A multi-protocol and cross-platform network migration management system

Abstract

The present invention relates to the field of migration management technology and provides a multi-protocol cross-platform network migration management system, which includes a data acquisition module, a protocol identification module, a migration optimization module, an anomaly monitoring module, a protocol conversion module and a load scheduling module; the system realizes in-depth analysis and intelligent identification of different protocol fields through the protocol identification module, effectively solving the protocol compatibility problem in cross-platform network migration; by introducing a double-critical strategy optimization algorithm in the migration optimization module, the optimal migration strategy is automatically generated and optimized to ensure the reasonable allocation of resources and the high efficiency of the migration process; the system can automatically adapt to a dynamically changing network environment, provide intelligent protocol identification and migration optimization, significantly improve the reliability and efficiency of network migration, and is particularly suitable for complex, multi-platform network migration scenarios.

Description

Technical Field

[0001] The present invention relates to the technical field of migration management, and in particular to a multi-protocol and cross-platform network migration management system. Background Art

[0002] To improve business flexibility, scalability, and resource efficiency, more and more organizations are facing the need for network migration. Network migration is more than just a simple device or system migration; it involves resolving protocol incompatibilities between different platforms and devices, reconfiguring network topologies, and adjusting to varying network performance requirements. These complex migration tasks often need to be performed efficiently and with low latency to ensure uninterrupted service and optimize network performance. However, existing network migration management systems still have many shortcomings. First, traditional systems lack sufficient intelligent adaptability to complex network topologies and ever-changing network conditions. Their decision-making processes are often based on fixed algorithms or templates, making them unable to dynamically perceive actual network changes. Second, traditional systems' intelligent capabilities in protocol identification remain limited. Existing protocol identification methods are mostly based on simple rules or shallow feature matching, failing to deeply understand and model the complex structure and hierarchical relationships of protocol fields. Especially in cross-platform migration scenarios, where different platforms may use multiple unknown or non-standard protocols, traditional methods often lack sufficient intelligent support, resulting in inefficient dynamic protocol identification and automatic conversion. Summary of the Invention

[0003] The present invention provides a multi-protocol cross-platform network migration management system, which aims to solve the problem of insufficient intelligence in the existing network migration management system in terms of protocol identification, migration optimization, performance scheduling, exception handling, etc.; the system combines the advanced technologies of Lorentz space embedding, hyperspherical distance learning and graph neural network through the protocol identification module to construct a hyperspherical Lorentz graph neural network to conduct in-depth analysis of multiple protocol fields in the network; this technology enables the system to effectively handle protocol differences between different platforms through intelligent protocol identification in complex network migration scenarios, and realize protocol compatibility optimization; especially when facing unknown protocols or dynamically changing network environments, the system can effectively handle protocol differences between different platforms through intelligent protocol identification in complex network migration scenarios, and realize protocol compatibility optimization; especially when facing unknown protocols or dynamically changing network environments, the system can effectively handle protocol differences between different platforms through intelligent protocol identification, and realize protocol compatibility optimization. The protocol identification module can analyze and adjust in real time to ensure protocol interoperability during the migration process; at the same time, the system also introduces a dual-criticality strategy optimization algorithm through the migration optimization module, combining network performance information, protocol identification results and network topology data to automatically generate the optimal migration strategy; this module can not only dynamically evaluate and optimize resource allocation during the migration process, but also adjust the migration strategy in real time to adapt to changes in the network environment, ensuring the efficiency and stability of the migration process; through the above technical features, the network migration management system of the present invention can provide intelligent and automated protocol identification and migration optimization in a complex and changeable cross-platform environment, significantly improving the reliability and efficiency of network migration.

[0004] The present invention provides a multi-protocol and cross-platform network migration management system, which includes a data acquisition module, a protocol identification module, a migration optimization module, an anomaly monitoring module, a protocol conversion module, and a load scheduling module;

[0005] The data acquisition module uses network monitoring technology to acquire network data packets, which include network performance information and protocol fields. It then analyzes the flow of network data packets to obtain network topology data. The data acquisition module transmits the protocol fields to the protocol identification module, which then transmits the network performance information and network topology data to the migration optimization module.

[0006] The protocol identification module combines Lorentz space embedding, hyperspherical distance learning, and graph neural networks to construct a hyperspherical Lorentz graph neural network. It uses the hyperspherical Lorentz graph neural network to analyze protocol fields and generate protocol identification results. The protocol identification module transmits the protocol identification results to the migration optimization module.

[0007] The migration optimization module builds a dual-criticality strategy optimization algorithm. It uses the dual-criticality strategy optimization algorithm to analyze network performance information, protocol identification results, and network topology data, generate the optimal migration strategy, and perform network migration. The migration optimization module transmits the optimal migration strategy to the load scheduling module.

[0008] Anomaly monitoring module, which is connected to the migration optimization module to monitor the network status and performance during the migration process of the migration optimization module;

[0009] The protocol conversion module is connected to the anomaly monitoring module. When the anomaly monitoring module detects that different devices and platforms use incompatible protocols, it generates protocol conversion rules through protocol analysis and matching mechanisms, and then performs protocol mapping;

[0010] The load scheduling module connects the migration optimization module and the exception monitoring module, receives the optimal migration strategy from the migration optimization module, and combines with the exception monitoring module to ensure reasonable load distribution and no overload of resources.

[0011] Furthermore, the process of generating the protocol identification result by the protocol identification module specifically includes the following steps:

[0012] Step S1: Construct a protocol graph, which includes nodes and edges; define protocol fields as nodes of the protocol graph, represent the features of the protocol fields as node features; and regard the relationships between protocol fields as edges;

[0013] Step S2: Embed the node features into the Lorentz space to ensure that the node features conform to the geometric constraints of the hypersurface space; this representation can capture the hierarchical structure and relationship of the features of the protocol field and generate the Lorentz embedding representation of each node;

[0014] Step S3: Generate a rich protocol graph node representation based on the Lorentz embedding representation of each node;

[0015] Step S4: Update the protocol graph according to the enriched protocol graph node representation, apply the readout function to obtain the graph embedding vector, use the multi-layer perceptron to perform protocol classification on the graph embedding vector, and output the protocol recognition result; the protocol recognition result includes the protocol type and the protocol classification confidence.

[0016] Furthermore, step S3 specifically includes: introducing a hypersphere distance learning method, constructing a hypersphere-Lorentz centroid aggregation method, and for the Lorentz embedding representation of each node, using the hypersphere-Lorentz centroid aggregation method to perform weighted aggregation on the Lorentz embedding representation of its neighboring nodes to generate a weighted aggregation result; using the Lorentz transform layer to perform nonlinear updates on the weighted aggregation result to further enrich the representation of the nodes in the protocol graph, ensuring that the features of each node can effectively capture the hierarchical structure and relationship of the protocol; generating an enriched protocol graph node representation.

[0017] Furthermore, the migration optimization module generates the optimal migration strategy, which specifically includes the following steps:

[0018] Step B1: Initialize the current strategy and criticism network of the dual criticism strategy optimization algorithm; the criticism network includes the traditional judgment network and the post-decision judgment network;

[0019] Step B2: Combine the protocol identification results, network topology data, and network performance information to construct a state space; define an action space, which includes migration sequence, migration batches, and migration time points;

[0020] Step B3: Based on the state space and action space, use the current strategy to calculate the traditional reward and post-decision reward, and collect trajectory data; the trajectory data includes the state, action, and reward sequence;

[0021] Step B4: Combine the trajectory data, calculate the traditional state advantage function through the traditional evaluation network, and calculate the post-decision state advantage function through the post-decision evaluation network. Take the larger value of the two at each time step to obtain the maximum advantage function as the basis for the optimal decision;

[0022] Step B5: Calculate the loss function of the current strategy based on the maximum advantage function, update the current strategy, and generate an updated strategy; calculate the loss of the traditional evaluation network and the loss of the post-decision evaluation network to update the criticism network;

[0023] The traditional judgment network is used to estimate the value function of the traditional state;

[0024] The post-decision evaluation network is used to estimate the value function of the post-decision state;

[0025] The relationship between the critic network and the current policy is as follows: the critic network provides evaluation signals for policy optimization, namely the value function, and the current policy adjusts its behavior based on these evaluation signals and ultimately selects the action that can obtain the maximum reward;

[0026] Step B6: Set the maximum number of iterations and repeat steps B2 to B5 to continuously update the critical network and current strategy to generate the optimal migration strategy.

[0027] By adopting the above scheme, the beneficial effects achieved by the present invention are as follows:

[0028] The multi-protocol cross-platform network migration management system provided by this invention achieves in-depth analysis and identification of different protocol fields through a protocol identification module combined with Lorentz space embedding, hypersphere distance learning, and graph neural network technology. This technology enables the system to intelligently identify and process protocol differences between different platforms, especially during cross-platform migration, ensuring optimized protocol compatibility. Compared with traditional methods, the system can automatically adapt to protocol changes in complex network environments, improving the stability and reliability of protocol interoperability during the migration process, thereby significantly increasing the success rate of cross-platform migration.

[0029] By introducing a dual-criticality strategy optimization algorithm into the migration optimization module, the present invention can intelligently generate the optimal migration strategy based on real-time network performance information, protocol identification results, and network topology data. This optimization algorithm not only dynamically adjusts resource allocation during the migration process, but also responds to changes in the network environment in real time to ensure optimal execution of the migration strategy. Through this automated migration optimization, the present invention significantly improves the efficiency and stability of network migration, avoids resource waste and performance bottlenecks during the migration process, and solves the problem that static optimization algorithms in traditional migration management systems are insufficiently adaptable to complex network environments.

[0030] In addition, the present invention demonstrates stronger adaptability when dealing with abnormal situations that arise during network migration through the close combination of protocol identification and migration optimization; the abnormal monitoring and intelligent adjustment mechanism can detect and respond to any sudden problems in the network in real time, such as protocol incompatibility, substandard network performance, etc., thereby reducing the risks during network migration; through the above technical characteristics, the present invention significantly enhances the system's adaptability to complex network environments, improves the security, reliability and efficiency of cross-platform network migration, and provides solid technical guarantees for enterprises and organizations to carry out efficient and low-risk network migration in a multi-platform environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 A schematic diagram of the modules of a multi-protocol and cross-platform network migration management system provided by the present invention;

[0032] Figure 2 This is a module diagram of the double criticism strategy optimization algorithm provided in Example 5. DETAILED DESCRIPTION

[0033] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0034] Example 1, according to Figure 1 , the present invention provides a multi-protocol and cross-platform network migration management system, which includes a data acquisition module, a protocol identification module, a migration optimization module, an anomaly monitoring module, a protocol conversion module and a load scheduling module;

[0035] The data acquisition module uses network monitoring technology to acquire network data packets, which include network performance information and protocol fields. It then analyzes the flow of network data packets to obtain network topology data. The data acquisition module transmits the protocol fields to the protocol identification module, which then transmits the network performance information and network topology data to the migration optimization module.

[0036] The protocol identification module combines Lorentz space embedding, hyperspherical distance learning, and graph neural networks to construct a hyperspherical Lorentz graph neural network. It uses the hyperspherical Lorentz graph neural network to analyze protocol fields and generate protocol identification results. The protocol identification module transmits the protocol identification results to the migration optimization module.

[0037] The migration optimization module builds a dual-criticality strategy optimization algorithm. It uses the dual-criticality strategy optimization algorithm to analyze network performance information, protocol identification results, and network topology data, generate the optimal migration strategy, and perform network migration. The migration optimization module transmits the optimal migration strategy to the load scheduling module.

[0038] Anomaly monitoring module, which is connected to the migration optimization module to monitor the network status and performance during the migration process of the migration optimization module;

[0039] The protocol conversion module is connected to the anomaly monitoring module. When the anomaly monitoring module detects that different devices and platforms use incompatible protocols, it generates protocol conversion rules through protocol analysis and matching mechanisms, and then performs protocol mapping;

[0040] The load scheduling module connects the migration optimization module and the exception monitoring module, receives the optimal migration strategy from the migration optimization module, and combines with the exception monitoring module to ensure reasonable load distribution and no overload of resources.

[0041] Embodiment 2: This embodiment is based on embodiment 1. In this embodiment, the process of generating a protocol identification result by the protocol identification module specifically includes the following steps:

[0042] Step S1: Construct a protocol graph, which includes nodes and edges; define protocol fields as nodes of the protocol graph, represent the features of the protocol fields as node features; and regard the relationships between protocol fields as edges;

[0043] Step S2: Embed the node features into the Lorentz space to ensure that the node features conform to the geometric constraints of the hypersurface space; this representation can capture the hierarchical structure and relationship of the features of the protocol field and generate the Lorentz embedding representation of each node;

[0044] Step S3: Generate a rich protocol graph node representation based on the Lorentz embedding representation of each node;

[0045] Step S4: Update the protocol graph according to the enriched protocol graph node representation, apply the readout function to obtain the graph embedding vector, use the multi-layer perceptron to perform protocol classification on the graph embedding vector, and output the protocol recognition result; the protocol recognition result includes the protocol type and the protocol classification confidence.

[0046] Example 3. This example is based on Example 2. In this example, step S3 specifically includes: introducing a hypersphere distance learning method, constructing a hypersphere-Lorentz centroid aggregation method, and for the Lorentz embedding representation of each node, using the hypersphere-Lorentz centroid aggregation method to perform weighted aggregation on the Lorentz embedding representation of its neighboring nodes to generate a weighted aggregation result; using the Lorentz transform layer to perform nonlinear updating on the weighted aggregation result to further enrich the representation of the nodes in the protocol graph, ensuring that the features of each node can effectively capture the hierarchical structure and relationship of the protocol; generating an enriched protocol graph node representation, the formula used is as follows:

[0047] Hypersphere-Lorentz center of mass aggregation method:

[0048] ;

[0049] in, and represents the node index in the protocol graph, Represents a node in the protocol graph The eigenvector of Represents neighbor nodes in the protocol graph The eigenvector of Representation node and nodes The hyperspherical distance between Representation node With neighboring nodes The similarity between them, that is, the weighted coefficient, represents the weighting of the hypersphere distance by an exponential function, Representation node The set of neighbor nodes of represents the normalization factor;

[0050] ;

[0051] in, Representation node The weighted aggregation result of represents the number of neighbor nodes, Representation node Weighted neighbor information aggregation, Indicates a point The weighted neighbor information aggregation result of norm;

[0052] ;

[0053] in, represents the Lorentz space, Represents the index of the graph neural network layer, Indicates the The feature vector of the layer node, that is, the node The characteristic representation in Lorentz space is, Indicates the Lorentz transform layer; represents an exponential map, Indicates the base point on which the mapping depends, Represents a hyperparameter that controls the The feature update amplitude of the layer, represents the scaling factor, represents the node feature vector of the previous layer, Indicates the The feature vector of the layer node, Represents a logarithmic mapping, Mapping from Lorentz space back to tangent space, Indicates the Node features after layer weighted aggregation, Express Apply a logarithmic mapping to transform the aggregation result from Lorentz space back to tangent space.

[0054] Example 4. This example is based on Example 2. In this example, step S3 specifically includes: constructing a Lorentz centroid aggregation method, for the Lorentz embedding representation of each node, using the Lorentz centroid aggregation method to perform weighted aggregation on the Lorentz embedding representation of its neighboring nodes to generate a weighted aggregation result; using the Lorentz transform layer to perform nonlinear updating on the weighted aggregation result to further enrich the representation of the nodes in the protocol graph, ensuring that the characteristics of each node can effectively capture the hierarchical structure and relationship of the protocol; generating an enriched protocol graph node representation.

[0055] Example 5, according to Figure 2 This embodiment is based on the third embodiment. In this embodiment, the migration optimization module analyzes network performance information, protocol identification results, and network topology data through a dual-critical strategy optimization algorithm to generate an optimal migration strategy. The process specifically includes the following steps:

[0056] Step B1: Strategy and Critique Network Initialization: Initialize the current strategy and criticism network of the dual criticism strategy optimization algorithm; the criticism network includes the traditional criticism network and the post-decision criticism network;

[0057] Step B2: State and action space construction: Combine the protocol identification results, network topology data, and network performance information to construct the state space; define the action space, which includes the migration sequence, migration batches, and migration time points;

[0058] Step B3: Trajectory data collection: Based on the state space and action space, use the current strategy to calculate the traditional reward and post-decision reward, and collect trajectory data; trajectory data includes state, action, and reward sequences;

[0059] Step B4: Advantage function calculation: Combined with the trajectory data, the traditional state advantage function is calculated through the traditional evaluation network, and the post-decision state advantage function is calculated through the post-decision evaluation network. The larger value of the two is taken at each time step to obtain the maximum advantage function as the basis for the optimal decision;

[0060] Step B5: Update the strategy and judgment network: Calculate the loss function of the current strategy based on the maximum advantage function, update the current strategy, and generate an updated strategy; calculate the loss of the traditional judgment network and the loss of the post-decision judgment network to update the criticism network. The formula used is as follows:

[0061] ;

[0062] in, represents the time step, Indicates the current strategy, Represents the time step The state of represents the maximum advantage function, Parameters of the current strategy, represents the loss function of the current strategy, represents the importance sampling ratio, represents the hyperparameter, i.e., the clipping range, Indicates clipping operation, limiting exist and within; represents the loss of the post-decision judgment network, express The weight of represents the loss of the traditional judgment network, express The weight of

[0063] The traditional judgment network is used to estimate the value function of the traditional state;

[0064] The post-decision evaluation network is used to estimate the value function of the post-decision state;

[0065] The relationship between the critic network and the current policy is as follows: the critic network provides evaluation signals for policy optimization, namely the value function, and the current policy adjusts its behavior based on these evaluation signals and ultimately selects the action that can obtain the maximum reward;

[0066] Step B6: Iterative optimization: Set the maximum number of iterations, repeat steps B2 to B5, continuously update the critical network and current strategy, and generate the optimal migration strategy.

[0067] Example 6: This example is based on Example 3. In this example, the migration optimization module generates an optimal migration strategy by specifically following the steps below:

[0068] Step R1: Initialize the current strategy and traditional judgment network of the dual criticism strategy optimization algorithm;

[0069] Step R2: Combine the protocol identification results, network topology data, and network performance information to construct a state space; define the action space, which includes the migration sequence, migration batches, and migration time points;

[0070] Step R3: Based on the state space and action space, use the current strategy to calculate the traditional reward and collect trajectory data; the trajectory data includes the state, action, and reward sequence;

[0071] Step R4: Combine the trajectory data and calculate the traditional state advantage function through the traditional judgment network as the basis for the optimal decision;

[0072] Step R5: Calculate the loss function of the current strategy based on the traditional state advantage function, update the current strategy, and generate an updated strategy;

[0073] Step R6: Set the maximum number of iterations, repeat steps R2 to R5, continuously update the traditional evaluation network and policy network, and generate the optimal migration strategy.

[0074] The present invention and its embodiments are described above. Such description is not restrictive. What is shown in the accompanying drawings is only one of the embodiments of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in this field are inspired by it and do not depart from the purpose of the invention, they can creatively design structural methods and embodiments similar to the technical solution, which should all fall within the scope of protection of the present invention.

Claims

1. A multi-protocol, cross-platform network migration management system, comprising a data acquisition module, which collects network performance information and protocol fields to obtain network topology data; characterized in that: The system also includes a protocol identification module and a migration optimization module; The protocol identification module constructs a hyperspherical Lorentz graph neural network, uses the hyperspherical Lorentz graph neural network to analyze the protocol field, and generates a protocol identification result; The migration optimization module builds a dual-criticality strategy optimization algorithm, which analyzes network performance information, protocol identification results, and network topology data to generate the optimal migration strategy. The hypersphere Lorentz graph neural network is constructed through Lorentz space embedding, hypersphere distance learning and graph neural network; The process of generating the protocol identification result by the protocol identification module specifically includes the following steps: Step S1: construct a protocol graph, the protocol graph includes nodes; define the protocol field as a node of the protocol graph, and represent the characteristics of the protocol field as node characteristics; Step S2: embed the node features into the Lorentz space to ensure that the node features conform to the geometric constraints of the hypersurface space; generate the Lorentz embedding representation of each node; Step S3: Generate a rich protocol graph node representation based on the Lorentz embedding representation of each node; Step S4: updating the protocol graph according to the enriched protocol graph node representation and outputting the protocol recognition result; Step S3 specifically includes: introducing a hypersphere distance learning method, constructing a hypersphere-Lorentz centroid aggregation method, and performing weighted aggregation on the Lorentz embedding representation of each node using the hypersphere-Lorentz centroid aggregation method to generate a weighted aggregation result; using a Lorentz transform layer to perform nonlinear updating on the weighted aggregation result to generate a rich protocol graph node representation; The process of generating the optimal migration strategy by the migration optimization module specifically includes the following steps: Step B1: Initialize the current policy and critic network of the dual-criticism strategy optimization algorithm; Step B2: Combine the protocol identification results, network topology data, and network performance information to construct a state space; define the action space; Step B3: Based on the state space and action space, use the current strategy to calculate the traditional reward and post-decision reward and collect trajectory data; Step B4: Combine the trajectory data, calculate the state advantage function through the critical network, take the maximum value, and obtain the maximum advantage function; Step B5: Calculate the loss function of the current strategy based on the maximum advantage function and update the current strategy; Step B6: Set the maximum number of iterations and repeat steps B2 to B5 to generate the optimal migration strategy.

2. The multi-protocol, cross-platform network migration management system according to claim 1, characterized in that: The action space includes migration order, migration batch and migration time point.

3. The multi-protocol, cross-platform network migration management system according to claim 1, characterized in that: Trajectory data includes state, action, and reward sequences.

Images