Application method and system of intelligent adaptive routing algorithm in high-speed network communication

Abstract

The present invention relates to the field of communication technology, and discloses an application method of an intelligent adaptive routing algorithm in high-speed network communication, including: defining communication nodes of a network communication scenario; determining communication influencing factors of the network communication scenario, configuring factor sensors of communication nodes, dividing network communication data into link state data, flow data, and node load data, analyzing the link state of the network communication scenario, and identifying the node load of the network communication scenario; using the time series historical state data corresponding to the network communication scenario, establishing a network state analysis model for the network communication scenario, and using the network state analysis model to analyze the network potential state of the network communication scenario; analyzing the coordination coefficient of the communication node under the sharing mechanism, using the Pareto routing algorithm to analyze the node dynamic parameters of the communication node, and performing communication optimization of the network communication scenario based on the node dynamic parameters. The present invention can improve the stability of network communication.

Description

Technical Field

[0001] The invention relates to an application method and system of an intelligent adaptive routing algorithm in high-speed network communication, belonging to the technical field of communication. Background Art

[0002] The application of intelligent adaptive routing algorithms in high-speed network communications refers to the use of advanced computing technology and algorithms to enable the network routing system to automatically adjust the transmission path of data packets according to changes in network status, so as to optimize network performance, improve data transmission efficiency, reduce latency, balance network load, and enhance network reliability and robustness.

[0003] The application of traditional intelligent adaptive routing algorithms in high-speed network communications usually relies on preset rules and heuristic algorithms, and dynamically adjusts routing decisions by monitoring network parameters such as latency, bandwidth, and packet loss rate. It lacks fine-grained analysis of network communication scenarios and cannot effectively predict and adapt to rapid changes in network status, which may lead to poor network performance. Summary of the invention

[0004] The present invention provides an application method and system of an intelligent adaptive routing algorithm in high-speed network communication, the main purpose of which is to improve the stability of network communication.

[0005] To achieve the above object, the present invention provides an application method of an intelligent adaptive routing algorithm in high-speed network communication, comprising:

[0006] Acquire a network communication scenario of high-speed network communication and its scenario communication requirements, identify a communication structure of the network communication scenario, and define a communication node of the network communication scenario based on the communication structure;

[0007] Based on the communication requirements of the scenario, determining a communication impact factor of the network communication scenario, configuring a factor sensor of the communication node according to the communication impact factor, and collecting network communication data of the network communication scenario based on the factor sensor;

[0008] Dividing the network communication data into link status data, flow data, and node load data, analyzing the link status of the network communication scenario through the link status data, determining the flow pattern of the network communication scenario based on the flow data, and identifying the node load of the network communication scenario according to the node load data;

[0009] Using the time series historical status data corresponding to the network communication scenario, a network status analysis model of the network communication scenario is established, and based on the link status, the traffic pattern and the node load, the network potential status of the network communication scenario is analyzed using the network status analysis model;

[0010] Establish a sharing mechanism for the communication nodes, analyze the coordination coefficient of the communication nodes under the sharing mechanism, and when the coordination coefficient meets the preset coordination threshold, analyze the node dynamic parameters of the communication nodes according to the potential state of the network and the sharing mechanism using a preset Pareto routing algorithm, and perform communication optimization of the network communication scenario based on the node dynamic parameters.

[0011] Optionally, the identifying the communication structure of the network communication scenario includes:

[0012] Determine the network communication scope of the network communication scenario;

[0013] Marking the communication entity within the network communication range;

[0014] analyzing data flows of the communication entities;

[0015] Based on the data flow, construct a communication flow chart of the communication entity;

[0016] The communication structure of the network communication scenario is determined through the communication flow chart.

[0017] Optionally, defining the communication node of the network communication scenario based on the communication structure includes:

[0018] Determining an initial communication node of the network communication scenario according to the communication structure;

[0019] Defining a node role of the initial communication node;

[0020] Marking the functional characteristics of the initial communication node through the node role;

[0021] Based on the communication structure, defining a node association degree of the initial communication node;

[0022] Calculating the necessary coefficient of the initial communication node in the network communication scenario according to the functional characteristics and the node association degree;

[0023] The communication nodes in the initial communication nodes are screened by using the necessary coefficients.

[0024] Optionally, the calculating, according to the functional characteristics and the node association degree, a necessary coefficient of the initial communication node in the network communication scenario includes:

[0025] According to the functional characteristics and the node association degree, define the node reliability, node performance, node security level and node scalability of the initial communication node in the network communication scenario;

[0026] Respectively define the node reliability weight, node performance weight, node security level weight and node scalability weight of the node reliability, node performance, node security level and node scalability;

[0027] In combination with the node reliability, the node performance, the node security level, the node scalability, the node reliability weight, the node performance weight, the node security level weight, and the node scalability weight, the necessary coefficient of the initial communication node in the network communication scenario is calculated using the following formula:

[0028]

[0029] in, represents the necessary coefficient for network communication scenarios, represents the node reliability, The node reliability weight represents the node reliability, The nonlinear weight index representing the node reliability, Indicates node performance, The node performance weight representing the node performance, A nonlinear weight index representing node performance, Indicates the node security level, The node safety level weight representing the node safety level, A nonlinear weight index representing the node safety level, Indicates node scalability, The node scalability weight representing the node scalability, A non-linear weight index representing the scalability of a node.

[0030] Optionally, configuring the factor sensor of the communication node according to the communication impact factor includes:

[0031] Analyzing the impact value of the communication impact factor on the communication node;

[0032] Defining the factor data to be collected of the communication node according to the influence value;

[0033] Identifying factor data features of the factor data to be collected;

[0034] Based on the factor data characteristics, defining a factor sensor to be configured of the communication node;

[0035] Analyzing the communication node characteristics of the communication node, and determining the sensor topology structure of the factor sensor to be configured according to the communication node characteristics;

[0036] Calculating node monitoring blind spots of the sensor topology for the communication nodes;

[0037] When the node monitoring blind spot meets the preset node monitoring threshold, the factor sensor to be configured is used as the factor sensor of the communication node.

[0038] Optionally, the calculating the node monitoring blind spot of the communication node of the sensor topology structure includes:

[0039] defining a node detection area of ​​the communication node;

[0040] Mark the sensor monitoring area, sensor quantity and sensor overlapping area of ​​the factor sensor to be configured corresponding to the sensor topology structure;

[0041] According to the node detection area, the sensor monitoring area, the number of sensors and the sensor overlapping area, the node monitoring blind spot area of ​​the sensor topology for the communication node is calculated using the following formula:

[0042]

[0043] in, represents the node monitoring blind spot area of ​​the communication node, represents the node detection area, Represents the sensor topology The failure probability of the sensor to be configured, Represents the sensor topology The sensor monitoring area of ​​the factor sensor to be configured, Represents the sensor topology The sensor overlap area of ​​the factor sensors to be configured, Indicates the number of sensors, Represents the probability product of the sensor of the configuration factor working normally.

[0044] Optionally, analyzing the link status of the network communication scenario through the link status data includes:

[0045] Defining link status indicators of the network communication scenario;

[0046] Based on the link status indicator and the link status data, analyzing the link bandwidth utilization, link delay and link packet loss rate of the network communication scenario;

[0047] Determining the link abnormality mode of the network communication scenario through the link bandwidth utilization, link delay and link packet loss rate;

[0048] Mapping the link abnormality mode with a network event in a preset network event library to obtain a mapped network event;

[0049] Analyzing the link abnormality pattern and the link status relationship of the mapped network event;

[0050] Based on the link status relationship, the link status of the network communication scenario is analyzed.

[0051] Optionally, the using the time series historical status data corresponding to the network communication scenario to establish a network status analysis model for the network communication scenario includes:

[0052] Analyze the network status change characteristics of the network communication scenario;

[0053] Defining a sequential network architecture of the network communication scenario according to the network state change characteristics;

[0054] Extracting historical link status features, historical traffic pattern features, and historical node load features of the time series historical status data;

[0055] Based on the historical link state characteristics, historical traffic pattern characteristics, and historical node load characteristics, the timing network architecture is trained to obtain a training network state analysis model;

[0056] Calculating a generalization coefficient of the training network state analysis model, and optimizing training parameters of the training network state analysis model based on the generalization coefficient to obtain optimized training parameters;

[0057] Based on the optimized training parameters, calculating the model performance of the training network state analysis model;

[0058] When the model performance meets the preset model performance threshold, the trained network status analysis model is used as the network status analysis model of the network communication scenario.

[0059] Optionally, analyzing the node dynamic parameters of the communication node using a preset Pareto routing algorithm according to the network potential state and the sharing mechanism includes:

[0060] Defining communication optimization indicators of the communication node corresponding to the network communication scenario;

[0061] Defining routing algorithm parameters of the Pareto routing algorithm according to the communication optimization index;

[0062] Defining a candidate routing set for the network communication scenario;

[0063] Calculating the response coefficient of the candidate routing set using the Pareto routing algorithm according to the potential state of the network, the sharing mechanism and the routing algorithm parameters;

[0064] Based on the response coefficient, determining a target candidate route for the network communication scenario;

[0065] According to the target candidate route, a node dynamic parameter of the communication node is defined.

[0066] In order to solve the above problems, the present invention also provides an application system of an intelligent adaptive routing algorithm in high-speed network communication, the system comprising:

[0067] A communication node definition module, used to obtain a network communication scenario of high-speed network communication and its scenario communication requirements, identify a communication structure of the network communication scenario, and define a communication node of the network communication scenario based on the communication structure;

[0068] A communication data acquisition module, configured to determine a communication impact factor of the network communication scenario based on the communication requirements of the scenario, configure a factor sensor of the communication node according to the communication impact factor, and collect network communication data of the network communication scenario based on the factor sensor;

[0069] A network communication analysis module, used to divide the network communication data into link status data, flow data and node load data, analyze the link status of the network communication scenario through the link status data, determine the flow pattern of the network communication scenario based on the flow data, and identify the node load of the network communication scenario according to the node load data;

[0070] A network potential state determination module, used to establish a network state analysis model for the network communication scenario by using the time series historical state data corresponding to the network communication scenario, and to analyze the network potential state of the network communication scenario by using the network state analysis model based on the link state, the traffic pattern and the node load;

[0071] A scenario communication optimization module is used to establish a sharing mechanism for the communication nodes, analyze the coordination coefficient of the communication nodes under the sharing mechanism, and when the coordination coefficient meets a preset coordination threshold, analyze the node dynamic parameters of the communication nodes using a preset Pareto routing algorithm according to the network potential state and the sharing mechanism, and perform communication optimization of the network communication scenario based on the node dynamic parameters.

[0072] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0073] at least one processor; and,

[0074] a memory communicatively connected to the at least one processor; wherein,

[0075] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to implement the above-mentioned application method of the intelligent adaptive routing algorithm in high-speed network communication.

[0076] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the application method of the above-mentioned intelligent adaptive routing algorithm in high-speed network communication.

[0077] Compared with the problems described in the background technology, firstly, this method can accurately identify the communication structure and communication nodes of the network communication scenario, ensuring the pertinence and efficiency of the network configuration. The communication influencing factors determined based on the scene communication requirements make the configuration of factor sensors more reasonable, so that the collected network communication data is more accurate and comprehensive. This data-driven management method provides a solid foundation for real-time monitoring and prediction of network status. Secondly, through the comprehensive analysis of link status, traffic patterns and node loads, the network status analysis model can effectively reveal the potential status of the network and provide forward-looking decision support for network administrators. This analysis helps to discover and prevent network performance bottlenecks and failure risks in advance. and service quality degradation, significantly improving the stability and reliability of the network. In addition, a sharing mechanism for communication nodes is established and the synergy coefficient is analyzed, which promotes the optimal allocation and efficient utilization of network resources. When the synergy coefficient meets the preset threshold, the Pareto routing algorithm is used to analyze the node dynamic parameters, further optimizing the network communication path and improving the overall performance of the network. Finally, the communication optimization based on the node dynamic parameters not only improves the efficiency of network communication, but also reduces the network operating costs and enhances user satisfaction. This systematic optimization method ensures the flexibility and scalability of the network in response to high-speed communication needs, and lays a solid foundation for the long-term healthy development of network communication. Therefore, the present invention can improve the stability of the network. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 A schematic diagram of a flow chart of a method for applying an intelligent adaptive routing algorithm in high-speed network communication provided by an embodiment of the present invention;

[0079] Figure 2 A functional module diagram of an application system of an intelligent adaptive routing algorithm in high-speed network communication provided by an embodiment of the present invention;

[0080] Figure 3A schematic diagram of the structure of an electronic device of an application system of an intelligent adaptive routing algorithm in high-speed network communication provided by an embodiment of the present invention;

[0081] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0082] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0083] The embodiment of the present application provides an application method of an intelligent adaptive routing algorithm in high-speed network communication. The execution subject of the application method of the intelligent adaptive routing algorithm in high-speed network communication includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the application method of the intelligent adaptive routing algorithm in high-speed network communication can be executed by software or hardware installed in a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0084] Embodiment 1:

[0085] Reference Figure 1 FIG. 1 is a flow chart of an application method of an intelligent adaptive routing algorithm in high-speed network communication provided by an embodiment of the present invention. In this embodiment, the application method of the intelligent adaptive routing algorithm in high-speed network communication includes:

[0086] S1. Obtain a network communication scenario of high-speed network communication and its scenario communication requirements, identify a communication structure of the network communication scenario, and define a communication node of the network communication scenario based on the communication structure.

[0087] It should be explained that the network communication scenario refers to a specific environment or application background, such as personal communication, enterprise network, remote work and other environments, and the scenario communication requirement refers to a series of conditions and service quality requirements that the network communication system must meet in this specific scenario.

[0088] The present invention identifies the communication structure of the network communication scenario and can systematically identify and construct a communication structure that meets the requirements of a specific network communication scenario.

[0089] In detail, the identifying the communication structure of the network communication scenario includes:

[0090] Determine the network communication scope of the network communication scenario;

[0091] Marking the communication entities within the network communication range;

[0092] analyzing data flows of the communication entities;

[0093] Based on the data flow, construct a communication flow chart of the communication entity;

[0094] The communication structure of the network communication scenario is determined through the communication flow chart.

[0095] Among them, the network communication scope refers to the specific area or boundary where network communication occurs, the communication entity refers to the individual or component participating in information transmission within the network communication scope, the data flow refers to the process and path of information transmission between network communication entities, the communication flow chart refers to a visual representation of the path and steps of data flow between communication entities, and the communication structure refers to the overall layout and organization of communication entities and data flow in the network communication scenario.

[0096] Optionally, the communication flow chart of the communication entity constructed based on the data flow can be drawn by 3Dmax software.

[0097] Based on the communication structure, the communication nodes that define the network communication scenario ensure that they can effectively support the communication needs of the entire network.

[0098] In detail, the communication node of the network communication scenario is defined based on the communication structure, including:

[0099] Determining an initial communication node of the network communication scenario according to the communication structure;

[0100] Defining a node role of the initial communication node;

[0101] Marking the functional characteristics of the initial communication node through the node role;

[0102] Based on the communication structure, defining a node association degree of the initial communication node;

[0103] Calculating the necessary coefficient of the initial communication node in the network communication scenario according to the functional characteristics and the node association degree;

[0104] The communication nodes in the initial communication nodes are screened by using the necessary coefficients.

[0105] Among them, the initial communication node refers to any device or system that participates in information transmission in network communication in a network communication scenario, the node role refers to the specific functions and responsibilities undertaken by the communication node in network communication, the functional characteristics refer to the specific capabilities or attributes possessed by the communication node, the node association refers to the connection strength between a communication node and other nodes, the necessary coefficient refers to the coefficient used to represent the importance of the initial communication node in a specific network communication scenario, and the communication node refers to a relatively important device or system that participates in information transmission in network communication.

[0106] Further, the calculating, according to the functional characteristics and the node association degree, a necessary coefficient of the initial communication node in the network communication scenario includes:

[0107] According to the functional characteristics and the node association degree, define the node reliability, node performance, node security level and node scalability of the initial communication node in the network communication scenario;

[0108] Respectively define the node reliability weight, node performance weight, node security level weight and node scalability weight of the node reliability, node performance, node security level and node scalability;

[0109] In combination with the node reliability, the node performance, the node security level, the node scalability, the node reliability weight, the node performance weight, the node security level weight, and the node scalability weight, the necessary coefficient of the initial communication node in the network communication scenario is calculated using the following formula:

[0110]

[0111] in, represents the necessary coefficient for network communication scenarios, represents the node reliability, The node reliability weight represents the node reliability, The nonlinear weight index representing the node reliability, Indicates node performance, The node performance weight representing the node performance, A nonlinear weight index representing node performance, Indicates the node security level, The node safety level weight representing the node safety level, A nonlinear weight index representing the node safety level, Indicates node scalability, The node scalability weight representing the node scalability, A non-linear weight index representing the scalability of a node.

[0112] Among them, the node reliability refers to the ability of the initial communication node to maintain normal operation within the specified time, the node performance refers to the processing capacity of the initial communication node, the node security level refers to the security protection capability of the initial communication node, the node scalability refers to the ability of the initial communication node to expand its capacity or performance in the future, the node reliability weight refers to the weight of the node reliability, the node performance weight refers to the importance of the node performance in the overall evaluation, the node security level weight refers to the importance of the node security level in the overall evaluation, the node scalability weight refers to the importance of the node scalability in the overall evaluation, and the nonlinear weight index refers to a parameter used to emphasize the importance of certain factors (node ​​reliability, node performance, node security level and node scalability) under specific conditions.

[0113] S2. Based on the communication requirements of the scenario, determine the communication impact factor of the network communication scenario, configure the factor sensor of the communication node according to the communication impact factor, and collect network communication data of the network communication scenario based on the factor sensor.

[0114] It should be explained that the communication influencing factors refer to factors that affect the communication quality in the network communication scenario, such as signal strength, network congestion and other factors.

[0115] The present invention configures the factor sensor of the communication node according to the communication influencing factor to collect the communication data of the network communication scenario in real time, thereby improving the authenticity of the data.

[0116] In detail, configuring the factor sensor of the communication node according to the communication impact factor includes:

[0117] Analyzing the impact value of the communication impact factor on the communication node;

[0118] Defining the factor data to be collected of the communication node according to the influence value;

[0119] Identifying factor data features of the factor data to be collected;

[0120] Based on the factor data characteristics, defining a factor sensor to be configured of the communication node;

[0121] Analyzing the communication node characteristics of the communication node, and determining the sensor topology structure of the factor sensor to be configured according to the communication node characteristics;

[0122] Calculating node monitoring blind spots of the sensor topology for the communication nodes;

[0123] When the node monitoring blind spot meets the preset node monitoring threshold, the factor sensor to be configured is used as the factor sensor of the communication node.

[0124] Among them, the impact value refers to the specific impact of the communication impact factor on the performance of a specific communication node, the factor data to be collected refers to the data that needs to be collected from the communication node or related equipment in order to evaluate and monitor the performance of the communication node, the factor data characteristics refer to the basic attributes and characteristics of the factor data to be collected, such as the type, range, accuracy, collection frequency, etc. of the data, the factor sensor to be configured refers to the sensor or monitoring equipment planned to be deployed in order to collect specific factor data, the communication node characteristics refer to the technical attributes and operating characteristics of the communication node, such as the hardware configuration, software version, network location, functional role and other characteristics of the node, the sensor topology structure refers to the layout and connection method of the factor sensor in the communication node or network, the node monitoring blind spot refers to the area or performance indicator that is not covered in the communication node monitoring system, the node monitoring threshold refers to the pre-set monitoring standard used to judge the effectiveness of the monitoring system, and the factor sensor refers to the sensor or monitoring equipment actually deployed on the communication node for collecting specific factor data.

[0125] Further, the calculating of the node monitoring blind spot of the communication node by the sensor topology structure includes:

[0126] defining a node detection area of ​​the communication node;

[0127] Mark the sensor monitoring area, sensor quantity and sensor overlapping area of ​​the factor sensor to be configured corresponding to the sensor topology structure;

[0128] According to the node detection area, the sensor monitoring area, the number of sensors and the sensor overlapping area, the node monitoring blind spot area of ​​the sensor topology for the communication node is calculated using the following formula:

[0129]

[0130] in, represents the node monitoring blind spot area of ​​the communication node, represents the node detection area, Represents the sensor topology The failure probability of the sensor to be configured, Represents the sensor topology The sensor monitoring area of ​​the factor sensor to be configured, Represents the sensor topology The sensor overlap area of ​​the factor sensors to be configured, Indicates the number of sensors, Represents the probability product of the sensor of the configuration factor working normally.

[0131] Among them, the node detection area refers to the total area that the communication node needs to be monitored, the sensor monitoring area refers to the monitoring area that a single sensor can cover, the number of sensors refers to the total number of sensors deployed in a specific sensor topology, the sensor overlap area refers to the area where two or more sensor monitoring areas intersect, and the failure probability refers to the probability of a single sensor failing during the monitoring process.

[0132] It should be explained that the network communication data refers to a data set involved in network communication in a network communication scenario.

[0133] S3. Divide the network communication data into link status data, traffic data and node load data, analyze the link status of the network communication scenario through the link status data, determine the traffic pattern of the network communication scenario based on the traffic data, and identify the node load of the network communication scenario according to the node load data.

[0134] It should be explained that the link status data refers to the current status information of each link in the network (i.e., the direct connection between two network nodes), the traffic data refers to the amount, type and characteristics of data transmitted in the network, and the node load data refers to the resource usage of a single network node (such as a server, router or switch).

[0135] The present invention can effectively analyze the link status in the network communication scenario by analyzing the link status data, timely discover and solve potential problems, and ensure the stability and efficiency of the network.

[0136] In detail, analyzing the link status of the network communication scenario through the link status data includes:

[0137] Defining link status indicators of the network communication scenario;

[0138] Based on the link status indicator and the link status data, analyzing the link bandwidth utilization, link delay and link packet loss rate of the network communication scenario;

[0139] Determining the link abnormality mode of the network communication scenario through the link bandwidth utilization, link delay and link packet loss rate;

[0140] Mapping the link abnormality mode with a network event in a preset network event library to obtain a mapped network event;

[0141] Analyzing the link status relationship between the link abnormality mode and the mapped network event;

[0142] Based on the link status relationship, the link status of the network communication scenario is analyzed.

[0143] Among them, the link status indicator refers to a set of quantitative parameters used to measure the performance of network links, including parameters such as link bandwidth utilization, link delay, link packet loss rate, link error rate, link availability, etc. The link bandwidth utilization refers to the ratio of the actually used link bandwidth to the total link bandwidth within a certain period of time, the link delay refers to the time required for a data packet to be transmitted from one network node to another network node, the link packet loss rate refers to the ratio of the number of data packets lost on the link to the total number of transmitted data packets within a certain period of time, the link abnormality pattern refers to the pattern of abnormal behavior or performance degradation that appears in the link status data, the mapped network event refers to associating the link abnormality pattern with known network events to identify the possible causes of these abnormalities, the link status relationship refers to the correlation between the link abnormality pattern and the mapped network event, and the link status refers to the performance and operating status of the network link at a specific point in time.

[0144] Optionally, the analyzing of the link abnormality pattern and the link status relationship of the mapped network event can be analyzed by components such as Gephi and Cytoscape.

[0145] The present invention determines the traffic pattern of the network communication scenario based on the traffic data, and can determine the traffic state of the network communication scenario, and further provide a basis for the network communication state analysis. The traffic pattern refers to a description of the flow mode of data in the network. In detail, the flow mode can be identified by a preset traffic pattern library. The traffic pattern library contains historical traffic patterns of network communication scenarios.

[0146] Optionally, the present invention can systematically identify the node load in the network communication scenario based on the node load data, and provide a basis for network management and optimization. The node load refers to the workload or number of tasks processed by a specific node in the network system.

[0147] S4. Using the time-series historical status data corresponding to the network communication scenario, a network status analysis model of the network communication scenario is established; based on the link status, the traffic pattern, and the node load, the network potential status of the network communication scenario is analyzed using the network status analysis model.

[0148] The present invention utilizes the time-series historical status data corresponding to the network communication scenario to establish a network status analysis model of the network communication scenario. An effective network status analysis model can be established for monitoring, analyzing and predicting the status of the network communication scenario, thereby improving the efficiency and quality of network management.

[0149] In detail, the use of the time series historical status data corresponding to the network communication scenario to establish a network status analysis model for the network communication scenario includes:

[0150] Analyze the network status change characteristics of the network communication scenario;

[0151] Defining a sequential network architecture of the network communication scenario according to the network state change characteristics;

[0152] Extracting historical link status features, historical traffic pattern features, and historical node load features of the time series historical status data;

[0153] Based on the historical link state characteristics, historical traffic pattern characteristics, and historical node load characteristics, the timing network architecture is trained to obtain a training network state analysis model;

[0154] Calculating a generalization coefficient of the training network state analysis model, and optimizing training parameters of the training network state analysis model based on the generalization coefficient to obtain optimized training parameters;

[0155] Based on the optimized training parameters, calculating the model performance of the training network state analysis model;

[0156] When the model performance meets the preset model performance threshold, the trained network status analysis model is used as the network status analysis model of the network communication scenario.

[0157] Among them, the network state change characteristics refer to the unique attributes and patterns of network state changes over time in network communication scenarios. The time series network architecture refers to the network structure defined according to the network state change characteristics, which can reflect the dynamic characteristics of the network evolution over time. The historical link state characteristics refer to link performance indicators extracted from historical state data, such as bandwidth utilization, delay, packet loss rate and other characteristics. The historical traffic pattern characteristics refer to network traffic behavior patterns extracted from historical data, such as traffic size, direction, periodicity and other characteristics. The historical node load characteristics refer to node resource usage extracted from historical data, such as CPU usage, memory usage and other characteristics. The training network The state analysis model refers to a model trained by a machine learning algorithm based on historical feature data, and is used to predict and analyze network states. The generalization coefficient refers to the model's performance ability on unknown data, which is usually evaluated through cross-validation and other methods. The optimized training parameters refer to the parameters in the model training process adjusted according to the generalization coefficient, such as learning rate, batch size, network structure and other parameters. The model performance refers to the performance of the trained model on a specific task. The model performance threshold refers to a pre-set model performance standard, which the model must meet or exceed to be considered valid. The network state analysis model refers to a model that has been trained and optimized to accurately analyze and predict network states.

[0158] Optionally, the historical link state features, historical traffic pattern features and historical node load features of the time-series historical state data may be extracted by a convolutional neural network (CNN).

[0159] The present invention uses the network state analysis model to analyze the potential state of the network communication scenario based on the link state, the traffic pattern and the node load, and can use the network state analysis model to effectively analyze the potential state of the network communication scenario, thereby providing decision support for network management and optimization. Wherein, the network potential state refers to the operating state that the network may appear in the current or future period of time.

[0160] S5. Establish a sharing mechanism for the communication nodes, analyze the coordination coefficient of the communication nodes under the sharing mechanism, and when the coordination coefficient meets the preset coordination threshold, analyze the node dynamic parameters of the communication nodes according to the potential state of the network and the sharing mechanism using a preset Pareto routing algorithm, and perform communication optimization of the network communication scenario based on the node dynamic parameters.

[0161] The present invention can establish an efficient, stable and secure communication node sharing mechanism by establishing the communication node sharing mechanism, thereby improving the utilization efficiency and service quality of network resources. Wherein, the sharing mechanism refers to the rules that allow multiple nodes in the network to effectively share resources.

[0162] It should be explained that the synergy coefficient refers to a quantitative indicator used to measure the strength of the synergy effect generated by the interaction of different communication nodes when sharing resources. In detail, the synergy coefficient is usually calculated by comparing the performance indicators before and after the nodes share resources, such as network throughput, delay, fault recovery time, etc. The synergy threshold is a standard or limit preset in the sharing mechanism to determine whether the synergy effect is strong enough to achieve the expected network performance or efficiency goals. For example, if the synergy threshold is set to a 10% increase in network throughput, then the synergy effect is considered to have been achieved only when the network throughput is increased by at least 10% after sharing resources.

[0163] The present invention uses a preset Pareto routing algorithm to analyze the node dynamic parameters of the communication nodes according to the potential state of the network and the sharing mechanism, which helps to achieve efficient and stable communication under the network sharing mechanism.

[0164] In detail, the analyzing the node dynamic parameters of the communication node using a preset Pareto routing algorithm according to the potential state of the network and the sharing mechanism includes:

[0165] Defining communication optimization indicators of the communication node corresponding to the network communication scenario;

[0166] Defining routing algorithm parameters of the Pareto routing algorithm according to the communication optimization index;

[0167] Defining a candidate routing set for the network communication scenario;

[0168] Calculating the response coefficient of the candidate routing set using the Pareto routing algorithm according to the potential state of the network, the sharing mechanism and the routing algorithm parameters;

[0169] Based on the response coefficient, determining a target candidate route for the network communication scenario;

[0170] According to the target candidate route, a node dynamic parameter of the communication node is defined.

[0171] The communication optimization index refers to a series of standards used to measure the performance of network communication scenarios, which reflect the quality, efficiency and other key performance indicators of network services. The routing algorithm parameters refer to a set of variables used to configure and adjust the routing algorithm. The candidate route set refers to a set of all routing paths that a data packet may take from a source node to a destination node in a network communication scenario. The response coefficient refers to an indicator used to quantify the degree of response of a candidate route to the communication optimization index. The target candidate route refers to the optimal or most appropriate routing path selected from the candidate route set based on the response coefficient and other considerations. The node dynamic parameters refer to parameters that describe the changes of communication nodes over time during operation, such as network resources, storage cache clearing time and other parameters.

[0172] Optionally, the response coefficient of the candidate route set is usually calculated by comparing the performance of the candidate routes on the communication optimization index.

[0173] Finally, the present invention performs communication optimization of the network communication scenario based on the node dynamic parameters to achieve efficient communication in the network communication scenario.

[0174] Compared with the problems described in the background technology, firstly, this method can accurately identify the communication structure and communication nodes of the network communication scenario, ensuring the pertinence and efficiency of the network configuration. The communication influencing factors determined based on the scene communication requirements make the configuration of factor sensors more reasonable, so that the collected network communication data is more accurate and comprehensive. This data-driven management method provides a solid foundation for real-time monitoring and prediction of network status. Secondly, through the comprehensive analysis of link status, traffic patterns and node loads, the network status analysis model can effectively reveal the potential status of the network and provide forward-looking decision support for network administrators. This analysis helps to discover and prevent network performance bottlenecks and failure risks in advance. and service quality degradation, significantly improving the stability and reliability of the network. In addition, a sharing mechanism for communication nodes is established and the synergy coefficient is analyzed, which promotes the optimal allocation and efficient utilization of network resources. When the synergy coefficient meets the preset threshold, the Pareto routing algorithm is used to analyze the node dynamic parameters, further optimizing the network communication path and improving the overall performance of the network. Finally, the communication optimization based on the node dynamic parameters not only improves the efficiency of network communication, but also reduces the network operating costs and enhances user satisfaction. This systematic optimization method ensures the flexibility and scalability of the network in response to high-speed communication needs, and lays a solid foundation for the long-term healthy development of network communication. Therefore, the present invention can improve the stability of the network.

[0175] Embodiment 2:

[0176] like Figure 2, which is a functional module diagram of an application system of an intelligent adaptive routing algorithm in high-speed network communication provided by an embodiment of the present invention.

[0177] The application system 200 of the intelligent adaptive routing algorithm in high-speed network communication of the present invention can be installed in an electronic device. According to the functions implemented, the application system 200 of the intelligent adaptive routing algorithm in high-speed network communication can include a communication node definition module 201, a communication data acquisition module 202, a network communication analysis module 203, a network potential state determination module 204 and a scene communication optimization module 205. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0178] In this embodiment, the functions of each module / unit are as follows:

[0179] The communication node definition module 201 is used to obtain a network communication scenario of high-speed network communication and its scenario communication requirements, identify a communication structure of the network communication scenario, and define a communication node of the network communication scenario based on the communication structure;

[0180] The communication data collection module 202 is used to determine the communication impact factor of the network communication scenario based on the communication demand of the scenario, configure the factor sensor of the communication node according to the communication impact factor, and collect the network communication data of the network communication scenario based on the factor sensor;

[0181] The network communication analysis module 203 is used to divide the network communication data into link status data, flow data and node load data, analyze the link status of the network communication scenario through the link status data, determine the flow pattern of the network communication scenario based on the flow data, and identify the node load of the network communication scenario according to the node load data;

[0182] The network potential state determination module 204 is used to establish a network state analysis model for the network communication scenario by using the time series historical state data corresponding to the network communication scenario, and analyze the network potential state of the network communication scenario by using the network state analysis model based on the link state, the traffic pattern and the node load;

[0183] The scenario communication optimization module 205 is used to establish a sharing mechanism for the communication nodes, analyze the coordination coefficient of the communication nodes under the sharing mechanism, and when the coordination coefficient meets the preset coordination threshold, analyze the node dynamic parameters of the communication nodes according to the potential state of the network and the sharing mechanism using the preset Pareto routing algorithm, and perform communication optimization of the network communication scenario based on the node dynamic parameters.

[0184] In detail, the modules described in the application system 200 of the intelligent adaptive routing algorithm in high-speed network communication in the embodiment of the present invention adopt the same technical means as the application method of the intelligent adaptive routing algorithm in high-speed network communication described in the accompanying drawings when used, and can produce the same technical effects, which will not be repeated here.

[0185] An embodiment of the present invention provides an electronic device for implementing an application method of an intelligent adaptive routing algorithm in high-speed network communication.

[0186] See also Figure 3 As shown, the electronic device may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as an application method program of an intelligent adaptive routing algorithm in high-speed network communication.

[0187] In some embodiments, the processor may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips, etc. The processor is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes various functions and processes data of the electronic device by running or executing programs or modules stored in the memory (for example, executing the application program of the intelligent adaptive routing algorithm in high-speed network communication, etc.), and calling the data stored in the memory.

[0188] The memory includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory may also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory may also include both an internal storage unit of the electronic device and an external storage device. The memory can be used not only to store application software and various types of data installed in the electronic device, such as the code of an application program based on an intelligent adaptive routing algorithm in high-speed network communication, but also to temporarily store data that has been output or is to be output.

[0189] The communication bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory and at least one processor, etc.

[0190] The communication interface is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0191] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor through a power management system, so that the power management system can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0192] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0193] The application of the intelligent adaptive routing algorithm stored in the memory of the electronic device in high-speed network communication is a combination of multiple instructions, which, when executed in the processor, can achieve:

[0194] Acquire a network communication scenario of high-speed network communication and its scenario communication requirements, identify a communication structure of the network communication scenario, and define a communication node of the network communication scenario based on the communication structure;

[0195] Based on the communication requirements of the scenario, determining a communication impact factor of the network communication scenario, configuring a factor sensor of the communication node according to the communication impact factor, and collecting network communication data of the network communication scenario based on the factor sensor;

[0196] Dividing the network communication data into link status data, flow data, and node load data, analyzing the link status of the network communication scenario through the link status data, determining the flow pattern of the network communication scenario based on the flow data, and identifying the node load of the network communication scenario according to the node load data;

[0197] Using the time series historical status data corresponding to the network communication scenario, a network status analysis model of the network communication scenario is established, and based on the link status, the traffic pattern and the node load, the network potential status of the network communication scenario is analyzed using the network status analysis model;

[0198] Establish a sharing mechanism for the communication nodes, analyze the coordination coefficient of the communication nodes under the sharing mechanism, and when the coordination coefficient meets the preset coordination threshold, analyze the node dynamic parameters of the communication nodes according to the potential state of the network and the sharing mechanism using a preset Pareto routing algorithm, and perform communication optimization of the network communication scenario based on the node dynamic parameters.

[0199] Specifically, the specific implementation method of the processor for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0200] Furthermore, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or system that can carry the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0201] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0202] Acquire a network communication scenario of high-speed network communication and its scenario communication requirements, identify a communication structure of the network communication scenario, and define a communication node of the network communication scenario based on the communication structure;

[0203] Based on the communication requirements of the scenario, determining a communication impact factor of the network communication scenario, configuring a factor sensor of the communication node according to the communication impact factor, and collecting network communication data of the network communication scenario based on the factor sensor;

[0204] Dividing the network communication data into link status data, flow data, and node load data, analyzing the link status of the network communication scenario through the link status data, determining the flow pattern of the network communication scenario based on the flow data, and identifying the node load of the network communication scenario according to the node load data;

[0205] Using the time series historical status data corresponding to the network communication scenario, a network status analysis model of the network communication scenario is established, and based on the link status, the traffic pattern and the node load, the network potential status of the network communication scenario is analyzed using the network status analysis model;

[0206] Establish a sharing mechanism for the communication nodes, analyze the coordination coefficient of the communication nodes under the sharing mechanism, and when the coordination coefficient meets the preset coordination threshold, analyze the node dynamic parameters of the communication nodes according to the potential state of the network and the sharing mechanism using a preset Pareto routing algorithm, and perform communication optimization of the network communication scenario based on the node dynamic parameters.

[0207] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0208] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0209] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0210] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0211] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0212] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0213] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or systems stated in a system claim can also be implemented by one unit or system through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A method for applying an intelligent adaptive routing algorithm in high-speed network communication, characterized in that: The method comprises: Acquire a network communication scenario of high-speed network communication and its scenario communication requirements, identify a communication structure of the network communication scenario, and define a communication node of the network communication scenario based on the communication structure; Based on the communication requirements of the scenario, determining a communication impact factor of the network communication scenario, configuring a factor sensor of the communication node according to the communication impact factor, and collecting network communication data of the network communication scenario based on the factor sensor; Dividing the network communication data into link status data, flow data, and node load data, analyzing the link status of the network communication scenario through the link status data, determining the flow pattern of the network communication scenario based on the flow data, and identifying the node load of the network communication scenario according to the node load data; Using the time series historical status data corresponding to the network communication scenario, a network status analysis model of the network communication scenario is established, and based on the link status, the traffic pattern and the node load, the network potential status of the network communication scenario is analyzed using the network status analysis model; Establish a sharing mechanism for the communication nodes, analyze the synergy coefficient of the communication nodes under the sharing mechanism, wherein the synergy coefficient refers to a quantitative indicator used to measure the strength of the synergy effect generated by the interaction of different communication nodes when sharing resources. When the synergy coefficient meets the preset synergy threshold, analyze the node dynamic parameters of the communication nodes using a preset Pareto routing algorithm according to the potential state of the network and the sharing mechanism, and perform communication optimization of the network communication scenario based on the node dynamic parameters. The parameters include: defining a communication optimization index of the communication node corresponding to the network communication scenario, defining routing algorithm parameters of the Pareto routing algorithm according to the communication optimization index, defining a candidate routing set of the network communication scenario, calculating a response coefficient of the candidate routing set using the Pareto routing algorithm according to the network potential state, the sharing mechanism and the routing algorithm parameters, determining a target candidate routing of the network communication scenario based on the response coefficient, and defining a node dynamic parameter of the communication node according to the target candidate routing, wherein the response coefficient refers to an index used to quantify the degree of response of the candidate routing to the communication optimization index.

2. The method for applying the intelligent adaptive routing algorithm in high-speed network communication according to claim 1, characterized in that: The communication structure for identifying the network communication scenario includes: Determine the network communication scope of the network communication scenario; Marking the communication entities within the network communication range; analyzing data flows of the communication entities; Based on the data flow, construct a communication flow chart of the communication entity; The communication structure of the network communication scenario is determined through the communication flow chart.

3. The method for applying the intelligent adaptive routing algorithm in high-speed network communication according to claim 2, characterized in that: The communication node of the network communication scenario is defined based on the communication structure, including: Determining an initial communication node of the network communication scenario according to the communication structure; Defining a node role of the initial communication node; Marking the functional characteristics of the initial communication node through the node role; Based on the communication structure, defining a node association degree of the initial communication node; Calculating the necessary coefficient of the initial communication node in the network communication scenario according to the functional characteristics and the node association degree; The communication nodes in the initial communication nodes are screened by using the necessary coefficients.

4. The method for applying the intelligent adaptive routing algorithm in high-speed network communication according to claim 3, characterized in that: The calculating, according to the functional characteristics and the node association degree, a necessary coefficient of the initial communication node in the network communication scenario includes: According to the functional characteristics and the node association degree, define the node reliability, node performance, node security level and node scalability of the initial communication node in the network communication scenario; Respectively define the node reliability weight, node performance weight, node security level weight and node scalability weight of the node reliability, node performance, node security level and node scalability; In combination with the node reliability, the node performance, the node security level, the node scalability, the node reliability weight, the node performance weight, the node security level weight, and the node scalability weight, the necessary coefficient of the initial communication node in the network communication scenario is calculated using the following formula: in, represents the necessary coefficient for network communication scenarios, represents the node reliability, The node reliability weight represents the node reliability, The nonlinear weight index representing the node reliability, Indicates node performance, The node performance weight representing the node performance, A nonlinear weight index representing node performance, Indicates the node security level, The node safety level weight representing the node safety level, A nonlinear weight index representing the node safety level, Indicates node scalability, The node scalability weight representing the node scalability, A non-linear weight index representing the scalability of a node.

5. The method for applying the intelligent adaptive routing algorithm in high-speed network communication according to claim 4, characterized in that: The configuring the factor sensor of the communication node according to the communication influencing factor comprises: Analyzing the impact value of the communication impact factor on the communication node; Defining the factor data to be collected of the communication node according to the influence value; Identifying factor data features of the factor data to be collected; Based on the factor data characteristics, defining a factor sensor to be configured of the communication node; Analyzing the communication node characteristics of the communication node, and determining the sensor topology structure of the factor sensor to be configured according to the communication node characteristics; Calculating node monitoring blind spots of the sensor topology for the communication nodes; When the node monitoring blind spot meets the preset node monitoring threshold, the factor sensor to be configured is used as the factor sensor of the communication node.

6. The method for applying the intelligent adaptive routing algorithm in high-speed network communication according to claim 5, characterized in that: The calculating of the node monitoring blind spots of the communication nodes by the sensor topology structure includes: defining a node detection area of ​​the communication node; Mark the sensor monitoring area, sensor quantity and sensor overlapping area of ​​the factor sensor to be configured corresponding to the sensor topology structure; According to the node detection area, the sensor monitoring area, the number of sensors and the sensor overlapping area, the node monitoring blind spot area of ​​the sensor topology for the communication node is calculated using the following formula: in, represents the node monitoring blind spot area of ​​the communication node, represents the node detection area, Represents the sensor topology The failure probability of the sensor to be configured, Represents the sensor topology The sensor monitoring area of ​​the factor sensor to be configured, Represents the sensor topology The sensor overlap area of ​​the factor sensors to be configured, Indicates the number of sensors, Represents the probability product of the sensor of the configuration factor working normally.

7. The method for applying the intelligent adaptive routing algorithm in high-speed network communication according to claim 6, characterized in that: The analyzing the link status of the network communication scenario through the link status data includes: Defining link status indicators of the network communication scenario; Based on the link status indicator and the link status data, analyzing the link bandwidth utilization, link delay and link packet loss rate of the network communication scenario; Determining the link abnormality mode of the network communication scenario through the link bandwidth utilization, link delay and link packet loss rate; Mapping the link abnormality mode with a network event in a preset network event library to obtain a mapped network event; Analyzing the link abnormality pattern and the link status relationship of the mapped network event; Based on the link status relationship, the link status of the network communication scenario is analyzed.

8. The method for applying the intelligent adaptive routing algorithm in high-speed network communication according to claim 7, characterized in that: The using the time series historical status data corresponding to the network communication scenario to establish a network status analysis model for the network communication scenario includes: Analyze the network status change characteristics of the network communication scenario; Defining a sequential network architecture of the network communication scenario according to the network state change characteristics; Extracting historical link status features, historical traffic pattern features, and historical node load features of the time series historical status data; Based on the historical link state characteristics, historical traffic pattern characteristics, and historical node load characteristics, the timing network architecture is trained to obtain a training network state analysis model; Calculating a generalization coefficient of the training network state analysis model, and optimizing training parameters of the training network state analysis model based on the generalization coefficient to obtain optimized training parameters; Based on the optimized training parameters, calculating the model performance of the training network state analysis model; When the model performance meets the preset model performance threshold, the trained network status analysis model is used as the network status analysis model of the network communication scenario.

9. An application system of intelligent adaptive routing algorithm in high-speed network communication, characterized in that: A method for applying the intelligent adaptive routing algorithm according to any one of claims 1 to 8 in high-speed network communication, the system comprising: A communication node definition module, used to obtain a network communication scenario of high-speed network communication and its scenario communication requirements, identify a communication structure of the network communication scenario, and define a communication node of the network communication scenario based on the communication structure; A communication data acquisition module, configured to determine a communication impact factor of the network communication scenario based on the communication requirements of the scenario, configure a factor sensor of the communication node according to the communication impact factor, and collect network communication data of the network communication scenario based on the factor sensor; A network communication analysis module, used to divide the network communication data into link status data, flow data and node load data, analyze the link status of the network communication scenario through the link status data, determine the flow pattern of the network communication scenario based on the flow data, and identify the node load of the network communication scenario according to the node load data; A network potential state determination module, used to establish a network state analysis model for the network communication scenario by using the time series historical state data corresponding to the network communication scenario, and to analyze the network potential state of the network communication scenario by using the network state analysis model based on the link state, the traffic pattern and the node load; A scenario communication optimization module is used to establish a sharing mechanism for the communication nodes, analyze the coordination coefficient of the communication nodes under the sharing mechanism, and when the coordination coefficient meets a preset coordination threshold, analyze the node dynamic parameters of the communication nodes using a preset Pareto routing algorithm according to the network potential state and the sharing mechanism, and perform communication optimization of the network communication scenario based on the node dynamic parameters.

Images