Transmission resource scheduling method and system for a clustered communication network
By constructing a hierarchical virtual resource pool in a clustered marine communication network and performing multi-level aggregation based on service characteristics, the problems of link heterogeneity and topology dynamism are solved, achieving efficient differentiated transmission scheduling and improving resource utilization and network adaptability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-07-01
- Publication Date
- 2026-07-28
AI Technical Summary
In clustered marine communication networks, links are highly heterogeneous and dynamic, network topology changes frequently, and service requirements are diverse. Traditional resource abstraction is insufficient to meet the differentiated quality of service requirements.
By using a self-arranged instruction intent space mapping and spatiotemporal extrapolation method, the physical link status is analyzed and multi-level aggregation is performed based on business characteristics to construct a hierarchical virtual resource pool, providing customized transmission scheduling strategies for services with different service quality requirements.
It decouples network resources from business needs, reduces decision-making latency, improves the efficiency of large-scale network scheduling, enhances adaptability to diverse business scenarios, and improves resource utilization and network evolution adaptability.
Smart Images
Figure CN122476053A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of computer application technology, and in particular to a method and system for scheduling transmission resources in a clustered communication network. Background Technology
[0002] Clustered marine communication networks are crucial information infrastructure supporting maritime operations and shipping activities. These networks typically consist of clustered, self-organizing bearer networks composed of mobile nodes such as ships, floating platforms, and drones, employing a hybrid network of multiple wireless links including shortwave, VHF, satellite, and microwave. The core challenges in this environment are: 1) Highly heterogeneous and dynamic links: Different links vary significantly in bandwidth, latency, and stability, and are affected by the marine environment, such as multipath fading, salt spray interference, and high-speed node movement, leading to drastic time-varying link quality; 2) Frequent changes in network topology: Node movement causes dynamic reorganization of the cluster structure, and traditional network-wide state synchronization mechanisms incur huge overhead; 3) Diverse service requirements: Services include decomposable multipath services, such as video streaming and file transfer, as well as highly reliable services requiring single-path guarantees, such as control commands and voice communication. Traditional "one-size-fits-all" resource abstraction is insufficient to meet differentiated Quality of Service (QoS) requirements. Summary of the Invention
[0003] This invention provides a method and system for instruction intent space mapping and spatiotemporal extrapolation based on autonomous orchestration, in order to overcome the deficiencies in the prior art. By analyzing the physical link status and performing multi-level aggregation based on service characteristics, a hierarchical virtual resource pool is constructed, thereby providing customized transmission scheduling strategies for services with different quality of service requirements.
[0004] In a first aspect, the present invention provides a method for scheduling transmission resources in a clustered communication network, characterized in that it includes: Obtain the status parameters of each physical link between each member node and its neighboring nodes in the communication network; Each physical link is divided into different resource partitions based on its status parameters; Based on different business feature tags, an aggregation algorithm is performed on the physical links between nodes within the cluster in the resource partition to obtain the virtual link matrix within the cluster. Based on different business feature tags, an aggregation algorithm is performed on the physical links between the boundary nodes of adjacent clusters in the resource partition to obtain inter-cluster virtual links, and an aggregation algorithm is performed on the physical links between the ingress boundary node and the egress boundary node within the cluster to obtain cluster aggregated virtual links. A virtual resource pool is formed based on the intra-cluster virtual link matrix, inter-cluster virtual links, and cluster aggregated virtual links; Based on the query request, which includes business characteristics and quality of service requirements, a transmission scheduling strategy adapted to the request is obtained from the virtual resource pool.
[0005] Furthermore, it also includes: updating the virtual resource pool in real time when an event affects the transmission performance of the physical link between member nodes and neighboring nodes.
[0006] Furthermore, it also includes: analyzing the motion vectors of member nodes, predicting that the member node will move to the edge of a neighboring cluster, and generating pre-update information based on future changes in link connections involving the node and bandwidth estimates to update the virtual resource pool.
[0007] The step of obtaining the status parameters of each physical link between each member node and its neighboring nodes in the communication network includes: obtaining the bandwidth parameters, latency parameters, and packet loss sequences of the past N periods for each physical link between each member node and its neighboring nodes in the communication network, and calculating the link stability index for the current period based on the packet loss sequences of the past N periods. The step of dividing each physical link into different resource partitions based on the status parameters of each physical link includes dividing each physical link into different resource partitions according to the latency level and stability level preset according to the service requirements.
[0008] Furthermore, based on different business feature tags, an aggregation algorithm is performed on the physical links between nodes within the cluster in the resource partition to obtain the intra-cluster virtual link matrix, including: When the business feature label is to support multi-path transmission, the stability-weighted maximum flow algorithm is executed on all physical links in the corresponding resource partition, and the current node is output to score the virtual link bandwidth and expected path stability under the current business requirements. When the service characteristic label is single-path transmission, physical links are first searched in the highest-level resource partition. If one exists, the physical link with the largest transmission bandwidth is selected. If one does not exist, the constraints of latency level and / or stability level in the resource partition are gradually reduced, and physical links are searched in other resource partitions.
[0009] Furthermore, based on different business feature tags, an aggregation algorithm is performed on the physical links between boundary node pairs of adjacent clusters in the resource partition to obtain inter-cluster virtual links, and an aggregation algorithm is performed on the physical links between ingress boundary nodes and egress boundary nodes within a cluster to obtain cluster aggregated virtual links, including: For all possible boundary node pairs in adjacent clusters, if the service feature label is to support multipath transmission, the stability-weighted maximum flow algorithm is executed on all physical links in the corresponding resource partition, and the virtual link bandwidth and expected path stability score of the current node pair under the current service requirements are output; if the service feature label is to support single-path transmission, within the range of resource partitions with corresponding physical links, the resource partition with the highest latency level and stability level is determined, and the physical link with the largest transmission bandwidth is selected from it. Between any ingress boundary node and any egress boundary node within a cluster, if the service feature label supports multipath transmission, the maximum flow algorithm is executed on all physical links in the resource partition that meets the quality of service requirements to obtain the inter-cluster virtual link; if the service feature label is single-path transmission, within the range of resource partitions with corresponding physical links, the resource partition with the highest latency level and stability level is determined, and the physical link with the largest transmission bandwidth is selected from it.
[0010] Furthermore, the virtual resource pool formed based on the intra-cluster virtual link matrix, inter-cluster virtual links, and cluster aggregated virtual links includes: The local virtual resource pool is constructed by constructing the intra-cluster virtual link matrix corresponding to each cluster head node in the communication network. Construct a regional collaborative resource pool by establishing inter-cluster virtual links and cluster aggregation virtual links corresponding to each cluster; Collect virtual link aggregation summaries from all clusters to form a global virtual resource pool.
[0011] Secondly, the present invention also provides a transmission resource scheduling system for a clustered communication network, comprising: a link sensing unit, used to acquire the status parameters of each physical link between each member node and its neighboring nodes in the communication network; The link differentiation unit is used to divide each physical link into different resource partitions based on the status parameters of each physical link; The virtual link aggregation unit is used to perform an aggregation algorithm on the physical links between nodes within a cluster in the resource partition according to different service feature tags, and to obtain the virtual link matrix within the cluster. And based on different business feature tags, an aggregation algorithm is performed on the physical links between the boundary nodes of adjacent clusters in the resource partition to obtain inter-cluster virtual links, and an aggregation algorithm is performed on the physical links between the ingress boundary node and the egress boundary node within the cluster to obtain cluster aggregated virtual links; The virtual resource pool management unit is used to form a virtual resource pool based on the intra-cluster virtual link matrix, inter-cluster virtual links, and cluster aggregated virtual links. A unified resource service unit is used to obtain a transmission scheduling strategy adapted to the request from the virtual resource pool based on the query request, which includes business characteristics and service quality requirements.
[0012] Thirdly, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the transmission resource scheduling method for any of the clustered communication networks described above.
[0013] Fourthly, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the transmission resource scheduling method for any of the above-described clustered communication networks.
[0014] The transmission resource scheduling method, system, and medium for clustered communication networks provided by this invention can produce the following beneficial technical effects compared with existing technologies: By employing state parameter-driven resource partitioning and combining it with a multi-level link aggregation algorithm based on business feature tags, a mapping architecture from physical links to virtual resource pools is constructed. This decouples network resources from business requirements, allowing upper layers to remain unaware of the complex underlying topology. Through a pre-computation aggregation mechanism, complex network topologies are compressed into structured virtual link representations. During scheduling, only matching needs to be retrieved from the virtual resource pool, significantly reducing decision latency and improving the efficiency of large-scale network scheduling. The same physical infrastructure can generate differentiated virtual resource views based on different business characteristics, enhancing adaptability to diverse business scenarios. Resource partitioning fully considers the dynamic state attributes of links, avoiding forced bundling of links with different states. This reduces resource fragmentation while ensuring service quality and improving resource utilization. Furthermore, this architecture supports dynamic adjustment of partition boundaries and aggregation parameters, exhibiting good network evolution adaptability and business expansion flexibility. Attached Figure Description
[0015] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0016] Figure 1 This is a flowchart illustrating a transmission resource scheduling method for a clustered communication network provided by the present invention; Figure 2 This is a schematic block diagram of the virtual resource pool provided by the present invention; Figure 3 This is a schematic diagram of the structure of an optional electronic device provided by the present invention. Detailed Implementation
[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.
[0018] It should be noted that, in the description of the embodiments of the present invention, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0019] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more.
[0020] In an optional embodiment, the clustered network of this invention operates in a certain sea area. The network can consist of one large vessel (as the core cluster leader), four medium-sized vessels (as ordinary cluster leaders), and several drones and small vessels (as member nodes), naturally forming five clusters. Links can include satellite links (high latency, medium bandwidth, relatively stable), microwave line-of-sight links (low latency, high bandwidth, but susceptible to obstruction), and ultra-shortwave links (medium latency, medium bandwidth, good coverage).
[0021] Figure 1 This is a flowchart illustrating the transmission resource scheduling method for clustered communication networks provided by the present invention, as shown below. Figure 1 As shown, including but not limited to the following steps: S102. Obtain the status parameters of each physical link between each member node and its neighboring nodes in the communication network; In an optional embodiment, obtaining the status parameters of each physical link between each member node and its neighboring nodes in the communication network includes: obtaining the bandwidth parameters, latency parameters, and packet loss sequences of the past N periods for each physical link between each member node and its neighboring nodes in the communication network, and calculating the link stability index for the current period based on the packet loss sequences of the past N periods. Specifically, each member node in the communication network periodically measures the state parameters of each physical link with all its neighbors. Using recent historical data (such as packet loss sequences from the past N periods), the Link Stability Index (LSI) for the current period is calculated. This index reflects the short-term reliability of the link in the dynamic marine environment. The LSI can also be calculated using signal strength variance and marine channel fading characteristics. The aforementioned state parameters may also include parameters such as transmission performance weights, which comprehensively consider the link's bit error rate and transmission energy consumption. This data is encapsulated into a unified message format and reported to the cluster head node.
[0022] S104. Divide each physical link into different resource partitions according to the status parameters of each physical link; In an optional embodiment, the step of dividing each physical link into different resource partitions based on the status parameters of each physical link includes: dividing each physical link into different resource partitions based on the latency level and stability level preset according to service requirements.
[0023] Specifically, after receiving the reported data, the cluster head node places each physical link into the corresponding resource partition according to the latency level (e.g., urgent, normal, and tolerant) and stability level (e.g., high stability, medium stability, and low stability) preset according to the general business needs.
[0024] For example, physical links with latency parameters less than or equal to 50ms are classified into the urgent latency level, those with latency parameters greater than 50ms but less than or equal to 200ms are classified into the normal latency level, and those with latency parameters greater than 200ms are classified into the latency tolerance level. As for stability level classification, physical links with a stability index greater than 0.8 are typically classified into the high stability level, those with a stability index less than 0.5 but greater than or equal to 0.5 are classified into the medium stability level, and those with a stability index less than 0.5 are classified into the low stability level. Low stability level physical links are usually not used for service establishment and are only used for early warning reference.
[0025] S106. Based on different business feature tags, perform an aggregation algorithm on the physical links between nodes within a cluster in the resource partition to obtain the virtual link matrix within the cluster. In an optional embodiment, the aggregation algorithm is performed on the physical links between nodes within the cluster in the resource partition according to different service feature labels to obtain the intra-cluster virtual link matrix. This includes: when the service feature label supports multi-path transmission, a stability-weighted maximum flow algorithm is performed on all physical links in the corresponding resource partition to output the virtual link bandwidth and expected path stability score of the current node under the current service requirements; when the service feature label is single-path transmission, physical links are preferentially searched in the highest-level resource partition. If they exist, the physical link with the largest transmission bandwidth is selected. If they do not exist, the constraints of latency level and / or stability level in the resource partition are successively reduced, and physical links are searched in other resource partitions.
[0026] Specifically, for a pair of nodes (or cluster boundary node pairs) that need to establish communication, the corresponding aggregation algorithm will be executed on the set of physical links within the corresponding resource partition according to different service type labels.
[0027] When the service is multi-path file transfer, the service tag indicates that multi-path is supported. Then, a stability-weighted maximum flow algorithm will be performed on all physical links within the (normal, medium-stable) and above resource partitions, outputting the node's virtual link bandwidth and expected path stability score under the current service and QoS requirements.
[0028] When the service is a single-path real-time control, the service label indicates that the single path must be highly reliable. The system will first search for links within the (urgent, high-stability) resource partitions. If a link exists, it will select the one with the largest bandwidth. If not, the stability or latency constraints will be relaxed sequentially, but the selected link's stability level must be higher than the minimum reliability threshold.
[0029] S108. Based on different business feature tags, perform an aggregation algorithm on the physical links between the boundary nodes of adjacent clusters in the resource partition to obtain inter-cluster virtual links, and perform an aggregation algorithm on the physical links between the ingress boundary node and the egress boundary node within the cluster to obtain cluster aggregated virtual links. In an optional embodiment, an aggregation algorithm is performed on the physical links between boundary node pairs of adjacent clusters in the resource partition according to different service feature tags to obtain inter-cluster virtual links, and an aggregation algorithm is performed on the physical links between ingress boundary nodes and egress boundary nodes within a cluster to obtain cluster aggregated virtual links, including: For all possible boundary node pairs in adjacent clusters, if the service feature label is to support multipath transmission, the stability-weighted maximum flow algorithm is executed on all physical links in the corresponding resource partition, and the virtual link bandwidth and expected path stability score of the current node pair under the current service requirements are output; if the service feature label is to support single-path transmission, within the range of resource partitions with corresponding physical links, the resource partition with the highest latency level and stability level is determined, and the physical link with the largest transmission bandwidth is selected from it. Between any ingress boundary node and any egress boundary node within a cluster, if the service feature label supports multipath transmission, the maximum flow algorithm is executed on all physical links in the resource partition that meets the quality of service requirements to obtain the inter-cluster virtual link; if the service feature label is single-path transmission, within the range of resource partitions with corresponding physical links, the resource partition with the highest latency level and stability level is determined, and the physical link with the largest transmission bandwidth is selected from it.
[0030] Specifically, for inter-cluster virtual links, it is necessary to consider all possible boundary node pairs of adjacent clusters. Based on the service type, within the corresponding resource partition, a cross-cluster aggregation calculation similar to step S106 is performed to generate a logical link representing the connection capability between the two clusters and record its dominant latency-stability level.
[0031] For cluster aggregation links, it is necessary to consider the optimal aggregation capability (maximum flow for multi-path and optimal single-path bandwidth) between any ingress boundary node and any egress boundary node within a single cluster under specific service types and QoS requirements, forming a summary link representing the "traversal capability" of that cluster.
[0032] S110. A virtual resource pool is formed based on the intra-cluster virtual link matrix, inter-cluster virtual links, and cluster aggregated virtual links; In an optional embodiment, forming a virtual resource pool based on the intra-cluster virtual link matrix, inter-cluster virtual links, and cluster aggregated virtual links includes: constructing the local virtual resource pool by using the intra-cluster virtual link matrix corresponding to each cluster head node in the communication network; constructing a regional collaborative resource pool by using the inter-cluster virtual links and cluster aggregated virtual links corresponding to each cluster; and collecting virtual link aggregation summaries of all clusters to form a global virtual resource pool.
[0033] Specifically, the virtual resource pool consists of three layers: a local virtual resource pool, a regional collaborative resource pool, and a global virtual resource pool. The local virtual resource pool is constructed through the intra-cluster virtual link matrix corresponding to each cluster head node; the regional collaborative resource pool is constructed through the inter-cluster virtual links and cluster aggregation virtual links corresponding to each cluster; and the global virtual resource pool is constructed by collecting the aggregation link summary of all clusters through controllable flooding or by selecting the root node.
[0034] S112. Based on the query request including business characteristics and service quality requirements, obtain a transmission scheduling strategy adapted to the request from the virtual resource pool.
[0035] Specifically, in this step, upper-layer applications or network orchestrators do not need to be aware of the complex underlying physical topology and maintenance mechanisms. They only need to submit a query request containing business characteristics and QoS requirements through the resource service API gateway to obtain accurate and consistent virtual resource views of different granularities from the three levels of local virtual resource pool, regional collaborative resource pool, and global virtual resource pool, thereby efficiently completing virtual network embedding, path calculation, and resource scheduling.
[0036] In one optional embodiment, corresponding to a specific workflow, the drone (cluster C1 member) needs to transmit high-definition video back to the large ship (cluster C0).
[0037] The UAV measured two reachable links to the cluster relay node: a microwave link (10Mbps bandwidth, 15ms latency, link stability index 0.9) and a satellite link (4Mbps bandwidth, 180ms latency, link stability index = 0.95). They were placed in resource partitions of (urgent, high stability) and (normal, high stability) respectively.
[0038] The service characteristic is marked as "multipath video". For the virtual link from the UAV to the exit node of cluster C1, the output bandwidth is 10Mbps within the (emergency, high stability) resource partition; at the same time, it can also utilize the satellite link in the (normal, high stability) resource partition.
[0039] The C1 cluster head calculates its cluster aggregation link to cluster C0 (assuming it's via microwave relay, bandwidth 8 Mbps, latency level urgent) and updates it to the regional collaborative resource pool. It then discovers the availability of the path from C1 to C0 from both the global virtual resource pool and the regional collaborative resource pool.
[0040] The available multipath bandwidth combinations are returned, and the final transmission resource scheduling may be as follows: critical I-frames take the low-latency emergency path, and a large number of P / B frames take the normal but highly stable satellite path, thereby achieving bandwidth aggregation and reliability improvement.
[0041] While current network virtualization research has proposed the concept of resource pooling, it still has the following shortcomings when applied to ocean clustered networks: lack of abstract models for multi-dimensional evaluation of link quality (such as stability, bit error rate, and energy efficiency); resource pool synchronization mechanisms have high overhead and slow response, making them unsuitable for highly dynamic environments; and the intelligent matching of service types and link abstraction strategies has not been achieved, resulting in low resource adaptation accuracy.
[0042] The aforementioned clustered communication network transmission resource scheduling method introduces multi-dimensional environmental awareness indicators such as link stability index and transmission performance weight. The abstract results of virtual links can more realistically reflect the available service capabilities under dynamic ocean channels, providing a more reliable basis for scheduling decisions. By differentiating different service characteristics and resource partitioning differentiation aggregation algorithms, the capability description of virtual links is highly matched with the actual transmission characteristics of services, effectively avoiding the problem of excessive resource reservation for single-path services or insufficient resource supply for multi-path services, and improving the overall resource utilization rate.
[0043] In an optional embodiment, the transmission resource scheduling method for the clustered communication network further includes: updating the virtual resource pool in real time when an event affects the transmission performance of the physical link between a member node and its neighboring nodes; and analyzing the motion vector of a member node and predicting that the member node will move to the edge of a neighboring cluster, generating pre-update information based on future changes in link connections involving the node and changes in bandwidth estimates to update the virtual resource pool.
[0044] Figure 2 This is a schematic diagram of the virtual resource pool provided by the present invention.
[0045] when Figure 2 When discrete events such as link interruption, node joining / leaving a cluster, or service resource monopolization occur in the physical network, these events will affect the transmission performance of the physical links between member nodes and neighboring nodes, immediately triggering a local virtual resource pool update. If this event also affects the cluster aggregation link capability or inter-cluster link capability of the cluster, it will trigger an update of the regional cooperative resource pool, and further determine whether it is necessary to synchronize the summary changes to the global resource pool. All of the above updates use incremental update messages, only synchronizing the change amount. In one embodiment, the periodic reporting period of the above event update member nodes is Δt = 15 seconds; the validity period of information in the regional cooperative resource pool is 20 seconds; and the maximum hard update interval of the summary information of the global virtual resource pool is 60 seconds, ensuring the timeliness of the virtual resource pool update after the event occurs.
[0046] Furthermore, linear motion prediction based on node GPS position and velocity can be performed by analyzing the motion vectors of member nodes, with a prediction window of 30 seconds. If a member node is predicted to move to the edge of a neighboring cluster, pre-update information is generated based on changes in link connections involving that node and bandwidth estimates in the future time period, and provided to the regional collaborative resource pool. This pre-update information may include: 1) suggesting a reduction in the estimated bandwidth of cluster aggregation links involving that node in the future; 2) indicating the possible imminent establishment of new inter-cluster links. When the predicted event actually occurs, the required real-time synchronization overhead and scheduling decision latency will be significantly reduced due to prior preparation.
[0047] The following effects can be achieved in the above embodiments: The synchronization overhead is significantly optimized. By introducing a regional collaborative resource pool as an intermediate layer through hierarchical pooling, the direct impact of intra-cluster dynamics on the global view is effectively isolated. It acts as a fast cache for cross-cluster resource information, enabling the system to significantly improve the response speed of cross-cluster business queries and establishment while maintaining low global synchronization overhead.
[0048] Through hybrid synchronization, incremental updates are triggered by events, ensuring the real-time nature of critical changes. A predictive pre-adjustment mechanism smooths out synchronization peaks caused by regular node movements, reducing sudden bursts of control signaling traffic. Simulation results demonstrate that, under the same network size and dynamics, the synchronization mechanism proposed in this invention can reduce global control message overhead by approximately 30%-50%.
[0049] Enhanced network scalability and robustness: Local topology changes are largely confined to local processing. Regional collaborative resource pools act as a buffer layer, isolating local dynamics from directly impacting the global view. Predictive mechanisms further enhance the system's anticipation and buffering capabilities against dynamic changes.
[0050] It lays a solid foundation for advanced network automation: the unified, accurate, and multi-granular resource view it provides is an ideal data foundation for realizing advanced functions such as AI-based intelligent routing, dynamic network slicing, and cross-domain collaborative protection.
[0051] In an optional embodiment, corresponding to a specific workflow, for example, based on the course and speed of the medium-sized vessel (the first node of cluster C2), it is calculated that the boundary node of cluster C3 will reach the optimal communication distance after 25 seconds, which may form a new high-quality inter-cluster link.
[0052] At the current moment, a predictive update message is sent to the regional coordination resource pools of clusters C2 and C3: "It is expected that at time t+25s, a new (urgent, high stability) inter-cluster virtual link may be added between clusters C2 and C3, with an estimated bandwidth of 6Mbps."
[0053] When a new cross-cluster service request needs to pass through this area at time t+20s, querying the regional coordination resource pool will not only show the current actual link status, but also this "predicted link". The engine can generate two alternative routes: one based on the current status, and the other based on the predicted status after t+25s (as the preferred recommendation).
[0054] At time t+25s, the new link is indeed established, triggering an event update. Because the regional coordination resource pool was already prepared, this update was completed almost imperceptibly, and services smoothly switched to the new, optimized path. Without a predictive mechanism, this process would involve a complete delay chain of "discovery-measurement-reporting-calculation-synchronization".
[0055] In summary, this application, by introducing multi-dimensional environmental awareness indicators such as the link stability index, enables the abstract results of virtual links to more accurately reflect the available service capabilities under dynamic ocean channels, providing a more reliable basis for scheduling decisions. Through aggregation algorithms that differentiate between different service characteristics and resource partitioning, the capability description of virtual links is highly matched with the actual transmission characteristics of services, effectively avoiding the problems of excessive resource reservation for single-path services or insufficient resource supply for multi-path services, thus improving overall resource utilization. This application, through hierarchical pooling, introduces a regional collaborative resource pool as an intermediate layer, effectively isolating the direct impact of intra-cluster dynamics on the global view and acting as a fast cache for cross-cluster resource information. This allows the system to maintain low global synchronization overhead while significantly improving the response speed of cross-cluster service queries and establishment. Through hybrid synchronization, event-triggered incremental updates ensure the real-time nature of critical changes; the predictive pre-adjustment mechanism smooths out synchronization peaks caused by regular node movements, reducing sudden traffic in control signaling.
[0056] This invention also provides a transmission resource scheduling system for clustered communication networks, including: The link awareness unit is used to acquire the status parameters of each physical link between each member node and its neighboring nodes in the communication network; The link differentiation unit is used to divide each physical link into different resource partitions based on the status parameters of each physical link; The virtual link aggregation unit is used to perform an aggregation algorithm on the physical links between nodes within a cluster in the resource partition according to different service feature tags, and to obtain the virtual link matrix within the cluster. And based on different business feature tags, an aggregation algorithm is performed on the physical links between the boundary nodes of adjacent clusters in the resource partition to obtain inter-cluster virtual links, and an aggregation algorithm is performed on the physical links between the ingress boundary node and the egress boundary node within the cluster to obtain cluster aggregated virtual links; The virtual resource pool management unit is used to form a virtual resource pool based on the intra-cluster virtual link matrix, inter-cluster virtual links, and cluster aggregated virtual links. A unified resource service unit is used to obtain a transmission scheduling strategy adapted to the request from the virtual resource pool based on the query request, which includes business characteristics and service quality requirements.
[0057] In addition, it also includes: The service feature identification and tagging unit is used to identify communication services and obtain corresponding service feature tags; The predictive synchronization coordination unit analyzes the motion vectors of member nodes and, if it predicts that a member node will move to the edge of a neighboring cluster, generates pre-update information based on future changes in link connections involving that node and changes in bandwidth estimates, in order to update the virtual resource pool.
[0058] It should be noted that the transmission resource scheduling system for clustered communication networks provided in this embodiment of the invention can execute the transmission resource scheduling method for clustered communication networks described in any of the above embodiments during actual operation, and will not be elaborated on in this embodiment.
[0059] The device may include a processor 310, a communications interface 320, a memory 330, and a communications bus 340, wherein the processor 310, the communications interface 320, and the memory 330 communicate with each other through the communications bus 340. The processor 310 can call logical instructions in the memory 330 to execute a transmission resource scheduling method based on a clustered communication network. This method includes: obtaining the status parameters of each physical link between each member node and its neighboring nodes in the communication network; dividing each physical link into different resource partitions based on the status parameters of each physical link; performing an aggregation algorithm on the physical links between nodes within a cluster in the resource partition according to different service feature tags to obtain an intra-cluster virtual link matrix; performing an aggregation algorithm on the physical links between boundary nodes of adjacent clusters in the resource partition according to different service feature tags to obtain inter-cluster virtual links, and performing an aggregation algorithm on the physical links between ingress boundary nodes and egress boundary nodes within a cluster to obtain cluster-aggregated virtual links; forming a virtual resource pool based on the intra-cluster virtual link matrix, inter-cluster virtual links, and cluster-aggregated virtual links; and obtaining a transmission scheduling strategy adapted to the query request, including service features and quality of service requirements, from the virtual resource pool.
[0060] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0061] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein when the program instructions are executed by a computer, the computer is able to execute the transmission resource scheduling method for the clustered communication network provided in the above embodiments, the method comprising: obtaining the status parameters of each physical link between each member node and its neighboring nodes in the communication network; dividing each physical link into different resource partitions according to the status parameters of each physical link; performing an aggregation algorithm on the physical links between nodes within a cluster in the resource partition according to different service feature tags to obtain an intra-cluster virtual link matrix; performing an aggregation algorithm on the physical links between boundary nodes of adjacent clusters in the resource partition according to different service feature tags to obtain inter-cluster virtual links, and performing an aggregation algorithm on the physical links between ingress boundary nodes and egress boundary nodes within a cluster to obtain cluster aggregated virtual links; forming a virtual resource pool according to the intra-cluster virtual link matrix, inter-cluster virtual links, and cluster aggregated virtual links; and obtaining a transmission scheduling strategy adapted to the request from the virtual resource pool according to a query request including service features and service quality requirements.
[0062] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements a transmission resource scheduling method for a clustered communication network provided in the above embodiments. The method includes: obtaining state parameters of each physical link between each member node and its neighboring nodes in the communication network; dividing each physical link into different resource partitions according to the state parameters of each physical link; performing an aggregation algorithm on the physical links between nodes within a cluster in the resource partition according to different service feature tags to obtain an intra-cluster virtual link matrix; performing an aggregation algorithm on the physical links between boundary nodes of adjacent clusters in the resource partition according to different service feature tags to obtain inter-cluster virtual links, and performing an aggregation algorithm on the physical links between ingress boundary nodes and egress boundary nodes within a cluster to obtain cluster aggregated virtual links; forming a virtual resource pool based on the intra-cluster virtual link matrix, inter-cluster virtual links, and cluster aggregated virtual links; and obtaining a transmission scheduling strategy adapted to the request from the virtual resource pool according to a query request including service features and quality of service requirements.
[0063] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0064] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0065] 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 them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for scheduling transmission resources in a clustered communication network, characterized in that, include: Obtain the status parameters of each physical link between each member node and its neighboring nodes in the communication network; Each physical link is divided into different resource partitions based on its status parameters; Based on different business feature tags, an aggregation algorithm is performed on the physical links between nodes within the cluster in the resource partition to obtain the virtual link matrix within the cluster. Based on different business feature tags, an aggregation algorithm is performed on the physical links between the boundary nodes of adjacent clusters in the resource partition to obtain inter-cluster virtual links, and an aggregation algorithm is performed on the physical links between the ingress boundary node and the egress boundary node within the cluster to obtain cluster aggregated virtual links. A virtual resource pool is formed based on the intra-cluster virtual link matrix, inter-cluster virtual links, and cluster aggregated virtual links; Based on the query request, which includes business characteristics and quality of service requirements, a transmission scheduling strategy adapted to the request is obtained from the virtual resource pool.
2. The transmission resource scheduling method according to claim 1, characterized in that, Also includes: When an event occurs that affects the transmission performance of the physical link between member nodes and neighboring nodes, the virtual resource pool is updated in real time.
3. The transmission resource scheduling method according to claim 2, characterized in that, It also includes: analyzing the motion vectors of member nodes, predicting that the member node will move to the edge of a neighboring cluster, and generating pre-update information based on future changes in link connections involving the node and changes in bandwidth estimates to update the virtual resource pool.
4. The transmission resource scheduling method according to claim 1, characterized in that, The step of obtaining the status parameters of each physical link between each member node and its neighboring nodes in the communication network includes: obtaining the bandwidth parameters, latency parameters, and packet loss sequences of the past N periods for each physical link between each member node and its neighboring nodes in the communication network, and calculating the link stability index for the current period based on the packet loss sequences of the past N periods. The step of dividing each physical link into different resource partitions based on the status parameters of each physical link includes dividing each physical link into different resource partitions according to the latency level and stability level preset according to the service requirements.
5. The transmission resource scheduling method according to claim 1, characterized in that, Based on different business feature tags, an aggregation algorithm is performed on the physical links between nodes within a cluster in the resource partition to obtain the intra-cluster virtual link matrix, including: When the business feature label is to support multi-path transmission, the stability-weighted maximum flow algorithm is executed on all physical links in the corresponding resource partition, and the current node is output to score the virtual link bandwidth and expected path stability under the current business requirements. When the service characteristic label is single-path transmission, physical links are first searched in the highest-level resource partition. If one exists, the physical link with the largest transmission bandwidth is selected. If one does not exist, the constraints of latency level and / or stability level in the resource partition are gradually reduced, and physical links are searched in other resource partitions.
6. The transmission resource scheduling method according to claim 1, characterized in that, Based on different business feature tags, an aggregation algorithm is performed on the physical links between boundary node pairs of adjacent clusters in the resource partition to obtain inter-cluster virtual links, and an aggregation algorithm is performed on the physical links between ingress boundary nodes and egress boundary nodes within a cluster to obtain cluster aggregated virtual links, including: For all possible boundary node pairs in adjacent clusters, if the service feature label is to support multipath transmission, the stability-weighted maximum flow algorithm is executed on all physical links in the corresponding resource partition, and the virtual link bandwidth and expected path stability score of the current node pair under the current service requirements are output; if the service feature label is to support single-path transmission, within the range of resource partitions with corresponding physical links, the resource partition with the highest latency level and stability level is determined, and the physical link with the largest transmission bandwidth is selected from it. Between any ingress boundary node and any egress boundary node within a cluster, if the service feature label supports multipath transmission, the maximum flow algorithm is executed on all physical links in the resource partition that meets the quality of service requirements to obtain the inter-cluster virtual link; if the service feature label is single-path transmission, within the range of resource partitions with corresponding physical links, the resource partition with the highest latency level and stability level is determined, and the physical link with the largest transmission bandwidth is selected from it.
7. The transmission resource scheduling method according to claim 3, characterized in that, The virtual resource pool is formed based on the intra-cluster virtual link matrix, inter-cluster virtual links, and cluster aggregated virtual links, including: The local virtual resource pool is constructed by constructing the intra-cluster virtual link matrix corresponding to each cluster head node in the communication network. Construct a regional collaborative resource pool by establishing inter-cluster virtual links and cluster aggregation virtual links corresponding to each cluster; Collect virtual link aggregation summaries from all clusters to form a global virtual resource pool.
8. A transmission resource scheduling system for a clustered communication network, characterized in that, include: The link awareness unit is used to acquire the status parameters of each physical link between each member node and its neighboring nodes in the communication network; The link differentiation unit is used to divide each physical link into different resource partitions based on the status parameters of each physical link; The virtual link aggregation unit is used to perform an aggregation algorithm on the physical links between nodes within a cluster in the resource partition according to different service feature tags, and to obtain the virtual link matrix within the cluster. And based on different business feature tags, an aggregation algorithm is performed on the physical links between the boundary nodes of adjacent clusters in the resource partition to obtain inter-cluster virtual links, and an aggregation algorithm is performed on the physical links between the ingress boundary node and the egress boundary node within the cluster to obtain cluster aggregated virtual links; The virtual resource pool management unit is used to form a virtual resource pool based on the intra-cluster virtual link matrix, inter-cluster virtual links, and cluster aggregated virtual links. A unified resource service unit is used to obtain a transmission scheduling strategy adapted to the request from the virtual resource pool based on the query request, which includes business characteristics and service quality requirements.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the transmission resource scheduling method for the clustered communication network as described in any one of claims 1 to 7.
10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the transmission resource scheduling method for the clustered communication network as described in any one of claims 1 to 7.