System and method for establishing VPN (Virtual Private Network) data flow acceleration model

Abstract

The invention relates to the technical field of network communication management, and discloses a system and a method for establishing a VPN (Virtual Private Network) data flow acceleration model, and the method comprises the following steps: distributing an IP (Internet Protocol) address for access equipment through a DHCP (Dynamic Host Configuration Protocol), and obtaining the IP address of a message queue telemetry transport protocol (MQTT) server; and the access device registers identity information through the MQTT and stores the identity information. And performing batch management on the access equipment according to the subscription mechanism of the MQTT server, wherein the management content comprises equipment configuration, operation state, terminal access and batch upgrading. Meanwhile, VPN data features and historical data features of the access device are obtained and stored, a VPN data flow classification model is established based on the features, and the VPN features of the device are substituted into the model to obtain a classification result. And finally, obtaining real-time performance data of a network link, determining an effective link according to a demand relationship between the real-time data and a classification result, and selecting an optimal path transmission mechanism based on the effective link so as to optimize the transmission performance of the VPN data stream.

Description

Technical Field

[0001] The present invention relates to the technical field of network communication management, and in particular to a system and method for establishing a VPN data flow acceleration model. Background Art

[0002] With the rapid development of network technology, especially with the widespread application of wireless access devices and VPN data flows, the traditional centralized management of access controllers (AC) and access points (AP) faces increasing challenges. Traditional AC / AP centralized management solutions usually use the CAPWAP protocol (Control and Configuration of Wireless Access Points Protocol) to implement device access, configuration, management and monitoring. However, the CAPWAP protocol has some serious limitations in high-concurrency, large-scale device access environments. The main problem is that the protocol design is too complex, with high resource consumption and large latency, resulting in the real-time and efficiency of device management and data flows being difficult to meet the needs of modern network environments.

[0003] In order to meet the growing demand for bandwidth and network traffic management, VPN data flow acceleration has become one of the key technologies. However, existing VPN acceleration technologies usually rely on static link configuration and protocol scheduling mechanisms, and cannot fully consider the dynamic changes between different devices and links. Especially when it comes to large-scale devices and complex network structures, traditional VPN traffic management and scheduling methods often cannot respond to changes in network load in real time, nor can they flexibly adjust the routing path and traffic control strategy of data flows. The lack of an intelligent scheduling mechanism based on real-time network performance data and device status leads to low transmission efficiency of VPN data flows, especially in an environment where equipment diversity and network complexity are increasing, the problem is more obvious.

[0004] Therefore, there is an urgent need to invent a network management system to solve the problem that the existing VPN acceleration technology relies on static link configuration and protocol scheduling, cannot respond to network load and dynamic changes of equipment in real time, resulting in low efficiency of data flow scheduling, especially in large-scale equipment and complex network environments, and cannot flexibly optimize the transmission path. Summary of the invention

[0005] In view of this, the present invention proposes a system and method for establishing a VPN data flow acceleration model, aiming to solve the problem that the existing VPN acceleration technology relies on static link configuration and protocol scheduling, cannot respond to network load and dynamic changes of equipment in real time, resulting in low data flow scheduling efficiency, especially in large-scale equipment and complex network environments. The transmission path cannot be flexibly optimized.

[0006] The present invention proposes a method for establishing a VPN data flow acceleration model, comprising:

[0007] Allocate an IP address to each access device based on the dynamic host configuration protocol, obtain the IP address of the message queue telemetry transmission protocol server based on the dynamic host configuration protocol; register the identity information of each access device based on the message queue telemetry transmission protocol, and store the identity information of each access device;

[0008] Obtaining a subscription mechanism of the message queue telemetry transmission protocol server, and performing batch management on each of the access devices according to the subscription mechanism, wherein the batch management includes configuration distribution of the access devices, reporting of operating status of the access devices, terminal access management of the access devices, and batch upgrade of each of the access devices;

[0009] Acquire and store VPN data characteristics of each access device, wherein the VPN data characteristics include: traffic pattern, data packet size, protocol type, delay and packet loss rate;

[0010] Acquire historical VPN data features, establish the VPN data flow classification model based on the historical VPN data features, substitute the VPN data features of the access device into the VPN data flow classification model, and obtain the classification result of the access device;

[0011] Acquire real-time performance data of each link in the network link, determine the effective link according to the relationship between the real-time performance data and the performance requirement data of the classification result, and determine the path transmission mechanism between the access device and the effective link based on the effective link.

[0012] Furthermore, when the VPN data flow classification model is established based on the historical VPN data characteristics, it includes:

[0013] Obtaining the traffic pattern, data packet size, protocol type, delay and packet loss rate of each historical VPN data in the historical VPN data characteristics, and establishing a historical VPN data association formula;

[0014] Obtaining the distance metric between the historical VPN data association equations based on the Euclidean distance:

[0015]

[0016] Wherein, D(x,y) is the distance metric between any two historical VPN data associations, xi and yi respectively refer to the i-th data feature between the two historical VPN data associations, the data features include: traffic pattern, data packet size, protocol type, delay and packet loss rate, and n is the total number of the data features;

[0017] constructing a distance matrix according to the distance metric, and iteratively clustering the historical VPN data association equations according to the distance matrix;

[0018] The historical VPN data association formula after iterative clustering is determined as the VPN data flow type association formula, the type of each VPN data flow is determined according to the number of each VPN data flow type association formula, and the VPN data flow classification model is established according to each VPN data flow type association formula and the type of each VPN data flow.

[0019] Further, when the VPN data flow classification model is established according to each VPN data flow type association formula and the type of each VPN data flow, it includes:

[0020] Obtaining a distance metric between each of the historical VPN data association formulas and each of the VPN data flow type association formulas, and classifying each of the historical VPN data association formulas according to the distance metric and a preset distance metric;

[0021] Acquire a linear relationship axis between each of the historical VPN data association equations under the type of the VPN data flow, and determine a characteristic vector of the type of the VPN data flow according to the linear relationship axis;

[0022] The VPN data flow classification model is established according to the feature vector of each type of the VPN data flow.

[0023] Further, determining a valid link according to the relationship between the real-time performance data and the performance requirement data of the classification result includes:

[0024] Determine the similarity between the real-time performance data and the performance requirement data according to the relationship between the real-time performance data and the performance requirement data:

[0025]

[0026] Wherein Li is the similarity between the real-time performance data and the performance requirement data, N is the total number of indicator data, Gi is the i-th indicator data in the real-time performance data, and gi is the i-th indicator data in the performance requirement data;

[0027] According to the relationship between the similarity and a preset similarity, each of the links is screened:

[0028] When the similarity is less than the preset similarity, determining to remove the link;

[0029] When the similarity is greater than or equal to a preset similarity, it is determined to retain the link, and the valid link is determined according to the relationship between the retained links.

[0030] Further, determining the valid link according to the relationship between the retained links includes:

[0031] Obtaining an average value between the retained real-time performance data between the links, and determining the average value as the preset performance data;

[0032] Determine the performance score of each link according to the relationship between the real-time performance data and the preset performance data:

[0033]

[0034] Wherein, S is the performance score of the link, Hi is the weight of the indicator feature in the real-time performance data, ai is the i-th indicator feature in the preset performance data, and Ai is the i-th indicator feature in the real-time data;

[0035] The performance scores are sorted in descending order, and the link corresponding to the performance score ranked first is determined as the valid link.

[0036] Compared with the prior art, the beneficial effect of the present invention is that by using the DHCP protocol to dynamically allocate an IP address to each access device, and at the same time obtaining the IP address of the message queue telemetry transmission protocol server, the access device and the network management system can be seamlessly connected. Through this mechanism, it is possible to ensure that the identity information of each device is automatically registered and stored, avoiding the complexity and error risks brought by traditional static configuration, and providing an efficient and automated solution for device management. In addition, the subscription mechanism based on the MQTT protocol can realize batch management of access devices. This not only includes the configuration distribution and operation status reporting of the device, but also involves key tasks such as terminal access management and batch upgrade of devices. Compared with traditional management methods, this MQTT-based solution greatly improves the flexibility and real-time performance of management, especially in large-scale equipment environments, it can achieve accurate real-time monitoring and scheduling, and greatly reduces the need for manual intervention. The status information of the device can be uploaded to the server in real time, and the administrator can obtain the latest operation data of the device at any time through the subscription mechanism, and quickly respond to any changes in the network, thereby effectively improving the overall management efficiency of the network and the working stability of the device. Furthermore, by acquiring and storing the VPN data characteristics of each access device, including traffic mode, packet size, protocol type, delay and packet loss rate, etc., valuable data support can be provided for subsequent network optimization and acceleration. By analyzing the historical VPN data characteristics and establishing a VPN data flow classification model, the VPN traffic of the access device can be intelligently classified, and different optimization strategies can be provided for different types of traffic based on the classification results. By inputting the real-time data of the access device into the model, the data flow type of each device can be accurately determined, so as to better formulate personalized acceleration plans for it and improve the transmission efficiency and user experience of the overall network. Finally, combined with the various performance data in the real-time network link, the optimal network link can be automatically determined based on the relationship between the classification model and the real-time performance data. This mechanism can not only ensure that the data flow of each access device is transmitted on the optimal path, but also adjust the transmission path of the data flow in real time according to the changes in the network load and link quality, avoiding the network congestion and performance bottleneck problems existing in the traditional static path allocation method. Through this dynamic path selection, it is possible to maintain a high data transmission quality in a complex network environment, while greatly improving the flexibility and adaptability of the network, ensuring the acceleration effect and stability of the VPN data flow.

[0037] On the other hand, the present application also provides a system for establishing a VPN data flow acceleration model, including:

[0038] Access devices and access controllers;

[0039] The access controller is used to perform batch management on each of the access devices, wherein the access controller includes: a connection unit, a storage unit, a first central control unit, a second central control unit and an adjustment unit;

[0040] The connection unit is configured to allocate an IP address to each access device based on a dynamic host configuration protocol, and obtain an IP address of a message queue telemetry transmission protocol server based on the dynamic host configuration protocol; the connection unit is also configured to register the identity information of each access device based on the message queue telemetry transmission protocol, and store the identity information of each access device;

[0041] The storage unit is configured to obtain and store VPN data characteristics of each of the access devices, wherein the VPN data characteristics include: traffic pattern, data packet size, protocol type, delay and packet loss rate; the storage unit is also configured to obtain historical VPN data characteristics;

[0042] The first central control unit is configured to obtain a subscription mechanism of the message queue telemetry transmission protocol server, and perform batch management on each of the access devices according to the subscription mechanism, wherein the batch management includes configuration distribution of the access device, reporting of the operation status of the access device, terminal access management of the access device, and batch upgrade of each of the access devices;

[0043] The second central control unit is configured to establish the VPN data flow classification model based on historical VPN data features, substitute the VPN data features of the access device into the VPN data flow classification model, and obtain the classification result of the access device;

[0044] The adjustment unit is configured to obtain real-time performance data of each link in the network link, determine the effective link according to the relationship between the real-time performance data and the performance requirement data of the classification result, and determine the path transmission mechanism between the access device and the effective link based on the effective link.

[0045] Furthermore, when the second central control unit establishes the VPN data flow classification model based on the historical VPN data features, it includes:

[0046] The second central control unit is further configured to obtain the traffic mode, data packet size, protocol type, delay and packet loss rate of each historical VPN data in the historical VPN data characteristics, and establish a historical VPN data association formula;

[0047] The second central control unit is further configured to obtain a distance metric between each of the historical VPN data association equations based on the Euclidean distance:

[0048]

[0049] Wherein, D(x,y) is the distance metric between any two historical VPN data associations, xi and yi respectively refer to the i-th data feature between the two historical VPN data associations, the data features include: traffic pattern, data packet size, protocol type, delay and packet loss rate, and n is the total number of the data features;

[0050] The second central control unit is further configured to construct a distance matrix according to the distance metric, and iteratively cluster the historical VPN data association equations according to the distance matrix;

[0051] The second central control unit is further configured to determine the historical VPN data association formula after iterative clustering as the VPN data flow type association formula, determine the type of each VPN data flow according to the number of each VPN data flow type association formula, and establish the VPN data flow classification model according to each VPN data flow type association formula and the type of each VPN data flow.

[0052] Further, when the second central control unit establishes the VPN data flow classification model according to each VPN data flow type association formula and the type of each VPN data flow, it includes:

[0053] The second central control unit is further configured to obtain a distance metric between each of the historical VPN data association formulas and each of the VPN data flow type association formulas, and classify each of the historical VPN data association formulas according to the distance metric and a preset distance metric;

[0054] The second central control unit is further configured to obtain a linear relationship axis between each of the historical VPN data association equations under the type of the VPN data flow, and determine a characteristic vector of the type of the VPN data flow according to the linear relationship axis;

[0055] The second central control unit is further configured to establish the VPN data flow classification model according to the feature vector of each type of the VPN data flow.

[0056] Furthermore, when the adjustment unit determines the valid link according to the relationship between the real-time performance data and the performance requirement data of the classification result, it includes:

[0057] The adjustment unit is further configured to determine a similarity between the real-time performance data and the performance requirement data according to a relationship between the real-time performance data and the performance requirement data:

[0058]

[0059] Wherein Li is the similarity between the real-time performance data and the performance requirement data, N is the total number of indicator data, Gi is the i-th indicator data in the real-time performance data, and gi is the i-th indicator data in the performance requirement data;

[0060] The adjustment unit is further configured to filter each of the links according to a relationship between the similarity and a preset similarity:

[0061] When the similarity is less than the preset similarity, the adjustment unit determines to remove the link;

[0062] When the similarity is greater than or equal to a preset similarity, the adjustment unit determines to retain the link, and determines the valid link according to the relationship between the retained links.

[0063] Further, when the adjustment unit determines the valid link according to the relationship between the reserved links, it includes:

[0064] Obtaining an average value between the retained real-time performance data between the links, and determining the average value as the preset performance data;

[0065] The adjustment unit is further configured to determine a performance score of each of the links according to a relationship between the real-time performance data and the preset performance data:

[0066]

[0067] Wherein, S is the performance score of the link, Hi is the weight of the indicator feature in the real-time performance data, ai is the i-th indicator feature in the preset performance data, and Ai is the i-th indicator feature in the real-time data;

[0068] The adjustment unit is further configured to sort the performance scores in reverse order, and determine the link corresponding to the performance score ranked first as the valid link.

[0069] It can be understood that the system and method for establishing a VPN data flow acceleration model in the above embodiments of the present invention have the same beneficial effects, which will not be described in detail. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0071] Figure 1A flowchart of a method for establishing a VPN data flow acceleration model provided by an embodiment of the present invention;

[0072] Figure 2 A structural block diagram of a system for establishing a VPN data flow acceleration model provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0073] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0074] like Figure 1 As shown, in some embodiments of the present application, this embodiment provides a method for establishing a VPN data flow acceleration model, including:

[0075] Step S100: Allocate an IP address to each access device based on the dynamic host configuration protocol, obtain the IP address of the message queue telemetry transmission protocol server based on the dynamic host configuration protocol, register the identity information of each access device based on the message queue telemetry transmission protocol, and store the identity information of each access device.

[0076] It is understandable that IP addresses are assigned to access devices by utilizing the Dynamic Host Configuration Protocol (DHCP). DHCP is an automated protocol that can simplify the device access configuration process by dynamically assigning IP addresses, avoiding the tediousness of manually configuring IP addresses. When each access device accesses the network, it requests an available IP address through DHCP and obtains other network configuration information at the same time. Through DHCP, the access device can quickly obtain the necessary configuration in the network, reduce the complexity of network management, and improve the scalability of the network and the efficiency of device access. Secondly, when the device obtains the IP address, based on the Message Queue Telemetry Transport Protocol (MQTT), each access device will register with the MQTT server. MQTT is a lightweight message transmission protocol suitable for low-bandwidth, high-latency or unstable network environments. Through MQTT, the access device can send its identity information (such as device ID, model, status, etc.) to the MQTT server for registration. This process provides a unified platform for device management, which can record the identity information of each device in real time and realize two-way communication between the device and the management system. This method not only improves the efficiency of device access, but also makes the management of device information more centralized and standardized. Finally, through the MQTT protocol, the identity information of all registered access devices will be stored on the server side. This process not only realizes the unique identification of device identity, but also provides basic data support for subsequent device management, configuration distribution, status monitoring, etc. By storing device identity information, management can obtain device status data and configuration information at any time to achieve dynamic monitoring and real-time management.

[0077] It can be seen that by using the Dynamic Host Configuration Protocol (DHCP) to automatically assign IP addresses to access devices, the complexity and risk of errors in manual configuration can be greatly reduced. DHCP enables each device to quickly obtain a suitable IP address when accessing the network, thereby saving time and improving the access efficiency of the device. In addition, the DHCP automatic allocation process also provides flexibility for network managers, making device access more scalable, especially when facing large-scale device access, it can effectively avoid bottlenecks in network configuration. Secondly, combined with the Message Queue Telemetry Transport Protocol (MQTT), intelligent registration and centralized management of device information can be achieved. MQTT is a lightweight and reliable message transmission protocol, through which the identity information of each access device can be uploaded to the server in a timely manner for registration. In this way, the management platform can grasp the basic situation, status information and interaction mode of each access device in real time, thereby improving the monitoring and management capabilities of the device. The centralized storage of the device identity information ensures the consistency and integrity of the device information, which is conducive to the subsequent dynamic scheduling, configuration management and fault diagnosis of the device. Finally, the storage of device identity information provides basic data support for subsequent device management, performance optimization and network configuration distribution. By storing device information, management can view and retrieve the status, configuration, and historical behavior of specific devices at any time, providing data support for real-time management and troubleshooting. This mechanism not only improves the automation of network management, but also enables network operators to perform equipment maintenance, batch upgrades, and dynamic adjustments more accurately, greatly improving the manageability, maintainability, and flexibility of the network.

[0078] Step S200, obtain the subscription mechanism of the message queue telemetry transmission protocol server, and perform batch management of each access device according to the subscription mechanism, wherein the batch management includes configuration distribution of the access device, reporting of the operating status of the access device, terminal access management of the access device, and batch upgrade of each access device.

[0079] It is understandable that the subscription mechanism of the Message Queuing Telemetry Transport Protocol (MQTT) server is obtained. The MQTT protocol adopts a publish / subscribe messaging mode, in which the server (or agent) manages all client subscription relationships. Under this mechanism, each access device, as an MQTT client, can subscribe to a specific message topic as needed, thereby receiving instructions and data related to it in real time. The MQTT server maintains these subscription relationships and can push configuration instructions, status information or update data according to the needs of the device. Through this mechanism, the device can obtain the necessary configuration information and status updates in a timely manner without frequent polling, thereby improving the efficiency and response speed of network management. Secondly, according to the subscription mechanism of the MQTT protocol, batch management of each access device is realized. Batch management means that through the subscription mechanism, the management platform can push configuration, status information or upgrade instructions to multiple access devices at one time. For example, the platform can issue a unified configuration file to all devices, or perform differentiated management according to the category and status of the device. Through this mechanism, administrators do not need to configure and manage each device one by one, which greatly reduces the complexity and labor cost of management operations. After receiving the command, the device will perform configuration updates, status reports, or version upgrades according to the subscribed topics, thus realizing batch and automated device management. Finally, the implementation of batch management includes key tasks such as configuration distribution, operation status reporting, terminal access management, and batch upgrades of access devices. Through the MQTT protocol, the platform can perform real-time status monitoring and data collection on access devices, such as regular reporting of device operation status, to ensure that the platform can grasp the health status of the device at any time. At the same time, the terminal access management of access devices ensures that the device access process is safe and smooth, avoiding conflicts or management omissions of access devices. In addition, with the help of the batch upgrade mechanism, the latest firmware version or configuration parameters can be uniformly pushed to the device to ensure that each access device can be updated synchronously and have the latest functions.

[0080] Step S300: Acquire and store VPN data characteristics of each access device, wherein the VPN data characteristics include: traffic pattern, data packet size, protocol type, delay and packet loss rate.

[0081] Step S400: Acquire historical VPN data features, establish a VPN data flow classification model based on the historical VPN data features, substitute the VPN data features of the access device into the VPN data flow classification model, and obtain the classification result of the access device.

[0082] Specifically, when establishing a VPN data flow classification model based on historical VPN data features, it includes: obtaining the traffic pattern, data packet size, protocol type, delay and packet loss rate of each historical VPN data in the historical VPN data features, and establishing a historical VPN data association formula. The distance measurement between each historical VPN data association formula is obtained based on the Euclidean distance:

[0083]

[0084] Where D(x,y) is the distance metric between any two historical VPN data associations, xi and yi refer to the i-th data feature between any two historical VPN data associations, respectively. The data features include: traffic pattern, packet size, protocol type, delay and packet loss rate, and n is the total number of data features. A distance matrix is ​​constructed based on the distance metric, and each historical VPN data association is iteratively clustered based on the distance matrix. The historical VPN data association after iterative clustering is determined as a VPN data flow type association, and the type of each VPN data flow is determined based on the number of each VPN data flow type association, and a VPN data flow classification model is established based on each VPN data flow type association and the type of each VPN data flow.

[0085] Specifically, when establishing a VPN data flow classification model according to each VPN data flow type association formula and each VPN data flow type, the method includes: obtaining a distance metric between each historical VPN data association formula and each VPN data flow type association formula, and classifying each historical VPN data association formula according to the distance metric and a preset distance metric. Obtaining a linear relationship axis between each historical VPN data association formula under the type of VPN data flow, and determining a feature vector of the type of VPN data flow according to the linear relationship axis. Establishing a VPN data flow classification model according to the feature vector of each VPN data flow type.

[0086] It can be understood that by collecting multiple features (such as traffic pattern, packet size, protocol type, delay and packet loss rate, etc.) in historical VPN data, each historical VPN data can be analyzed and the correlation between them can be established. Then, based on these feature information, the Euclidean distance is used to measure the similarity between each pair of historical VPN data. The Euclidean distance formula can effectively quantify the differences between different VPN data flows in multiple feature dimensions, thereby laying the foundation for subsequent data clustering and classification. By calculating the distance measurement between historical VPN data, the similarity between these data can be quantified, and a distance matrix can be constructed based on this to provide necessary input data for clustering analysis. Secondly, after the distance matrix is ​​established, the historical VPN data is classified by an iterative clustering method, and each VPN data flow type association formula is further generated. The clustering algorithm can classify similar VPN data features into the same category based on the distance relationship between historical data, thereby forming multiple VPN data flow type association formulas. Each data flow type association formula represents a specific type of VPN data flow, and these classifications can define different data flow types based on their quantity and characteristics. For example, some data flows may have low latency and small packet sizes, indicating efficient real-time application traffic, while other data flows may exhibit high packet loss rates and large packets, suitable for large-scale file transfers. After clustering, each VPN data flow type association will provide a basis for subsequent data flow classification and enable better identification and management of different data flow types. Finally, through the construction of the type feature vector of VPN data flows, a specific classification model can be established for each VPN data flow type. First, based on the historical VPN data and the association formula of each VPN data flow type, the feature vectors of each type of VPN data flow are determined by calculating the linear relationship axis between them. These feature vectors reflect the core characteristics of each data flow type, including traffic pattern, packet size, latency, packet loss rate, etc. These feature vectors are then used to establish a VPN data flow classification model, thereby realizing the automatic classification of VPN traffic on access devices.

[0087] It can be seen that by deeply analyzing multiple features of historical VPN data (such as traffic pattern, packet size, protocol type, delay and packet loss rate, etc.), the potential rules and changing trends of VPN traffic can be captured. The establishment of this classification model can more accurately identify various types of VPN data flows, optimize traffic management and scheduling strategies, thereby improving the performance and transmission efficiency of VPN connections, and reducing network congestion and resource waste. Secondly, through Euclidean distance measurement and cluster analysis, accurate clustering of historical VPN data associations can be achieved, and similar data flows can be classified into the same category. This similarity-based clustering method helps to identify the commonalities and differences between different types of VPN data flows. Based on this clustering result, the VPN data of access devices can be accurately classified, and different processing strategies or priorities can be assigned to each type of data flow, thereby achieving more intelligent traffic management. For example, for delay-sensitive real-time traffic, a lower delay path can be assigned, while for large-volume file transfer traffic, a link with a larger bandwidth can be selected. Finally, through the construction of feature vectors and the establishment of VPN data flow classification models, corresponding optimization strategies can be formulated according to the characteristics of each type of VPN data flow. These feature vectors can not only help identify different types of data flows, but also guide decisions on network routing and bandwidth allocation, thereby ensuring efficient use of network resources. Through this classification model, it is possible to flexibly respond to changes in network load and adjust transmission strategies in real time to accelerate data flows and maximize transmission efficiency. This is particularly important for large-scale network environments with numerous devices and complex traffic, and can effectively improve the intelligence level of network management and reduce operation and maintenance costs.

[0088] Step S500: Acquire real-time performance data of each link in the network link, determine the effective link according to the relationship between the real-time performance data and the performance requirement data of the classification result, and determine the path transmission mechanism between the access device and the effective link.

[0089] Specifically, determining the effective link according to the relationship between the real-time performance data and the performance requirement data of the classification result includes: determining the similarity between the real-time performance data and the performance requirement data according to the relationship between the real-time performance data and the performance requirement data:

[0090]

[0091] Where Li is the similarity between the real-time performance data and the performance requirement data, N is the total number of indicator data, Gi is the i-th indicator data in the real-time performance data, and gi is the i-th indicator data in the performance requirement data. According to the relationship between the similarity and the preset similarity, each link is screened: when the similarity is less than the preset similarity, the link is determined to be eliminated. When the similarity is greater than or equal to the preset similarity, the retained link is determined, and the valid link is determined according to the relationship between the retained links.

[0092] Specifically, when determining the effective link based on the relationship between the reserved links, it includes: obtaining the average value of the real-time performance data between the reserved links, and determining the average value as the preset performance data. Determine the performance score of each link based on the relationship between the real-time performance data and the preset performance data:

[0093]

[0094] Among them, S is the performance score of the link, Hi is the weight of the indicator feature in the real-time performance data, ai is the i-th indicator feature in the preset performance data, and Ai is the i-th indicator feature in the real-time data. The performance scores are sorted in descending order, and the link corresponding to the first performance score is determined as a valid link.

[0095] It can be understood that by defining the similarity formula, the difference between the real-time performance data and the performance requirement data is calculated, and which links meet the performance requirements are determined. The core of this process is to identify those links that match the requirements by comparing the similarity between the real-time performance data (such as bandwidth, delay, packet loss rate, etc.) of each link and the preset performance requirements (such as traffic pattern, delay requirements, etc.). Specifically, by calculating the similarity, the links that do not meet the performance requirements are screened out, and the links are classified and screened according to the similarity. Secondly, after the qualified links are screened out, the performance scores of the links are calculated. By obtaining the real-time performance data of the retained links and calculating their average values, a preset performance data is formed. The gap between these links and the preset performance data will be measured by the performance score to judge the performance of each link. By introducing the weight coefficient, the score calculation can be dynamically adjusted according to the importance of different performance indicators to ensure that the influence of important performance indicators (such as delay, bandwidth, etc.) on link selection is maximized. This calculation method ensures that when selecting effective links, various performance indicators can be comprehensively considered to make more accurate decisions. Finally, according to the performance score of the link, the best link is selected by sorting. Among all eligible links, the link with the highest score is selected as the effective link based on the reverse order of performance score. This sorting method ensures that the best link is selected from multiple candidate links and the best network path is allocated to the access device. This process not only improves the transmission efficiency of data flow, but also avoids delays and packet loss caused by poor network performance, thereby optimizing the acceleration effect of VPN data flow.

[0096] It can be seen that by calculating the similarity between real-time performance data and performance requirement data, it is possible to effectively identify which links meet the predetermined performance requirements, such as network performance indicators such as bandwidth and delay. This method can dynamically evaluate the applicability of links, thereby avoiding the shortcomings of traditional static link selection, making the selection of network links more flexible and real-time, and adapting to changing network conditions. Secondly, through the performance scoring mechanism, the scheme can conduct in-depth analysis and prioritize the reserved links. The performance score of each link is calculated based on the difference between the real-time performance data and the preset data, and by introducing the weight coefficient, it highlights the importance of key performance indicators (such as delay, throughput, etc.). Through this scoring method, the best performing link can be identified to provide the best transmission path for data traffic. This not only improves the efficiency of link selection, but also ensures the quality and stability of data transmission, and avoids interference from low-quality links. Finally, by sorting and selecting effective links, it can ensure that the best network path and transmission mechanism are provided for access devices. By sorting the performance scores of the links, the best performing link can be selected as the effective link to ensure the communication quality of the access device and the efficient transmission of the data flow. This intelligent link selection strategy based on real-time data effectively improves the overall performance of the network, enhances the acceleration effect of VPN data flow, optimizes resource utilization, reduces network latency and packet loss rate, and provides an intelligent and reliable solution for complex equipment and link requirements in the network environment.

[0097] In the above embodiment, by using the DHCP protocol to dynamically allocate an IP address to each access device, and at the same time obtaining the IP address of the message queue telemetry transmission protocol server, the access device and the network management system can be seamlessly connected. Through this mechanism, it is possible to ensure that the identity information of each device is automatically registered and stored, avoiding the complexity and error risks brought by traditional static configuration, and providing an efficient and automated solution for device management. In addition, the subscription mechanism based on the MQTT protocol can realize batch management of access devices. This not only includes the configuration distribution and operation status reporting of the device, but also involves key tasks such as terminal access management and batch upgrade of devices. Compared with traditional management methods, this MQTT-based solution greatly improves the flexibility and real-time performance of management, especially in large-scale equipment environments, it can achieve accurate real-time monitoring and scheduling, and greatly reduces the need for manual intervention. The status information of the device can be uploaded to the server in real time, and the administrator can obtain the latest operation data of the device at any time through the subscription mechanism, and quickly respond to any changes in the network, thereby effectively improving the overall management efficiency of the network and the working stability of the device. Furthermore, by obtaining and storing the VPN data characteristics of each access device, including traffic mode, data packet size, protocol type, delay and packet loss rate, etc., valuable data support can be provided for subsequent network optimization and acceleration. By analyzing the characteristics of historical VPN data and establishing a VPN data flow classification model, the VPN traffic of access devices can be intelligently classified, and different optimization strategies can be provided for different types of traffic based on the classification results. By inputting the real-time data of access devices into the model, the data flow type of each device can be accurately determined, so as to better formulate personalized acceleration plans for it and improve the transmission efficiency and user experience of the overall network. Finally, combined with the various performance data in the real-time network link, the optimal network link can be automatically determined based on the relationship between the classification model and the real-time performance data. This mechanism can not only ensure that the data flow of each access device is transmitted on the optimal path, but also adjust the transmission path of the data flow in real time according to the changes in network load and link quality, avoiding the network congestion and performance bottleneck problems existing in the traditional static path allocation method. Through this dynamic path selection, it is possible to maintain a high data transmission quality in a complex network environment, while greatly improving the flexibility and adaptability of the network, ensuring the acceleration effect and stability of the VPN data flow.

[0098] In another preferred embodiment based on the above embodiment, Figure 2 As shown, this embodiment provides a system for establishing a VPN data flow acceleration model, including: an access device and an access controller.

[0099] Specifically, the access controller is used to perform batch management on each access device, wherein the access controller includes: a connection unit, a storage unit, a first central control unit, a second central control unit and an adjustment unit. The connection unit is configured to allocate an IP address to each access device based on the dynamic host configuration protocol, and obtain the IP address of the message queue telemetry transmission protocol server based on the dynamic host configuration protocol. The connection unit is also configured to register the identity information of each access device based on the message queue telemetry transmission protocol, and store the identity information of each access device. The storage unit is configured to obtain and store the VPN data characteristics of each access device, wherein the VPN data characteristics include: traffic mode, data packet size, protocol type, delay and packet loss rate. The storage unit is also configured to obtain historical VPN data characteristics. The first central control unit is configured to obtain the subscription mechanism of the message queue telemetry transmission protocol server, and perform batch management on each access device according to the subscription mechanism, wherein the batch management includes the configuration distribution of the access device, the operation status reporting of the access device, the terminal access management of the access device and the batch upgrade of each access device. The second central control unit is configured to establish a VPN data flow classification model based on historical VPN data features, substitute the VPN data features of the access device into the VPN data flow classification model, and obtain the classification result of the access device. The adjustment unit is configured to obtain real-time performance data of each link in the network link, determine the effective link according to the relationship between the real-time performance data and the performance requirement data of the classification result, and determine the path transmission mechanism between the access device and the effective link.

[0100] Specifically, when the second central control unit establishes a VPN data flow classification model based on the historical VPN data characteristics, it includes: the second central control unit is also configured to obtain the traffic mode, data packet size, protocol type, delay and packet loss rate of each historical VPN data in the historical VPN data characteristics, and establish a historical VPN data association formula. The second central control unit is also configured to obtain the distance measurement between each historical VPN data association formula based on the Euclidean distance:

[0101]

[0102] Wherein, D(x,y) is the distance metric between any two historical VPN data associations, xi and yi respectively refer to the i-th data feature between the two historical VPN data associations, the data features include: traffic pattern, data packet size, protocol type, delay and packet loss rate, and n is the total number of data features. The second central control unit is also configured to construct a distance matrix based on the distance metric, and iteratively cluster each historical VPN data association according to the distance matrix. The second central control unit is also configured to determine the historical VPN data association after iterative clustering as a VPN data flow type association, determine the type of each VPN data flow according to the number of each VPN data flow type association, and establish a VPN data flow classification model according to each VPN data flow type association and the type of each VPN data flow.

[0103] Specifically, when the second central control unit establishes a VPN data flow classification model according to each VPN data flow type association formula and each VPN data flow type, it includes: the second central control unit is also configured to obtain a distance metric between each historical VPN data association formula and each VPN data flow type association formula, and classify each historical VPN data association formula according to the distance metric and a preset distance metric. The second central control unit is also configured to obtain a linear relationship axis between each historical VPN data association formula under the type of VPN data flow, and determine a feature vector of the type of VPN data flow according to the linear relationship axis. The second central control unit is also configured to establish a VPN data flow classification model according to the feature vector of each VPN data flow type.

[0104] Specifically, when the adjustment unit determines the valid link according to the relationship between the real-time performance data and the performance requirement data of the classification result, the adjustment unit is further configured to determine the similarity between the real-time performance data and the performance requirement data according to the relationship between the real-time performance data and the performance requirement data:

[0105]

[0106] Wherein Li is the similarity between the real-time performance data and the performance requirement data, N is the total number of indicator data, Gi is the i-th indicator data in the real-time performance data, and gi is the i-th indicator data in the performance requirement data. The adjustment unit is further configured to screen each link according to the relationship between the similarity and the preset similarity: when the similarity is less than the preset similarity, the adjustment unit determines to remove the link. When the similarity is greater than or equal to the preset similarity, the adjustment unit determines to retain the link, and determines the valid link according to the relationship between the retained links.

[0107] Specifically, when the adjustment unit determines the valid link based on the relationship between the reserved links, it includes: obtaining the average value between the real-time performance data between the reserved links, and determining the average value as the preset performance data. The adjustment unit is also configured to determine the performance score of each link based on the relationship between the real-time performance data and the preset performance data:

[0108]

[0109] Wherein, S is the performance score of the link, Hi is the weight of the indicator feature in the real-time performance data, ai is the i-th indicator feature in the preset performance data, and Ai is the i-th indicator feature in the real-time data. The adjustment unit is further configured to sort the performance scores in reverse order, and determine the link corresponding to the first-ranked performance score as a valid link.

[0110] It can be understood that the system and method for establishing a VPN data flow acceleration model in the above embodiments of the present invention have the same beneficial effects, which will not be described in detail.

[0111] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0112] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0113] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0114] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0115] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for establishing a VPN data flow acceleration model, characterized in that: include: Allocate an IP address to each access device based on the dynamic host configuration protocol, and obtain the IP address of the message queue telemetry transport protocol server based on the dynamic host configuration protocol; Registering the identity information of each access device based on a message queue telemetry transmission protocol, and storing the identity information of each access device; Obtaining a subscription mechanism of the message queue telemetry transmission protocol server, and performing batch management on each of the access devices according to the subscription mechanism, wherein the batch management includes configuration distribution of the access devices, reporting of operating status of the access devices, terminal access management of the access devices, and batch upgrade of each of the access devices; Acquire and store VPN data characteristics of each access device, wherein the VPN data characteristics include: traffic pattern, data packet size, protocol type, delay and packet loss rate; Acquire historical VPN data features, establish the VPN data flow classification model based on the historical VPN data features, substitute the VPN data features of the access device into the VPN data flow classification model, and obtain the classification result of the access device; Acquire real-time performance data of each link in the network link, determine the effective link according to the relationship between the real-time performance data and the performance requirement data of the classification result, and determine the path transmission mechanism between the access device and the effective link based on the effective link.

2. The method for establishing a VPN data flow acceleration model according to claim 1, characterized in that: When the VPN data flow classification model is established based on the historical VPN data characteristics, it includes: Obtaining the traffic pattern, data packet size, protocol type, delay and packet loss rate of each historical VPN data in the historical VPN data characteristics, and establishing a historical VPN data association formula; Obtaining the distance metric between the historical VPN data association equations based on the Euclidean distance: Wherein, D(x,y) is the distance metric between any two historical VPN data associations, xi and yi respectively refer to the i-th data feature between the two historical VPN data associations, the data features include: traffic pattern, data packet size, protocol type, delay and packet loss rate, and n is the total number of the data features; constructing a distance matrix according to the distance metric, and iteratively clustering the historical VPN data association equations according to the distance matrix; The historical VPN data association formula after iterative clustering is determined as the VPN data flow type association formula, the type of each VPN data flow is determined according to the number of each VPN data flow type association formula, and the VPN data flow classification model is established according to each VPN data flow type association formula and the type of each VPN data flow.

3. The method for establishing a VPN data flow acceleration model according to claim 2, characterized in that: When the VPN data flow classification model is established according to each VPN data flow type association formula and the type of each VPN data flow, it includes: Obtaining a distance metric between each of the historical VPN data association formulas and each of the VPN data flow type association formulas, and classifying each of the historical VPN data association formulas according to the distance metric and a preset distance metric; Acquire a linear relationship axis between each of the historical VPN data association equations under the type of the VPN data flow, and determine a characteristic vector of the type of the VPN data flow according to the linear relationship axis; The VPN data flow classification model is established according to the feature vector of each type of the VPN data flow.

4. The method for establishing a VPN data flow acceleration model according to claim 3, characterized in that: Determining a valid link according to a relationship between the real-time performance data and the performance requirement data of the classification result includes: Determine the similarity between the real-time performance data and the performance requirement data according to the relationship between the real-time performance data and the performance requirement data: Where Li is the similarity between the real-time performance data and the performance requirement data, N is the total number of indicator data, Gi is the i-th indicator data in the real-time performance data, and gi is the i-th indicator data in the performance requirement data; According to the relationship between the similarity and a preset similarity, each of the links is screened: When the similarity is less than the preset similarity, determining to remove the link; When the similarity is greater than or equal to a preset similarity, it is determined that the link is retained, and the valid link is determined according to the relationship between the retained links.

5. The method for establishing a VPN data flow acceleration model according to claim 4, characterized in that: Determining the valid link according to the relationship between the reserved links includes: Obtaining an average value between the retained real-time performance data between the links, and determining the average value as the preset performance data; Determine the performance score of each link according to the relationship between the real-time performance data and the preset performance data: Wherein, S is the performance score of the link, Hi is the weight of the indicator feature in the real-time performance data, ai is the i-th indicator feature in the preset performance data, and Ai is the i-th indicator feature in the real-time data; The performance scores are sorted in descending order, and the link corresponding to the performance score ranked first is determined as the valid link.

6. A VPN data flow acceleration model establishment system, used in a VPN data flow acceleration model establishment method as claimed in any one of claims 1 to 5, characterized in that: include: Access devices and access controllers; The access controller is used to perform batch management on each of the access devices, wherein the access controller includes: a connection unit, a storage unit, a first central control unit, a second central control unit and an adjustment unit; The connection unit is configured to allocate an IP address to each access device based on a dynamic host configuration protocol, and obtain an IP address of a message queue telemetry transmission protocol server based on the dynamic host configuration protocol; the connection unit is also configured to register the identity information of each access device based on the message queue telemetry transmission protocol, and store the identity information of each access device; The storage unit is configured to obtain and store VPN data characteristics of each of the access devices, wherein the VPN data characteristics include: traffic pattern, data packet size, protocol type, delay and packet loss rate; the storage unit is also configured to obtain historical VPN data characteristics; The first central control unit is configured to obtain a subscription mechanism of the message queue telemetry transmission protocol server, and perform batch management on each of the access devices according to the subscription mechanism, wherein the batch management includes configuration distribution of the access device, reporting of the operation status of the access device, terminal access management of the access device, and batch upgrade of each of the access devices; The second central control unit is configured to establish the VPN data flow classification model based on historical VPN data features, substitute the VPN data features of the access device into the VPN data flow classification model, and obtain the classification result of the access device; The adjustment unit is configured to obtain real-time performance data of each link in the network link, determine the effective link according to the relationship between the real-time performance data and the performance requirement data of the classification result, and determine the path transmission mechanism between the access device and the effective link based on the effective link.

7. The VPN data flow acceleration model establishment system according to claim 6, characterized in that: When the second central control unit establishes the VPN data flow classification model based on the historical VPN data characteristics, it includes: The second central control unit is further configured to obtain the traffic mode, data packet size, protocol type, delay and packet loss rate of each historical VPN data in the historical VPN data characteristics, and establish a historical VPN data association formula; The second central control unit is further configured to obtain a distance metric between each of the historical VPN data association equations based on the Euclidean distance: Wherein, D(x,y) is the distance metric between any two historical VPN data associations, xi and yi respectively refer to the i-th data feature between the two historical VPN data associations, the data features include: traffic pattern, data packet size, protocol type, delay and packet loss rate, and n is the total number of the data features; The second central control unit is further configured to construct a distance matrix according to the distance metric, and iteratively cluster the historical VPN data association equations according to the distance matrix; The second central control unit is further configured to determine the historical VPN data association formula after iterative clustering as the VPN data flow type association formula, determine the type of each VPN data flow according to the number of each VPN data flow type association formula, and establish the VPN data flow classification model according to each VPN data flow type association formula and the type of each VPN data flow.

8. The VPN data flow acceleration model establishment system according to claim 7, characterized in that: When the second central control unit establishes the VPN data flow classification model according to each VPN data flow type association formula and the type of each VPN data flow, it includes: The second central control unit is further configured to obtain a distance metric between each of the historical VPN data association formulas and each of the VPN data flow type association formulas, and classify each of the historical VPN data association formulas according to the distance metric and a preset distance metric; The second central control unit is further configured to obtain a linear relationship axis between each of the historical VPN data association equations under the type of the VPN data flow, and determine a characteristic vector of the type of the VPN data flow according to the linear relationship axis; The second central control unit is further configured to establish the VPN data flow classification model according to the feature vector of each type of the VPN data flow.

9. The VPN data flow acceleration model establishment system according to claim 8, characterized in that: When the adjustment unit determines the valid link according to the relationship between the real-time performance data and the performance requirement data of the classification result, it includes: The adjustment unit is further configured to determine a similarity between the real-time performance data and the performance requirement data according to a relationship between the real-time performance data and the performance requirement data: Where Li is the similarity between the real-time performance data and the performance requirement data, N is the total number of indicator data, Gi is the i-th indicator data in the real-time performance data, and gi is the i-th indicator data in the performance requirement data; The adjustment unit is further configured to filter each of the links according to a relationship between the similarity and a preset similarity: When the similarity is less than the preset similarity, the adjustment unit determines to remove the link; When the similarity is greater than or equal to a preset similarity, the adjustment unit determines to retain the link, and determines the valid link according to the relationship between the retained links.

10. The VPN data flow acceleration model establishment system according to claim 9, characterized in that: When the adjustment unit determines the valid link according to the relationship between the reserved links, it includes: Obtaining an average value between the retained real-time performance data between the links, and determining the average value as the preset performance data; The adjustment unit is further configured to determine a performance score of each of the links according to a relationship between the real-time performance data and the preset performance data: Wherein, S is the performance score of the link, Hi is the weight of the indicator feature in the real-time performance data, ai is the i-th indicator feature in the preset performance data, and Ai is the i-th indicator feature in the real-time data; The adjustment unit is further configured to sort the performance scores in reverse order, and determine the link corresponding to the performance score ranked first as the valid link.

Images