An enterprise adaptive decision-making method and system based on edge computing

Abstract

The application relates to the technical field of network communication, in particular to an enterprise adaptive decision-making method and system based on edge computing. The method comprises the following steps: acquiring real-time state data of each edge node, and constructing an initial connection topology by using a minimum spanning tree algorithm; performing fault detection based on the initial connection topology, recalculating an alternative path, updating a routing configuration, and obtaining a fault repair connection topology; performing communication delay evaluation on the fault repair connection topology, activating a backup link set when the communication delay exceeds a preset delay threshold, and obtaining a low-delay connection topology; performing transmission rate verification on the low-delay connection topology according to a service transmission requirement, and determining a final connection topology; and configuring a routing strategy and a security strategy according to the final connection topology, and determining an edge communication architecture. The scheme can effectively cope with the dynamic changes of the edge environment and the different requirements of the service transmission, and meet the diversified, high-reliability and high-real-time service transmission and decision-making requirements of enterprises.

Description

Technical Field

[0001] This application relates to the field of network communication technology, and in particular to an enterprise adaptive decision-making method and system based on edge computing. Background Technology

[0002] With the acceleration of digital transformation, enterprise business data is experiencing explosive growth. Edge computing, with its advantages of "nearby processing, low latency, and high reliability", has become a core technology supporting real-time decision-making and efficient collaboration for enterprises, and is widely used in various distributed business scenarios.

[0003] Existing enterprise node interconnection and data transmission solutions based on edge computing mostly adopt fixed network connection structures, constructing the initial connection topology of edge nodes using conventional path algorithms and performing simple path replacements in the event of a failure. However, such static topologies cannot dynamically optimize connection paths based on the real-time load status and geographical environment information of edge nodes, which can easily lead to excessively high service transmission latency. At the same time, backup paths are only triggered and activated when the link is completely interrupted, making it impossible to handle scenarios with localized link performance degradation in a timely manner, and also making it difficult to provide differentiated scheduling strategies based on the transmission requirements of different services.

[0004] In summary, existing technical solutions lack the ability to make adaptive decisions based on dynamic changes in the edge environment and differences in service transmission, making it difficult to meet the diverse, highly reliable, and real-time service transmission and decision-making needs of enterprises. Summary of the Invention

[0005] This application provides an enterprise adaptive decision-making method and system based on edge computing to solve the problems of static and rigid topology, delayed fault recovery, and inability to adapt to dynamic changes in the edge environment and differences in service transmission in existing edge node interconnection and data transmission schemes.

[0006] According to one aspect of this application, an enterprise adaptive decision-making method based on edge computing is provided, comprising: Obtain real-time status data of each edge node, and construct an initial connection topology based on the real-time status data using the minimum spanning tree algorithm; Based on the initial connection topology, fault detection is performed to locate abnormal nodes and abnormal links and generate an analysis report. Based on the analysis report, alternative paths are recalculated and routing configurations are updated to obtain the fault repair connection topology. The communication latency of the fault repair connection topology is evaluated. When the communication latency exceeds a preset latency threshold, the backup link set is activated to obtain a low-latency connection topology. The transmission rate of the low-latency connection topology is verified according to the service transmission requirements. The candidate topologies that pass the verification are retained, and the global connectivity of the candidate topologies is verified and repaired to determine the final connection topology. Based on the final connection topology, configure routing and security policies to determine the edge communication architecture.

[0007] Optionally, after determining the edge communication architecture by configuring routing and security policies based on the final connection topology, the method further includes: The operation status of the edge communication architecture is monitored in real time. When the operation status is abnormal or the service transmission requirements change, the availability of the connection topology of the edge communication architecture is re-verified and the routing configuration is updated.

[0008] According to another aspect of this application, an enterprise adaptive decision-making system based on edge computing is provided, comprising: The initial topology construction module is used to obtain the real-time status data of each edge node, and construct the initial connection topology based on the real-time status data using the minimum spanning tree algorithm. The fault detection and repair module is used to detect faults based on the initial connection topology, locate abnormal nodes and abnormal links and generate an analysis report, recalculate alternative paths and update routing configurations based on the analysis report, and obtain a fault-repaired connection topology. The communication delay optimization module is used to evaluate the communication delay of the fault repair connection topology. When the communication delay exceeds a preset delay threshold, the backup link set is activated to obtain a low-latency connection topology. The rate verification and connectivity repair module is used to verify the transmission rate of the low-latency connection topology according to the service transmission requirements, retain the candidate topologies that pass the verification, and perform global connectivity verification and repair on the candidate topologies to determine the final connection topology. The routing and security configuration module is used to configure routing and security policies according to the final connection topology and determine the edge communication architecture.

[0009] Optional, also includes: The status monitoring and update module is used to monitor the operating status of the edge communication architecture in real time. When the operating status is abnormal or the service transmission requirements change, the availability of the connection topology of the edge communication architecture is re-verified and the routing configuration is updated.

[0010] The technical solution of this application effectively solves the technical problems of static and rigid topology, delayed fault recovery, and inability to adapt to the differences in service transmission and the dynamic changes in the edge environment in existing edge node interconnection solutions. First, this application dynamically generates the initial connection topology based on the real-time status of edge nodes, enabling the initial connection topology to reflect environmental information such as node load and geographical location in real time, fundamentally avoiding the shortcomings of static topologies that cannot be dynamically optimized. Second, this solution uses a two-layer optimization mechanism combining proactive fault detection and quantitative evaluation of communication latency to identify abnormal nodes, abnormal links, and performance degradation issues such as excessive latency in the initial connection topology in real time. It can proactively locate anomalies and automatically calculate alternative paths, activate backup link sets, and update route configurations without waiting for complete link interruption, achieving early intervention and rapid self-healing of the edge network in performance degradation scenarios. Finally, the technical solution of this application verifies the transmission rate of the optimized low-latency connection topology according to service transmission requirements and removes and repairs unqualified links, ensuring that the final connection topology matches the actual service transmission rate requirements of the enterprise, achieving dynamic scheduling based on service differences. In summary, the technical solution of this application forms a closed-loop adaptive decision-making mechanism from multiple dimensions, including dynamic initial topology construction, real-time perception and repair of abnormal states, proactive optimization of communication latency, adaptation to service transmission requirements, and global connectivity assurance. This mechanism can effectively cope with the dynamic changes in the edge environment and the differentiated needs of service transmission, and meet the diverse, highly reliable, and highly real-time service transmission and decision-making needs of enterprises.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 A flowchart illustrating an enterprise adaptive decision-making method based on edge computing, provided in an embodiment of this application; Figure 2 A flowchart illustrating another enterprise adaptive decision-making method based on edge computing provided in this application embodiment; Figure 3 A flowchart illustrating yet another enterprise adaptive decision-making method based on edge computing provided in this application embodiment; Figure 4This is a schematic diagram of the structure of an enterprise adaptive decision-making system based on edge computing, provided in an embodiment of this application. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0015] It should be noted that the terms "target," "initial," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] Figure 1 This is a flowchart illustrating an enterprise adaptive decision-making method based on edge computing, provided as an embodiment of this application. This embodiment is applicable to scenarios involving interconnected distributed edge nodes, real-time transmission of business data, and adaptive decision-making within an enterprise. This method can be executed by an enterprise adaptive decision-making system based on edge computing, which can be implemented in hardware and / or software. Figure 1 As shown, the method includes: S110. Obtain the real-time status data of each edge node, and construct the initial connection topology based on the real-time status data using the minimum spanning tree algorithm.

[0017] Specifically, an edge node refers to a physical or logical node located in an edge computing network, close to the site where business data is generated, and possessing the capabilities for data acquisition, status awareness, data processing, and communication transmission. Real-time status data refers to operational data collected and reported by edge nodes in real time during operation. Real-time status data includes, but is not limited to, node load status, geographical location information, link communication status, and transmission performance. Real-time status data reflects the current operational status of nodes and the network. The minimum spanning tree algorithm refers to an algorithm that, in a weighted undirected graph composed of several nodes and communication links, selects the link combination with the minimum total weight to form a connected tree structure while ensuring that all nodes are connected. The minimum spanning tree algorithm can minimize the overall network communication cost while avoiding loops and can be used to construct a stable and efficient initial network connection topology. Examples of minimum spanning tree algorithms include Prim's algorithm and Kruskal's algorithm. The initial connection topology refers to the network structure initially constructed using the minimum spanning tree algorithm based on the real-time status data of each edge node. It describes the physical or logical connection relationships between edge nodes and serves as the foundational architecture for subsequent topology optimization and repair.

[0018] In this embodiment, real-time status data of each edge node is first acquired. This real-time status data may include node geographic location, load status, link communication latency, and packet loss rate. Then, a weighted network graph is constructed with edge nodes as vertices, inter-node communication links as edges, and communication performance as weights. The minimum spanning tree algorithm is then used to traverse all nodes, selecting the path combination with the minimum total weight while ensuring network connectivity. Redundant links and loops are eliminated to construct the initial connection topology.

[0019] Taking Prim's algorithm as an example, suppose an enterprise has four edge nodes: warehouse A, production line B, dispatch center C, and logistics point D. The communication delays between these nodes are as follows: 20ms between A and B, 50ms between A and C, 30ms between B and C, 40ms between B and D, and 60ms between C and D. Using these communication delays as the weights of the corresponding communication links, and taking any edge node as the starting node, Prim's algorithm is used to gradually expand the connected domain. While ensuring all nodes are connected and no loops are formed, the combination of communication links with the minimum total weight is selected, ultimately yielding the optimal connection paths AB, BC, and BD. This structure achieves connectivity for all edge nodes while minimizing overall network communication delay costs, and eliminates redundant links and loops. Therefore, it can be used as the initial connection topology in this application.

[0020] S120. Based on the initial connection topology, perform fault detection, locate abnormal nodes and abnormal links, generate an analysis report, recalculate alternative paths and update routing configurations according to the analysis report, and obtain the fault repair connection topology.

[0021] Specifically, abnormal nodes and abnormal links refer to edge nodes and inter-node communication links identified as having abnormal operating states, performance degradation, or communication anomalies during fault detection. Anomalies in abnormal nodes and links include, but are not limited to, node or link failures, excessive packet loss rates, excessive communication latency, communication interruptions, and other performance degradation or inability to communicate normally. An analysis report is a written report generated based on the anomaly location results after fault detection is completed. The analysis report may include the specific location of the abnormal node or link, the anomaly type, the severity of the anomaly, the scope of impact, and preliminary handling suggestions. The analysis report provides data support for subsequent alternative path calculation and route configuration updates. The fault repair connection topology refers to the edge node connection structure obtained after fault and performance degradation handling, based on the initial connection topology, through anomaly location, alternative path calculation, and route updates.

[0022] In this embodiment, based on the initial connection topology, the status of each edge node and communication link is monitored. By detecting the operating status of each edge node, link communication quality, transmission latency, and packet loss rate, abnormal nodes and links that have failed or degraded can be located, and an analysis report including the location, type, and scope of the anomaly can be generated. Based on the analysis report, alternative paths that can bypass the abnormal nodes and links are replanned and calculated, and the routing configuration for data forwarding is updated to restore normal network communication, ultimately resulting in a fault-repaired connection topology. This process can promptly detect and locate abnormal nodes and links in the network, and by automatically reconstructing alternative paths and updating routing configurations, it ensures that the network can still communicate normally when failures or performance degradation occur, thereby improving the stability and reliability of the edge network.

[0023] S130. Evaluate the communication delay of the fault repair connection topology. When the communication delay exceeds the preset delay threshold, activate the backup link set to obtain a low-latency connection topology.

[0024] Specifically, communication latency assessment refers to the process of detecting, calculating, and evaluating the data transmission latency between links and nodes in a fault repair connection topology, thereby determining whether the communication latency exceeds a preset latency threshold, and thus deciding whether to activate a backup link set for topology optimization. The preset latency threshold is the maximum allowable communication latency value pre-set and configured based on the real-time requirements, transmission scenarios, transmission distances, and historical communication data of different enterprise services. The preset latency threshold can be set by system default or customized by the user according to actual business needs. For example, for services with high low-latency requirements such as real-time scheduling and video surveillance, the preset latency threshold can be set to 50ms; for latency-insensitive services such as ordinary data synchronization and log uploading, the preset latency threshold can be set to 200ms. A backup link set refers to a pre-planned and reserved set of backup communication links that can replace the original abnormal or degraded links. The backup link set is activated when the original link latency exceeds the limit to ensure low latency and stability of data transmission. A low-latency connection topology refers to the edge node connection structure that meets low-latency transmission requirements after communication latency assessment and optimization of the fault repair connection topology, and adjustment by activating the backup link set when latency exceeds the limit.

[0025] In this embodiment, the communication latency between nodes in the fault repair connection topology is detected, calculated, and evaluated, and the actual communication latency is compared with a pre-set latency threshold. If the communication latency of a certain link exceeds the preset latency threshold, it is determined that the link cannot meet the real-time requirements of service transmission. At this time, a pre-planned set of backup links is activated to replace the original link with excessive latency, and the transmission path between nodes is re-optimized to control the overall network communication latency within an acceptable range, ultimately resulting in a low-latency connection topology. This embodiment can effectively reduce network transmission latency, ensure the real-time and efficient transmission of data, and avoid affecting the normal operation of services due to excessive communication latency.

[0026] S140. Based on the service transmission requirements, perform transmission rate verification on the low-latency connection topology, retain the candidate topologies that pass the verification, and perform global connectivity verification and repair on the candidate topologies to determine the final connection topology.

[0027] Specifically, business transmission requirements refer to the transmission rate, reliability, and real-time performance requirements that an enterprise's actual business needs to meet during data transmission. The rate requirement is primarily used as the basis for transmission rate verification. Transmission rate verification refers to the process of testing and verifying the actual transmission capacity of each link in the low-latency connection topology according to the actual business transmission rate requirements, to determine whether it meets the normal transmission requirements of the business. Candidate topology refers to the edge node connection topology that meets the business transmission rate requirements and is retained after the low-latency connection topology has undergone transmission rate verification and links with substandard rates have been removed. Global connectivity refers to the network state in which there is a valid communication path between any two edge nodes in the edge node connection topology, enabling data exchange. The final connection topology refers to the stable, reliable, and business-compliant edge node network connection structure that is finally determined after initial construction, fault repair, latency optimization, transmission rate verification, and global connectivity repair.

[0028] In this embodiment, based on preset service transmission requirements, the actual transmission rate of each communication link in the low-latency connection topology is verified to determine whether it meets the rate requirements for normal service transmission. Topologies that pass the verification are retained as candidate topologies. Further, global connectivity verification is performed on the candidate topologies to check whether normal communication is possible between any two edge nodes. Path repair is performed on any parts with connectivity anomalies to ensure the stability, integrity, and reliability of the entire network. Finally, the final connection topology that meets the service requirements is determined. This embodiment ensures that the generated final connection topology meets both service transmission rate requirements and global connectivity, thereby improving the availability and service adaptability of the edge network.

[0029] S150. Configure routing and security policies based on the final connection topology to determine the edge communication architecture.

[0030] Specifically, routing policies refer to the data forwarding paths, transmission orders, and scheduling rules between edge nodes set according to the final connection topology. Routing policies ensure efficient and orderly data transmission. Security policies refer to the authentication, access control, and transmission encryption rules adopted to ensure secure data interaction between edge nodes. Security policies prevent data from being illegally obtained, tampered with, or attacked. Edge communication architecture refers to a complete communication system based on the final connection topology, formed by configuring routing rules and security policies, to support data transmission, business collaboration, and adaptive decision-making between enterprise edge nodes.

[0031] In this embodiment, based on the determined final connection topology, corresponding routing and security policies are configured for each edge node. According to the node relationships and link paths in the final connection topology, the forwarding paths, transmission order, and scheduling rules for data between nodes are planned to form a routing policy. Simultaneously, rules related to node authentication, access control, and data encryption are set to form a security policy. After completing the unified configuration of the routing and security policies, an overall edge communication architecture capable of supporting stable, secure, and efficient communication for each edge node is constructed. This embodiment clearly defines data transmission rules and network security protection mechanisms, enabling the entire edge network to have the ability for orderly forwarding, stable communication, and secure transmission, providing reliable network support for enterprise business operations.

[0032] The technical solution of this application effectively solves the technical problems of static and rigid topology, delayed fault recovery, and inability to adapt to the differences in service transmission and dynamic changes in the edge environment in existing edge node interconnection schemes. First, this application dynamically generates the initial connection topology based on the real-time status of edge nodes, enabling the initial connection topology to reflect environmental information such as node load and geographical location in real time, fundamentally avoiding the shortcomings of static topologies that cannot be dynamically optimized. Second, this application adopts a two-layer optimization mechanism combining proactive fault detection and quantitative evaluation of communication latency to identify abnormal nodes, abnormal links, and performance degradation issues such as excessive latency in the initial connection topology in real time. It can proactively locate anomalies and automatically calculate alternative paths, activate backup link sets, and update route configurations without waiting for complete link interruption, achieving early intervention and rapid self-healing of the edge network in performance degradation scenarios. Finally, the technical solution of this application verifies the transmission rate of the optimized low-latency connection topology according to service transmission requirements and removes and repairs unqualified links, ensuring that the final connection topology matches the actual service transmission rate requirements of the enterprise, achieving dynamic scheduling oriented towards service differences. In summary, the technical solution of this application forms a closed-loop adaptive decision-making mechanism from multiple dimensions, including dynamic initial topology construction, real-time perception and repair of abnormal states, proactive optimization of communication latency, adaptation to service transmission requirements, and global connectivity assurance. This mechanism can effectively cope with the dynamic changes in the edge environment and the differentiated needs of service transmission, and meet the diverse, highly reliable, and highly real-time service transmission and decision-making needs of enterprises.

[0033] Figure 2 A flowchart illustrating another enterprise adaptive decision-making method based on edge computing provided in this application embodiment. Based on the above embodiments, as... Figure 2 As shown, optionally, the method includes: S210. Obtain the real-time status data of each edge node, and construct the initial connection topology based on the real-time status data using the minimum spanning tree algorithm.

[0034] S220. Monitor the data transmission status between edge nodes based on the initial connection topology, and locate abnormal nodes and abnormal links according to the data transmission status.

[0035] Specifically, data transmission status refers to the operational state of edge nodes during data transmission. This includes link connectivity and packet loss rate. Link connectivity refers to the connectivity of the communication link between edge nodes, including normal connectivity, communication interruption, or intermittent connectivity. Packet loss rate refers to the proportion of lost data packets to the total number of transmitted data packets, used to measure the transmission quality and stability of the communication link. An abnormal node refers to an edge node that cannot normally perform data forwarding and interaction functions due to its own failure or communication anomalies. An abnormal link refers to a communication link between nodes with abnormal connectivity, an excessively high packet loss rate, and inability to meet normal data transmission requirements.

[0036] In this embodiment, firstly, based on the initial connection topology, the data transmission status between edge nodes is monitored in real time to obtain the data transmission status between nodes. Specifically, the data transmission status includes link connectivity and packet loss rate. By detecting and judging whether the link is normally connected and whether data packets are lost during transmission, edge nodes and communication links with communication anomalies and performance degradation are identified, thereby achieving the location of abnormal nodes and links. This embodiment can perceive the actual communication status of the edge network in real time, and quickly and accurately identify faulty nodes and links through link connectivity and packet loss rate, providing accurate basis for subsequent fault analysis, path replacement, and network repair, ensuring that network faults can be detected in a timely manner.

[0037] S230. Determine the corresponding abnormal path based on the abnormal node and abnormal link, and generate an analysis report.

[0038] The analysis report includes the abnormal path, fault location, and fault impact range.

[0039] Specifically, an abnormal path refers to a transmission path containing abnormal nodes or links that cannot complete data transmission normally or whose communication quality does not meet requirements. Fault location refers to the specific node location or node information at both ends of the abnormal node or link within the edge network topology. Fault impact range refers to the node area, business scenarios, and affected data transmission paths where normal communication is impossible due to abnormal node or link failures.

[0040] In this embodiment, by combining the identified abnormal nodes and links, transmission paths containing these abnormal nodes or links that cannot achieve normal data transmission are identified and designated as abnormal paths. Simultaneously, specific information about these abnormal paths is integrated, including the specific locations of the abnormal nodes and links in the network topology (i.e., fault locations), the node areas, service ranges, and affected transmission paths resulting from these anomalies (i.e., fault impact ranges), generating a complete analysis report to provide a clear and comprehensive basis for subsequent path reconstruction.

[0041] S240. Based on the analysis report, recalculate the abnormal path and generate an alternative path.

[0042] Specifically, the alternative path refers to a data transmission path that bypasses abnormal nodes and abnormal links and is reconstructed through normal nodes and normal communication links. This path is used to replace the abnormal paths that were originally unable to communicate normally, ensuring that data between edge nodes can be forwarded and transmitted normally.

[0043] Optionally, based on the analysis report, the abnormal path is recalculated to generate an alternative path. This includes: removing fault-related links from the abnormal path based on the fault location and impact range in the analysis report; and recalculating the abnormal path to generate an alternative path that avoids the fault area, with the goal of minimizing the number of hops between nodes.

[0044] Specifically, fault-related links refer to communication links directly related to abnormal nodes or paths, experiencing communication failures or substandard transmission quality, and thus unable to continue being used for data forwarding. Hop count refers to the number of intermediate nodes and links through which data travels from the source edge node to the target edge node. Minimizing hop count means optimizing path planning by minimizing the number of forwards, resulting in shorter transmission paths and higher transmission efficiency.

[0045] In this embodiment, firstly, based on the fault location and impact range recorded in the analysis report, fault-related links within the abnormal path are removed from the network topology to prevent data from passing through unavailable links or nodes again. Then, in the remaining network topology after removing fault-related links, the original abnormal path is re-planned and calculated with the goal of minimizing the number of hops between nodes, to obtain an available path that completely avoids the fault area and has the fewest forwarding times, thus forming an alternative path.

[0046] This application's embodiments, by first eliminating fault-related links before path calculation, can prevent data transmission from entering the faulty area at the source, improving the accuracy and reliability of path generation. Generating alternative paths with the goal of minimizing hop counts reduces data forwarding, transmission latency, and link overhead, ensuring data transmission efficiency while simultaneously repairing network faults and improving the overall response speed and operational stability of the edge network.

[0047] S250: Distribute the alternative path to the edge nodes and update the routing configuration to form a fault repair connection topology.

[0048] Specifically, updating the routing configuration refers to the edge node modifying its internal data forwarding rules according to the issued alternative path, deleting or replacing the old routing entries that originally pointed to the abnormal link or abnormal node, and adding forwarding rules that point to the new alternative path, so that subsequent data packets are transmitted along the new, normal path and no longer pass through the faulty area.

[0049] In this embodiment, after determining the alternative path, the path information is distributed to the corresponding edge nodes via the edge network. Upon receiving the new path information, the edge nodes automatically update their internal routing rules, replacing the forwarding entries that originally pointed to the abnormal link or node with the new alternative path. For example, assuming the original data transmission path is node M → node N → node P, and because the link between node N and node P is abnormal, node M → node Q → node P is used as the alternative path. First, the alternative path is distributed to nodes M, Q, and P. Each node updates its own routing configuration, causing subsequent data packets to be forwarded according to the path node M → node Q → node P, thereby bypassing the faulty link and forming a fault-repair connection topology that allows normal communication.

[0050] S260. Evaluate the communication delay of the fault repair connection topology. When the communication delay exceeds the preset delay threshold, activate the backup link set to obtain a low-latency connection topology.

[0051] S270. Based on the service transmission requirements, perform transmission rate verification on the low-latency connection topology, retain the candidate topologies that pass the verification, and perform global connectivity verification and repair on the candidate topologies to determine the final connection topology.

[0052] S280. Based on the node connection relationships, link directions, and available transmission links in the final connection topology, generate corresponding routing forwarding entries for each available transmission link, and update the routing forwarding entries to the routing tables of each edge node.

[0053] Specifically, node connectivity refers to the connectivity, adjacency, and data transmission correspondence among the edge nodes in the final connection topology. Link direction refers to the transmission direction of data forwarding on available transmission links. Available transmission links refer to links that, after fault repair, latency assessment, rate verification, and connectivity verification, are in normal communication status and can stably transmit data. Routing and forwarding entries refer to the rule entries used to guide edge nodes in data forwarding, including information such as the destination node, next-hop node, outgoing link, and forwarding priority. The routing table is the collection of all routing and forwarding entries stored and managed internally by the edge node. Each edge node determines how to forward data based on the routing table.

[0054] In this embodiment, based on the edge node connection relationships, link transmission directions, and available transmission links determined in the final connection topology, a corresponding routing and forwarding entry is generated for each normally available link. This forwarding entry clearly defines the data's source node, destination node, the link to be selected, and the next-hop forwarding node. All generated routing and forwarding entries are uniformly distributed and updated in the routing tables of each edge node, enabling edge nodes to accurately and stably complete data forwarding based on the routing tables. By generating standardized routing and forwarding entries for each available link and updating the routing tables of each edge node, this embodiment clarifies the forwarding rules for the entire network, ensuring stable, orderly, and traceable data transmission paths, avoiding forwarding conflicts or path chaos, and improving the reliability and transmission efficiency of the entire edge communication architecture.

[0055] S290. Configure node identity verification rules for each edge node, authenticate the edge node that initiates data transmission, and allow the edge node that passes the authentication to participate in data interaction.

[0056] Specifically, node identity verification rules refer to pre-defined criteria used to verify the legitimacy of edge node identities, including verification rules for node identifiers, authentication keys, and permission scopes. When an edge node initiates data transmission, it needs to carry its own node identifier and authentication information. The enterprise adaptive decision-making system based on edge computing compares these with the legitimate information in a whitelist. If they match, verification is passed and communication is allowed; otherwise, access is denied. For example, unique identity IDs are configured for enterprise edge nodes E, F, and G: Node_E, Node_F, and Node_G, respectively, along with corresponding authentication keys. These three sets of identity information are stored in an authentication whitelist, forming identity verification rules. When a node initiates data transmission, its reported identity ID and key are verified. If it is a legitimate node among Node_E, Node_F, and Node_G, verification passes and data interaction is allowed; otherwise, network access is prohibited.

[0057] The technical solution of this application, by eliminating faulty associated links and recalculating alternative paths with the goal of minimizing hop count, can avoid faulty areas while ensuring shorter data transmission paths and higher transmission efficiency. Furthermore, by generating routing forwarding entries and updating the routing table based on the final connection topology, unified configuration of data forwarding rules can be achieved, improving the stability and orderliness of network communication. Simultaneously, by configuring node identity verification rules, edge nodes are authenticated, effectively ensuring network access security and preventing unauthorized node intrusion. In summary, this application embodiment can achieve automatic fault detection, adaptive path repair, and efficient route configuration in edge networks, significantly improving the stability, real-time performance, adaptability, and security protection level of enterprise edge computing networks, better meeting the needs of continuous business operation.

[0058] Figure 3 A flowchart illustrating yet another enterprise adaptive decision-making method based on edge computing provided in this application embodiment. Based on the above embodiments, as... Figure 3 As shown, optionally, the method includes: S310. Obtain the real-time status data of each edge node, and construct the initial connection topology based on the real-time status data using the minimum spanning tree algorithm.

[0059] S320. Based on the initial connection topology, perform fault detection, locate abnormal nodes and abnormal links, generate an analysis report, recalculate alternative paths and update routing configurations according to the analysis report, and obtain the fault repair connection topology.

[0060] S330: Real-time acquisition of communication delay of each link in the fault repair connection topology, comparison of communication delay with preset delay threshold, and activation of backup link set when the communication delay of at least one link is greater than the preset delay threshold.

[0061] Specifically, communication latency refers to the time consumed in the transmission link between edge nodes, from the sending end to the receiving end, and is used to measure the real-time performance and response efficiency of the link transmission.

[0062] In this embodiment, by collecting link communication latency in real time and comparing it with a preset latency threshold, links with excessively high communication latency can be accurately identified. By presetting latency thresholds that meet business requirements, the judgment criteria are ensured to be highly matched with the actual application scenarios of enterprises. When excessive latency is detected, a backup link set is automatically activated, which can quickly reduce network transmission latency, ensure the real-time performance and efficiency of data transmission, and enable the edge network to have low-latency adaptive capabilities of automatic perception, automatic judgment, and automatic optimization.

[0063] S340. Select backup links whose communication delay is lower than a preset delay threshold to form a candidate optimized link set.

[0064] Specifically, the candidate optimized link set refers to the set of available high-quality links that are retained from the active backup link set after filtering by communication latency. These links have communication latency lower than a preset latency threshold and meet the real-time requirements of the business. For example, assuming the preset latency threshold is 30ms, the currently active backup link set includes the following backup links: Backup link 1: communication latency 22ms; Backup link 2: communication latency 38ms; Backup link 3: communication latency 18ms. Backup links 1 and 3, which have communication latency lower than the preset latency threshold, are retained to form the candidate optimized link set.

[0065] In this embodiment, only links that meet the communication latency requirements are retained to form a candidate optimized link set, which can further ensure the low latency characteristics of network transmission, avoid using backup links with excessive latency, and enable the edge network to have the adaptive optimization capability of multi-level screening and selection of the best option.

[0066] S350. With the goal of minimizing communication latency, the optimal link is selected from the candidate optimized link set as the target link. The forwarding path corresponding to the target link is distributed to each edge node and the routing table is updated to obtain a low-latency connection topology.

[0067] In this embodiment, the optimal link is the link with the minimum communication latency among the candidate optimized links. Selecting the optimal link with the goal of minimizing communication latency ensures that the data transmission path has the lowest possible transmission delay. After the corresponding forwarding path is distributed and the routing table is updated, edge nodes can efficiently forward data according to the optimal path, effectively reducing network transmission latency and improving service response speed.

[0068] S360. Based on the preset service transmission rate, verify the actual transmission rate of each link in the low-latency connection topology, and classify each link as a qualified link or an unqualified link based on the verification result.

[0069] Specifically, the preset service transmission rate refers to the minimum available link rate threshold set in advance to meet the normal business data transmission needs of an enterprise. It is used to determine whether the actual transmission rate of the link meets the standard. The preset service transmission rate can be pre-configured according to different business scenarios, and can be statically set or dynamically adjusted according to the load. For example, for ordinary enterprise data reporting and control command services, the preset service transmission rate can be set to 1Mbps; for high-definition video or large file transmission services, the preset service transmission rate can be set to 4Mbps to 10Mbps; for industrial IoT small data acquisition services, the preset service transmission rate can be set to 512kbps.

[0070] For example, each link in the low-latency connection topology is tested individually, with the sender of each link sending a test data stream to the receiver of the corresponding link. Within a preset testing time, the actual data traffic received by the receiver of each link is counted, and the actual transmission rate of each link is determined based on the sent test data stream, the received data traffic, and the preset testing time. Then, the actual transmission rate is compared with a preset service transmission rate. If the actual transmission rate is greater than or equal to the preset service transmission rate, the link is determined to be qualified; otherwise, it is determined to be unqualified.

[0071] In this embodiment, the links in the low-latency topology are divided into qualified links and unqualified links, which can provide a basis for subsequent path optimization and link elimination, ensuring that all links participating in data transmission meet the minimum bandwidth requirements of the service, avoiding lag, packet loss or service interruption due to insufficient speed, thereby improving the stability, reliability and service adaptability of the edge network.

[0072] S370. Remove unqualified links from the low-latency connection topology to obtain a candidate topology consisting of qualified links.

[0073] In this embodiment, only qualified links with reliable transmission performance and meeting the speed requirements are retained, which can improve the stability and smoothness of network transmission and provide a solid foundation for the subsequent construction of an efficient and reliable final connection topology.

[0074] S380. Verify whether the candidate topology satisfies global connectivity. If the candidate topology satisfies global connectivity, then determine it as the final connected topology. If the candidate topology does not satisfy global connectivity, then repair the candidate topology to obtain the final connected topology.

[0075] In this embodiment, by verifying whether the candidate topology satisfies global connectivity, it is ensured that the optimized network topology has complete and reliable overall communication capabilities, avoiding problems such as node isolation, network partitioning, or transmission interruption due to the removal of some links. Directly determining the final connection topology when global connectivity is satisfied ensures the legality and validity of the topology structure. Timely repair of candidate topologies when they are not satisfied further improves the availability and robustness of the network topology.

[0076] Optionally, if global connectivity cannot be restored by supplementing links, a topology reconstruction process is triggered. Specifically, based on the currently available edge nodes and link information, the link selection, path calculation, and topology generation steps are re-executed. Using the initial connection topology as a foundation, and combining currently available resources, a new network topology structure is reconstructed to meet the requirements of global connectivity, transmission rate, and communication latency, ensuring uninterrupted network operation and normal service transmission.

[0077] Optionally, the candidate topology is repaired to obtain the final connection topology, including: performing actual transmission rate tests on each link in the candidate optimized link set, and retaining links with actual transmission rates not lower than the preset service transmission rate as valid candidate links. With the goal of minimizing the number of newly added links, links that can restore the candidate topology to a globally connected graph are selected from the valid candidate links as supplementary links. The supplementary links are activated and added to the candidate topology to form the final connection topology.

[0078] In this embodiment, by strictly filtering the rate and supplementing the target-oriented link, the transmission quality and bandwidth of the links in the candidate topology are guaranteed to meet the standards. At the same time, by minimizing the addition of new links, the topology structure is simplified and optimized, which significantly improves the self-healing capability, structural stability and service adaptability of the edge network. This enables the enterprise adaptive decision-making system based on edge computing to quickly and reliably resume normal operation after a failure.

[0079] S390. Configure routing and security policies based on the final connection topology to determine the edge communication architecture.

[0080] S300 monitors the operational status of the edge communication architecture in real time. When the operational status is abnormal or the service transmission requirements change, it re-verifies the availability of the connection topology of the edge communication architecture and updates the routing configuration.

[0081] Specifically, the system collects real-time data on the operational status, link communication quality, and service load of each edge node in the edge communication architecture. When abnormal operational statuses such as node disconnection, link interruption, excessively high communication latency, or substandard transmission rates are detected, or when changes occur in service bandwidth requirements, real-time transmission requirements, or the number of access nodes, an availability check of the current edge communication architecture's connection topology is automatically triggered. Performance indicators such as link connectivity, communication latency, and transmission rate are re-tested and evaluated. Based on the check results, the connection topology is optimized, adjusted, or reconstructed, and the routing configuration of each edge node is updated synchronously, ensuring that the edge communication architecture always maintains a stable, efficient, and available operational state.

[0082] The technical solution of this application effectively improves the real-time performance and efficiency of data transmission by performing latency assessment on the fault repair topology, activating backup links, and selecting the optimal low-latency link. By eliminating unqualified links through transmission rate verification and verifying and repairing the connectivity of candidate topologies, it ensures that the links meet the service bandwidth requirements and the overall network reliability. At the same time, topology repair is achieved with a minimum number of new links, improving the self-healing capability and resource utilization of the edge network. Finally, by combining real-time monitoring of the operating status and dynamic topology verification, the edge network can be adaptively adjusted, significantly improving the stability, real-time performance, and intelligence level of the enterprise edge communication architecture.

[0083] Figure 4 This is a schematic diagram illustrating the structure of an enterprise adaptive decision-making system based on edge computing, provided as an embodiment of this application. Figure 4 As shown, this edge computing-based enterprise adaptive decision-making system includes: The initial topology construction module 410 is used to obtain the real-time status data of each edge node and construct the initial connection topology based on the real-time status data using the minimum spanning tree algorithm.

[0084] The fault detection and repair module 420 is used to detect faults based on the initial connection topology, locate abnormal nodes and abnormal links and generate an analysis report, recalculate alternative paths and update routing configurations based on the analysis report, and obtain the fault repair connection topology.

[0085] The communication delay optimization module 430 is used to evaluate the communication delay of the fault repair connection topology. When the communication delay exceeds the preset delay threshold, the backup link set is activated to obtain a low-latency connection topology.

[0086] The rate verification and connectivity repair module 440 is used to verify the transmission rate of the low-latency connection topology according to the service transmission requirements, retain the candidate topology that passes the verification, and perform global connectivity verification and repair on the candidate topology to determine the final connection topology.

[0087] The routing and security configuration module 450 is used to configure routing and security policies based on the final connection topology and determine the edge communication architecture.

[0088] Based on the above embodiments, continue to refer to Figure 4 Optionally, the edge computing-based enterprise adaptive decision-making system also includes a status monitoring and update module 460, which is used to monitor the operating status of the edge communication architecture in real time. When the operating status is abnormal or the business transmission requirements change, the availability of the connection topology of the edge communication architecture is re-verified and the routing configuration is updated.

[0089] The edge computing-based enterprise adaptive decision-making system provided in this application can execute the edge computing-based enterprise adaptive decision-making method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects of the execution method.

Claims

1. An enterprise adaptive decision-making method based on edge computing, characterized in that, include: Obtain real-time status data of each edge node, and construct an initial connection topology based on the real-time status data using the minimum spanning tree algorithm; Based on the initial connection topology, fault detection is performed to locate abnormal nodes and abnormal links and generate an analysis report. Based on the analysis report, alternative paths are recalculated and routing configurations are updated to obtain the fault repair connection topology. The communication latency of the fault repair connection topology is evaluated. When the communication latency exceeds a preset latency threshold, the backup link set is activated to obtain a low-latency connection topology. The transmission rate of the low-latency connection topology is verified according to the service transmission requirements. The candidate topologies that pass the verification are retained, and the global connectivity of the candidate topologies is verified and repaired to determine the final connection topology. Based on the final connection topology, configure routing and security policies to determine the edge communication architecture.

2. The enterprise adaptive decision-making method based on edge computing according to claim 1, characterized in that, The process of fault detection based on the initial connection topology, locating abnormal nodes and links and generating an analysis report, recalculating alternative paths and updating routing configurations based on the analysis report, and obtaining a fault-repaired connection topology includes: Based on the initial connection topology, the data transmission status between the edge nodes is monitored, and abnormal nodes and abnormal links are located according to the data transmission status; wherein, the data transmission status includes link connectivity status and packet loss rate; The abnormal path is determined based on the abnormal node and the abnormal link, and the analysis report is generated; wherein, the analysis report includes the abnormal path, the fault location, and the fault impact range; Based on the analysis report, the abnormal path is recalculated to generate the alternative path; The alternative path is distributed to the edge node and the routing configuration is updated to form the fault repair connection topology.

3. The enterprise adaptive decision-making method based on edge computing according to claim 2, characterized in that, The step of recalculating the abnormal path based on the analysis report to generate the alternative path includes: Based on the fault location and the fault impact range in the analysis report, fault-related links in the abnormal path are removed; With the goal of minimizing the number of hops between nodes, the abnormal path is recalculated to generate an alternative path that avoids the faulty area.

4. The enterprise adaptive decision-making method based on edge computing according to claim 1, characterized in that, The step of evaluating the communication latency of the fault repair connection topology, and activating the backup link set when the communication latency exceeds a preset latency threshold to obtain a low-latency connection topology, includes: The communication delay of each link in the fault repair connection topology is collected in real time, and the communication delay is compared with the preset delay threshold. When the communication delay of at least one link is greater than the preset delay threshold, the backup link set is activated. Select links in the backup link set whose communication latency is lower than the preset latency threshold to form a candidate optimized link set; With the goal of minimizing communication latency, the optimal link is selected from the candidate optimized link set as the target link, and the forwarding path corresponding to the target link is distributed to each of the edge nodes and the routing table is updated to obtain the low-latency connection topology; wherein, the optimal link is the link with the minimum communication latency in the candidate optimized link set.

5. The enterprise adaptive decision-making method based on edge computing according to claim 4, characterized in that, The process of verifying the transmission rate of the low-latency connection topology according to service transmission requirements, retaining candidate topologies that pass the verification, and performing global connectivity verification and repair on the candidate topologies to determine the final connection topology includes: Based on the preset service transmission rate, the actual transmission rate of each link in the low-latency connection topology is verified, and each link is divided into qualified links or unqualified links according to the verification result. Remove the unqualified links from the low-latency connection topology to obtain the candidate topology composed of the qualified links; Verify whether the candidate topology satisfies global connectivity. If the candidate topology satisfies global connectivity, it is determined as the final connected topology. If the candidate topology does not satisfy global connectivity, it is repaired to obtain the final connected topology.

6. The enterprise adaptive decision-making method based on edge computing according to claim 5, characterized in that, The process of repairing the candidate topology to obtain the final connection topology includes: For each link in the candidate optimized link set, perform an actual transmission rate test, and retain the links whose actual transmission rate is not lower than the preset service transmission rate as valid candidate links. With the goal of minimizing the number of new links, links that can restore the candidate topology to a global connected graph are selected from the effective candidate links as supplementary links; The supplementary link is activated and added to the candidate topology to form the final connection topology.

7. The enterprise adaptive decision-making method based on edge computing according to claim 1, characterized in that, The step of configuring routing and security policies based on the final connection topology to determine the edge communication architecture includes: Based on the node connection relationships, link directions, and available transmission links in the final connection topology, a corresponding routing and forwarding entry is generated for each available transmission link, and the routing and forwarding entry is updated to the routing table of each edge node; Configure node identity verification rules for each edge node, authenticate the edge node that initiates data transmission, and allow the edge node that passes the authentication to participate in data interaction.

8. The enterprise adaptive decision-making method based on edge computing according to claim 1, characterized in that, After determining the edge communication architecture by configuring routing and security policies based on the final connection topology, the method further includes: The operation status of the edge communication architecture is monitored in real time. When the operation status is abnormal or the service transmission requirements change, the availability of the connection topology of the edge communication architecture is re-verified and the routing configuration is updated.

9. An enterprise adaptive decision-making system based on edge computing, characterized in that, include: The initial topology construction module is used to obtain the real-time status data of each edge node, and construct the initial connection topology based on the real-time status data using the minimum spanning tree algorithm. The fault detection and repair module is used to detect faults based on the initial connection topology, locate abnormal nodes and abnormal links and generate an analysis report, recalculate alternative paths and update routing configurations based on the analysis report, and obtain a fault-repaired connection topology. The communication delay optimization module is used to evaluate the communication delay of the fault repair connection topology. When the communication delay exceeds a preset delay threshold, the backup link set is activated to obtain a low-latency connection topology. The rate verification and connectivity repair module is used to verify the transmission rate of the low-latency connection topology according to the service transmission requirements, retain the candidate topologies that pass the verification, and perform global connectivity verification and repair on the candidate topologies to determine the final connection topology. The routing and security configuration module is used to configure routing and security policies according to the final connection topology and determine the edge communication architecture.

10. The enterprise adaptive decision-making system based on edge computing according to claim 9, characterized in that, Also includes: The status monitoring and update module is used to monitor the operating status of the edge communication architecture in real time. When the operating status is abnormal or the service transmission requirements change, the availability of the connection topology of the edge communication architecture is re-verified and the routing configuration is updated.

Images