5G intelligent networking method and system based on edge computing

Abstract

The invention provides a 5G intelligent networking method and system based on edge computing. The method comprises the following steps: deploying edge computing nodes, and designing a hierarchical network architecture and a dynamic routing mechanism; deploying an edge model on the edge computing node, and carrying out real-time processing and anomaly detection; dynamically distributing network resources, and carrying out network switching and load balancing by utilizing an edge model; decomposing the complex task into a plurality of sub-tasks, and performing distribution and parallel processing of the sub-tasks; updating and optimizing the edge model, and dynamically adjusting a networking strategy; and data security protection is realized, and network data and user feedback are monitored. The system comprises an edge deployment module, a data analysis module, a networking strategy module, a collaborative computing module, a collaborative optimization module and a security protection module. According to the invention, network resources can be efficiently utilized, intelligent networking and network switching are carried out, load balancing is realized, the response speed, the processing capability and the adaptive capability of the network are greatly improved, and the experience feeling of a user is improved.

Description

Technical Field

[0001] The present invention relates to the field of network management technology, and in particular to a 5G intelligent networking method and system based on edge computing. Background Art

[0002] The configuration, optimization and management of the network refers to the planning, adjustment and maintenance of network resources and services to ensure the efficient operation of the network and meet user needs. This includes setting up network equipment, allocating network resources, monitoring network performance, adjusting network parameters, etc. With the popularization of 5G communication technology and the rapid development of the Internet of Things (IoT), the network needs to process massive amounts of data and support a variety of application scenarios. Intelligent networking based on 5G networks can utilize the high bandwidth, low latency and large-scale connection capabilities of 5G networks to automate network management. However, the existing networking methods require complex configuration and management, which increases the difficulty of operation and maintenance, and the resource allocation is not intelligent enough, resulting in waste or insufficient resources, further reducing the response speed and affecting network use. Summary of the invention

[0003] In order to overcome the shortcomings of the prior art, the purpose of the present invention is to provide a 5G intelligent networking method and system based on edge computing, which can efficiently utilize network resources, perform intelligent networking and network switching, achieve load balancing, greatly improve the network's response speed, processing capability and adaptability, and enhance the user experience.

[0004] To achieve the above object, the present invention provides the following solution: a 5G intelligent networking method based on edge computing, comprising the following steps:

[0005] Select user areas and network nodes, deploy multiple edge computing nodes at the selected locations, and design a hierarchical network architecture and dynamic routing mechanism;

[0006] Collect multi-source data, and deploy a lightweight edge model on the edge computing node to perform real-time processing and anomaly detection tasks on the multi-source data to obtain data analysis results;

[0007] Dynamically allocate network resources according to data analysis results, and use the edge model to perform network switching and load balancing;

[0008] Identify complex tasks in the edge model, decompose the complex tasks into multiple subtasks, and assign the multiple subtasks to different edge computing nodes for parallel processing;

[0009] According to the calculation process of the edge computing node, the edge model is updated and optimized in real time, and the networking strategy is dynamically adjusted;

[0010] Introduce encryption technology and access control strategies during data transmission to protect data security, and continuously monitor network data and user feedback.

[0011] Optionally, select user areas and network nodes and deploy multiple edge computing nodes at the selected locations, including:

[0012] Obtain user traffic data and user geographic information through user devices, analyze the acquired historical data using big data analysis technology, identify user-dense areas, and identify key nodes in the network based on the user-dense areas;

[0013] Deploy multiple edge computing nodes on the user-dense area and the key nodes;

[0014] Using virtualization technology, dynamically manage the computing resources of the edge computing nodes, and introduce a resource scheduling system to intelligently allocate computing resources according to the real-time load and task requirements of the edge computing nodes;

[0015] Design a hierarchical network architecture and deploy AI-driven routing algorithms in the hierarchical network architecture to perform network load analysis, data path management, and edge node adjustment;

[0016] The layered network architecture includes a core network layer for overall data management and long-distance data transmission, an edge network layer for local data processing and short-distance transmission, and an access network layer for providing user equipment access services.

[0017] Optionally, multi-source data is collected, and a lightweight edge model is deployed on the edge computing node to perform real-time processing and anomaly detection tasks of the multi-source data to obtain data analysis results, including:

[0018] Acquire user equipment data, base station data and network equipment data to obtain multi-source data;

[0019] According to the time dimension and the space dimension, the multi-source data are integrated using timestamps and geographic location tags, and then the integrated data are analyzed and integrated using semantic technology to obtain a unified data set;

[0020] Selecting a lightweight deep learning model, using the unified data set to train the deep learning model, and setting anomaly detection rules in the deep learning model to obtain an edge model;

[0021] The edge model is deployed on the edge computing node, real-time data is processed and anomaly detected, and data analysis results are obtained.

[0022] Optionally, the user device data includes signal strength, location information, connection time and application usage, the base station data includes base station load, signal coverage, current number of active connections and available bandwidth, and the network equipment data includes router traffic statistics, switch traffic statistics, delay and packet loss rate.

[0023] Optionally, dynamically allocating network resources according to the data analysis results, and using the edge model to perform network switching and load balancing, including:

[0024] Based on the data analysis results, the network usage and user demand are monitored in real time, the bandwidth and spectrum usage trends are identified, and the network demand changes are predicted using the edge model, and the identification results and prediction results are integrated into resource data;

[0025] According to the resource data, dynamically adjust and allocate resources in units of edge computing nodes;

[0026] The user's historical movement data is used to predict the user's movement path and movement speed, and the user's travel data is obtained. Based on the user's travel data, a new site or network node is predicted before the user leaves the current base station range, and a network switch is performed;

[0027] Deploy a real-time monitoring dashboard on the edge computing node for displaying current load status and historical data analysis, and deploy an alarm system for load alarms;

[0028] A load balancing algorithm is deployed on the edge computing node, and the load orientation between different edge computing nodes is adjusted according to the monitoring alarm results of the monitoring dashboard and the alarm system to reduce single point overload and achieve network balance.

[0029] Optionally, a complex task in the edge model is identified and the complex task is decomposed into a plurality of subtasks, including:

[0030] According to the complexity and characteristics of the tasks, the tasks are divided into static tasks and dynamic tasks;

[0031] For the static tasks, a task template and a standardized processing flow are established and deployed on the edge computing node. For the dynamic tasks, load analysis and dependency analysis are performed to decompose the dynamic tasks and obtain multiple subtasks.

[0032] The subtasks are modeled using a directed acyclic graph model to clarify the dependencies and execution order between the subtasks, and then the directed acyclic graph is divided into multiple subgraphs using a graph partitioning algorithm, and the subgraphs are paired with the subtasks.

[0033] Optionally, multiple subtasks are assigned to different edge computing nodes for parallel processing, including:

[0034] A subtask allocation strategy is formulated using a reinforcement learning algorithm, the subtasks are allocated according to the performance of each edge computing node, and a fault-tolerant mechanism is established on the edge computing node to achieve redistribution when a node fails;

[0035] Determine the task priority according to the urgency, importance and delay sensitivity of each task, and match the best node type for each task according to the task characteristics;

[0036] Use a lightweight transmission protocol and set a differential transmission strategy to compress and transmit only changed data and newly added data;

[0037] For the task calculation results of each edge computing node, correlation analysis and importance evaluation are performed. Based on the analysis and evaluation results, multi-threading technology and parallel computing technology are used to merge the processing results of each subtask, and the merging order of the processing results is optimized.

[0038] Optionally, according to the computing process of the edge computing node, the edge model is updated and optimized in real time, and the networking strategy is dynamically adjusted, including:

[0039] The edge-terminal collaborative learning mechanism and federated learning framework are used to conduct cross-node model collaborative training. During the training process, local fine-tuning of user data is supported on each edge computing node, and only the changed data and newly added data are updated and trained through incremental training.

[0040] Use the dynamic strategy table to save the current networking strategy, and dynamically adjust the networking strategy based on real-time data analysis results and model output to obtain a new networking strategy, and then use the CI / CD tool chain to gradually deploy the new networking strategy.

[0041] Optionally, encryption technology and access control strategies are introduced during data transmission to protect data security, and network data and user feedback are continuously monitored, including:

[0042] End-to-end encryption technology and homomorphic encryption algorithm are used for data encryption, and blockchain technology is used to store encrypted data;

[0043] Assign access rights based on user roles and provide multiple authentication methods for network access by combining biometrics and behavioral features;

[0044] In combination with WiFi probe technology, performance indicators are collected on user equipment, the core network layer, the edge network layer and the access network layer to perform performance monitoring.

[0045] The present invention also provides a 5G intelligent networking system based on edge computing, comprising:

[0046] The edge deployment module is used to select user areas and network nodes, deploy multiple edge computing nodes at the selected locations, and design a hierarchical network architecture and dynamic routing mechanism;

[0047] A data analysis module is used to collect multi-source data and deploy a lightweight edge model on the edge computing node to perform real-time processing and anomaly detection tasks of the multi-source data to obtain data analysis results;

[0048] A networking strategy module, used to dynamically allocate network resources according to data analysis results, and use the edge model to perform network switching and load balancing;

[0049] A collaborative computing module, used to identify complex tasks in the edge model, decompose the complex tasks into multiple subtasks, and assign the multiple subtasks to different edge computing nodes for parallel processing;

[0050] A collaborative optimization module, used to update and optimize the edge model in real time according to the calculation process of the edge computing node, and dynamically adjust the networking strategy;

[0051] The security protection module is used to introduce encryption technology and access control strategies during data transmission to protect data security and continuously monitor network data and user feedback.

[0052] The present invention discloses the following technical effects by providing a 5G intelligent networking method and system based on edge computing:

[0053] Efficient network response speed and resource utilization: Through data-driven methods and modular resource configuration, edge computing nodes are flexibly and efficiently deployed in user-dense areas and near key network nodes to reduce data transmission delays. At the same time, by designing a layered network architecture and dynamic routing mechanism, not only the network response speed and resource utilization are improved, but also the 5G network is ensured to meet the ever-changing user needs and complex application scenarios.

[0054] Efficient switching and load balancing of networking strategies: Data resource allocation and priority management are performed through the data analysis results and anomaly detection results of lightweight edge models, and efficient switching and load balancing of networking strategies are performed to achieve collaborative balance among edge nodes and thus achieve network balance.

[0055] Efficient network processing capabilities and adaptability: Through task decomposition and task division, it can achieve rational resource utilization and parallel processing of tasks, reduce network latency and communication overhead; and through edge optimization, multiple edge nodes can be collaboratively trained and updated to quickly adapt to changes in various network environments and user needs.

[0056] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0058] Figure 1 A schematic diagram of a method flow chart provided by an embodiment of the present invention;

[0059] Figure 2 A schematic diagram of a method flow chart of intelligent networking provided by an embodiment of the present invention;

[0060] Figure 3 A schematic diagram of a system architecture provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0063] like Figure 1-2 As shown, the present invention provides a 5G intelligent networking method based on edge computing, comprising the following steps:

[0064] 1. Select user areas and network nodes, deploy multiple edge computing nodes at the selected locations, and design a hierarchical network architecture and dynamic routing mechanism. Including:

[0065] 1.1 Edge Nodes

[0066] Through the user's device, obtain user traffic data and user geographic information. This can be achieved through data such as mobile device connection records and application usage frequency.

[0067] Big data analysis technology is used to analyze the acquired historical data to identify user-dense areas, and based on the user-dense areas, key nodes in the network are identified, such as traffic convergence points and near data centers. These nodes are usually bottlenecks or critical paths for data transmission.

[0068] A plurality of edge computing nodes are deployed in the user-dense area and the key nodes.

[0069] Using virtualization technology (such as Docker, Kubernetes), the computing resources of the edge computing nodes are dynamically managed and allocated to improve resource utilization. A resource scheduling system is introduced to intelligently allocate computing resources according to the real-time load and task requirements of the edge computing nodes to ensure efficient operation of the edge nodes.

[0070] 1.2 Network Architecture

[0071] Design a layered network architecture, including:

[0072] Core network layer: performs overall data management and long-distance data transmission, and connects various edge networks;

[0073] Edge network layer: located between users and the core network, responsible for local data processing and short-distance transmission, reducing the burden on the core network;

[0074] Access network layer: directly connected to user devices, providing last-mile access services to user devices.

[0075] AI-driven routing algorithms are deployed in the hierarchical network architecture to perform network load analysis, data path management, and edge node adjustment.

[0076] 2. Collect multi-source data and deploy a lightweight edge model on the edge computing node to perform real-time processing and anomaly detection tasks on the multi-source data to obtain data analysis results. Including:

[0077] 2.1 Data Collection

[0078] User device data: Get data such as signal strength, location information, connection time, application usage, etc. User devices can provide this information by installing a lightweight client or using data packets in the communication protocol.

[0079] Base station data: collects the load, signal coverage, number of current active connections, available bandwidth, etc. of the base station to which the user is connected.

[0080] Network device data: Collects traffic statistics, latency, and packet loss from routers and switches using protocols such as SNMP and NetFlow.

[0081] The collected data is integrated to obtain multi-source data, and the multi-source data is integrated according to the time dimension and the space dimension using timestamps and geographic location tags to form a unified data set for synchronous analysis, which can be achieved through timestamps and geographic location tags.

[0082] Using semantic technology, the integrated data is analyzed and fused, and data with similar semantic content is combined together. For example, the bandwidth requirements of different applications are combined with the capacity of network equipment for analysis to obtain a unified data set.

[0083] 2.2 Edge Model

[0084] A lightweight deep learning model, such as a convolutional neural network (CNN) or a recurrent neural network (RNN), is selected, the unified data set is used to train the deep learning model, and anomaly detection rules (such as threshold detection) are set in the deep learning model to obtain an edge model.

[0085] The edge model is deployed on the edge computing node, real-time data is processed and anomaly detected, and data analysis results are obtained.

[0086] 3. Dynamically allocate network resources based on data analysis results, and use the edge model to perform network switching and load balancing. Including:

[0087] 3.1 Resource Allocation

[0088] Based on the data analysis results, the network usage and user demand are monitored in real time, the bandwidth and spectrum usage trends are identified, and the edge model is used to predict changes in network demand, such as sudden application traffic or new user connections. The identification results and prediction results are integrated into resource data.

[0089] According to the resource data, resources are dynamically adjusted and allocated in units of edge computing nodes to reduce the burden on the core network.

[0090] 3.2 Network Switching

[0091] The user's historical movement data is used to predict the user's movement path and movement speed to obtain the user's travel data. Based on the user's travel data, new sites or network nodes are predicted before the user leaves the current base station range, and network switching is performed.

[0092] During the switching process, network protocols that support seamless switching can be developed to ensure that user applications are not affected during the switching process. For network edges and critical areas, reserve resources are allocated in advance for rapid takeover.

[0093] 3.3 Load Balancing

[0094] A real-time monitoring dashboard for displaying the current load status and historical data analysis is deployed on the edge computing node, and an alarm system for load alarm is deployed to issue an early warning when the load exceeds the limit or a bottleneck occurs.

[0095] A load balancing algorithm is deployed on the edge computing node, and according to the monitoring alarm results of the monitoring dashboard and the alarm system, the load orientation between different edge computing nodes is adjusted to reduce single-point overload, achieve collaborative work between edge nodes, and assign tasks of overloaded nodes to nodes with lighter loads to achieve network balance.

[0096] 4. Identify the complex tasks in the edge model, decompose the complex tasks into multiple subtasks, and assign the multiple subtasks to different edge computing nodes for parallel processing. Including:

[0097] 4.1 Task Decomposition

[0098] According to the complexity and characteristics of the tasks, tasks are divided into static tasks and dynamic tasks. Static tasks are suitable for processing tasks with high repetitiveness and clear calculation patterns. Dynamic tasks are divided using real-time analysis data and are suitable for tasks with uncertain calculation patterns.

[0099] For the static tasks, task templates and standardized processing procedures are established and deployed on the edge computing nodes. For dynamic tasks, load analysis and dependency analysis are performed to complete the decomposition of the dynamic tasks and obtain multiple subtasks.

[0100] The subtasks are modeled using a directed acyclic graph model to clarify the dependencies and execution order between the subtasks. Then, a graph partitioning algorithm (such as METIS and SCOTCH) is used to divide the directed acyclic graph into multiple subgraphs, and the subgraphs are paired with the subtasks so that each subgraph corresponds to a subtask that can be executed independently on an edge node.

[0101] 4.2 Subtask Allocation and Parallel Processing

[0102] A subtask allocation strategy is formulated using a reinforcement learning algorithm, the subtasks are allocated according to the performance of each edge computing node, and a fault-tolerant mechanism is established on the edge computing node to achieve redistribution in the event of a node failure and ensure task continuity.

[0103] Determine the task priority according to the urgency, importance, and delay sensitivity of each task, and match the best node type for each task according to the task characteristics (such as CPU intensive, GPU intensive, I / O intensive).

[0104] Use lightweight transmission protocols, such as gRPC, QUIC and other efficient transmission protocols, and set differential transmission strategies to compress and transmit only changed data and new data, reducing the amount of data and bandwidth usage.

[0105] For the task calculation results of each edge computing node, correlation analysis and importance evaluation are performed. Based on the analysis and evaluation results, multi-threading technology and parallel computing technology are used to accelerate the merging of the processing results of each subtask and optimize the merging order of the processing results.

[0106] 5. According to the calculation process of the edge computing node, the edge model is updated and optimized in real time, and the networking strategy is dynamically adjusted. Including:

[0107] The edge-terminal collaborative learning mechanism and the federated learning framework are used to perform cross-node collaborative model training. During the training process, local fine-tuning of user data is supported on each edge computing node, and incremental training is used to update only the changed data and new data to minimize the burden of model updates while ensuring rapid adaptation to environmental changes.

[0108] Use the dynamic policy table to save the current networking policy, and dynamically adjust the networking policy based on the real-time data analysis results and model output to obtain a new networking policy, and then use the CI / CD tool chain to gradually deploy the new networking policy. Gradual deployment reduces the uncertain impact of new policies on the overall network by deploying in stages or regions.

[0109] 6. Introduce encryption technology and access control strategies during data transmission to protect data security and continuously monitor network data and user feedback. Including:

[0110] End-to-end encryption technology and homomorphic encryption algorithm are used for data encryption, and blockchain technology is used to store encrypted data.

[0111] Assign access rights based on user roles and combine biometrics and behavioral features to provide multiple authentication methods for network access.

[0112] In combination with WiFi probe technology, performance indicators are collected on user equipment, the core network layer, the edge network layer and the access network layer to perform performance monitoring.

[0113] like Figure 3 As shown, the present invention also provides a 5G intelligent networking system based on edge computing, including:

[0114] The edge deployment module is used to select user areas and network nodes, deploy multiple edge computing nodes at the selected locations, and design a hierarchical network architecture and dynamic routing mechanism.

[0115] The data analysis module is used to collect multi-source data and deploy a lightweight edge model on the edge computing node to perform real-time processing and anomaly detection tasks of the multi-source data to obtain data analysis results.

[0116] The networking strategy module is used to dynamically allocate network resources according to the data analysis results, and use the edge model to perform network switching and load balancing.

[0117] The collaborative computing module is used to identify complex tasks in the edge model, decompose the complex tasks into multiple subtasks, and assign the multiple subtasks to different edge computing nodes for parallel processing.

[0118] The collaborative optimization module is used to update and optimize the edge model in real time according to the calculation process of the edge computing node, and to dynamically adjust the networking strategy.

[0119] The security protection module is used to introduce encryption technology and access control strategies during data transmission to protect data security and continuously monitor network data and user feedback.

[0120] Therefore, the present invention provides a 5G intelligent networking method and system based on edge computing, which can efficiently utilize network resources, perform intelligent networking and network switching, and achieve load balancing, thereby greatly improving the network's response speed, processing capability, and adaptability, thereby enhancing the user experience.

[0121] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0122] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A 5G intelligent networking method based on edge computing, characterized in that: The following steps are involved: Select user areas and network nodes, deploy multiple edge computing nodes at the selected locations, and design a hierarchical network architecture and dynamic routing mechanism; Collect multi-source data, and deploy a lightweight edge model on the edge computing node to perform real-time processing and anomaly detection tasks on the multi-source data to obtain data analysis results; Dynamically allocate network resources according to data analysis results, and use the edge model to perform network switching and load balancing; Identify complex tasks in the edge model, decompose the complex tasks into multiple subtasks, and assign the multiple subtasks to different edge computing nodes for parallel processing; According to the calculation process of the edge computing node, the edge model is updated and optimized in real time, and the networking strategy is dynamically adjusted; Introduce encryption technology and access control strategies during data transmission to protect data security, and continuously monitor network data and user feedback.

2. A 5G intelligent networking method based on edge computing according to claim 1, characterized in that: Select user areas and network nodes, and deploy multiple edge computing nodes at the selected locations, including: Obtain user traffic data and user geographic information through user devices, analyze the acquired historical data using big data analysis technology, identify user-dense areas, and identify key nodes in the network based on the user-dense areas; Deploy multiple edge computing nodes on the user-dense area and the key nodes; Using virtualization technology, dynamically manage the computing resources of the edge computing nodes, and introduce a resource scheduling system to intelligently allocate computing resources according to the real-time load and task requirements of the edge computing nodes; Design a hierarchical network architecture and deploy AI-driven routing algorithms in the hierarchical network architecture to perform network load analysis, data path management, and edge node adjustment; The layered network architecture includes a core network layer for overall data management and long-distance data transmission, an edge network layer for local data processing and short-distance transmission, and an access network layer for providing user equipment access services.

3. A 5G intelligent networking method based on edge computing according to claim 2, characterized in that: Collect multi-source data, and deploy a lightweight edge model on the edge computing node to perform real-time processing and anomaly detection tasks on the multi-source data to obtain data analysis results, including: Acquire user equipment data, base station data and network equipment data to obtain multi-source data; According to the time dimension and the space dimension, the multi-source data are integrated using timestamps and geographic location tags, and then the integrated data are analyzed and integrated using semantic technology to obtain a unified data set; Selecting a lightweight deep learning model, using the unified data set to train the deep learning model, and setting anomaly detection rules in the deep learning model to obtain an edge model; The edge model is deployed on the edge computing node, real-time data is processed and anomaly detected, and data analysis results are obtained.

4. A 5G intelligent networking method based on edge computing according to claim 3, characterized in that: The user device data includes signal strength, location information, connection time and application usage; the base station data includes base station load, signal coverage, current number of active connections and available bandwidth; and the network equipment data includes router traffic statistics, switch traffic statistics, delay and packet loss rate.

5. A 5G intelligent networking method based on edge computing according to claim 4, characterized in that: Dynamically allocate network resources based on data analysis results, and use the edge model to perform network switching and load balancing, including: Based on the data analysis results, the network usage and user demand are monitored in real time, the bandwidth and spectrum usage trends are identified, and the network demand changes are predicted using the edge model, and the identification results and prediction results are integrated into resource data; According to the resource data, dynamically adjust and allocate resources in units of edge computing nodes; The user's historical movement data is used to predict the user's movement path and movement speed, and the user's travel data is obtained. Based on the user's travel data, a new site or network node is predicted before the user leaves the current base station range, and a network switch is performed; Deploy a real-time monitoring dashboard for displaying current load status and historical data analysis on the edge computing node, and deploy an alarm system for load alarm; A load balancing algorithm is deployed on the edge computing node, and the load orientation between different edge computing nodes is adjusted according to the monitoring alarm results of the monitoring dashboard and the alarm system to reduce single point overload and achieve network balance.

6. A 5G intelligent networking method based on edge computing according to claim 5, characterized in that: Identify complex tasks in the edge model and decompose the complex tasks into multiple subtasks, including: According to the complexity and characteristics of the tasks, the tasks are divided into static tasks and dynamic tasks; For the static tasks, a task template and a standardized processing flow are established and deployed on the edge computing node. For the dynamic tasks, load analysis and dependency analysis are performed to decompose the dynamic tasks and obtain multiple subtasks. The subtasks are modeled using a directed acyclic graph model to clarify the dependencies and execution order between the subtasks, and then the directed acyclic graph is divided into multiple subgraphs using a graph partitioning algorithm, and the subgraphs are paired with the subtasks.

7. A 5G intelligent networking method based on edge computing according to claim 6, characterized in that: Assign multiple subtasks to different edge computing nodes for parallel processing, including: A subtask allocation strategy is formulated using a reinforcement learning algorithm, the subtasks are allocated according to the performance of each edge computing node, and a fault-tolerant mechanism is established on the edge computing node to achieve redistribution when a node fails; Determine the task priority according to the urgency, importance and delay sensitivity of each task, and match the best node type for each task according to the task characteristics; Use a lightweight transmission protocol and set a differential transmission strategy to compress and transmit only changed data and newly added data; For the task calculation results of each edge computing node, correlation analysis and importance evaluation are performed. Based on the analysis and evaluation results, multi-threading technology and parallel computing technology are used to merge the processing results of each subtask, and the merging order of the processing results is optimized.

8. A 5G intelligent networking method based on edge computing according to claim 7, characterized in that: According to the calculation process of the edge computing node, the edge model is updated and optimized in real time, and the networking strategy is dynamically adjusted, including: The edge-terminal collaborative learning mechanism and federated learning framework are used to conduct cross-node model collaborative training. During the training process, local fine-tuning of user data is supported on each edge computing node, and only the changed data and newly added data are updated and trained through incremental training. Use the dynamic strategy table to save the current networking strategy, and dynamically adjust the networking strategy based on real-time data analysis results and model output to obtain a new networking strategy, and then use the CI / CD tool chain to gradually deploy the new networking strategy.

9. A 5G intelligent networking method based on edge computing according to claim 8, characterized in that: Introduce encryption technology and access control strategies during data transmission to protect data security, and continuously monitor network data and user feedback, including: End-to-end encryption technology and homomorphic encryption algorithm are used for data encryption, and blockchain technology is used to store encrypted data; Assign access rights based on user roles and provide multiple authentication methods for network access by combining biometrics and behavioral features; In combination with WiFi probe technology, performance indicators are collected on user equipment, the core network layer, the edge network layer and the access network layer to perform performance monitoring.

10. A 5G intelligent networking system based on edge computing, characterized in that: include: The edge deployment module is used to select user areas and network nodes, deploy multiple edge computing nodes at the selected locations, and design a hierarchical network architecture and dynamic routing mechanism; A data analysis module is used to collect multi-source data and deploy a lightweight edge model on the edge computing node to perform real-time processing and anomaly detection tasks of the multi-source data to obtain data analysis results; A networking strategy module, used to dynamically allocate network resources according to data analysis results, and use the edge model to perform network switching and load balancing; A collaborative computing module, used to identify complex tasks in the edge model, decompose the complex tasks into multiple subtasks, and assign the multiple subtasks to different edge computing nodes for parallel processing; A collaborative optimization module, used to update and optimize the edge model in real time according to the calculation process of the edge computing node, and dynamically adjust the networking strategy; The security protection module is used to introduce encryption technology and access control strategies during data transmission to protect data security and continuously monitor network data and user feedback.

Images