Bandwidth allocation method and apparatus, electronic device, and non-transitory storage medium

Abstract

This application discloses a bandwidth allocation method, apparatus, electronic device, and non-volatile storage medium. The method includes: acquiring multi-dimensional feature data of multiple VPN subnets, wherein the multi-dimensional feature data includes at least bandwidth usage, subnet size of the multiple VPN subnets, and service type corresponding to each VPN subnet; analyzing the multi-dimensional feature data using a bandwidth allocation prediction model to obtain prediction results, wherein the prediction results are used to predict the bandwidth allocated to each VPN subnet; and dynamically allocating bandwidth to the multiple VPN subnets based on the prediction results and real-time monitoring results, wherein the real-time monitoring results are used to adjust the weights of the multiple VPN subnets. This application solves the technical problem in related technologies where only fixed bandwidth can be allocated when allocating bandwidth to multiple VPN subnets, making dynamic adjustment of VPN subnet bandwidth impossible.

Description

Technical Field

[0001] This application relates to the field of network technology, and more specifically, to a bandwidth allocation method, apparatus, electronic device, and non-volatile storage medium. Background Technology

[0002] With the rapid development of cloud-network convergence services, efficient and automated network operation and management have increasingly become a focus of attention. For example, in enterprise networks, specific bandwidth is allocated to meet business needs, ensuring that critical businesses have sufficient network resources while ordinary office work also has bandwidth allocated reasonably. Efficient and intelligent management of dedicated networks has become a necessary measure for enterprises and organizations.

[0003] In private networks across various industries, access layer leased lines are often divided into multiple Virtual Private Network (VPN) subnets. For example, an education private network may be divided into: global internet access, financial management, electronic proctoring, video surveillance, and physics and chemistry exams. These VPN subnets share a physical leased line from the school to a nearby telecommunications bureau. The overall bandwidth of this leased line is fixed. In related technologies, when allocating bandwidth to these subnets, a specific bandwidth is assigned to each VPN, and this allocation cannot be adjusted afterward. However, in actual business environments, the bandwidth required by these VPN subnets changes dynamically depending on the usage time and circumstances. Therefore, in related technologies, when allocating bandwidth to multiple VPN subnets, only a fixed bandwidth can be allocated, and dynamic adjustment of VPN subnet bandwidth cannot be achieved.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This application provides a bandwidth allocation method, apparatus, electronic device, and non-volatile storage medium to at least solve the technical problem in the related art that when allocating bandwidth to multiple VPN subnets, only fixed bandwidth can be allocated, and dynamic adjustment of VPN subnet bandwidth cannot be achieved.

[0006] According to one aspect of the embodiments of this application, a bandwidth allocation method is provided, comprising: acquiring multi-dimensional feature data of multiple virtual private network subnets, wherein the multi-dimensional feature data includes at least bandwidth usage, subnet size of the multiple virtual private network subnets, and service type corresponding to each virtual private network subnet; analyzing the multi-dimensional feature data using a bandwidth allocation prediction model to obtain prediction results, wherein the prediction results are used to predict the bandwidth allocated to each virtual private network subnet, and the bandwidth allocation prediction model is obtained by training an initial bandwidth allocation prediction model using historical multi-dimensional feature data of the multiple virtual private network subnets; and dynamically allocating bandwidth to the multiple virtual private network subnets based on the prediction results and real-time monitoring results, wherein the real-time monitoring results are used to adjust the weights of the multiple virtual private network subnets.

[0007] According to some embodiments of this application, the subnet size of multiple virtual private network subnets is obtained by obtaining the subnet size of multiple virtual private network subnets from the database of the virtual private network subnet control center, wherein the subnet size includes at least the address space size of each virtual private network subnet and the number of devices contained therein.

[0008] According to some embodiments of this application, bandwidth usage is obtained by: acquiring network traffic data of multiple virtual private network subnets; cleaning the network traffic data; extracting feature data that affects bandwidth allocation from the cleaned network traffic data, and using the feature data as bandwidth usage, wherein the feature data includes at least the peak network traffic and the average network traffic of each virtual private network subnet within a preset time period.

[0009] According to some embodiments of this application, each virtual private network subnet corresponds to a service type, and a first weight is assigned to each virtual private network subnet based on the service type, wherein the first weight is determined based on a bandwidth allocation prediction model.

[0010] According to some embodiments of this application, the bandwidth allocation prediction model is trained in the following manner: Step 1: Obtain historical multi-dimensional feature data, wherein the historical multi-dimensional feature data includes at least historical bandwidth usage, subnet size of multiple virtual private network subnets, and service type corresponding to each virtual private network subnet; Step 2: Train the initial bandwidth allocation prediction model using the historical multi-dimensional feature data, adjust the weight of each virtual private network subnet based on the weight of the previous iteration, the preset learning rate, and the preset loss function, wherein the weight of the previous iteration in the first iteration is the preset weight; Iterate through Step 2 until the iteration number is reached and then stop iterating to obtain the bandwidth allocation prediction model, and use the weight of each virtual private network subnet in the last iteration as the first weight of each virtual private network subnet.

[0011] According to some embodiments of this application, bandwidth is dynamically allocated to multiple virtual private network (VPN) subnets based on prediction results and real-time monitoring results, including: determining the bandwidth occupancy rate of each VPN subnet at preset time intervals as a real-time monitoring result, wherein the bandwidth occupancy rate is determined by the ratio of the real-time bandwidth of each VPN subnet to the total bandwidth of the multiple VPN subnets, and the real-time bandwidth is used to indicate the bandwidth corresponding to the timestamp indicated by the current time period; adjusting the first weight of each VPN subnet based on the bandwidth occupancy rate; sorting the multiple VPN subnets in descending order of the adjusted first weight to obtain a priority sequence; adjusting the bandwidth allocated to each VPN subnet as indicated in the prediction results based on the priority sequence to obtain a bandwidth allocation result; and allocating bandwidth to the multiple VPN subnets based on the bandwidth allocation result.

[0012] According to some embodiments of this application, adjusting the first weight of each virtual private network subnet based on bandwidth utilization includes: increasing the first weight of the first virtual private network subnet by a preset value and decreasing the first weight of the second virtual private network subnet by a preset value, wherein the first virtual private network subnet is a virtual private network subnet with a bandwidth utilization greater than or equal to a first preset threshold, and the second virtual private network subnet is a virtual private network subnet with a bandwidth utilization less than the first preset threshold.

[0013] According to another aspect of the embodiments of this application, a bandwidth allocation apparatus is also provided, comprising: an acquisition module, configured to acquire multi-dimensional feature data of multiple virtual private network subnets, wherein the multi-dimensional feature data includes at least bandwidth usage, subnet size of the multiple virtual private network subnets, and service type corresponding to each virtual private network subnet; an analysis module, configured to analyze the multi-dimensional feature data using a bandwidth allocation prediction model to obtain prediction results, wherein the prediction results are used to predict the bandwidth allocated to each virtual private network subnet, and the bandwidth allocation prediction model is obtained by training an initial bandwidth allocation prediction model using historical multi-dimensional feature data of the multiple virtual private network subnets; and an allocation module, configured to dynamically allocate bandwidth to the multiple virtual private network subnets based on the prediction results and real-time monitoring results, wherein the real-time monitoring results are used to adjust the weights of the multiple virtual private network subnets.

[0014] According to another aspect of the embodiments of this application, a non-volatile storage medium is also provided, wherein a program is stored in the non-volatile storage medium, wherein the program controls the device where the non-volatile storage medium is located to execute the bandwidth allocation method of any one of the above-mentioned methods when it runs.

[0015] According to another aspect of the embodiments of this application, an electronic device is also provided, including: a memory and a processor, the processor being configured to run a program stored in the memory, wherein the program executes the bandwidth allocation method of any of the above-mentioned methods during runtime.

[0016] In this embodiment, multi-dimensional feature data of multiple VPN subnets is acquired. This multi-dimensional feature data includes at least bandwidth usage, subnet size, and service type for each VPN subnet. A bandwidth allocation prediction model is used to analyze the multi-dimensional feature data to obtain prediction results. These prediction results are used to predict the bandwidth allocated to each VPN subnet. The bandwidth allocation prediction model is trained on an initial bandwidth allocation prediction model using historical multi-dimensional feature data from multiple VPN subnets. Based on the prediction results and real-time monitoring results, bandwidth is dynamically allocated to the multiple VPN subnets. The real-time monitoring results are used to adjust the weights of the multiple VPN subnets. By acquiring multi-dimensional feature data of multiple VPN subnets, analyzing it with the bandwidth allocation prediction model to obtain prediction results, and dynamically allocating bandwidth based on these prediction results and real-time monitoring results, the goal of dynamically allocating bandwidth to multiple VPN subnets is achieved. This solves the problem in related technologies where only fixed bandwidth can be allocated when allocating bandwidth to multiple VPN subnets, making dynamic adjustment of VPN subnet bandwidth impossible. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0018] Figure 1 This is a hardware structure block diagram of a computer terminal for implementing a bandwidth allocation method according to an embodiment of this application;

[0019] Figure 2 This is a flowchart of a bandwidth allocation method provided according to an embodiment of this application;

[0020] Figure 3 This is a schematic diagram of a VPN subnet adaptive configuration adjustment device method according to an embodiment of this application;

[0021] Figure 4 This is an example diagram of a VPN subnet adaptive configuration adjustment device method provided in the embodiments of this application;

[0022] Figure 5 This is a schematic diagram of a bandwidth allocation device provided according to an embodiment of this application. Detailed Implementation

[0023] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0024] The information collected in this application embodiment is information and data authorized by the user or fully authorized by all parties. The collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data all comply with the relevant laws, regulations and standards of the relevant regions, and necessary confidentiality measures have been taken. It does not violate public order and good morals, and provides corresponding operation entry points for users to choose to authorize or reject the automated decision results. If the user chooses to reject, the process will proceed to the expert decision-making process.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] In related technologies, bandwidth allocation for these subnets involves assigning specific bandwidth to different VPNs, which cannot be adjusted after allocation. However, in actual business environments, the bandwidth required by these VPN subnets changes dynamically depending on the usage time and circumstances. Therefore, related technologies suffer from the problem that when allocating bandwidth to multiple Virtual Private Network (VPN) subnets, only fixed bandwidth can be allocated, making dynamic adjustment of VPN subnet bandwidth impossible. To address this issue, this application provides a related solution, which is detailed below.

[0027] According to an embodiment of this application, an embodiment of a bandwidth allocation method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0028] The methods and embodiments provided in this application can be executed on a computer terminal or similar computing device. Figure 1 A hardware block diagram of a computer terminal for implementing a bandwidth allocation method is shown. Figure 1 As shown, the computer terminal 10 may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission module 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0029] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10. As involved in the embodiments of this application, the data processing circuits serve as a form of processor control (e.g., selection of a variable resistor termination path connected to an interface).

[0030] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the bandwidth allocation method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the bandwidth allocation method described above. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0031] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0032] The display may be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10.

[0033] In the above operating environment, this application provides an embodiment of a bandwidth allocation method. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0034] like Figure 2 The diagram shown is a flowchart of a bandwidth allocation method according to an embodiment of this application, including:

[0035] Step S202: Obtain multi-dimensional feature data of multiple virtual private network subnets. The multi-dimensional feature data includes at least bandwidth usage, subnet size of multiple virtual private network subnets, and service type corresponding to each virtual private network subnet.

[0036] In the technical solution provided in step S202, the subnet sizes of multiple virtual private network (VPN) subnets can be obtained in the following way: The subnet sizes of multiple VPN subnets are obtained from the database of the VPN subnet control center. The subnet size includes at least the address space size and the number of devices contained in each VPN subnet. By accurately determining the subnet size, bandwidth requirements can be predicted more precisely, ensuring more reasonable bandwidth allocation in large-scale network environments and improving network operating efficiency. This is suitable for scenarios requiring refined management, such as enterprise internal networks and educational institution networks.

[0037] Bandwidth usage can be obtained through the following methods: acquiring network traffic data from multiple VPN subnets; cleaning the network traffic data; extracting feature data that affects bandwidth allocation from the cleaned network traffic data, and using this feature data as bandwidth usage data. The feature data must include at least the peak and average network traffic for each VPN subnet within a preset time period. This method improves the accuracy of bandwidth usage analysis through data cleaning and feature extraction, facilitating rapid responses in dynamically changing network environments and making it suitable for network applications that require real-time bandwidth adjustments.

[0038] It is important to note that each VPN subnet corresponds to a specific service type. A first weight is assigned to each VPN subnet based on this service type, and this first weight is determined using a bandwidth allocation prediction model. By assigning different weights to different service types, the bandwidth requirements of critical services can be prioritized, thereby improving the stability and reliability of network services.

[0039] The following are specific examples:

[0040] Before acquiring multi-dimensional characteristic data from multiple VPN subnets, initialization is required. First, the VPN subnet control center device needs to be initialized. The VPN subnet control center acts as a communication bridge allocating bandwidth to each VPN subnet. After initialization, it can receive registration requests from various VPN subnets. Each VPN subnet initiates a registration request to the control center via a dedicated network line. The control center first authenticates each VPN subnet. After successful authentication, the control center stores information about each VPN subnet (e.g., the subnet size in a database, including at least the address space size and the number of devices contained in each subnet). To ensure comprehensive and accurate bandwidth allocation, multi-dimensional characteristic data needs to be acquired from various factors affecting bandwidth allocation, such as bandwidth usage, subnet size, and the service type corresponding to each VPN subnet. Each VPN subnet corresponds to one service type. Different service types have different bandwidth requirements, such as video conferencing and data transmission. Therefore, it is necessary to consider the impact of service type on bandwidth allocation.

[0041] When acquiring multi-dimensional feature data, a data receiving and processing device can be used to obtain the subnet scale of multiple VPN subnets from the database of the VPN subnet control center. A network traffic monitoring tool can be used to obtain real-time network traffic data for these multiple VPN subnets (i.e., the network traffic data of the aforementioned multiple VPN subnets). This step can be timed, for example, by acquiring data every five minutes to ensure data real-time performance. The acquired real-time network traffic data is then cleaned. For example, data cleaning can be performed as follows: by calculating the mean and standard deviation of the data, data points exceeding a certain range (e.g., mean ± 3 times the standard deviation) are identified as outliers and deleted or replaced; data points that are significantly inconsistent with the time series trend are identified and deleted. For example, if network traffic is stable most of the time but suddenly shows an extremely high peak, that data point is deleted. Data consistency checks are performed: ensuring that all data timestamps are continuous; if data is missing, interpolation or filling with the most recent normal value can be performed. All traffic data is converted to the same unit, such as from kbps to Mbps, to avoid analysis errors caused by inconsistent units. Finally, the traffic data is normalized or standardized to allow data of different scales to be compared on the same scale. Feature data affecting bandwidth allocation is extracted from the cleaned network traffic data. This feature data is data related to and influencing bandwidth allocation; for example, peak traffic values ​​(P1, P2, P3...Pk) and average traffic values ​​(A1, A2, A3...Ak) for a preset time period (1-k minutes) are extracted from the network traffic data. This feature data is used as information on bandwidth usage.

[0042] Step S204: The bandwidth allocation prediction model is used to analyze the multi-dimensional feature data to obtain the prediction results. The prediction results are used to predict the bandwidth allocated to each virtual private network subnet. The bandwidth allocation prediction model is obtained by training the initial bandwidth allocation prediction model with the historical multi-dimensional feature data of multiple virtual private network subnets.

[0043] In the technical solution provided in step S204, the bandwidth allocation prediction model is trained in the following way: Step 1: Obtain historical multi-dimensional feature data, wherein the historical multi-dimensional feature data includes at least historical bandwidth usage, subnet size of multiple virtual private network subnets, and service type corresponding to each virtual private network subnet; Step 2: Train the initial bandwidth allocation prediction model using the historical multi-dimensional feature data, adjust the weight of each virtual private network subnet based on the weight of the previous iteration, the preset learning rate, and the preset loss function, wherein the weight of the previous iteration in the first iteration is the preset weight; Iterate through step 2 until the iteration number is reached and stop the iteration to obtain the bandwidth allocation prediction model, and use the weight of each virtual private network subnet in the last iteration as the first weight of each virtual private network subnet.

[0044] The following are specific examples:

[0045] Step 1: Obtain historical multi-dimensional feature data (e.g., hourly network traffic data over the past year). Step 2: Train the initial bandwidth allocation prediction model (e.g., an AI model based on a multilayer perceptron (MPL)) using the historical multi-dimensional feature data. Adjust the weights of each VPN subnet based on the weights from the previous iteration, a preset learning rate, and a preset loss function. Iterate through Step 2 until the desired number of iterations is reached, at which point the iteration stops, resulting in the bandwidth allocation prediction model. Use the weights of each VPN subnet from the last iteration as the first weight for each VPN subnet. For example, the weights of each VPN subnet can be updated using the following formula:

[0046]

[0047] Among them, W i W represents the weights determined in the previous iteration (preset weights in the first iteration). i ′ This represents the updated weights determined in the previous iteration (the first weights in the last iteration), α represents the learning rate, and E represents the preset loss function. This indicates that the preset loss function E is related to the weights W. i The partial derivatives of .

[0048] Step S206: Dynamically allocate bandwidth to multiple virtual private network subnets based on prediction results and real-time monitoring results, wherein the real-time monitoring results are used to adjust the weights of multiple virtual private network subnets.

[0049] In the technical solution provided in step S206, there are multiple ways to dynamically allocate bandwidth to multiple virtual private network (VPN) subnets based on prediction results and real-time monitoring results. For example, bandwidth can be dynamically allocated to multiple VPN subnets based on prediction results and real-time monitoring results in the following ways: The bandwidth occupancy rate of each VPN subnet is determined at preset time intervals as the real-time monitoring result. The bandwidth occupancy rate is determined by the ratio of the real-time bandwidth of each VPN subnet to the total bandwidth of all VPN subnets. The real-time bandwidth indicates the bandwidth corresponding to the timestamp indicated by the current time period. The first weight of each VPN subnet is adjusted based on the bandwidth occupancy rate. The VPN subnets are then sorted in descending order of the adjusted first weight to obtain a priority sequence. The bandwidth allocated to each VPN subnet as indicated in the prediction result is adjusted based on the priority sequence to obtain the bandwidth allocation result. Finally, bandwidth is allocated to multiple VPN subnets based on the bandwidth allocation result. This method, through real-time monitoring and dynamic adjustment, can quickly respond to network changes, effectively improving the flexibility and efficiency of bandwidth allocation. It is suitable for scenarios with large network traffic fluctuations, such as network management during holidays and large-scale events.

[0050] There are several ways to adjust the first weight of each VPN subnet based on bandwidth utilization in the above steps. For example, the first weight of the first VPN subnet can be increased by a preset value, and the first weight of the second VPN subnet can be decreased by a preset value. Here, the first VPN subnet is one with a bandwidth utilization rate greater than or equal to a first preset threshold, and the second VPN subnet is one with a bandwidth utilization rate less than the first preset threshold. This weight adjustment mechanism ensures that high-load subnets receive more bandwidth resources, while low-load subnets release resources, achieving a reasonable reallocation of resources. It is particularly suitable for resource optimization and cost control scenarios, such as network resource management in data centers.

[0051] The following are specific examples:

[0052] The bandwidth allocation prediction model consists of an input layer, a subnet feature fusion layer, a hidden layer, and an output layer. The input layer receives multi-dimensional feature data. The subnet feature fusion layer learns the weights between different features and fuses them into a more representative feature vector (i.e., determining the first weights for each VPN subnet). The hidden layer is the core of the bandwidth allocation prediction model, responsible for extracting non-linear features from the input data. The number of hidden layers and neurons per layer can be adjusted according to the complexity of the problem. More layers and neurons mean higher probability of overfitting. The output layer outputs the prediction results, indicating the expected bandwidth allocated to each VPN subnet. For example, the hidden and output layers process the data to obtain the prediction results using the following formula:

[0053]

[0054] Where y represents the prediction result (i.e., the expected bandwidth allocated to each VPN subnet, which meets the bandwidth requirements of the service type), X i W represents the input value (multi-dimensional feature data of the i-th VPN subnet). i Let represent the first weight corresponding to the i-th VPN subnet, b represent the bias term, which is a preset constant, and f represent the preset activation function.

[0055] To achieve dynamic bandwidth allocation, a real-time monitoring device continuously monitors the network status, analyzing current bandwidth usage, user behavior, and other data. The bandwidth utilization of each VPN subnet is determined at preset time intervals (e.g., 1 minute) as the real-time monitoring result. This enables real-time monitoring of the bandwidth utilization of each VPN subnet connection (U1, U2, U3…Uk). For example, the bandwidth utilization can be obtained and updated in real-time using the following formula:

[0056]

[0057] Among them, U i BW represents the bandwidth utilization of the i-th subnet. i This represents the real-time bandwidth of the i-th VPN subnet. This represents the total bandwidth of all VPN subnets (the sum of the bandwidth of the multiple virtual private network subnets mentioned above), which is the bandwidth of the entire leased line and is a fixed value.

[0058] The decision-making and dynamic adjustment mechanisms adjust the first weight of each VPN subnet based on bandwidth utilization. Multiple VPN subnets are then sorted in descending order of their adjusted first weights to obtain a priority sequence. A first preset threshold (e.g., 90%) is set. When the bandwidth utilization of a VPN subnet exceeds this threshold, it indicates that the subnet's bandwidth resources are strained and it may be in the service execution phase, requiring priority allocation of more bandwidth. The first weight of this subnet is increased by a preset value (e.g., 0.1). The weights of VPN subnets with bandwidth utilization below the first preset threshold are decreased. For example, if the bandwidth utilization of a VPN subnet is 10... At this point, the VPN subnet is not in a high-traffic period. The first weight is reduced by a preset value (e.g., 0.1). Multiple VPN subnets are then sorted in descending order of the adjusted first weight to obtain a priority sequence. This priority sequence ensures that the VPN subnets are sorted according to their bandwidth resource scarcity; the higher the priority, the more bandwidth is allocated. Based on the priority sequence, the bandwidth allocated to each VPN subnet as indicated in the prediction results is adjusted to obtain the bandwidth allocation result. Based on this bandwidth allocation result, bandwidth is allocated to multiple VPN subnets. The adjusted bandwidth allocation result can meet the real-time bandwidth requirements of each VPN subnet. Because a timer is used, the bandwidth utilization rate of each VPN subnet is determined at preset time intervals as a real-time monitoring result, ensuring that the bandwidth allocated to different VPN subnets is dynamically adjusted according to the real-time network status, so that the utilization rate of each VPN subnet reaches its optimal level. For example, if network congestion occurs at a certain node during the first cycle (corresponding to a VPN subnet bandwidth utilization rate as high as 90%), the bandwidth allocated to the VPN subnet at the bottom of the priority sequence will be reduced based on the adjusted bandwidth allocation results (while still ensuring normal connectivity of the VPN subnet), and the reduced bandwidth will be preferentially allocated to that VPN subnet. If, during the second cycle, the bandwidth utilization rate of that VPN subnet drops to 20%, indicating that the service on that VPN subnet has ended, then based on the adjusted priority sequence for this cycle, the bandwidth previously preferentially allocated to that VPN subnet will be allocated to the higher-ranking VPN subnets in other priority sequences.

[0059] Through the above steps, bandwidth can be intelligently predicted and allocated according to the actual needs and service types of the virtual private network subnet, effectively avoiding resource waste and network congestion. It is particularly suitable for bandwidth management in large-scale network environments such as cloud computing, data centers, and the Internet of Things.

[0060] This application also provides a schematic diagram of a VPN subnet adaptive configuration adjustment device method, as shown in the embodiments. Figure 3The diagram shows a schematic of the VPN subnet adaptive configuration adjustment device and method applicable to the implementation of this application. The adaptive configuration adjustment device and method module is responsible for implementing the core function of dynamic bandwidth allocation, which dynamically allocates bandwidth to multiple VPN subnets 1-VPN subnet k. The VPN subnet control center is the communication bridge for allocating bandwidth to each VPN subnet. Each VPN subnet initiates a registration application to the control center by connecting to the network leased line reserved by the VPN subnet control center. First, the authentication of each VPN subnet is performed. After successful authentication, the VPN subnet control center stores the information of each VPN subnet.

[0061] This application also provides an example diagram of a VPN subnet adaptive configuration adjustment device method, such as... Figure 4 The diagram illustrates the implementation process of the method in this embodiment. First, VPN subnet registration is performed: each VPN subnet initiates a registration application to the control center via a dedicated network line reserved by the VPN subnet control center. Information about each VPN subnet is obtained from the control center, and data acquisition and cleaning are performed using a data collection and preprocessing device and a feature extraction device to obtain multi-dimensional feature data and historical multi-dimensional feature data. The initial bandwidth allocation prediction model is trained using a data training device to obtain a bandwidth allocation prediction model. Real-time monitoring results are obtained using a real-time monitoring device. Then, bandwidth is dynamically allocated to each VPN subnet using a decision-making device and a dynamic adjustment device. That is, bandwidth is dynamically allocated to multiple VPN subnets based on the prediction results and real-time monitoring results, where the real-time monitoring results are used to adjust the weights of the multiple VPN subnets.

[0062] This application also provides a schematic diagram of the structure of a bandwidth allocation device, as shown in the embodiments. Figure 5 As shown, it includes:

[0063] The acquisition module 502 is used to acquire multi-dimensional feature data of multiple virtual private network subnets. The multi-dimensional feature data includes at least bandwidth usage, subnet size of multiple virtual private network subnets, and service type corresponding to each virtual private network subnet.

[0064] The acquisition module 502 is also used to acquire the subnet size of multiple virtual private network subnets from the database of the virtual private network subnet control center, wherein the subnet size includes at least the address space size and the number of devices contained in each virtual private network subnet.

[0065] The acquisition module 502 is also used to acquire network traffic data of multiple virtual private network subnets; perform data cleaning on the network traffic data; and extract feature data that affects bandwidth allocation from the cleaned network traffic data. The feature data includes at least the peak network traffic and the average network traffic of each virtual private network subnet within a preset time period.

[0066] Analysis module 504 is used to analyze multi-dimensional feature data using a bandwidth allocation prediction model to obtain prediction results. The prediction results are used to predict the bandwidth allocated to each virtual private network subnet. The bandwidth allocation prediction model is obtained by training an initial bandwidth allocation prediction model using historical multi-dimensional feature data from multiple virtual private network subnets.

[0067] The allocation module 506 is used to dynamically allocate bandwidth to multiple virtual private network subnets based on prediction results and real-time monitoring results, wherein the real-time monitoring results are used to adjust the weights of the multiple virtual private network subnets.

[0068] The allocation module 506 is also used to determine the bandwidth utilization rate of each virtual private network (VPN) subnet at preset time intervals. The bandwidth utilization rate is determined by the ratio of the real-time bandwidth of each VPN subnet to the total bandwidth of multiple VPN subnets. The real-time bandwidth is used to indicate the bandwidth corresponding to the timestamp indicated by the current time period. The module adjusts the first weight of each VPN subnet based on the bandwidth utilization rate. The multiple VPN subnets are sorted in descending order of the adjusted first weight to obtain a priority sequence. The bandwidth allocated to each VPN subnet as indicated in the prediction result is adjusted based on the priority sequence to obtain a bandwidth allocation result. The module allocates bandwidth to multiple VPN subnets based on the bandwidth allocation result.

[0069] The allocation module 506 is further configured to increase the first weight of the first virtual private network subnet by a preset value and decrease the first weight of the second virtual private network subnet by a preset value, wherein the first virtual private network subnet is a virtual private network subnet with a bandwidth utilization rate greater than or equal to a first preset threshold, and the second virtual private network subnet is a virtual private network subnet with a bandwidth utilization rate less than the first preset threshold.

[0070] It should be noted that, Figure 5 The bandwidth allocation device shown is used to perform Figure 2 The bandwidth allocation method shown is therefore Figure 2 The explanations and descriptions regarding the bandwidth allocation method in the document also apply to the bandwidth allocation device, and will not be repeated here.

[0071] It should be noted that each module in the bandwidth allocation device described above can be a program module (e.g., a set of program instructions that implements a specific function) or a hardware module. For the latter, it can take the following forms, but is not limited to them: each of the above modules is represented by a processor, or the functions of each of the above modules are implemented by a processor.

[0072] This application also provides a non-volatile storage medium, which includes a stored program. During program execution, the device containing the non-volatile storage medium executes the bandwidth allocation method described above. For example, it acquires multi-dimensional feature data of multiple virtual private network (VPN) subnets, where the multi-dimensional feature data includes at least bandwidth usage, subnet size of the multiple VPN subnets, and service type corresponding to each VPN subnet. A bandwidth allocation prediction model is used to analyze the multi-dimensional feature data to obtain prediction results. These prediction results are used to predict the bandwidth allocated to each VPN subnet. The bandwidth allocation prediction model is trained on an initial bandwidth allocation prediction model using historical multi-dimensional feature data from multiple VPN subnets. Based on the prediction results and real-time monitoring results, bandwidth is dynamically allocated to the multiple VPN subnets, where the real-time monitoring results are used to adjust the weights of the multiple VPN subnets.

[0073] This application also provides an electronic device, including a processor for running a program, wherein the above-described bandwidth allocation method is executed during program execution. For example, multi-dimensional feature data of multiple virtual private network (VPN) subnets are acquired, wherein the multi-dimensional feature data includes at least bandwidth usage, subnet size of the multiple VPN subnets, and service type corresponding to each VPN subnet; a bandwidth allocation prediction model is used to analyze the multi-dimensional feature data to obtain prediction results, wherein the prediction results are used to predict the bandwidth allocated to each VPN subnet, and the bandwidth allocation prediction model is obtained by training an initial bandwidth allocation prediction model using historical multi-dimensional feature data of the multiple VPN subnets; bandwidth is dynamically allocated to the multiple VPN subnets based on the prediction results and real-time monitoring results, wherein the real-time monitoring results are used to adjust the weights of the multiple VPN subnets.

[0074] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements the above-described bandwidth allocation method. For example, it involves acquiring multi-dimensional feature data of multiple virtual private network (VPN) subnets, wherein the multi-dimensional feature data includes at least bandwidth usage, subnet size of the multiple VPN subnets, and service type corresponding to each VPN subnet; analyzing the multi-dimensional feature data using a bandwidth allocation prediction model to obtain prediction results, wherein the prediction results are used to predict the bandwidth allocated to each VPN subnet, and the bandwidth allocation prediction model is obtained by training an initial bandwidth allocation prediction model using historical multi-dimensional feature data of the multiple VPN subnets; and dynamically allocating bandwidth to the multiple VPN subnets based on the prediction results and real-time monitoring results, wherein the real-time monitoring results are used to adjust the weights of the multiple VPN subnets.

[0075] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0076] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0077] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0078] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0079] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to related technologies, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0080] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A bandwidth allocation method, characterized in that, include: Acquire multi-dimensional feature data of multiple virtual private network subnets, wherein the multi-dimensional feature data includes at least bandwidth usage, subnet size of the multiple virtual private network subnets, and service type corresponding to each virtual private network subnet; A bandwidth allocation prediction model is used to analyze the multi-dimensional feature data to obtain prediction results. The prediction results are used to predict the bandwidth allocated to each of the virtual private network subnets. The bandwidth allocation prediction model is obtained by training an initial bandwidth allocation prediction model with historical multi-dimensional feature data of the multiple virtual private network subnets. Based on the prediction results and real-time monitoring results, bandwidth is dynamically allocated to the plurality of virtual private network subnets, wherein the real-time monitoring results are used to adjust the weights of the plurality of virtual private network subnets; The dynamic allocation of bandwidth to the multiple virtual private network subnets based on the prediction results and real-time monitoring results includes: The bandwidth utilization rate of each virtual private network subnet is determined at preset time intervals as the real-time monitoring result. The bandwidth utilization rate is determined by the ratio of the real-time bandwidth of each virtual private network subnet to the total bandwidth of the multiple virtual private network subnets. The real-time bandwidth is used to indicate the bandwidth corresponding to the timestamp indicated by the current time period. The first weight of each virtual private network subnet is adjusted based on the bandwidth utilization rate; The multiple virtual private network subnets are sorted in descending order of their adjusted first weights to obtain a priority sequence; Based on the priority sequence, the bandwidth allocated to each virtual private network subnet as indicated in the prediction result is adjusted to obtain the bandwidth allocation result; Based on the bandwidth allocation result, bandwidth is allocated to the plurality of virtual private network subnets, wherein the first weight is determined based on the bandwidth allocation prediction model, the bandwidth allocation prediction model includes at least a subnet feature fusion layer and a hidden layer, the subnet feature fusion layer is used to determine the first weight corresponding to each virtual private network subnet, and the hidden layer is used to extract nonlinear features from the input data, the input data being the multi-dimensional feature data.

2. The method according to claim 1, characterized in that, The subnet size of the multiple virtual private network subnets is obtained in the following way: The subnet sizes of the multiple virtual private network subnets are obtained from the database of the virtual private network subnet control center, wherein the subnet size includes at least the address space size and the number of devices contained in each virtual private network subnet.

3. The method according to claim 1, characterized in that, The bandwidth usage information is obtained through the following methods: Obtain network traffic data for the multiple virtual private network subnets; The network traffic data is cleaned. Extract feature data that affects bandwidth allocation from the cleaned network traffic data, and use the feature data as the bandwidth usage. The feature data includes at least the peak and average network traffic of each virtual private network subnet within a preset time period.

4. The method according to claim 1, characterized in that, Each virtual private network subnet corresponds to a service type, and a first weight is assigned to each virtual private network subnet based on the service type.

5. The method according to claim 4, characterized in that, The bandwidth allocation prediction model is trained in the following way: Step 1: Obtain the historical multi-dimensional feature data, wherein the historical multi-dimensional feature data includes at least historical bandwidth usage, subnet size of the multiple virtual private network subnets, and service type corresponding to each virtual private network subnet; Step 2: Train the initial bandwidth allocation prediction model using the historical multi-dimensional feature data, and adjust the weight of each virtual private network subnet based on the weight of the previous iteration, the preset learning rate, and the preset loss function. In the first iteration, the weight of the previous iteration is the preset weight. Step 2 is executed iteratively until the number of iterations is reached, at which point the iteration stops, resulting in the bandwidth allocation prediction model. The weight of each virtual private network subnet at the time of the last iteration is then used as the first weight of each virtual private network subnet.

6. The method according to claim 1, characterized in that, The adjustment of the first weight of each virtual private network subnet based on the bandwidth utilization rate includes: The first weight of the first virtual private network subnet is increased by a preset value, and the first weight of the second virtual private network subnet is decreased by the preset value. The first virtual private network subnet is the virtual private network subnet whose bandwidth utilization rate is greater than or equal to a first preset threshold, and the second virtual private network subnet is the virtual private network subnet whose bandwidth utilization rate is less than the first preset threshold.

7. A bandwidth allocation device, characterized in that, include: The acquisition module is used to acquire multi-dimensional feature data of multiple virtual private network subnets, wherein the multi-dimensional feature data includes at least bandwidth usage, subnet size of the multiple virtual private network subnets, and service type corresponding to each virtual private network subnet; The analysis module is used to analyze the multi-dimensional feature data using a bandwidth allocation prediction model to obtain prediction results. The prediction results are used to predict the bandwidth allocated to each of the virtual private network subnets. The bandwidth allocation prediction model is obtained by training an initial bandwidth allocation prediction model using historical multi-dimensional feature data of the multiple virtual private network subnets. The allocation module is used to dynamically allocate bandwidth to the plurality of virtual private network (VPN) subnets based on the prediction results and real-time monitoring results: It determines the bandwidth utilization rate of each VPN subnet at preset time intervals as the real-time monitoring result, wherein the bandwidth utilization rate is determined by the ratio of the real-time bandwidth of each VPN subnet to the total bandwidth of the plurality of VPN subnets, and the real-time bandwidth is used to indicate the bandwidth corresponding to the timestamp indicated by the current time period; it adjusts the first weight of each VPN subnet based on the bandwidth utilization rate; and it sorts the plurality of VPN subnets in descending order of the adjusted first weight to obtain a priority. The sequence is used to adjust the bandwidth allocated to each virtual private network subnet as indicated in the prediction result based on the priority sequence, thereby obtaining a bandwidth allocation result. Bandwidth is then allocated to the plurality of virtual private network subnets based on the bandwidth allocation result, wherein the real-time monitoring result is used to adjust the weights of the plurality of virtual private network subnets; wherein the first weight is determined based on the bandwidth allocation prediction model, the bandwidth allocation prediction model includes at least a subnet feature fusion layer and a hidden layer, the subnet feature fusion layer is used to determine the first weight corresponding to each virtual private network subnet, and the hidden layer is used to extract nonlinear features from the input data, the input data being the multi-dimensional feature data.

8. A non-volatile storage medium, characterized in that, The non-volatile storage medium stores a program, wherein when the program is executed, it controls the device where the non-volatile storage medium is located to perform the bandwidth allocation method according to any one of claims 1 to 6.

9. An electronic device, characterized in that, include: A memory and a processor, the processor being configured to run a program stored in the memory, wherein the program, when running, executes the bandwidth allocation method according to any one of claims 1 to 6.

Images