Heterogeneous network resource reservation method, apparatus, device, and storage medium

Abstract

The application discloses a heterogeneous network resource reservation method and device, equipment and storage medium, and relates to the technical field of power systems. The method comprises the following steps: extracting multi-dimensional context information from operation state data and service demand data reported by an edge intelligent gateway, generating a cross-domain resource state model and a service quality characteristic model; based on the service quality characteristic model and the cross-domain resource state model, screening a bearable path meeting link capacity constraint conditions and delay constraint conditions from a candidate bearing path of a to-be-reserved service flow; based on the bearable path, generating an initial resource reservation strategy; mapping a demand value of the to-be-reserved service flow in a quality of service dimension into a gateway execution parameter of the edge intelligent gateway; and based on the initial resource reservation strategy and the gateway execution parameter, generating a target resource reservation strategy. In the foregoing manner, a deterministic resource reservation strategy of a key service flow is generated, and the deterministic resource guarantee of the key service flow is realized.

Description

Technical Field

[0001] This application relates to the field of power system technology, and in particular to methods, apparatus, equipment and storage media for reserving resources in heterogeneous networks. Background Technology

[0002] With the continuous development of the Industrial Internet and intelligent manufacturing, industrial sites are placing more stringent deterministic requirements on the end-to-end latency, jitter, and reliability of communication networks. Currently, 5G networks, with their high bandwidth, low latency, and massive connectivity, can meet the wireless access and wide-area transmission needs of industrial sites. Time-Sensitive Networking (TSN) provides deterministic transmission capabilities to Ethernet through time synchronization and scheduling mechanisms. The 5G-TSN heterogeneous network formed by the integration of 5G and TSN can simultaneously support the concurrent operation of multiple types of services, including control, monitoring, and high-bandwidth services, exhibiting strong service carrying flexibility.

[0003] However, in complex industrial environments, concurrent multi-service operations and fluctuating service loads are commonplace. Relying solely on local queue configurations or partial scheduling mechanisms often fails to achieve consistent resource protection across domains. On one hand, differences exist between the 5G and TSN domains in resource representation, queue scheduling mechanisms, and QoS (Quality of Service) assurance methods, leading to low efficiency in cross-domain resource mapping and difficulty in achieving unified resource reservation decisions. On the other hand, policy coordination and consistency are challenging under multi-gateway and multi-link conditions. The end-to-end performance of critical service flows is prone to fluctuations with changes in background traffic, making it difficult to consistently and stably meet latency and reliability requirements. Furthermore, directly modifying the control plane of 5G base stations or TSN switching equipment typically involves high engineering costs and long implementation cycles, hindering rapid deployment and iterative iteration within existing industrial networks.

[0004] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, device, and storage medium for reserving resources in heterogeneous networks, aiming to solve the technical problems of low efficiency in cross-domain resource mapping and difficulty in achieving unified resource reservation decisions in heterogeneous network scenarios in the prior art.

[0006] To achieve the above objectives, this application provides a method for reserving resources in a heterogeneous network, the method comprising: Multidimensional context information is extracted from the operational status data reported by the edge intelligent gateway and the business requirement data of the business flow to be reserved. Based on the multi-dimensional context information, a cross-domain resource status model and a business service quality characteristic model are generated. Based on the cross-domain resource status model, a bearable path that meets the link capacity constraint and latency constraint is selected from the candidate bearer paths of the service flow to be reserved. Based on the bearable path, an initial resource reservation strategy is generated; The service quality characteristic model is used to map the demand values ​​of the service flow to be reserved in each service quality dimension to the gateway execution parameters of the edge intelligent gateway. Based on the initial resource reservation policy and the gateway execution parameters, a target resource reservation policy is generated.

[0007] In one embodiment, the step of extracting multi-dimensional context information from the operational status data reported by the edge intelligent gateway and the service requirement data of the service flow to be reserved includes: The system receives operational status data and service requirement data for the service flows to be reserved from the edge intelligent gateway. The operational status data includes queue length, port throughput, packet loss rate, forwarding latency, and link utilization. The service requirement data includes the type, priority, and quality of service requirements of the service flows to be reserved. The operational status data and the business requirement data are aggregated to obtain aggregated data under multiple aggregation dimensions, including gateway dimension, business flow dimension and time window dimension. The aggregated data under the multiple aggregation dimensions are preprocessed to obtain multidimensional context information. The preprocessing includes at least time alignment, anomaly filtering, and format normalization.

[0008] In one embodiment, the step of aggregating the operational status data and the business requirement data to obtain aggregated data under multiple aggregation dimensions includes: Based on the operational status data and business requirement data reported by the same edge intelligent gateway, the status statistics of each edge intelligent gateway are determined, and the status statistics of each edge intelligent gateway are used as aggregated data under the gateway dimension. The status statistics include at least port statistics, queue statistics and business flow statistics. Based on the operational status data and the business demand data, the forwarding information of the business flow to be reserved under different edge intelligent gateways and the forwarding information of the business flow to be reserved at different times are statistically analyzed to obtain the trajectory data of the business flow to be reserved. The trajectory data of the business flow to be reserved is used as aggregated data under the business flow dimension. Based on a preset sliding time window, a carrying capacity index is statistically derived from the operational status data and the business demand data, and the carrying capacity index is used as aggregated data under the time window dimension.

[0009] In one embodiment, the step of generating a cross-domain resource status model and a service quality feature model based on the multi-dimensional context information includes: Based on the multi-dimensional context information, the status values ​​of the resource attributes of the resource object are determined. The resource object includes 5G domain links, TSN domain links, edge intelligent gateway ports, and gateway queues. The resource attributes include capacity limit, current available value, and current occupied value. The current available value includes any one of the link available bandwidth, edge intelligent gateway port available bandwidth, and gateway queue service capacity. The current occupied value includes the link occupied bandwidth, edge intelligent gateway port occupied bandwidth, and gateway queue occupied capacity. Based on the resource object, the resource attributes of the resource object, and the status values ​​of the resource attributes, a cross-domain resource status model is generated. Based on the multi-dimensional context information, the service quality requirements of the service flow to be reserved are determined. The service quality dimensions include service type, service priority, end-to-end latency upper bound, and reliability requirements. Based on the business flow to be reserved, the service quality dimension of the business flow to be reserved, and the demand value of the service quality dimension, a business service quality feature model is generated.

[0010] In one embodiment, the step of generating an initial resource reservation strategy based on the bearable path includes: Based on the resource consumption cost of the bearable path, the target bearer path and the resource reservation level of the service flow to be reserved are determined. An initial resource reservation strategy is generated based on the target bearer path of the service flow to be reserved and the resource reservation level of the service flow to be reserved.

[0011] In one embodiment, the method further includes: Based on the scarcity of each resource object in the bearable path, determine the weight of the current occupancy value of each resource object in the bearable path; Based on the weight of the current occupancy value of each resource object in the bearable path, the current occupancy value of the resource objects in the bearable path is weighted to obtain the resource occupancy cost of the bearable path.

[0012] In one embodiment, the gateway execution parameters include queue priority level, scheduling policy parameters, and flow control parameters. The step of mapping the demand values ​​of the service quality flow to be reserved in each service quality dimension in the service service quality feature model to the gateway execution parameters of the edge intelligent gateway includes: The service quality characteristic model is used to convert the service flow requirements in each service quality dimension into priority requirements, latency requirements and bandwidth guarantee requirements. Map the priority requirements to queue priority levels; Map the latency requirements to scheduling policy parameters; The bandwidth guarantee requirement is mapped to flow control parameters.

[0013] Furthermore, to achieve the above objectives, this application also proposes a heterogeneous network resource reservation device, which includes: The context-aware module is used to extract multi-dimensional context information from the operational status data reported by the edge intelligent gateway and the business requirement data of the business flow to be reserved. The resource modeling module is used to generate a cross-domain resource status model and a business service quality characteristic model based on the multi-dimensional context information. The reservation and mapping module is used to select a bearable path that meets the link capacity constraint and latency constraint from the candidate bearer paths of the service flow to be reserved based on the cross-domain resource status model. The reservation and mapping module is also used to generate an initial resource reservation strategy based on the bearable path; The reservation and mapping module is also used to map the demand values ​​of the service quality flow to be reserved in each service quality dimension in the service quality feature model to the gateway execution parameters of the edge smart gateway. The reservation and mapping module is also used to generate a target resource reservation policy based on the initial resource reservation policy and the gateway execution parameters.

[0014] In addition, to achieve the above objectives, this application also proposes a heterogeneous network resource reservation device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the heterogeneous network resource reservation method described above.

[0015] In addition, to achieve the above objectives, the present invention also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the heterogeneous network resource reservation method described above.

[0016] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the heterogeneous network resource reservation method described above.

[0017] This application provides a method for reserving resources in heterogeneous networks. It extracts multi-dimensional context information from the operational status data reported by the edge intelligent gateway and the service demand data of the service flow to be reserved. Based on the multi-dimensional context information, it generates a cross-domain resource status model and a service quality characteristic model. Based on the cross-domain resource status model, it selects bearable paths that meet the link capacity and latency constraints from the candidate bearer paths of the service flow to be reserved. Based on the bearable paths, it generates an initial resource reservation strategy. It maps the service quality demand values ​​of the service flow to be reserved in each service quality dimension in the service quality characteristic model to the gateway execution parameters of the edge intelligent gateway. Based on the initial resource reservation strategy and the gateway execution parameters, it generates a target resource reservation strategy. This application utilizes operational information and business requirement information reported by edge intelligent gateways to construct a multi-dimensional context, enabling resource reservation decisions to be based on observable real-time states rather than static configurations. Based on this multi-dimensional context, a cross-domain resource state model and a business QoS characteristic model are established, providing unified modeling of resource states and unified expression of QoS requirements. Based on these models, deterministic resource reservation policies for critical business flows are generated, and business QoS requirements are mapped to executable queue levels, scheduling policies, and flow control parameters on the edge intelligent gateway side. This integrates resource reservation decisions and gateway-side executable configurations into a unified policy output, achieving deterministic resource guarantees for critical business flows. This solves the technical problem of low efficiency in cross-domain resource mapping and difficulty in achieving unified resource reservation decisions in heterogeneous network scenarios. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating an embodiment of the heterogeneous network resource reservation method of this application. Figure 2 This is a schematic diagram of the control plane of the heterogeneous network resource reservation method provided in Embodiment 1 of this application; Figure 3 This is a flowchart illustrating Embodiment 2 of the heterogeneous network resource reservation method of this application; Figure 4 This is a schematic diagram of the module structure of the heterogeneous network resource reservation device in an embodiment of this application; Figure 5This is a schematic diagram of the device structure of the hardware operating environment involved in the heterogeneous network resource reservation method in the embodiments of this application.

[0021] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0023] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0024] The main solution of this application embodiment is as follows: extract multi-dimensional context information from the operation status data reported by the edge intelligent gateway and the service requirement data of the service flow to be reserved; generate a cross-domain resource status model and a service quality feature model based on the multi-dimensional context information; select a bearable path that meets the link capacity constraint and latency constraint from the candidate bearer paths of the service flow to be reserved based on the cross-domain resource status model; generate an initial resource reservation policy based on the bearable path; map the requirement values ​​of the service flow to be reserved in each service quality dimension in the service quality feature model to the gateway execution parameters of the edge intelligent gateway; and generate a target resource reservation policy based on the initial resource reservation policy and the gateway execution parameters.

[0025] On the one hand, the 5G domain and the TSN domain differ in resource representation, queue scheduling mechanism and QoS guarantee methods, resulting in low efficiency of cross-domain resource mapping and difficulty in achieving unified resource reservation decisions. On the other hand, policy coordination and consistency are difficult to guarantee under multiple gateways and multiple links, and the end-to-end performance of critical business flows is prone to fluctuation with changes in background traffic, making it difficult to continuously and stably meet the upper limit of latency and reliability requirements.

[0026] This application provides a solution that utilizes operational information and business requirement information reported by edge intelligent gateways to construct a multi-dimensional context, enabling resource reservation decisions to be based on observable real-time states rather than static configurations. Based on this multi-dimensional context, a cross-domain resource state model and a business QoS characteristic model are established, providing unified modeling of resource states and unified expression of QoS requirements. Based on the model, deterministic resource reservation policies for critical business flows are generated, and business QoS requirements are mapped to executable queue levels, scheduling policies, and flow control parameters on the edge intelligent gateway side. This integrates resource reservation decisions and gateway-side executable configurations into a unified policy output, achieving deterministic resource guarantees for critical business flows. This solves the technical problem of low efficiency in cross-domain resource mapping and difficulty in achieving unified resource reservation decisions in heterogeneous network scenarios.

[0027] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or heterogeneous network resource reservation device capable of performing the above functions. This embodiment does not specifically limit it in this regard. The following uses a heterogeneous network resource reservation device as an example to describe this embodiment and the following embodiments.

[0028] This application provides a method for reserving resources in heterogeneous networks, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the heterogeneous network resource reservation method of this application.

[0029] In this embodiment, the heterogeneous network resource reservation method includes steps S10 to S60: Step S10: Extract multi-dimensional context information from the operating status data reported by the edge intelligent gateway and the business requirement data of the business flow to be reserved; It should be noted that the heterogeneous network in this embodiment refers to the 5G-TSN heterogeneous network formed after the integration of 5G and TSN. Furthermore, the heterogeneous network resource reservation equipment in this embodiment is deployed on the control plane of the management platform, as shown in the reference... Figure 2 It includes a context-aware module, a resource modeling module, a QoS mapping module (reservation and mapping module), and a policy delivery module. The overall architecture adopts a control plane and data plane separation architecture. The management and control platform is responsible for centralized perception, modeling, and decision-making, while the edge intelligent gateway, as the main policy execution entity of the data plane, is responsible for classifying, queuing, scheduling, and controlling the bandwidth of business flows, and reporting the execution status back to the control plane.

[0030] Additionally, it should be noted that the service flow to be reserved refers to the critical service flow that is currently arriving and requires resource reservation. Operational status data refers to the real-time operational status information of ports, queues, and service flows, including queue length, port throughput, packet loss rate, forwarding latency, and link utilization. Service requirement data refers to the real-time QoS requirements of the service flow to be reserved, including the type, priority, and quality of service requirements of the service flow to be reserved; this embodiment does not specifically limit these requirements.

[0031] Understandably, the context-aware module does not rely on static configuration. Instead, it periodically collects real-time operating status and real-time service requirements from the edge intelligent gateway. It then associates and organizes these real-time operating status and service requirements according to three dimensions: gateway, service flow, and time window. This forms multi-dimensional context information that reflects the current network carrying capacity and current service requirements. Subsequent resource modeling and policy decisions are based on this multi-dimensional context information, enabling resource reservation decisions to be dynamically adjusted according to changes in network operating status and service load.

[0032] In one feasible implementation, step S10 includes steps S101 to S103: Step S101: Receive the operating status data and business requirement data of the business flow to be reserved reported by the edge intelligent gateway; It should be noted that this embodiment accesses and aggregates operational status data and business requirement data from the edge intelligent gateway, organizing them into multi-dimensional contextual information for resource reservation decisions. In specific implementation, the context-aware module can be further divided into a data access and aggregation unit and a data preprocessing and unified representation unit.

[0033] Step S102: Aggregate the running status data and the business requirement data to obtain aggregated data under multiple aggregation dimensions; In one feasible implementation, step S102 includes: determining the status statistics of each edge intelligent gateway based on the operation status data and service demand data reported by the same edge intelligent gateway, and using the status statistics of each edge intelligent gateway as aggregated data under the gateway dimension. The status statistics include at least port statistics, queue statistics, and service flow statistics. Based on the operation status data and the service demand data, calculating the forwarding information of the service flow to be reserved under different edge intelligent gateways and the forwarding information of the service flow to be reserved at different times, to obtain the trajectory data of the service flow to be reserved, and using the trajectory data of the service flow to be reserved as aggregated data under the service flow dimension. Based on a preset sliding time window, calculating the carrying capacity index from the operation status data and the service demand data, and using the carrying capacity index as aggregated data under the time window dimension.

[0034] It should be noted that the aggregation dimension is the dimension used when aggregating runtime status data and business requirement data, including gateway dimension, business flow dimension, and time window dimension. Each dimension is aggregated separately, and the resulting data is the aggregated data.

[0035] Understandably, the data access and aggregation unit receives operational status data and business requirement data reported by the edge intelligent gateway, and aggregates the data according to the gateway dimension, business flow dimension, and time window dimension.

[0036] At the gateway level, using the gateway identifier of the edge intelligent gateway as the primary key, the information reported by the same edge intelligent gateway is statistically analyzed. The obtained port statistics, queue statistics, and service flow statistics are merged into the status statistics of each edge intelligent gateway, thereby obtaining the aggregated data corresponding to the gateway level.

[0037] In the business flow dimension, using the business flow quintuple or business flow identifier as the primary key, the forwarding records (forwarding information) of the same business flow at different edge smart gateways and at different times are statistically aggregated into the corresponding business flow's running trajectory (trajectory data), thereby obtaining the aggregated data corresponding to the business flow dimension.

[0038] Within the time window dimension, instantaneous statistics within a preset sliding time window (e.g., on the order of hundreds of milliseconds or seconds) are aggregated to obtain a windowed statistical indicator reflecting the current carrying capacity level, i.e., a carrying capacity indicator. This reduces the interference of instantaneous fluctuations on decision-making, thus yielding aggregated data corresponding to the time window dimension. The aggregation operation includes any one of the following: mean calculation, peak calculation, or quantile calculation.

[0039] Step S103: Preprocess the aggregated data under the multiple aggregation dimensions to obtain multidimensional context information.

[0040] It should be noted that preprocessing includes at least time alignment, anomaly filtering, and format regularization.

[0041] Understandably, the data preprocessing and unified representation unit performs time alignment, anomaly filtering, and format regularization on aggregated data across multiple aggregation dimensions, forming structured multidimensional contextual information that provides a unified input for resource modeling and strategy computation.

[0042] Step S20: Based on the multi-dimensional context information, generate a cross-domain resource status model and a business service quality feature model; In one feasible implementation, step S20 may include steps S201 to S202: Step S201: Based on the multi-dimensional context information, determine the state value of the resource attribute of the resource object; and generate a cross-domain resource state model based on the resource object, the resource attribute of the resource object, and the state value of the resource attribute. It should be noted that the resource modeling module constructs a cross-domain resource state model and a service quality of service characteristic model (service QoS characteristic model) based on multi-dimensional contextual information, and forms parameterized inputs and constraints that can be used for resource reservation calculations. The resource modeling module can be further divided into a resource state modeling unit, a service QoS characteristic modeling unit, and a resource demand description unit.

[0043] Additionally, it should be noted that the resource status modeling unit performs unified modeling of resource status on the heterogeneous network side. The cross-domain resource status model is a parametric model with "resource object-resource attribute-status value" as its basic structure. Resource objects include 5G domain links, TSN domain links, edge smart gateway ports, and gateway queues. Resource attributes include capacity limit, current available value, and current occupied value. The current available value includes any one of the following: available bandwidth of the link, available bandwidth of the edge smart gateway port, and service capacity of the gateway queue. The current occupied value includes the bandwidth occupied by the link, the bandwidth occupied by the edge smart gateway port, and the capacity occupied by the gateway queue.

[0044] Understandably, the gateway queue service capacity is determined by the queue configuration information (number of queues, scheduling weight or time slice allocation for each queue, maximum forwarding rate, etc.) reported by the edge intelligent gateway during the initialization phase, combined with the actual dequeue rate reported by the gateway during operation. The gateway queue occupied capacity, i.e. the current occupancy level of the gateway queue, is obtained by statistically analyzing the queue length, inbound rate, and outbound rate reported periodically by the gateway. After data preprocessing and aggregation by a unified representation unit within a time window, it is expressed in the form of used capacity / queue service capacity or occupied capacity / queue service capacity.

[0045] It should be understood that by extracting the latest numerical values ​​from multidimensional contextual information to fill in the state values, a cross-domain resource state model is obtained, which enables the availability of each resource object to be calculated and compared in a unified manner.

[0046] Step S202: Based on the multi-dimensional context information, determine the service quality requirement value of the service flow to be reserved in the service quality dimension, and generate a service quality feature model based on the service flow to be reserved, the service quality dimension of the service flow to be reserved, and the service quality requirement value.

[0047] It should be noted that the business QoS feature modeling unit uniformly expresses business requirements such as business type, business priority, end-to-end latency upper bound, and reliability requirements, forming a business QoS feature model. The business QoS feature model is a parameterized model with "business flow - service quality dimension - requirement value" as its basic structure. The service quality dimension (QoS dimension) includes at least the business type (control / monitoring / high bandwidth), business priority, end-to-end latency upper bound, and reliability requirements (e.g., packet loss rate upper bound).

[0048] Understandably, the latest values ​​are extracted from multi-dimensional contextual information to populate the demand values, thereby obtaining the business service quality characteristic model.

[0049] In practice, the resource modeling module subscribes to the multi-dimensional context information output by the context awareness module, and refreshes the state values ​​and demand values ​​in the model at the beginning of each decision cycle, thereby maintaining the consistency between the model and the actual operating state of the network.

[0050] Furthermore, it should be noted that the resource requirement description unit maps the QoS dimension to parameterized descriptions of bandwidth guarantee requirements and queue guarantee requirements. Bandwidth guarantee requirements are jointly determined by the service's bandwidth requirements (average / peak) and reliability requirements. A redundancy coefficient is added to the peak bandwidth based on reliability requirements to obtain the minimum bandwidth parameter that should be reserved for the service flow. Queue guarantee requirements are jointly determined by service priority and the upper bound of end-to-end latency. Services with more urgent latency upper bounds and higher priorities are mapped to higher queue priority levels and stricter scheduling parameters (e.g., smaller queuing latency thresholds). The mapped bandwidth guarantee requirements and queue guarantee requirements serve as parameterized inputs and boundary conditions, and as decision inputs and boundary conditions for the reservation and mapping modules.

[0051] Step S30: Based on the cross-domain resource status model, select the bearable paths that meet the link capacity constraints and latency constraints from the candidate bearer paths of the service flow to be reserved. It should be noted that candidate bearer paths are candidate bearer schemes, while capable bearer paths are the selected candidate bearer paths that can meet the link capacity constraints and latency constraints.

[0052] Additionally, it should be noted that the link capacity constraint means that after superimposing the bandwidth guarantee requirements of the corresponding service flow on each link and each gateway port, the remaining available bandwidth is still not less than zero. In other words, the candidate solution will not cause any link or port to become overloaded. The end-to-end latency constraint means that the estimated forwarding latency accumulated along the path (including link transmission latency, gateway queuing latency, and cross-domain conversion latency) does not exceed the upper bound of the end-to-end latency of the corresponding service flow, thereby ensuring that the deterministic latency requirements of the service flow can be met.

[0053] Understandably, for the current service flow to be reserved, all feasible bearer paths from the source to the destination are enumerated as candidate bearer paths. Each candidate bearer path corresponds to a combination of cross-domain links and gateway queue resources in the cross-domain resource state model. Each candidate bearer path is evaluated to see if it can simultaneously meet the link capacity constraint and the latency constraint. If it does not meet either constraint, the candidate bearer path is eliminated. If it meets all constraints, the candidate bearer path is a bearable path and serves as input for subsequent cost comparison and scheme selection.

[0054] It should be understood that, in specific implementation, if there are multiple business flows to be reserved, these business flows can be sorted according to their business priority and end-to-end latency upper bound to form an ordered business flow list. Then, the resource reservation strategy is generated in sequence according to the ordered business flow list.

[0055] Step S40: Generate an initial resource reservation strategy based on the bearable path; It should be noted that the initial resource reservation strategy is the resource reservation strategy initially generated.

[0056] It is understandable that this embodiment needs to find the bearer path with the lower resource consumption cost from the bearer paths as the final bearer path, and then generate the initial resource reservation strategy.

[0057] In one feasible implementation, step S40 may include steps S401 to S402: Step S401: Based on the resource occupancy cost of the bearable path, determine the target bearer path of the service flow to be reserved and the resource reservation level of the service flow to be reserved; In one feasible implementation, the step of determining the resource occupancy cost includes: determining the weight of the current occupancy value of each resource object in the bearable path based on the scarcity of each resource object in the bearable path; and weighting the current occupancy values ​​of the resource objects in the bearable path based on the weight of the current occupancy values ​​of each resource object in the bearable path to obtain the resource occupancy cost of the bearable path.

[0058] It should be noted that the target bearer path is the final bearer path / scheme selected.

[0059] Understandably, the resource occupancy cost is used to optimize among multiple feasible bearer paths. Its value is obtained by weighting the occupancy levels of various resource objects among the candidate bearer paths. For example, the weight of the occupancy level of each resource object is determined according to its scarcity. Typically, scarce resources (such as high-priority queues and low-latency links) are given greater weight, thus prioritizing the option that occupies fewer scarce resources as the target bearer path during decision-making. The occupancy level of a resource object can be represented by its current occupancy value.

[0060] It should be understood that the resource reservation level reflects the strength of resource guarantee for the corresponding service flow in a heterogeneous network, and is usually determined based on a comprehensive consideration of service priority, end-to-end latency upper bound, and resource occupancy cost of the target bearer path. Generally speaking, service flows with higher priority and more urgent latency requirements will be assigned a higher resource reservation level.

[0061] Step S402: Generate an initial resource reservation strategy based on the target bearer path of the service flow to be reserved and the resource reservation level of the service flow to be reserved.

[0062] Understandably, based on the target carrying path, the corresponding resource reservation level is bound as the initial resource reservation strategy.

[0063] Step S50: Map the service quality requirement value of the service flow to be reserved to the gateway execution parameters of the edge intelligent gateway. It should be noted that gateway execution parameters refer to key parameters on the edge intelligent gateway side, including queue priority level, scheduling policy parameters, and traffic control parameters.

[0064] In one feasible implementation, step S50 may include: converting the service quality dimension demand value of the service flow to be reserved into priority demand, latency demand and bandwidth guarantee demand; mapping the priority demand to queue priority level; mapping the latency demand to scheduling policy parameters; and mapping the bandwidth guarantee demand to traffic control parameters.

[0065] It is understandable that business priorities are converted into requirements for priorities, and the upper limit of end-to-end latency is converted into requirements for latency. For example, for latency-sensitive applications, bandwidth requirements (average / peak) and reliability requirements are converted into bandwidth guarantee requirements. For example, based on peak bandwidth, a redundancy coefficient is added according to reliability requirements to obtain the minimum bandwidth parameter that should be reserved.

[0066] It should be understood that priority requirements are mapped to queue priority levels, for example, high-priority service flows are bound to high-priority queues; latency requirements are mapped to scheduling policy parameters, for example, latency-sensitive service flows use shorter scheduling cycles or time-triggered scheduling methods; and bandwidth guarantee requirements are mapped to flow control parameters, which can be Committed Rate (CIR), Peak Rate (PIR), burst size, etc. This embodiment does not specifically limit these parameters.

[0067] Step S60: Generate a target resource reservation policy based on the initial resource reservation policy and the gateway execution parameters.

[0068] It should be noted that the target resource reservation policy refers to the complete resource reservation policy generated based on the initial resource reservation policy, that is, the resource reservation and QoS mapping policy.

[0069] Understandably, a complete resource reservation strategy needs to be further bound to the resource reservation level, as well as the queue priority level, scheduling strategy parameters, and traffic control parameters on the edge intelligent gateway side, based on the target bearer path.

[0070] It should be understood that a target resource reservation policy is typically a set of multiple policy entries. Each policy entry corresponds to a service flow that has completed a reservation decision. The entry content includes at least: service flow identifier, target bearer scheme (target bearer path and cross-domain resource usage), resource reservation level, and queue priority level, scheduling policy parameters, and traffic control parameters on the edge intelligent gateway side. The decision result of resource reservation and QoS mapping for a single service flow constitutes a resource reservation policy entry. The resource reservation policy entries of several service flows are aggregated to form a resource reservation and QoS mapping policy.

[0071] This embodiment provides a method for reserving resources in heterogeneous networks. It extracts multi-dimensional context information from the operational status data reported by the edge intelligent gateway and the service demand data of the service flow to be reserved. Based on the multi-dimensional context information, it generates a cross-domain resource status model and a service quality characteristic model. Based on the cross-domain resource status model, it selects bearable paths that meet the link capacity and latency constraints from the candidate bearer paths of the service flow to be reserved. Based on the bearable paths, it generates an initial resource reservation strategy. It maps the service quality demand values ​​of the service flow to be reserved in each service quality dimension in the service quality characteristic model to the gateway execution parameters of the edge intelligent gateway. Based on the initial resource reservation strategy and the gateway execution parameters, it generates a target resource reservation strategy. This embodiment utilizes operational information and service requirement information reported by the edge intelligent gateway to construct a multi-dimensional context, enabling resource reservation decisions to be based on observable real-time states rather than static configurations. A cross-domain resource state model and a service QoS characteristic model are established based on this multi-dimensional context, providing unified modeling of resource states and unified expression of QoS requirements. Based on these models, deterministic resource reservation strategies for critical service flows are generated, and service QoS requirements are mapped to executable queue levels, scheduling strategies, and flow control parameters on the edge intelligent gateway side. This allows resource reservation decisions and gateway-side executable configurations to form an integrated policy output, achieving deterministic resource assurance for critical service flows.

[0072] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 Step S60 may be followed by step S70: Step S70: Send the configuration instruction corresponding to the target resource reservation policy to the edge intelligent gateway so that the edge intelligent gateway can provide deterministic resource guarantee for the service flow to be reserved.

[0073] Understandably, the policy distribution and execution module is responsible for converting the target resource reservation policy into configuration instructions for the edge intelligent gateway, and distributing them to the edge intelligent gateway through the southbound interface. This drives the edge intelligent gateway to perform business classification, queue mapping, priority scheduling, and bandwidth control on the data plane, so as to achieve deterministic resource guarantee for critical business flows.

[0074] It should be noted that the southbound interface refers to the standardized communication interface between the management and control platform and the edge intelligent gateway for policy issuance and execution status feedback. Specifically, it can be implemented based on NETCONF / YANG, gRPC, RESTCONF or a vendor-defined management channel. The southbound interface carries downlink gateway configuration views and uplink execution status information, and is a collaborative channel between the control plane and the data plane.

[0075] Additionally, it should be noted that deterministic resources refer to network resources that have been explicitly allocated to specific critical service flows through resource reservation decisions and are subject to target resource reservation policies. These include reserved link bandwidth shares, bound gateway port forwarding capabilities, allocated gateway queue priorities and scheduling slots, and corresponding traffic control quotas. The service classification, queue mapping, priority scheduling, and bandwidth control performed by the edge intelligent gateway on the data plane are essentially the scheduling and usage control of these pre-reserved deterministic resources, ensuring that critical service flows continuously receive the promised reserved resources during network operation.

[0076] In practical implementation, the policy distribution and execution module can be divided into a policy parsing and gateway configuration view generation unit, a configuration distribution unit, and an execution status feedback unit. The policy parsing and gateway configuration view generation unit parses the target resource reservation policy into a configuration view at the edge intelligent gateway level. The configuration view includes at least service classification rules, queue mapping relationships, queue priority parameters, and flow control parameters. All data in the configuration view originates from the field values ​​of the corresponding policy entries in the target resource reservation policy. Service classification rules are derived from the service flow identifiers and matching features (such as 5-tuples, VLANs, DSCPs, etc.) in the policy entries. Queue mapping relationships are derived from the correspondence between service flow identifiers and gateway queue levels in the policy entries. Queue priority parameters are taken from the queue priority level and scheduling policy parameters mapped from the policy entries. Flow control parameters are taken from parameters such as CIR / PIR / burst size mapped from the policy entries. The configuration distribution unit distributes the configuration view to the corresponding edge intelligent gateway through the southbound interface. The execution status feedback unit receives the policy execution status information reported by the gateway and feeds it back to the context awareness module for updating multi-dimensional context information.

[0077] It should be understood that the execution status feedback unit receives the policy execution results and operation indicators (including policy effectiveness status, actual queue occupancy of each service flow, actual forwarding latency, packet loss statistics, actual bandwidth usage, etc.) periodically reported by the edge intelligent gateway, and feeds them back to the context awareness module as a new round of context information. The context awareness module refreshes the status fields of the corresponding service flow and gateway in the multi-dimensional context information accordingly, triggering the resource modeling module to recalculate the model parameters. This enables the target resource reservation policy generated in the next decision cycle to be dynamically adjusted based on the latest data, forming a dynamic closed-loop mechanism of "perception-modeling-decision-execution-feedback-re-perception", which makes the resource reservation capability dynamically adjustable and evolvable.

[0078] It should be noted that this embodiment is applicable to 5G-TSN heterogeneous network environments in industrial settings where control-type services and high-bandwidth services operate concurrently, load fluctuations are significant, and end-to-end deterministic guarantees are required. By centralizing decision-making on the control plane and using edge intelligent gateways as the primary execution targets, it is possible to prioritize critical service flows and achieve end-to-end performance stability control without heavily relying on modifications to the control plane of 5G base stations or TSN switching equipment, while also considering both engineering feasibility and system scalability.

[0079] This embodiment provides a method for reserving resources in heterogeneous networks. It sends the configuration instructions corresponding to the target resource reservation policy to an edge intelligent gateway, enabling the edge intelligent gateway to provide deterministic resource guarantees for the service flows to be reserved. This embodiment parses the policy into a gateway-oriented configuration view via a southbound interface and distributes it. The gateway performs service classification, queue mapping, priority scheduling, and bandwidth control on the data plane, while simultaneously transmitting back the policy execution status and key indicators, supporting closed-loop updates and dynamic adjustments to the control plane.

[0080] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the heterogeneous network resource reservation method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0081] This application also provides a heterogeneous network resource reservation device; please refer to [reference needed]. Figure 4 The heterogeneous network resource reservation device includes: Context awareness module 10 is used to extract multi-dimensional context information from the running status data reported by the edge intelligent gateway and the business requirement data of the business flow to be reserved. Resource modeling module 20 is used to generate a cross-domain resource status model and a business service quality feature model based on the multi-dimensional context information; The reservation and mapping module 30 is used to select a bearable path that meets the link capacity constraint and latency constraint from the candidate bearer paths of the service flow to be reserved based on the cross-domain resource status model. The reservation and mapping module 30 is also used to generate an initial resource reservation strategy based on the bearable path; The reservation and mapping module 30 is also used to map the demand values ​​of the service quality flow to be reserved in each service quality dimension in the service quality feature model to the gateway execution parameters of the edge smart gateway. The reservation and mapping module 30 is also used to generate a target resource reservation strategy based on the initial resource reservation strategy and the gateway execution parameters.

[0082] In one feasible implementation, the context-aware module 10 is further configured to receive the operating status data and the service requirement data of the service flow to be reserved reported by the edge intelligent gateway. The operating status data includes queue length, port throughput, packet loss rate, forwarding latency and link utilization. The service requirement data includes the type, priority and quality of service requirements of the service flow to be reserved. The operational status data and the business requirement data are aggregated to obtain aggregated data under multiple aggregation dimensions, including gateway dimension, business flow dimension and time window dimension. The aggregated data under the multiple aggregation dimensions are preprocessed to obtain multidimensional context information. The preprocessing includes at least time alignment, anomaly filtering, and format normalization.

[0083] In one feasible implementation, the context-aware module 10 is further configured to aggregate the running status data and the business requirement data to obtain aggregated data under multiple aggregation dimensions, including: Based on the operational status data and business requirement data reported by the same edge intelligent gateway, the status statistics of each edge intelligent gateway are determined, and the status statistics of each edge intelligent gateway are used as aggregated data under the gateway dimension. The status statistics include at least port statistics, queue statistics and business flow statistics. Based on the operational status data and the business demand data, the forwarding information of the business flow to be reserved under different edge intelligent gateways and the forwarding information of the business flow to be reserved at different times are statistically analyzed to obtain the trajectory data of the business flow to be reserved. The trajectory data of the business flow to be reserved is used as aggregated data under the business flow dimension. Based on a preset sliding time window, a carrying capacity index is statistically derived from the operational status data and the business demand data, and the carrying capacity index is used as aggregated data under the time window dimension.

[0084] In one feasible implementation, the resource modeling module 20 is further configured to include the following steps in generating a cross-domain resource status model and a business service quality characteristic model based on the multi-dimensional context information: Based on the multi-dimensional context information, the status values ​​of the resource attributes of the resource object are determined. The resource object includes 5G domain links, TSN domain links, edge intelligent gateway ports, and gateway queues. The resource attributes include capacity limit, current available value, and current occupied value. The current available value includes any one of the link available bandwidth, edge intelligent gateway port available bandwidth, and gateway queue service capacity. The current occupied value includes the link occupied bandwidth, edge intelligent gateway port occupied bandwidth, and gateway queue occupied capacity. Based on the resource object, the resource attributes of the resource object, and the status values ​​of the resource attributes, a cross-domain resource status model is generated. Based on the multi-dimensional context information, the service quality requirements of the service flow to be reserved are determined. The service quality dimensions include service type, service priority, end-to-end latency upper bound, and reliability requirements. Based on the business flow to be reserved, the service quality dimension of the business flow to be reserved, and the demand value of the service quality dimension, a business service quality feature model is generated.

[0085] In one feasible implementation, the reservation and mapping module 30 is further configured to include the following steps in generating an initial resource reservation strategy based on the bearable path: Based on the resource consumption cost of the bearable path, the target bearer path and the resource reservation level of the service flow to be reserved are determined. An initial resource reservation strategy is generated based on the target bearer path of the service flow to be reserved and the resource reservation level of the service flow to be reserved.

[0086] In one feasible implementation, the reservation and mapping module 30 is further configured to include the following in the method: Based on the scarcity of each resource object in the bearable path, determine the weight of the current occupancy value of each resource object in the bearable path; Based on the weight of the current occupancy value of each resource object in the bearable path, the current occupancy value of the resource objects in the bearable path is weighted to obtain the resource occupancy cost of the bearable path.

[0087] In one feasible implementation, the reservation and mapping module 30 is further configured to include queue priority level, scheduling strategy parameters, and flow control parameters as gateway execution parameters, and the step of mapping the demand values ​​of the service flow to be reserved in each service quality dimension in the service quality feature model to the gateway execution parameters of the edge intelligent gateway includes: The service quality characteristic model is used to convert the service flow requirements in each service quality dimension into priority requirements, latency requirements and bandwidth guarantee requirements. Map the priority requirements to queue priority levels; Map the latency requirements to scheduling policy parameters; The bandwidth guarantee requirement is mapped to flow control parameters.

[0088] The heterogeneous network resource reservation device provided in this application, employing the heterogeneous network resource reservation method in the above embodiments, can solve the technical problem of low efficiency in cross-domain resource mapping and difficulty in achieving unified resource reservation decisions in heterogeneous network scenarios. Compared with the prior art, the beneficial effects of the heterogeneous network resource reservation device provided in this application are the same as those of the heterogeneous network resource reservation method provided in the above embodiments, and other technical features in the heterogeneous network resource reservation device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0089] This application provides a heterogeneous network resource reservation device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the heterogeneous network resource reservation method in the above embodiment 1.

[0090] The following is for reference. Figure 5 This document illustrates a structural diagram suitable for implementing heterogeneous network resource reservation devices in the embodiments of this application. The heterogeneous network resource reservation devices in the embodiments of this application may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The heterogeneous network resource reservation device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0091] like Figure 5 As shown, the heterogeneous network resource reservation device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in ROM (Read Only Memory) 1002 or a program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the heterogeneous network resource reservation device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the heterogeneous network resource reservation device to communicate wirelessly or wiredly with other devices to exchange data. Although heterogeneous network resource reservation devices with various systems are shown in the figure, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented or possessed alternatively.

[0092] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0093] The heterogeneous network resource reservation device provided in this application, employing the heterogeneous network resource reservation method in the above embodiments, can solve the technical problem of low efficiency in cross-domain resource mapping and difficulty in achieving unified resource reservation decisions in heterogeneous network scenarios. Compared with the prior art, the beneficial effects of the heterogeneous network resource reservation device provided in this application are the same as those of the heterogeneous network resource reservation method provided in the above embodiments, and other technical features in this heterogeneous network resource reservation device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0094] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0095] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0096] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the heterogeneous network resource reservation method in the above embodiments.

[0097] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0098] The aforementioned computer-readable storage medium may be included in a heterogeneous network resource reservation device; or it may exist independently and not be assembled into a heterogeneous network resource reservation device.

[0099] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the heterogeneous network resource reservation device, the heterogeneous network resource reservation device: extracts multi-dimensional context information from the operational status data reported by the edge intelligent gateway and the service requirement data of the service flow to be reserved; generates a cross-domain resource status model and a service quality characteristic model based on the multi-dimensional context information; selects a bearable path that meets the link capacity constraint and latency constraint from the candidate bearable paths of the service flow to be reserved based on the cross-domain resource status model; generates an initial resource reservation policy based on the bearable path; maps the service quality requirement values ​​of the service flow to be reserved in each service quality dimension in the service quality characteristic model to the gateway execution parameters of the edge intelligent gateway; and generates a target resource reservation policy based on the initial resource reservation policy and the gateway execution parameters.

[0100] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0101] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0102] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0103] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described heterogeneous network resource reservation method. This solves the technical problem of low efficiency in cross-domain resource mapping and difficulty in achieving unified resource reservation decisions in heterogeneous network scenarios. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the heterogeneous network resource reservation method provided in the above embodiments, and will not be elaborated upon here.

[0104] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the heterogeneous network resource reservation method described above.

[0105] The computer program product provided in this application can solve the technical problem of low efficiency in cross-domain resource mapping and difficulty in achieving unified resource reservation decisions in heterogeneous network scenarios. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the heterogeneous network resource reservation method provided in the above embodiments, and will not be repeated here.

[0106] The above are only some embodiments of this application and do not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for reserving resources in a heterogeneous network, characterized in that, The method includes: Multidimensional context information is extracted from the operational status data reported by the edge intelligent gateway and the business requirement data of the business flow to be reserved. Based on the multi-dimensional context information, a cross-domain resource status model and a business service quality characteristic model are generated. Based on the cross-domain resource status model, a bearable path that meets the link capacity constraint and latency constraint is selected from the candidate bearer paths of the service flow to be reserved. Based on the bearable path, an initial resource reservation strategy is generated; The service quality characteristic model is used to map the demand values ​​of the service flow to be reserved in each service quality dimension to the gateway execution parameters of the edge intelligent gateway. Based on the initial resource reservation policy and the gateway execution parameters, a target resource reservation policy is generated.

2. The method as described in claim 1, characterized in that, The step of extracting multi-dimensional context information from the operating status data reported by the edge intelligent gateway and the business requirement data of the business flow to be reserved includes: The system receives operational status data and service requirement data for the service flows to be reserved from the edge intelligent gateway. The operational status data includes queue length, port throughput, packet loss rate, forwarding latency, and link utilization. The service requirement data includes the type, priority, and quality of service requirements of the service flows to be reserved. The operational status data and the business requirement data are aggregated to obtain aggregated data under multiple aggregation dimensions, including gateway dimension, business flow dimension and time window dimension. The aggregated data under the multiple aggregation dimensions are preprocessed to obtain multidimensional context information. The preprocessing includes at least time alignment, anomaly filtering, and format normalization.

3. The method as described in claim 2, characterized in that, The step of aggregating the operational status data and the business requirement data to obtain aggregated data under multiple aggregation dimensions includes: Based on the operational status data and business requirement data reported by the same edge intelligent gateway, the status statistics of each edge intelligent gateway are determined, and the status statistics of each edge intelligent gateway are used as aggregated data under the gateway dimension. The status statistics include at least port statistics, queue statistics and business flow statistics. Based on the operational status data and the business demand data, the forwarding information of the business flow to be reserved under different edge intelligent gateways and the forwarding information of the business flow to be reserved at different times are statistically analyzed to obtain the trajectory data of the business flow to be reserved. The trajectory data of the business flow to be reserved is used as aggregated data under the business flow dimension. Based on a preset sliding time window, a carrying capacity index is statistically derived from the operational status data and the business demand data, and the carrying capacity index is used as aggregated data under the time window dimension.

4. The method as described in claim 1, characterized in that, The steps for generating the cross-domain resource status model and the business service quality feature model based on the multi-dimensional context information include: Based on the multi-dimensional context information, the status values ​​of the resource attributes of the resource object are determined. The resource object includes 5G domain links, TSN domain links, edge intelligent gateway ports, and gateway queues. The resource attributes include capacity limit, current available value, and current occupied value. The current available value includes any one of the link available bandwidth, edge intelligent gateway port available bandwidth, and gateway queue service capacity. The current occupied value includes the link occupied bandwidth, edge intelligent gateway port occupied bandwidth, and gateway queue occupied capacity. Based on the resource object, the resource attributes of the resource object, and the status values ​​of the resource attributes, a cross-domain resource status model is generated. Based on the multi-dimensional context information, the service quality requirements of the service flow to be reserved are determined. The service quality dimensions include service type, service priority, end-to-end latency upper bound, and reliability requirements. Based on the business flow to be reserved, the service quality dimension of the business flow to be reserved, and the demand value of the service quality dimension, a business service quality feature model is generated.

5. The method as described in claim 1, characterized in that, The step of generating an initial resource reservation strategy based on the bearable path includes: Based on the resource consumption cost of the bearable path, the target bearer path and the resource reservation level of the service flow to be reserved are determined. An initial resource reservation strategy is generated based on the target bearer path of the service flow to be reserved and the resource reservation level of the service flow to be reserved.

6. The method as described in claim 5, characterized in that, The method further includes: Based on the scarcity of each resource object in the bearable path, determine the weight of the current occupancy value of each resource object in the bearable path; Based on the weight of the current occupancy value of each resource object in the bearable path, the current occupancy value of the resource objects in the bearable path is weighted to obtain the resource occupancy cost of the bearable path.

7. The method as described in claim 1, characterized in that, The gateway execution parameters include queue priority level, scheduling policy parameters, and flow control parameters. The step of mapping the demand values ​​of the service quality flow to be reserved in each service quality dimension in the service quality feature model to the gateway execution parameters of the edge intelligent gateway includes: The service quality characteristic model is used to convert the service flow requirements in each service quality dimension into priority requirements, latency requirements and bandwidth guarantee requirements. Map the priority requirements to queue priority levels; Map the latency requirements to scheduling policy parameters; The bandwidth guarantee requirement is mapped to flow control parameters.

8. A heterogeneous network resource reservation device, characterized in that, The device includes: The context-aware module is used to extract multi-dimensional context information from the operational status data reported by the edge intelligent gateway and the business requirement data of the business flow to be reserved. The resource modeling module is used to generate a cross-domain resource status model and a business service quality characteristic model based on the multi-dimensional context information. The reservation and mapping module is used to select a bearable path that meets the link capacity constraint and latency constraint from the candidate bearer paths of the service flow to be reserved, based on the cross-domain resource status model. The reservation and mapping module is also used to generate an initial resource reservation strategy based on the bearable path; The reservation and mapping module is also used to map the demand values ​​of the service quality flow to be reserved in each service quality dimension in the service quality feature model to the gateway execution parameters of the edge smart gateway. The reservation and mapping module is also used to generate a target resource reservation policy based on the initial resource reservation policy and the gateway execution parameters.

9. A heterogeneous network resource reservation device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the heterogeneous network resource reservation method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the heterogeneous network resource reservation method as described in any one of claims 1 to 7.

Images