A Data Node Adaptive Optimization Method Based on Causal Reasoning and Prototype Learning

Abstract

The present invention discloses a data node adaptive optimization method based on causal reasoning and prototype learning, including the steps of: generating a dynamic causal mapping network according to the real-time network state; extracting representative prototypes by clustering different data circulation data sets, and constructing a prototype library adapted to different network scenarios; binding the generation of the causal mapping network and the prototypes in the prototype library through a causal mapping-driven prototype symbiosis mechanism to achieve real-time interaction; dynamically adjusting the results of layout optimization through a self-learning feedback mechanism; this solution has significant performance advantages in a network environment with high load and large-scale data circulation, and can be widely applied to complex network environments requiring efficient and stable transmission.

Description

Technical Field

[0001] The present invention relates to the field of network data node layout optimization, and particularly to a data node adaptive optimization method based on causal reasoning and prototype learning. Background Art

[0002] With the rapid development of information technology, data circulation has become one of the important driving forces for promoting economic and social development. The rise of technologies such as big data, the Internet of Things, and artificial intelligence has led to a continuous increase in the demand for various data generation, transmission, and application. Data circulation nodes are key components in the entire data circulation network, and their layout directly affects the data transmission efficiency, processing performance, and the reliability and stability of the overall system. Therefore, optimizing the layout of data circulation nodes to improve data circulation efficiency has become the focus of current research. In a data circulation system, a reasonable layout of nodes can effectively reduce the time delay, bandwidth consumption, and network congestion problems during data transmission. At the same time, the security, privacy protection, and data integrity during data transmission also require the node layout to have a high degree of flexibility and adaptability. Therefore, how to use intelligent methods to optimize the node layout to adapt to a complex and dynamically changing network environment is a research topic of great practical significance.

[0003] Currently, the optimization methods for data circulation node layout mainly focus on the following categories: optimization methods based on static models, node layout optimization methods based on machine learning, and node layout methods based on distributed computing. Among them, the optimization methods based on static models assume that the topological structure of the data circulation network is fixed, and use traditional theories such as graph theory and network flow models to analyze the node layout optimization problem through mathematical modeling. Common methods include the minimum spanning tree, maximum flow minimum cut model, etc. These methods perform well in scenarios with relatively simple structures and less changes. With the development of machine learning technology, many studies have begun to attempt to use machine learning algorithms to optimize the node layout. The node layout optimization methods based on machine learning usually collect historical data, model the topological structure and traffic pattern of the network, and use algorithms such as supervised learning or reinforcement learning to optimize the node layout of data circulation. In addition, to cope with the complexity of large-scale distributed networks, some studies have proposed node layout optimization methods based on distributed computing and edge computing. These methods use edge nodes in the network to perform distributed computing and decision-making, aiming to improve the efficiency of data processing and transmission and reduce the computational burden on the central node.

[0004] Although existing optimization methods have achieved certain results in specific scenarios, there are still some significant deficiencies. First, static models lack flexibility. Optimization methods based on static models usually rely on assumptions about the network structure. However, in practical applications, data circulation networks are often in dynamic changes. Factors such as network topology, data traffic, and transmission requirements may all change. Static models are difficult to adapt to this complexity and dynamicity, resulting in limited optimization effects. Second, although machine learning-based methods have achieved good optimization effects in some specific scenarios, this method usually relies on a large amount of historical data and manual annotation. In some scenarios where data is scarce or the network changes frequently, the generalization ability of the model is insufficient, and it is prone to overfitting or unable to effectively adapt to the new environment. In addition, many existing methods do not fully consider the real-time requirements of data circulation networks. In the layout optimization of data circulation nodes, real-time is a crucial factor. Traditional optimization methods usually require long-term calculations and cannot respond to network changes in a timely manner, affecting the efficiency of the entire system. Finally, most existing optimization methods are based on correlation analysis and ignore the causal relationships between nodes and between data transmission paths. In practical applications, the optimization of node layout often involves complex causal relationships. For example, the adjustment of the layout of one node may affect the transmission efficiency of other nodes. Existing methods that fail to fully utilize causal reasoning are difficult to comprehensively consider these complex factors, resulting in unsatisfactory layout optimization effects. Summary of the Invention

[0005] Therefore, there is a need to provide a data node adaptive optimization method that combines causal reasoning and prototype learning, can more flexibly and accurately respond to dynamic network environments, reduce the dependence on a large amount of historical data, and handle complex causal relationships while maintaining real-time performance.

[0006] To achieve the above object, the inventor provides a data node adaptive optimization method based on causal reasoning and prototype learning, including the steps of:

[0007] S1, generating a dynamic causal mapping network according to the real-time network state;

[0008] S2, clustering different data circulation data sets, extracting representative prototypes, and constructing a prototype library suitable for different network scenarios;

[0009] S3, through the prototype symbiosis mechanism driven by causal mapping, binding the generation of the causal mapping network and the prototypes in the prototype library to achieve real-time interaction;

[0010] S4, dynamically adjusting the result of layout optimization through a self-learning feedback mechanism.

[0011] As a preferred mode of the present invention, step S1 further includes:

[0012] S101. Define the changes or adjustments in the network as causal events. At time t, the changes in the network represent a causal event , where i represents the i-th event, and the expression of the causal event is:

[0013] ;

[0014] Among them, represents the state of the nodes in the network at time t, represents the bandwidth usage of the network at time t, represents the network performance parameters at time, and F represents the network state change function;

[0015] If event occurs and causes event , then through the causal chain function define , and the expression is:

[0016] ;

[0017] Among them, represents the random noise term, represents the propagation delay of the event;

[0018] S102. At any time t, the dynamic causal mapping model automatically generates a graph-structured causal mapping network according to each change , and the expression is:

[0019] ;

[0020] Among them, represents generating causal event nodes in the network through the state space model, represents the similarity function, represents the causal relationship edge between causal event nodes, represents the graph structure generation network, and N represents a total of N causal events;

[0021] S103. At any time t, for the already generated causal mapping network , connect it with the new causal event through recursive reasoning, deeply analyze the interaction of various factors in the network and generate a dynamic causal mapping network , and the expression is:

[0022] ;

[0023] Among them, denotes a graph neural network, and k represents that there are k new causal events. denotes a Markov model, and e is the base of the natural logarithm. is the vector squared two-norm operation. denotes the time delay of event propagation.

[0024] As a preferred embodiment of the present invention, step S2 includes:

[0025] S201, obtaining the data traffic information in the network from T large-scale network traffic data sets, and the expression is:

[0026] ;

[0027] Among them, denotes different node states, and n ∈ 1, 2, 3,..., n;

[0028] Based on the clustering algorithm calculated by mutual information for generate W clustering centers , and the expression is:

[0029] ;

[0030] Among them, denotes the function of finding the minimum subscript, and denote two different Gaussian noise terms, and denote the corresponding weight functions respectively, and denote the conditional probability function, denotes the marginal probability distribution function, denotes the mutual information calculation, which is used to measure the dependence between parameters;

[0031] S202, analyzing the clustering results, and extracting the representative clustering centers as prototypes. For the W clustering centers , the extraction method of the prototype is expressed as:

[0032] ;

[0033] Among them, denotes that there are a total of H prototypes, denotes the set of all clustering center points, A denotes the initialized prototype vector, and e denotes the base of the natural logarithm;

[0034] As a preferred embodiment of the present invention, step S2 further includes the step:

[0035] S203, continuously collecting new network traffic data sets , and compare these new data with the prototypes in the existing prototype library . If the distance of a data point from the existing prototype exceeds the threshold, prototype update is performed. The expression is:

[0036] ;

[0037] Among them, represents the updated prototype, represents the clustering center with respect to the new network traffic dataset the mathematical expectation between, represents the learning rate parameter.

[0038] As a preferred embodiment of the present invention, step S3 includes the steps of:

[0039] S301, introduce an adaptive learning rate and the causal event feedback at the current time t, adjust the prototype parameters, and define the evolution of the updated prototype as a game process. The optimization goal is to minimize the error function of the current causal event. The expression is:

[0040] ;

[0041] Among them, represents the prototype after parameter adjustment, the loss function measures the degree of matching between the updated prototype and the causal network, the gradient descent function is used to adjust the loss;

[0042] S302, perform reverse optimization on the causal mapping network through a multi-level feedback structure. The expression is:

[0043] ;

[0044] Among them, represents the change in mutual information between the dynamic causal mapping network after a time delay and the prototype after parameter adjustment. I represents the mutual information comparison function;

[0045] S303, when the network environment changes, according to the dynamic causal mapping network , select the prototype that meets the current situation from the prototype after parameter adjustment to drive the layout optimization decision. The expression is:

[0046] ;

[0047] Among them, represents the prototype after parameter adjustment under the dynamic causal mapping network the time delay, represents the prototype after parameter adjustment under the dynamic causal mapping network the degree of congestion, means that each prototype in the prototype library is compared.

[0048] As a preferred embodiment of the present invention, step S4 includes the steps:

[0049] S401, after introducing the self-learning feedback mechanism, the objective function of layout optimization will be dynamically adjusted to adapt to the changing network environment. For each feedback, the weight parameters in the optimization formula are adjusted according to real-time data, and the expression is:

[0050]

[0051] Among them, and represent timely updating and dynamic adjustment of weights according to changes in the current network state, represents the prototype that conforms to the current situation under the dynamic causal mapping network the degree of congestion, represents the prototype that conforms to the current situation under the dynamic causal mapping network the time delay.

[0052] Different from the prior art, the beneficial effects achieved by the above technical solutions are:

[0053] (1) This method deeply analyzes the interaction behaviors, transmission paths, and data traffic changes of each node in the network through causal reasoning, identifies key causal factors, and can clarify causal relationships in node layout optimization by establishing a causal model, rather than relying solely on historical data or correlations. In this way, it can better predict the impact of different layout schemes on network performance, make more forward-looking and accurate decisions, and improve the overall efficiency of data circulation;

[0054] (2) By introducing the prototype learning method, this method can effectively cope with the situation of insufficient data and reduce the sensitivity of the model to environmental changes by constructing multiple prototypes to represent different network topologies and data traffic patterns; prototype learning can not only capture different types of typical patterns in the network, but also adapt to new scenarios and requirements by continuously updating prototypes, thereby enhancing the adaptability of the layout optimization model in a complex dynamic environment;

[0055] (3) This method combines causal reasoning with prototype learning. Causal reasoning provides guidance for prototype learning, helping to identify the most influential causal factors. By combining prototype learning, layout optimization is carried out in various complex scenarios to improve the applicability and effectiveness of the optimization strategy. Description of the Drawings

[0056] Figure 1 It is a framework diagram of the method described in the specific implementation manner. Specific Implementation Manner

[0057] To describe in detail the technical content, structural features, achieved objectives and effects of the technical solution, the following is described in detail in combination with specific embodiments and with reference to the drawings.

[0058] As Figure 1 shown, this embodiment provides a data node adaptive optimization method based on causal reasoning and prototype learning, including the steps:

[0059] S1. Generate a dynamic causal mapping network according to the real-time network state;

[0060] S2. By clustering different data circulation data sets, extract representative prototypes and construct a prototype library adapted to different network scenarios;

[0061] S3. Through the prototype symbiosis mechanism driven by causal mapping, bind the generation of the causal mapping network and the prototypes in the prototype library to achieve real-time interaction;

[0062] S4. Dynamically adjust the result of layout optimization through the self-learning feedback mechanism.

[0063] In step S1 of the above embodiment, a dynamic causal mapping network is proposed. Different from the traditional causal reasoning method that only performs single causal chain analysis, in this embodiment, each change in the network environment is regarded as a potential causal event. Instead of relying on a static causal graph for each layout optimization decision, a "causal mapping network" is automatically generated according to the real-time network state. Through multiple recursive inferences, this network dynamically captures the complex associations among factors such as nodes, traffic, bandwidth, and delay, forming a continuously updated dynamic causal mapping network;

[0064] In step S2 of the above embodiment, prototype learning clusters different data circulation data sets, extracts representative prototypes, and constructs a prototype library adapted to different network scenarios. The prototypes in the prototype library are used to describe and capture typical network topologies and data flow patterns, thereby reducing the dependence on large-scale historical data. By continuously updating and learning new prototype patterns, the system can dynamically adapt to changes in the network environment and improve the generalization ability of layout optimization. Even in scenarios with scarce data or rapid network changes, it can maintain a high optimization effect;

[0065] In step S3 of the above embodiment, through the prototype symbiosis mechanism driven by causal mapping, causal mapping and prototype generation are tightly bound to achieve real-time interaction between them. When the causal mapping network changes, it triggers the corresponding prototype layer to automatically generate and evolve; conversely, the generation of new prototypes will also inversely affect the causal mapping, further improving the causal relationship chain of the system. Through this symbiosis mechanism, the deep integration of causal reasoning and prototype learning is achieved, ensuring that the decision-making of layout optimization not only has a scientific basis in the causal chain but also has sufficient flexibility and foresight;

[0066] In step S4 of the above embodiment, the result of each layout optimization will be re-input through the self-learning feedback mechanism to form a closed-loop feedback. The prototype library structure is continuously updated according to the optimization result and the actual network performance, ultimately enhancing the adaptive ability and optimization effect of the system. Through this closed-loop, the self-learning mechanism can continuously improve the layout optimization scheme, enabling the network to always operate efficiently in a complex environment.

[0067] In the specific implementation process of the above embodiment, step S1 further includes:

[0068] S101, Define each change or adjustment in the network as a causal event. Assume that at a certain moment t, the changes in the network, such as an increase in node load, bandwidth fluctuation, etc., can be represented as an event , where i represents the i-th event, and the expression of the causal event is:

[0069] ;

[0070] Among them, represents the state of the nodes in the network at time t, such as load, number of connections, etc., represents the network bandwidth usage at time t, represents other network performance parameters such as network latency at time t, and F represents the network state change function, which is used to capture the comprehensive impact of these changes on network performance; further, if event occurs and causes event , then the causal chain function can be used to define , and the expression is:

[0071] ;

[0072] Among them, represents the random noise term, which is used to describe the influence of other unconsidered factors, represents the time delay of event propagation;

[0073] S102. At any moment t, the state of the network environment changes continuously. Traditional causal reasoning often analyzes based on a fixed causal chain, while the dynamic causal mapping model in this embodiment can automatically generate a graph-structured causal mapping network according to each change. , and the expression is:

[0074] ;

[0075] Among them, represents generating causal event nodes in the network through a state space model, represents a similarity function, represents the causal relationship edge between causal event nodes in the graph, represents a graph structure generation network, which generates a causal mapping network by associating causal event nodes and causal relationship edges. N represents that there are N causal events in total.

[0076] S103. At any moment t, for the already generated causal mapping network , it is associated with new causal events through recursive reasoning, deeply analyzes the interaction of various factors in the network, and generates a dynamic causal mapping network . This process can capture network state changes in real time and construct complex associations between causal events. The expression is:

[0077] ;

[0078] Among them, represents a graph neural network, k represents that there are k new causal events, represents a Markov model, e represents the natural base, represents a vector square two-norm operation, represents the time delay of event propagation.

[0079] In the specific implementation process of the above embodiment, step S2 further includes:

[0080] S201. Perform clustering analysis on network patterns with different topologies. First, obtain the data traffic information in the network from T large-scale network traffic data sets. The expression is:

[0081] ;

[0082] Among them, represents different node states;

[0083] Then, based on the clustering algorithm calculated by mutual information, generate W clustering centers , and the expression is:

[0084] ;

[0085] Among them, represents the function to find the subscript of the minimum value, and represent two different Gaussian noise terms, and represent the corresponding weight functions respectively, and represent the conditional probability function, represents the marginal probability distribution function, represents the calculation of mutual information, which is used to measure the dependence between parameters;

[0086] S202. Analyze the clustering results, and extract representative cluster centers as prototypes. The role of the prototypes is to describe different network topologies and traffic patterns. For W cluster centers , the prototype is extracted by the following expression:

[0087] ;

[0088] Among them, represents that there are a total of H prototypes, represents the set of all cluster center points, A is the initialized prototype vector, and e is the natural logarithm base, is the vector square two-norm operation.

[0089] S203. In addition, continuously collect new network traffic data sets , and compare these new data with the prototypes in the existing prototype library . If it is found that the network environment has changed significantly, that is, the distance of some data points from the existing prototypes exceeds the threshold, then the prototype is updated. The expression is:

[0090] ;

[0091] Among them, represents the updated prototype, represents the cluster center with respect to the new network traffic data set mathematical expectation, is the learning rate parameter.

[0092] In the specific implementation process of the above embodiment, step S3 includes the steps:

[0093] S301. After the updated prototype is generated, the system does not directly apply the updated prototype , but by introducing an adaptive learning rate and the causal event feedback at the current time t to adjust the prototype parameters. Assume that the evolution of the updated prototype is defined as a game process, and the optimization goal is to minimize the error function of the current causal event, and the expression is:

[0094] ;

[0095] Among them, represents the prototype after parameter adjustment, represents the updated version after gradient descent optimization, which represents the optimal prototype updated after the interaction of the causal mapping network prototype learning at the current time, represents that the loss function measures the matching degree between the prototype and the causal mapping network. When the loss is large, it means that the current prototype cannot well describe the relationship of the causal mapping network, represents that the gradient descent function is used to determine to adjust the loss, so as to generate a more accurate prototype, represents the causal mapping network generated at time t.

[0096] S302. The evolution of the prototype not only affects the layout optimization, but also performs reverse optimization on the causal mapping network through a multi-level feedback structure. Specifically, the evolution of the prototype will have feedback on some key causal relationship edges in, so as to correct the direction and weight of the causal relationship edges, as follows:

[0097] ;

[0098] Among them, represents the change in mutual information between the dynamic causal mapping network after time delay and the prototype after parameter adjustment. This change represents how the adjustment of the prototype affects the information transmission ability in the causal mapping network during the evolution of the causal mapping network. I represents the mutual information comparison function.

[0099] S303. Adopt prototype library-driven layout optimization. When the network environment changes, according to the dynamic causal mapping network , select the prototype that best suits the current situation from the prototype after parameter adjustment to drive the layout optimization decision. The optimization goal is to minimize the congestion and delay in the network, and the expression is:

[0100] ;

[0101] Among them, Prototype after parameter adjustment In the dynamic causal mapping network The time delay under Prototype after parameter adjustment In the dynamic causal mapping network The congestion degree under Indicates that each prototype in the prototype library is compared.

[0102] In the specific implementation process of the above embodiment, step S4 includes the steps:

[0103] S401. After introducing the self-learning feedback mechanism, the objective function of layout optimization Will be dynamically adjusted to adapt to the changing network environment. For each feedback, the system will adjust the weight parameters in the optimization formula according to the real-time data. The expression is:

[0104]

[0105] Among them, Is the prototype that best suits the current situation, And Indicates that the scientific department dynamically adjusts the weight according to the change of the current network state to update the layout strategy in a timely manner, Indicates the prototype that best suits the current situation In the dynamic causal mapping network The congestion degree under Indicates the prototype that best suits the current situation In the dynamic causal mapping network The time delay under.

[0106] To verify the effectiveness of the above embodiment, a public data set was used for verification. Specifically as follows: The Géant Network Traffic data set contains rich real network traffic data and is suitable for studying traffic patterns, node layout optimization and performance analysis in high-bandwidth and complex networks. This data set provides multi-dimensional traffic parameters, including transmission rate, delay, bandwidth utilization, etc., and is suitable for research such as network traffic modeling, congestion control and dynamic network optimization. It has important application value especially in large-scale academic and scientific research network environments.

[0107] As shown in Table 1, the experimental results show that this method performs the best in network performance optimization, especially in terms of improving throughput, reducing delay, reducing packet loss rate and jitter, and increasing bandwidth utilization, which are significantly better than other methods. Specifically, this method increases the throughput to 1300 Mbps, far exceeding 700 Mbps of the K-nearest neighbor algorithm and 510 Mbps of the naive Bayes, and significantly reduces the delay from the original 120 ms to 35 ms, showing excellent real-time performance.

[0108] Table 1: Experimental Results of Performance Comparison of Different Network Optimization Methods

[0109]

[0110] In terms of packet loss rate, this method reduces it to 0.2%, while the K-nearest neighbor algorithm and Naive Bayes only reduce it to 0.9% and 1.5% respectively, indicating its outstanding performance in data transmission reliability. In addition, this method is also particularly excellent in jitter control, reducing jitter from 30ms to 5ms, significantly improving the transmission stability. In terms of bandwidth utilization, this method also reaches 93%, far higher than other methods, showing efficient utilization of network resources. At the same time, this method also performs excellently in network congestion and path optimization, successfully controlling network congestion to a "low" level and achieving "efficient" path optimization, significantly improving the efficiency and reliability of data transmission. In contrast, the K-nearest neighbor algorithm performs moderately in most metrics, while the optimization effect of the Naive Bayes algorithm is poor and is more suitable for scenarios with low performance requirements. Generally speaking, this method demonstrates significant performance advantages in a network environment with high load and large-scale data circulation and is suitable for complex network environments that require efficient and stable transmission.

[0111] It should be noted that although the above embodiments have been described in this article, the patent protection scope of the present invention is not limited thereby. Therefore, based on the innovative concept of the present invention, any changes and modifications to the embodiments described in this article, or equivalent structural or equivalent process transformations made using the content of the specification and drawings of the present invention, and directly or indirectly applying the above technical solutions to other related technical fields, are all included in the patent protection scope of the present invention.

Claims

1. A data node adaptive optimization method based on causal reasoning and prototype learning, characterized in that: Includes steps: S1, generates a dynamic causal mapping network based on the real-time network status; S2, by clustering different data circulation datasets, extracting representative prototypes, and building a prototype library that adapts to different network scenarios; S3, through the prototype symbiosis mechanism driven by causal mapping, binds the causal mapping network and the prototype generation in the prototype library to achieve real-time interaction; S4, dynamically adjust the layout optimization results through a self-learning feedback mechanism; Step S1 also includes: S101, defines changes or adjustments in the network as causal events. At time t, the change in the network represents a causal event. , where i represents the i-th event, and the expression of the causal event is: ； in, represents the state of the nodes in the network at time t, Indicates the bandwidth usage of the network at time t, express The network performance parameters at each moment, F represents the network state change function; If the event Will cause events after , then through the causal chain function definition , the expression is: ； in, represents the random noise term, Indicates the delay of event propagation; S102, at any time t, the dynamic causal mapping model automatically generates a graph-structured causal mapping network based on each change , the expression is: ； in, It represents the causal event nodes in the network generated by the state space model. represents the similarity function, represents the causal relationship edge between causal event nodes, Represents a graph structure generating network, N represents a total of N causal events; S103, at any time t, for the generated causal mapping network , and recursively connect it to new causal events In-depth analysis of the interaction of various factors in the network and generation of dynamic causal mapping network , the expression is: ； in, represents a graph neural network, k represents a total of k new causal events, represents the Markov model, e is the natural base, is the vector squared norm operation, Indicates the delay of event propagation; Step S2 includes: S201, obtain the data flow information in the network from T large-scale network flow data sets, the expression is: ； in, Represents different node states, n∈1,2,3,…,n; Clustering algorithm based on mutual information calculation Generate W cluster centers , the expression is: ； in, It means finding the minimum subscript function. and represents two different Gaussian noise terms, and They represent the corresponding weight functions, and represents the conditional probability function, represents the marginal probability distribution function, represents the mutual information calculation, which is used to measure the dependence between parameters; S202, analyzing the clustering results, extracting representative cluster centers as prototypes, and ,prototype The extraction expression is: ； in, It means there are H prototypes in total. represents the set of all cluster center points, A represents the initialization prototype vector, and e represents the natural base; Step S2 also includes the steps of: S203, continue to collect new network circulation data sets , and compare these new data with the prototypes in the existing prototype library For comparison, if the distance between a data point and the existing prototype exceeds the threshold, the prototype is updated. The expression is: ； in, represents the updated prototype, Represents the cluster center Relative to the new network circulation dataset The mathematical expectation between Represents the learning rate parameter; Step S3 includes the steps of: S301, introducing adaptive learning rate And the causal event feedback at the current time t, adjust the prototype parameters, and update the prototype The evolution of is defined as a game process, and the optimization goal is to minimize the error function of the current causal event, expressed as: ； in, represents the prototype after parameter adjustment, It means that the loss function measures the degree to which the updated prototype matches the causal network. represents the gradient descent function used to adjust the loss; S302, reversely optimize the causal mapping network through a multi-level feedback structure, the expression is: ； in, Indicates that after Dynamic Causal Mapping Network after Time Delay Prototype with adjusted parameters The change of mutual information between them, I represents the mutual information contrast function; S303, when the network environment changes, the network is mapped according to the dynamic causal , from the prototype after parameter adjustment Select the prototype that suits your situation , to drive layout optimization decisions, the expression is: ； in, Represents the prototype after parameter adjustment In dynamic causal mapping networks The delay below, Represents the prototype after parameter adjustment In dynamic causal mapping networks The congestion level under Indicates that each prototype in the prototype library is compared.

2. The data node adaptive optimization method based on causal reasoning and prototype learning according to claim 1 is characterized in that: Step S4 comprises the steps of: S401, after the introduction of the self-learning feedback mechanism, the objective function of layout optimization It will be adjusted dynamically to adapt to the ever-changing network environment. For each feedback, the weight parameter in the optimization formula is adjusted according to the real-time data. The expression is: in, and Indicates that the weights are updated and adjusted dynamically in a timely manner according to the current network status changes. Represents a prototype that fits the current situation In dynamic causal mapping networks The congestion level under Represents a prototype that fits the current situation In dynamic causal mapping networks The next delay.

Images