A dynamic communication adaptation system and implementation method for a virtual network terminal

Abstract

This invention relates to a dynamic communication adaptation system and implementation method for virtual network terminals, belonging to the technical field of communication adaptation. The system includes: analyzing the network performance needs of a user group and constructing a network demand matrix for the user group; based on data analysis from a network measurement platform, real-time monitoring of network conditions and device operating status to obtain the network resource allocation status of the user group's communication device software and generate a network behavior profile of the user group; combining the network demand matrix and the network behavior profile of the user group to dynamically adjust and optimize the network resource allocation strategy of the virtual network terminal; and based on the optimized network resource allocation strategy of the virtual network terminal, constructing a dynamic communication adaptation model for the virtual network terminal to achieve communication quality optimization and adaptation of the virtual network in various network environments. The beneficial effects of this invention are: improved system adaptability and reliability under high load conditions, and significantly improved user experience and communication efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of communication adaptation, in particular to a dynamic communication adaptation system and implementation method of a virtual network terminal. BACKGROUND

[0002] The existing virtual network terminal communication adaptation system usually relies on fixed protocol stack and static configuration, and lacks the adaptability to dynamic network environment changes; in the prior art, many systems cannot flexibly adjust the communication strategy when facing different network conditions, resulting in insufficient utilization of network resources or unstable communication quality; especially in high load and complex network environment, the adaptation efficiency of the existing system is low, and the reliability and stability of communication cannot be effectively guaranteed, and there is a lack of targeted optimization strategy, which is difficult to meet the rapidly changing network demand. SUMMARY

[0003] The present application provides a dynamic communication adaptation scheme for a virtual network terminal to solve the technical problems in the prior art.

[0004] The technical solution of the present application to solve the above technical problems is as follows:

[0005] A dynamic communication adaptation implementation method of a virtual network terminal, comprising:

[0006] Based on the historical network usage data of the user group, the demand of the user group for network performance is analyzed, and a user group network demand matrix is constructed;

[0007] Based on network measurement platform data analysis, real-time monitoring of network status and device running state, acquisition of network resource allocation status of user group communication equipment software, generation of user group network behavior portrait;

[0008] Using reinforcement learning algorithm, combining user group network demand matrix and user group network behavior portrait, dynamically adjusting and optimizing the network resource allocation strategy of virtual network terminal;

[0009] Based on the optimized network resource allocation strategy of the virtual network terminal, a dynamic communication adaptation model of the virtual network terminal is constructed, and the communication quality optimization and adaptation of the virtual network in multiple network environments are realized.

[0010] Preferably, based on the historical network usage data of the user group, the data is preprocessed, the abnormal values are processed by linear interpolation method, and the historical network usage time series data of the user group is constructed;

[0011] Based on the historical network usage time series data of the user group, the user group demand index is divided, the user group demand is quantified, the user group demand features are learned by using self-encoder technology, and the user group network demand matrix is constructed;

[0012] As a further development, the user group demand indicators include: latency tolerance, bandwidth requirements, and service priority.

[0013] Preferably, network status data is acquired in real time based on a network measurement platform, and end-to-end latency, packet loss rate and bandwidth utilization are monitored in real time. Combined with a 5-second sampling period, a timestamp sequence is generated.

[0014] Based on the device operating status data in the network measurement platform, CPU utilization and memory utilization are collected in real time to generate device status vectors.

[0015] Based on the network performance timestamp sequence, the average latency, packet loss rate fluctuation, peak bandwidth, and average device load characteristics are calculated to generate a single user behavior vector.

[0016] Preferably, the K-Means clustering algorithm is used to determine the number of clusters K for a single user behavior vector, randomly select K single user behavior vectors as initial cluster centers, calculate the distance between each point and the cluster center according to the Euclidean formula, assign each single user behavior vector to the nearest cluster center, form K subsets, calculate the mean of all single user behavior vectors assigned to the cluster, update the cluster center, iterate until the cluster center is stable, and output the clustering result;

[0017] By employing time window technology, the similarity of individual user behavior vectors within different time windows is grouped, and combined with the historical network demand matrix of user groups, a network behavior profile of user groups is generated.

[0018] Preferably, a Markov decision process model is constructed by using the user group network demand matrix and user group network behavior profile as the state space, and the adjustment of bandwidth and CPU utilization as the action space. The reward function of the reinforcement learning model is defined, and user satisfaction, resource cost, and service achievement reward are combined to construct the Markov decision process model.

[0019] Preferably, the policy gradient algorithm is used, with the state space as the network input and the action distribution adjusted by bandwidth and CPU as the output. The parameters of the policy network and the value network are randomly initialized, the current state value is estimated using the value network, the advantage function is calculated, the objective function is obtained to update the policy network, the policy network parameters are optimized by the gradient descent method, the resource allocation is constrained by the action masking mechanism, and the reinforcement learning model is iteratively trained until convergence is obtained to obtain the optimal network resource allocation strategy. The network resource configuration of the virtual network terminal is dynamically adjusted to achieve efficient utilization of network resources.

[0020] Preferably, based on the optimized network resource allocation strategy of the virtual network terminal and the real-time network status, network status data is collected, preprocessed, and a neural network model is trained. The network status index is used as the input layer, and multiple hidden layers are designed to form a deep neural network structure. The network resource allocation strategy category is used as the output layer. The Softmax activation function is used to generate the probability distribution of each network resource allocation strategy. The cross-entropy loss function is used to calculate the error between the prediction result and the actual label. The weight parameters of the neural network model are optimized through the backpropagation algorithm until the loss function converges, thus obtaining the dynamic communication adaptation model of the virtual network terminal.

[0021] Preferably, the dynamic communication adaptation model based on virtual network terminals adopts a dynamic update mechanism to adjust the parameters of the neural network model to adapt to the network environment, evaluates the network status of the virtual network terminal in real time, and dynamically selects the optimal network resource allocation strategy according to the current network status, thereby realizing the optimization and adaptation of the communication quality of the virtual network in various network environments.

[0022] Furthermore, a dynamic communication adaptation system for a virtual network terminal, used to implement the aforementioned dynamic communication adaptation method for a virtual network terminal, includes:

[0023] The module includes a network demand matrix module, a network behavior profiling module, a network resource allocation strategy module, and a communication quality optimization and adaptation module.

[0024] The network demand matrix module is used to analyze the network performance needs of user groups based on historical network usage data and to construct a network demand matrix for user groups.

[0025] The network behavior profiling module is used to analyze data from the network measurement platform, monitor network conditions and device operating status in real time, obtain the network resource allocation status of user group communication device software, and generate user group network behavior profiles.

[0026] The network resource allocation strategy module is electrically connected to the network demand matrix module and the network behavior profile module. The network resource allocation strategy module is used to dynamically adjust and optimize the network resource allocation strategy of the virtual network terminal by using reinforcement learning algorithms and combining the user group network demand matrix and the user group network behavior profile.

[0027] The communication quality optimization and adaptation module is electrically connected to the network resource allocation strategy module. The communication quality optimization and adaptation module is used to construct a dynamic communication adaptation model for the virtual network terminal based on the optimized network resource allocation strategy of the virtual network terminal, so as to realize the communication quality optimization and adaptation of the virtual network in various network environments.

[0028] The beneficial effects of this invention are as follows: By analyzing historical network data and real-time network conditions of user groups, and using reinforcement learning algorithms to dynamically optimize the resource allocation strategy of virtual network terminals, it can adapt to the ever-changing network environment in real time, improving communication quality and stability; by constructing a dynamic communication adaptation model for virtual network terminals, this method effectively optimizes the utilization of network resources, ensures efficient communication in complex network environments, improves the system's adaptability and reliability under high load conditions, and significantly improves user experience and communication efficiency. Attached Figure Description

[0029] Figure 1 This is a flowchart of the method of the present invention;

[0030] Figure 2 This is a system framework diagram of the present invention. Detailed Implementation

[0031] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0032] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0033] In the description of this application, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0034] Example 1: A method for implementing dynamic communication adaptation of a virtual network terminal, comprising:

[0035] S1. Based on the historical network usage data of the user group, analyze the user group's network performance requirements and construct a network requirement matrix for the user group;

[0036] Step S1 includes the following:

[0037] Based on the historical network usage data of the user group, the data is preprocessed, and outliers are processed by linear interpolation to construct the historical network usage time series data of the user group.

[0038] Based on historical network usage time series data of user groups, user group demand indicators are divided, user group demand is quantified, and user group demand is learned using autoencoder technology to construct user group network demand matrix.

[0039] As a further development, the user group demand indicators include: latency tolerance, bandwidth requirements, and service priority.

[0040] When using it, refer to the content of step S1 above:

[0041] Existing technologies face problems such as low data processing accuracy, simplistic demand modeling, and lack of flexibility when constructing network demand matrices for user groups. This step uses linear interpolation to accurately handle outliers, introduces multi-dimensional demand indicators such as latency tolerance, bandwidth requirements, and service priorities, and utilizes autoencoder technology to deeply learn user demand characteristics. This enables a more comprehensive and accurate modeling of user demands, overcomes the limitations of traditional methods, and improves the intelligence and personalization of network services.

[0042] S2. Based on network measurement platform data analysis, monitor network conditions and equipment operation status in real time, obtain network resource allocation status of user group communication device software, and generate user group network behavior profiles.

[0043] Step S2 includes the following:

[0044] Based on the network measurement platform, network status data is acquired in real time, and end-to-end latency, packet loss rate and bandwidth utilization are monitored in real time. Combined with a 5-second sampling period, a timestamp sequence is generated.

[0045] Based on the device operating status data in the network measurement platform, CPU utilization and memory utilization are collected in real time to generate device status vectors.

[0046] Based on the network performance timestamp sequence, the average latency, packet loss rate fluctuation, peak bandwidth, and average device load characteristics are calculated to generate a single user behavior vector.

[0047] Using the K-Means clustering algorithm, determine the number of clusters K for a single user behavior vector, randomly select K single user behavior vectors as initial cluster centers, calculate the distance between each point and the cluster center according to the Euclidean formula, assign each single user behavior vector to the nearest cluster center, forming K subsets, calculate the mean of all single user behavior vectors assigned to the cluster, update the cluster centers, iterate until the cluster centers are stable, and output the clustering results;

[0048] By employing time window technology, the similarity of individual user behavior vectors within different time windows is grouped, and combined with the historical network demand matrix of user groups, a network behavior profile of user groups is generated.

[0049] When using it, please refer to the steps above:

[0050] Existing network monitoring technologies suffer from poor real-time performance, single-dimensional analysis, and insufficient static clustering, making it impossible to accurately capture user behavior and device changes. This step, however, dynamically generates more accurate user group network behavior profiles by monitoring network conditions and device status in real time, combined with the K-Means clustering algorithm and time window technology. This method not only optimizes network resource allocation and improves accuracy but also better adapts to changes in user needs, ultimately enhancing network performance and user experience.

[0051] S3. Using reinforcement learning algorithms, combined with the network demand matrix of user groups and the network behavior profile of user groups, dynamically adjust and optimize the network resource allocation strategy of virtual network terminals.

[0052] Step S3 includes the following:

[0053] Based on the user group network demand matrix and user group network behavior profile as the state space, and using the adjustment of bandwidth and CPU utilization as the action space, the reward function of the reinforcement learning model is defined. By combining user satisfaction, resource cost, and service achievement reward, a Markov decision process model is constructed.

[0054] Using the policy gradient algorithm, the state space is used as the network input, and the action distribution adjusted by bandwidth and CPU is used as the output. The parameters of the policy network and the value network are randomly initialized. The current state value is estimated using the value network, the advantage function is calculated, the objective function is obtained to update the policy network, the policy network parameters are optimized by gradient descent, and the resource allocation is constrained by the action masking mechanism. The reinforcement learning model is continuously trained iteratively until convergence, and the optimal network resource allocation strategy is obtained. The network resource configuration of the virtual network terminal is dynamically adjusted to achieve efficient utilization of network resources.

[0055] When using it, refer to the content of step S3 above:

[0056] Existing technologies at home and abroad have the following problems: On the one hand, it is difficult to update the user demand matrix and behavior profile in real time, which makes it impossible for the state space to accurately reflect user needs; on the other hand, reinforcement learning consumes a lot of computational resources, has a slow convergence speed, and low optimization efficiency in large-scale complex environments; and the reward function design is too simple and fails to balance user experience, resource cost and service quality.

[0057] This step overcomes these shortcomings by combining user demand matrices and behavioral profiles, and employing policy gradient algorithms and value network optimization. Through advantage functions and action masking mechanisms, it can efficiently and dynamically adjust network resources, improve resource utilization, optimize user satisfaction and costs, and significantly enhance the flexibility and efficiency of network resource allocation.

[0058] S4. Based on the optimized network resource allocation strategy of the virtual network terminal, construct a dynamic communication adaptation model for the virtual network terminal to achieve communication quality optimization and adaptation of the virtual network in various network environments.

[0059] Step S4 includes the following:

[0060] Based on the optimized network resource allocation strategy and real-time network status of the virtual network terminal, network status data is collected, preprocessed, and a neural network model is trained. The network status index is used as the input layer, and multiple hidden layers are designed to form a deep neural network structure. The network resource allocation strategy category is used as the output layer. The Softmax activation function is used to generate the probability distribution of each network resource allocation strategy. The cross-entropy loss function is used to calculate the error between the prediction result and the actual label. The weight parameters of the neural network model are optimized through the backpropagation algorithm until the loss function converges, thus obtaining the dynamic communication adaptation model of the virtual network terminal.

[0061] The dynamic communication adaptation model based on virtual network terminals adopts a dynamic update mechanism to adjust the parameters of the neural network model to adapt to the network environment, evaluates the network status of virtual network terminals in real time, and dynamically selects the optimal network resource allocation strategy according to the current network status, thereby realizing the optimization and adaptation of communication quality of virtual networks in various network environments.

[0062] When using it, refer to the content of step S4 above:

[0063] Existing virtual network resource allocation technologies mostly rely on static or rule-based methods, which are difficult to cope with complex dynamic network environments. Although some methods use machine learning, their generalization ability is poor and they lack real-time update mechanisms, resulting in unstable communication quality and resource waste. This step constructs a dynamic communication adaptation model based on deep neural networks, collects network status data in real time, and dynamically selects the optimal resource allocation strategy, thereby enhancing the adaptability and optimization capabilities of virtual networks, avoiding resource waste and performance bottlenecks, and improving communication quality and efficiency.

[0064] Example 2: A dynamic communication adaptation system for a virtual network terminal, comprising:

[0065] The module includes a network demand matrix module, a network behavior profiling module, a network resource allocation strategy module, and a communication quality optimization and adaptation module.

[0066] The network demand matrix module is used to analyze the network performance needs of user groups based on historical network usage data and to construct a network demand matrix for user groups.

[0067] The network behavior profiling module is used to analyze data from the network measurement platform, monitor network conditions and device operating status in real time, obtain the network resource allocation status of user group communication device software, and generate user group network behavior profiles.

[0068] The network resource allocation strategy module is electrically connected to the network demand matrix module and the network behavior profile module. The network resource allocation strategy module is used to dynamically adjust and optimize the network resource allocation strategy of the virtual network terminal by using reinforcement learning algorithms and combining the user group network demand matrix and the user group network behavior profile.

[0069] The communication quality optimization and adaptation module is electrically connected to the network resource allocation strategy module. The communication quality optimization and adaptation module is used to construct a dynamic communication adaptation model for the virtual network terminal based on the optimized network resource allocation strategy of the virtual network terminal, so as to realize the communication quality optimization and adaptation of the virtual network in various network environments.

[0070] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0071] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0072] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0073] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0074] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0075] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0076] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for implementing dynamic communication adaptation of a virtual network terminal, characterized in that, include: S1. Based on the historical network usage data of the user group, analyze the user group's network performance requirements and construct a network requirement matrix for the user group; S2. Based on network measurement platform data analysis, monitor network conditions and equipment operation status in real time, obtain network resource allocation status of user group communication device software, and generate user group network behavior profiles. S3. Using reinforcement learning algorithms, combined with the network demand matrix of user groups and the network behavior profile of user groups, dynamically adjust and optimize the network resource allocation strategy of virtual network terminals. S4. Based on the optimized network resource allocation strategy of the virtual network terminal, construct a dynamic communication adaptation model for the virtual network terminal to achieve communication quality optimization and adaptation of the virtual network in various network environments. The method of dynamically adjusting and optimizing the network resource allocation strategy for virtual network terminals by utilizing reinforcement learning algorithms, combined with user group network demand matrices and user group network behavior profiles, includes: Based on the user group network demand matrix and user group network behavior profile as the state space, and using the adjustment of bandwidth and CPU utilization as the action space, the reward function of the reinforcement learning model is defined. By combining user satisfaction, resource cost, and service achievement reward, a Markov decision process model is constructed. Using the policy gradient algorithm, the state space is used as the network input, and the action distribution adjusted by bandwidth and CPU is used as the output. The parameters of the policy network and the value network are randomly initialized. The current state value is estimated using the value network, the advantage function is calculated, the objective function is obtained to update the policy network, the policy network parameters are optimized by the gradient descent method, and the resource allocation is constrained by the action masking mechanism. The reinforcement learning model is continuously trained iteratively until convergence, and the optimal network resource allocation strategy is obtained, which dynamically adjusts the network resource configuration of the virtual network terminal.

2. The method for dynamic communication adaptation of a virtual network terminal according to claim 1, characterized in that, S1 includes: Based on the historical network usage data of the user group, data preprocessing is performed, outliers are processed using linear interpolation, and time series data of the historical network usage of the user group is constructed. Based on historical network usage time series data of user groups, user group demand indicators are divided, user group demand is quantified, and user group demand is learned using autoencoder technology to construct user group network demand matrix. As a further development, the user group demand indicators include: latency tolerance, bandwidth requirements, and service priority.

3. The method for dynamic communication adaptation of a virtual network terminal according to claim 1, characterized in that, S2 includes: Based on the network measurement platform, network status data is acquired in real time, and end-to-end latency, packet loss rate and bandwidth utilization are monitored in real time. Combined with a 5-second sampling period, a timestamp sequence is generated. Based on the device operating status data in the network measurement platform, CPU utilization and memory utilization are collected in real time to generate device status vectors. Based on the network performance timestamp sequence, the average latency, packet loss rate fluctuation, peak bandwidth, and average device load characteristics are calculated to generate a single user behavior vector.

4. The method for dynamic communication adaptation of a virtual network terminal according to claim 3, characterized in that, S2 further includes: Using the K-Means clustering algorithm, determine the number of clusters K for a single user behavior vector, randomly select K single user behavior vectors as initial cluster centers, calculate the distance between each point and the cluster center according to the Euclidean formula, assign each single user behavior vector to the nearest cluster center, forming K subsets, calculate the mean of all single user behavior vectors assigned to the cluster, update the cluster centers, iterate until the cluster centers are stable, and output the clustering results; By employing time window technology, the similarity of individual user behavior vectors within different time windows is grouped, and combined with the historical network demand matrix of user groups, a network behavior profile of user groups is generated.

5. The method for dynamic communication adaptation of a virtual network terminal according to claim 4, characterized in that, S4 includes: Based on the optimized network resource allocation strategy and real-time network conditions of the virtual network terminal, network status data is collected, preprocessed, and a neural network model is trained. Using network status indicators as the input layer, multiple hidden layers are designed to form a deep neural network structure. The network resource allocation strategy category is used as the output layer. The Softmax activation function is used to generate the probability distribution of each network resource allocation strategy. The cross-entropy loss function is used to calculate the error between the prediction result and the actual label. The weight parameters of the neural network model are optimized through the backpropagation algorithm until the loss function converges, thus obtaining the dynamic communication adaptation model of the virtual network terminal.

6. The method for dynamic communication adaptation of a virtual network terminal according to claim 5, characterized in that, S4 further includes: The dynamic communication adaptation model based on virtual network terminals adopts a dynamic update mechanism to adjust the parameters of the neural network model to adapt to the network environment, evaluates the network status of virtual network terminals in real time, and dynamically selects the optimal network resource allocation strategy according to the current network status, thereby realizing the optimization and adaptation of communication quality of virtual networks in various network environments.

7. A dynamic communication adaptation system for a virtual network terminal, characterized in that, A method for implementing dynamic communication adaptation of a virtual network terminal as described in any one of claims 1-6 includes: The module includes a network demand matrix module, a network behavior profiling module, a network resource allocation strategy module, and a communication quality optimization and adaptation module. The network demand matrix module is used to analyze the network performance needs of user groups based on historical network usage data and to construct a network demand matrix for user groups. The network behavior profiling module is used to analyze data from the network measurement platform, monitor network conditions and device operating status in real time, obtain the network resource allocation status of user group communication device software, and generate user group network behavior profiles. The network resource allocation strategy module is electrically connected to the network demand matrix module and the network behavior profile module. The network resource allocation strategy module is used to dynamically adjust and optimize the network resource allocation strategy of the virtual network terminal by using reinforcement learning algorithms and combining the user group network demand matrix and the user group network behavior profile. The communication quality optimization and adaptation module is electrically connected to the network resource allocation strategy module. The communication quality optimization and adaptation module is used to construct a dynamic communication adaptation model for the virtual network terminal based on the optimized network resource allocation strategy of the virtual network terminal, so as to realize the communication quality optimization and adaptation of the virtual network in various network environments.

Images