion control method as described in claim 1, characterized in that, In step 4, the method for determining the optimal detour strategy includes: For congested links in the east-west direction, the satellite compares the row coordinates of the current node and the target node: if the target node is above, it chooses to detour northward; if it is below, it chooses to detour southward. For congested links in the north-south direction, the route is detoured to the east or west based on the difference in column coordinates.

6. The low-orbit satellite congestion control method as described in claim 1, characterized in that, In step 5, the affinity calculation formula is: Affinity(Ab)=w1×ΔρR+w2×ηT+w3×(1-ρmax) In the formula, ΔρR=(ρ(t0)-ρ(t0+Δt)) / ρ(t0) represents the relative reduction in queue occupancy, ηT=T(t0+Δt) / T(t0) represents the throughput maintenance rate, ρmax represents the maximum queue occupancy within the window, and the weighting coefficients satisfy w1+w2+w3=1.

7. The low-orbit satellite congestion control method as described in claim 1, characterized in that, In step 6, when an upward trend is found for three consecutive cycles, the diversion ratio p is adjusted to p_new = p_current + 5%.

8. The low-orbit satellite congestion control method as described in claim 7, characterized in that, In step 6, to ensure network stability, the satellite sets upper and lower thresholds for the offloading ratio: a lower limit of 20% to ensure basic utilization of the main path and an upper limit of 80% to prevent the alternative path from being overloaded; when the offloading ratio reaches the threshold, the satellite locks the current configuration for at least 100 time units to avoid network oscillations caused by frequent adjustments.

9. The low-orbit satellite congestion control method as described in claim 1, characterized in that, In step 7, the satellite stores the high-performance strategy from step 5 as an effective antibody in the memory cell bank in the form of a quadruple MC = (L, A, S, D), where L is the congested link identifier, A is the set of alternative paths determined in step 4, S is the final optimized diversion ratio, and D is the set of affected destination nodes obtained from the analysis in step 3.

10. The low-orbit satellite congestion control method as described in claim 1, characterized in that, In step 7, the satellite performs a cleanup every preset time unit to assess the usage frequency of memory cells and remove memory cells that have been used zero times in the most recent assessment period. When a new congestion scenario occurs, the satellite prioritizes calculating the Jaccard similarity with the stored memory cells. When a memory cell with a similarity exceeding the threshold is found, its stored control strategy is directly reused to achieve a rapid response to recurring congestion.

Images