Key flow-based SRv6 explicit path intelligent scheduling method and system

Abstract

The application relates to a key flow-based SRv6 explicit path intelligent scheduling method and system, and belongs to the field of communication information technologies.The application comprises the following steps: key degree scoring is performed through a semi-supervised-transfer hybrid learning model to output a key flow; a full-dimension network twin model is constructed to predict a congestion risk trend and verify a link path survival rate; based on the key flow and the link path survival rate, a low-latency source node list is generated through a key flow path enhancement algorithm; a micro-isolation queue is created by analyzing the low-latency source node list; when a digital twin detects that an actual state deviates from a predicted value, a pre-verified backup path identifier chain is called to complete path switching in real time; and a double-channel learning model is used to perform closed-loop optimization based on key operation state data.The application solves the technical problems of low key flow recognition accuracy, poor adaptability of SRv6 path scheduling to network states, lagging fault switching and insufficient core model optimization in the prior art.

Description

TECHNICAL FIELD

[0001] The application relates to a key flow-based SRv6 explicit path intelligent scheduling method and system, and belongs to the field of communication information technology. BACKGROUND

[0002] With the development of 5G, industrial internet and other scenarios, the key flow in the network has strict requirements on delay and reliability. In the prior art, key flow identification depends on manual rules or a single feature, and the precision is insufficient; SRv6 explicit path scheduling is often statically configured, and it is difficult to dynamically adapt to network load changes and topology fluctuations. When the network twin model is constructed, the data fusion degree is low, and the accuracy of congestion risk prediction and path survival rate verification is limited. When a fault occurs, path switching depends on manual intervention or a simple triggering mechanism, which easily leads to interruption of key flow transmission. At the same time, there is a lack of closed-loop optimization mechanism for key flow identification model, twin model and path algorithm, and the overall scheduling adaptability and intelligence cannot meet the needs of complex network scenarios. The present application aims to solve the technical problems of low key flow identification precision, poor adaptability of SRv6 path scheduling to network state, lagging fault switching and insufficient optimization of core models in the prior art. SUMMARY

[0003] The technical problem solved by the present application is that the present application provides a key flow-based SRv6 explicit path intelligent scheduling method and system to solve the technical problems of low key flow identification precision, poor adaptability of SRv6 path scheduling to network state, lagging fault switching and insufficient optimization of core models in the prior art.

[0004] The technical solution of the present application is: a key flow-based SRv6 explicit path intelligent scheduling method, the method comprising:

[0005] Collecting multi-dimensional dynamic characteristics of traffic, performing key degree scoring through a semi-supervised-migration hybrid learning model, and outputting key flows carrying delay tolerance threshold values;

[0006] Collecting network fine-grained state data, constructing a full-dimensional network twin model, predicting congestion risk trends, and verifying link path survival rates;

[0007] Based on the key flow and the link path survival rate, a low-delay source node list is generated through a key flow path enhancement algorithm;

[0008] Analyzing the low-delay source node list to create a micro-isolation queue, reserving resources for key flows, and guiding non-key flows to low-load links;

[0009] When the digital twin detects that the actual state deviates from the predicted value, a backup path identification chain verified in advance is called to complete path switching in real time;

[0010] Based on the key operating state data, a semi-supervised-transfer hybrid learning model, a full-dimensional network twin model, and a key flow path enhancement algorithm are optimized by using a dual-channel learning model.

[0011] Further, the multi-dimensional dynamic characteristics of the collected traffic are scored by the semi-supervised-transfer hybrid learning model, and the key flow carrying the delay tolerance threshold is output, including:

[0012] The multi-dimensional dynamic characteristics of the collected traffic are input into the semi-supervised-transfer hybrid learning model for preliminary key degree scoring to identify potential key flows.

[0013] Based on the scoring results and the delay tolerance threshold, the key flow carrying the threshold is output, and the key flow is filtered by dynamic optimization of the semi-supervised-transfer hybrid learning model.

[0014] Further, network fine-grained state data is collected to build a full-dimensional network twin model to predict congestion risk trends and verify link path survival rates, including:

[0015] The network fine-grained state data is collected to build a full-dimensional network twin model, and a high-precision digital map is created through multi-dimensional data fusion.

[0016] The full-dimensional network twin model is used to predict congestion risk trends and verify link path survival rates, and the reliability index is output through real-time simulation and prediction analysis to guide path selection.

[0017] Further, based on the key flow and the link path survival rate, a low-latency source node list is generated by the key flow path enhancement algorithm, including:

[0018] The delay tolerance threshold of the key flow and the link path survival rate are fused to build a weighted directed graph model, and a topological mining algorithm is used to filter effective source nodes.

[0019] The key flow path enhancement algorithm is triggered by the source node, and backtracking pruning is performed in the weighted directed graph model to generate a low-latency source node list that meets the key flow service level agreement.

[0020] Further, the low-latency source node list is parsed to create a micro-isolation queue, reserve resources for key flows, and guide non-key flows to low-load links, including:

[0021] The low-latency source node list is parsed to construct a micro-isolation queue container at the entry node, and a priority forwarding identifier is injected into the segment routing header to reserve bandwidth and time slot resources.

[0022] Based on real-time link load data, a non-key flow guidance strategy is generated, and non-key flows are redirected to low-load paths by combining equivalent multipath entropy calculation.

[0023] Further, when the digital twin detects that the actual state deviates from the predicted value, the pre-verified backup path identification chain is called to complete the path switching in real time, including:

[0024] By continuously comparing the actual network state with the predicted value through the digital twin, when the key indicators break through the dynamic threshold, the path switching instruction based on the network service chain is activated;

[0025] The pre-stored backup path identification chain is called to perform the segment routing identification stack switching operation to complete the traffic rerouting.

[0026] Further, the multi-dimensional dynamic characteristics of the collected traffic are input into the semi-supervised-migration hybrid learning model to perform preliminary key degree scoring and identify potential key flows; specifically including:

[0027] The multi-dimensional dynamic characteristics of the collected traffic, including bandwidth fluctuation, transmission delay change, protocol type, application identifier, and interaction frequency, are standardized and preprocessed to form a feature matrix; the feature matrix is input into the semi-supervised-migration hybrid learning model, wherein the semi-supervised module uses a small number of labeled samples and a large number of unlabeled traffic data to construct a feature space mapping, and uses a clustering algorithm to mine the internal correlation pattern of the traffic; the migration learning module introduces key flow identification knowledge in similar network scenarios, and adjusts the model parameters through a domain adaptation mechanism to adapt to the current network environment; the semi-supervised-migration hybrid learning model processes the input features in a hierarchical manner, first capturing the key feature vector through the feature extraction layer, and then outputting the preliminary key degree score of each traffic through the scoring layer: the key degree score K is calculated as follows:

[0028]

[0029] wherein, and defines the time window boundary for traffic feature collection, is the start time of collection, is the end time of collection, used to limit the observation time length of traffic dynamic characteristics; represents the instantaneous change rate of bandwidth fluctuation, where B represents the bandwidth, i.e. the amount of data that can be transmitted per unit time, and t represents the current t time; is the transmission delay change rate; is the protocol key coefficient; represents the application priority; is the interaction frequency; is the feature space mapping distance; is the feature space standard deviation; in which, is the matrix trace operation, is the labeled sample confidence matrix, is the transpose of the domain adaptation coefficient matrix M, is the bandwidth fluctuation Laplacian operator; is the truncation order of the series expansion; is the application priority standard deviation; n represents the nth order of the series expansion stage;

[0030] According to the preliminary key degree score distribution, a preliminary threshold is set, and the flow whose score exceeds the threshold is marked as a potential key flow.

[0031] Further, the full-dimensional network twin model is used to predict the congestion risk trend and verify the link path survival rate, and the reliability index is output through real-time simulation and prediction analysis to guide path selection; specifically including:

[0032] The full-dimensional network twin model is called, the real-time collected network fine-grained state data and traffic change trend are input, and the dynamic simulation engine is started; through time series analysis algorithm, the trend of link bandwidth and node load index is deduced, the congestion risk level and spread path of each link in the future period are predicted; at the same time, based on the reachability analysis method of graph theory, the link connectivity in various fault scenarios is simulated in the full-dimensional network twin model, the survival probability of different paths in the preset time window is calculated, and the link path survival rate is verified;

[0033] Wherein, the link path survival rate The formula is:

[0034]

[0035] Wherein, T represents the total time length of the time window for analyzing the link path state; m represents the number of links constituting the path; is the instantaneous reliability of the ith link at time t, reflecting the stability of the link with time; n1 is the number of time steps after discretization; is the interval of adjacent time steps; is the failure rate of the path at the k1th time step corresponding to the time; is the matrix trace operation, which sums the main diagonal elements of the matrix; is the topological connectivity matrix, which is used to describe the connectivity relationship of links and nodes in the network topology structure; is the node processing capacity matrix; is the inverse matrix thereof; is the Hadamard product, which integrates the topological connectivity information and the node processing capacity information through the operation; is the failure recovery rate at the end L of the path; is the failure recovery rate at the start of the path; reflects the change of the path failure recovery ability; is the approximate calculation of the standard normal distribution integral, which is used to quantify the probability characteristics of path congestion and other risks; x is the normalized risk statistic, calculated from the path congestion probability , the congestion probability mean , the standard deviation ; u is the integral variable of the standard normal distribution;

[0036] The simulation results are fused with the prediction data, and statistical analysis is used to generate reliability indicators such as path available duration, fault recovery probability, and congestion occurrence probability, and these indicators are quantified as evaluation parameters that can be directly used for path decision.

[0037] Further, the delay tolerance threshold of the key flow and the link path survival rate are fused to construct a weighted directed graph model, and a topology mining algorithm is used to screen effective source nodes; specifically including:

[0038] The key flow and its key degree score are received, the link data and the link path survival rate are fused, and after association calibration and standardization processing, a weighted directed graph model is constructed; in the weighted directed graph model, the nodes correspond to network source nodes and forwarding nodes, the edges represent physical links, and the edge weights are generated by a weighted fusion algorithm of the key flow key degree score and the link survival rate; at the same time, potential source nodes are deduced based on network topology characteristics; combined with the communication characteristics of the key flow and the reachability constraints of the network topology, a topology mining algorithm is used to identify candidate source nodes matching the key flow, and through checking the link path survival rate and the key degree score of the nodes, effective source nodes with the ability to carry the key flow are screened out, and their delay sensitivity level and path weight initial value are marked;

[0039] Among them, the source node screening formula is:

[0040]

[0041] Among them, K is the key degree score of the key flow, which is used to measure the criticality of the flow; R represents the node resource surplus, which reflects the resource situation of the remaining loadable flow of the node; U is the node resource utilization rate; is the resource sensitivity coefficient; S is the link path survival rate; T represents the time observation window length of the source node screening; Ψ(t) is the node time-varying availability function, which is the availability of the source node at time t; D is the link delay jitter, which reflects the fluctuation of the link transmission delay; is the maximum eigenvalue of the matrix obtained by multiplying the node association matrix and the path stability matrix transpose, which reflects the comprehensive characteristic value of node association and path stability; is the delay jitter variance; is the path length, which is used to quantify the negative impact of factors such as link delay jitter on source node screening; Historical failure rate of the node; It is the vector of topological coupling coefficients; It is the topological coupling index; is the Fourier transform of the distance attenuation factor; j is the imaginary unit; f is the frequency variable; r is the distance variable.

[0042] The present invention also provides an SRv6 explicit path intelligent scheduling system based on critical flow, the system comprising: a module for executing the SRv6 explicit path intelligent scheduling method based on critical flow.

[0043] The beneficial effects of this invention are as follows: This invention improves the accuracy of critical flow identification through semi-supervised-transfer hybrid learning, ensuring accurate screening of critical flows; the full-dimensional network twin model enhances congestion prediction and path reliability verification capabilities, providing accurate basis for scheduling; the critical flow path enhancement algorithm, combined with weighted graph backtracking pruning, generates a sequence of efficient source nodes; the dynamic path switching and closed-loop optimization mechanism improves fault response speed and model adaptability, ultimately achieving low-latency, high-reliability transmission of critical flows and optimizing network resource utilization. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0045] Figure 1 A flowchart of the SRv6 explicit path intelligent scheduling method based on critical flow provided in Embodiment 1 of this application;

[0046] Figure 2 This is a schematic diagram of the SRv6 explicit path intelligent scheduling system based on critical flow, provided in Embodiment 2 of this application. Detailed Implementation

[0047] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0048] Example 1: As Figure 1 As shown, Embodiment 1 of this application provides an SRv6 explicit path intelligent scheduling method based on critical flows, including:

[0049] S1: collect multi-dimensional dynamic characteristics of traffic, score key degree through a semi-supervised-transfer hybrid learning model, and output key flows carrying a delay tolerance threshold;

[0050] In the method, multi-dimensional dynamic characteristics of traffic are collected, key degree is scored through a semi-supervised-transfer hybrid learning model, and key flows carrying a delay tolerance threshold are output. The method comprises the following sub-steps:

[0051] S11: input multi-dimensional dynamic characteristics of traffic into a semi-supervised-transfer hybrid learning model, score preliminary key degree, and identify potential key flows;

[0052] The multi-dimensional dynamic characteristics of traffic include bandwidth fluctuation, transmission delay change, protocol type, application identifier and interaction frequency of the traffic. After standardization preprocessing, the characteristics form a feature matrix. The feature matrix is input into the semi-supervised-transfer hybrid learning model. The semi-supervised module uses a small amount of labeled samples and a large amount of unlabeled traffic data to construct a feature space mapping, and mines the internal correlation mode of traffic through a clustering algorithm. The transfer learning module introduces key flow identification knowledge in a similar network scenario, and adjusts model parameters through a domain adaptation mechanism to adapt to the current network environment. The semi-supervised-transfer hybrid learning model processes the input features in a hierarchical manner. First, the feature extraction layer captures the key feature vector, and then the scoring layer outputs the preliminary key degree score of each flow. The key degree score K is calculated according to the following formula:

[0053]

[0054] In the formula, B represents bandwidth, t represents the current time t, and K represents the key degree score. And defines the time window boundary of traffic feature collection, is the collection start time, is the collection end time, which is used to limit the observation time length of traffic dynamic characteristics; represents the instantaneous change rate of bandwidth fluctuation, where B represents bandwidth, i.e. the amount of data that can be transmitted per unit time, and t represents the current time t; is the transmission delay change rate; is the protocol key coefficient; represents the application priority; is the interaction frequency; is the feature space mapping distance; is the feature space standard deviation; In the formula, is the matrix trace operation, is the labeled sample confidence matrix, is the transpose of the domain adaptation coefficient matrix M, is the bandwidth fluctuation Laplacian operator; is the truncation order of the series expansion; and is the application priority standard deviation; n represents the nth order number in the series expansion stage;

[0055] According to the preliminary criticality score distribution, a preliminary threshold is set, and the traffic with a score exceeding the threshold is marked as a potential key flow.

[0056] S12: Based on the score result and the delay tolerance threshold, the key flow carrying the threshold is output, and the key flow is accurately screened through dynamic optimization of the mixed learning model.

[0057] The potential key flow and its preliminary criticality score are received, and the delay tolerance threshold corresponding to each flow is introduced. The score result is associated and matched with the delay tolerance threshold, and a comprehensive evaluation data set containing traffic features, criticality scores and threshold parameters is constructed. Through the dynamic optimization module of the semi-supervised-transfer mixed learning model, the newly added traffic data collected in real time is used to incrementally train the model, adjust the feature weight and score algorithm parameter, and improve the adaptability of key flow identification. Based on the optimized model, the potential key flow is scored again, and double verification is performed in combination with the delay tolerance threshold to eliminate the traffic with score fluctuation exceeding the limit or unable to meet the delay constraint, and finally the accurate key flow set carrying the explicit delay tolerance threshold is output.

[0058] S2: Collect network fine-grained state data, build a full-dimensional network twin model, predict congestion risk trend, and verify link path survival rate;

[0059] Among them, collecting network fine-grained state data, building a full-dimensional network twin model, predicting congestion risk trend, and verifying link path survival rate include the following sub-steps:

[0060] S21: Collect network fine-grained state data, build a full-dimensional network twin model, and create high-precision digital mapping through multi-dimensional data fusion;

[0061] The network fine-grained state data is collected through distributed monitoring nodes, which include device port traffic, CPU utilization, memory occupation, link bandwidth utilization, packet loss rate, delay and topology connection relationship, etc. After standardization processing, a multi-source heterogeneous data set is formed. Based on the data set, a full-dimensional network twin model is built. First, the hierarchical architecture of physical layer, logical layer and business layer is built. The physical layer maps network devices and link entities, the logical layer abstracts routing protocols and forwarding rules, and the business layer associates the application traffic features carried. The device state, link performance and topology structure data are associated in space and time, and the data redundancy and conflict are eliminated. The dynamic mapping mechanism is used to bind the real-time collected data and the corresponding entities in the twin model, realizing high-precision mapping of physical network state to digital space.

[0062] S22: Utilize the full-dimensional network twin model to predict the congestion risk trend and verify the link path survival rate, output the reliability index through real-time simulation and prediction analysis, and guide path selection;

[0063] Call the full-dimensional network twin model, input the real-time collected network fine-grained state data and traffic change trend, start the dynamic simulation engine; Through time series analysis algorithm, the trend of link bandwidth and node load index is deduced, the congestion risk level and spread path of each link in future period are predicted; At the same time, based on the reachability analysis method of graph theory, the link connectivity in various fault scenarios is simulated in the full-dimensional network twin model, the survival probability of different paths in the preset time window is calculated, and the link path survival rate is verified;

[0064] Among them, the link path survival rate The formula is:

[0065]

[0066] Among them, T represents the total time length of the time window for analyzing the link path state; m represents the number of links constituting the path; is the instantaneous reliability of the ith link at time t, reflecting the stability of the link with time change; n 1 is the number of time steps after discretization; is the interval of adjacent time steps; is the failure rate of the path at the k 1 time step corresponding time; is the matrix trace operation, summing the main diagonal elements of the matrix; is the topological connectivity matrix, used to describe the connectivity relationship of links and nodes in the network topology structure; is the node processing capacity matrix; is its inverse matrix; is the Hadamard product, which integrates the topological connectivity information and node processing capacity information through the operation; is the failure recovery rate at the end point L of the path; is the failure recovery rate at the start point of the path; reflects the change of the path failure recovery ability; is the approximate calculation of the integral of the standard normal distribution, used to quantify the probability characteristics of path congestion and other risks; , x is the standardized risk statistic, which is calculated by path congestion probability , congestion probability mean , standard deviation ; u is the integral variable of the standard normal distribution;

[0067] The simulation results are fused with the prediction data, statistical analysis is used to generate reliability indexes such as path available duration, fault recovery probability and congestion occurrence probability, and these indexes are quantified as evaluation parameters that can be directly used for path decision.

[0068] S3: generating a low-latency source node list through a key flow path enhancement algorithm based on the key flow and link path survival rate;

[0069] The low-latency source node list generated through the key flow path enhancement algorithm based on the key flow and link path survival rate includes the following sub-steps:

[0070] S31: fusing the delay tolerance threshold of the key flow and the link path survival rate, constructing a weighted directed graph model, and screening effective source nodes by using a topology mining algorithm;

[0071] The key flow and its key degree score are received, link data and link path survival rate are fused, a weighted directed graph model is constructed after association calibration and standardization processing, nodes in the weighted directed graph model correspond to network source nodes and forwarding nodes, edges represent physical links, and edge weights are generated through a weighted fusion algorithm of the key degree score of the key flow and the link survival rate. At the same time, potential source nodes are deduced based on network topology characteristics. In combination with the communication characteristics of the key flow and the reachability constraints of the network topology, a topology mining algorithm is used to identify candidate source nodes matched with the key flow, and through checking the link path survival rate and the key degree score of the nodes, effective source nodes with the ability to carry the key flow are screened out, and their delay sensitivity levels and path weight initial values are marked;

[0072] The source node screening formula is:

[0073]

[0074] K is the key degree score of the key flow, used to measure the criticality of the flow; R represents the resource margin of the node, reflecting the resource situation of the remaining bearable flow of the node; U is the resource utilization rate of the node; is a resource sensitivity coefficient; S is the link path survival rate; T represents the time observation window length of the source node screening; Ψ(t) is the time-varying availability function of the node, which is the availability degree of the source node at time t; D is the link delay jitter, reflecting the fluctuation of the link transmission delay; is the maximum eigenvalue of the matrix obtained by transposing and multiplying the node association matrix and the path stability matrix , which represents the comprehensive characteristic value of the node association and the path stability; is the delay jitter variance; is the path length, used to quantify the negative influence of factors such as link delay jitter on source node screening; is the node historical failure rate; is the topology coupling coefficient vector; is the topology coupling index; is the Fourier transform of the distance decay factor; j is the imaginary unit; f is the frequency variable; r is the distance variable.

[0075] S32: Trigger the key flow path enhancement algorithm by the source node, perform backtracking pruning deduction in the weighted directed graph model, and generate a low-latency source node sequence list meeting the key flow service level agreement.

[0076] Based on the weighted directed graph model, trigger the key flow path enhancement algorithm, and perform backtracking search in the graph with the service level agreement constraint of the key flow as the pruning condition. By dynamically evaluating the cumulative weight of the path and the constraint satisfaction degree, the substandard path branches are pruned and removed, and the effective path with low latency and high survival rate is reserved. Finally, the path starting point information meeting the condition is integrated to generate a low-latency source node sequence list sorted by priority.

[0077] S4: Analyze the low-latency source node list to create a micro-isolation queue, reserve resources for the key flow, and guide non-key flows to low-load links;

[0078] Among them, analyzing the low-latency source node list to create a micro-isolation queue, reserving resources for the key flow, and guiding non-key flows to low-load links includes the following sub-steps:

[0079] S41: Analyze the low-latency source node list, construct a micro-isolation queue container at the entry node, and inject a priority forwarding identifier into the segment routing header to reserve bandwidth and time slot resources;

[0080] Receive the low-latency source node sequence, perform structural analysis, extract the identification information, priority ranking, and corresponding key flow service level agreement parameters of each source node. Based on the analysis result, deploy a micro-isolation queue container at the network entry node, divide independent queues according to the priority and latency sensitivity level of the key flow, and configure the resource occupancy threshold and scheduling weight of the queue. At the same time, according to the segment routing protocol specification, generate SRv6 header information containing the priority forwarding identifier, inject the identifier into the data packet header of the key flow through the protocol conversion interface, and establish the mapping relationship between the key flow and the reserved resources. Through interaction with the resource management module of the entry node, based on the bandwidth demand and time slot allocation strategy of the key flow, complete the bandwidth resource reservation and time slot scheduling table configuration to ensure that the key flow obtains priority processing right in the forwarding process.

[0081] S42: Generate a non-key flow guidance strategy based on real-time link load data, and redirect non-key traffic to low-load paths combined with equivalent multipath entropy calculation.

[0082] Real-time acquisition of load data of each link, including bandwidth utilization, packet queue length and forwarding delay, etc., normalization processing through data preprocessing module, construction of link load state matrix. Generate non-critical flow guidance strategy framework, clarify the forwarding constraints and path selection range of non-critical flow. Perform entropy calculation on the load balancing degree of each candidate path, the higher the entropy value, the more balanced the path load distribution. According to the calculation result, the system selects the path with low load and meets the entropy value, redirects the non-critical flow to these paths, and monitors the load change of the redirected link in real time. If the load fluctuation exceeds the threshold value, trigger the dynamic adjustment mechanism to ensure that the non-critical flow is always transmitted on the low-load link, avoiding the occupation of the reserved resources for critical flow.

[0083] S5: When the digital twin detects that the actual state deviates from the predicted value, call the pre-verified backup path identification chain to complete the path switching in real time;

[0084] When the digital twin detects that the actual state deviates from the predicted value, call the pre-verified backup path identification chain to complete the path switching in real time, including the following sub-steps:

[0085] S51: Through the digital twin, continuously compare the network state with the predicted value, when the key indicators break through the dynamic threshold, activate the path switching instruction based on network service chain;

[0086] Through the full-dimensional network twin, real-time acquisition of key running state data of physical network and continuous comparison with predicted value generated by twin model. Set dynamic threshold adjustment mechanism, based on the service level agreement parameters of key flow and the current load status of network, real-time update the deviation tolerance threshold of each indicator. When the comparison result shows that a key indicator breaks through the corresponding dynamic threshold, and the deviation duration exceeds the preset window, it is determined that the network state deviates from the predicted trend, which may affect the transmission quality of key flow, then activate the path switching instruction generation module based on network service chain, according to the identification information of key flow and the current path characteristics, preliminarily select the adaptive switching strategy.

[0087] S52: Call the pre-stored backup path identification chain, perform segment routing identification stack switching operation to complete flow rerouting.

[0088] In response to a path switching instruction, a backup path identifier chain matching the current critical flow is retrieved from a preset backup path library, the identifier chain including a pre-verified SRv6 segment routing identifier sequence and corresponding node forwarding rules. After the identifier chain is verified for legality and it is confirmed that the link survival rate and the delay parameter meet the critical flow service level agreement requirements, a segment routing identifier stack switching mechanism is started. By interacting with the forwarding plane of the nodes along the way, the identifier stack information of the original path is replaced in sequence, and a path switching announcement is sent to the related nodes to update the forwarding table entries. During the switching process, the transmission state of the critical flow is monitored in real time, and a smooth transition algorithm is used to avoid traffic interruption or jitter. After the new path carries stable traffic and the indicators meet the requirements, the original path forwarding process is terminated, and the seamless rerouting of the critical flow is completed.

[0089] S6: Utilize the dual-channel learning model to close-loop optimize the semi-supervised-migration hybrid learning model, the full-dimension network twin model, and the critical flow path enhancement algorithm based on the critical operation state data.

[0090] The system collects critical operation state data, including at least the accuracy deviation of critical flow identification, the prediction error of the full-dimension network twin model, the matching degree of the output of the path enhancement algorithm and the service level agreement, etc. After standardization processing, the data are input into the dual-channel learning model. One channel extracts the associated features of each model and algorithm and network dynamics through a graph neural network, analyzes the feature extraction deviation of the semi-supervised-migration model, the topology mapping error of the twin model, and the constraint adaptation defects of the path enhancement algorithm. The other channel models the constraint relationship of each optimization target by linear programming, and quantifies the parameter range that needs to be adjusted. Through the fusion analysis of the two channels, the feature weight correction value of the semi-supervised-migration model, the dynamic mapping coefficient adjustment amount of the twin model, and the pruning threshold optimization parameter of the path enhancement algorithm are generated. These parameters are then injected back into the corresponding model and algorithm to start the iterative optimization. Through continuous comparison of the deviation between the output after optimization and the expected target, the optimization strategy of the dual-channel learning model is dynamically adjusted to form a closed-loop mechanism.

[0091] Embodiment 2, as shown in Figure 2 The application embodiment 2 provides an SRv6 explicit path intelligent scheduling system based on a critical flow, which includes:

[0092] The critical flow intelligent identification module 21 is used for collecting multi-dimensional dynamic features of the flow, performing critical degree scoring through a semi-supervised-migration hybrid learning model, and outputting a critical flow carrying a delay tolerance threshold.

[0093] The congestion prediction and path verification module 22 is used for collecting network fine-grained state data, constructing a full-dimension network twin model, predicting congestion risk trends, and verifying link path survival rates.

[0094] The low-latency source node generation module 23 is configured to generate a low-latency source node list based on the key flow and the link path survival rate through a key flow path enhancement algorithm.

[0095] The key flow traffic scheduling module 24 is configured to parse the low-latency source node list to create a micro-isolation queue, reserve resources for the key flow, and guide non-key flows to low-load links.

[0096] The fault awareness and path switching module 25 is configured to call a pre-verified backup path identification chain to complete real-time path switching when the digital twin detects that the actual state deviates from the predicted value.

[0097] The iterative optimization module 26 is configured to use a dual-channel learning model to close-loop optimize a semi-supervised-migration hybrid learning model, a full-dimension network twin model and a key flow path enhancement algorithm based on key operating state data.

[0098] Corresponding to the above-mentioned embodiments, the embodiments of the present application provide a computer storage medium, comprising at least one memory and at least one processor.

[0099] The memory is configured to store one or more program instructions.

[0100] The processor is configured to run the one or more program instructions to execute the key flow-based SRv6 explicit path intelligent scheduling method.

[0101] Corresponding to the above-mentioned embodiments, the embodiments of the present application provide a computer readable storage medium, and the computer storage medium contains one or more program instructions, and the one or more program instructions are used to execute the key flow-based SRv6 explicit path intelligent scheduling method by the processor.

[0102] The embodiments disclosed by the present application provide a computer readable storage medium, and the computer readable storage medium stores computer program instructions, and when the computer program instructions run on a computer, the computer executes the above-mentioned key flow-based SRv6 explicit path intelligent scheduling method.

[0103] In the embodiments of the present application, the processor can be an integrated circuit chip with a signal processing capability. The processor can be a general purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0104] The disclosed methods, steps, and logic block diagrams in the embodiments of the present application can be implemented or performed with a general- purpose processor, a special purpose processor, or any other processor. The steps of the methods disclosed in the embodiments of the present application can be directly embodied to a hardware code, a processor code, or a software code for execution by a processor. The software code can reside in the storage media such as the random access memory (RAM), the flash memory, the read only memory (ROM), the programmable read only memory (PROM), the electrically programmable read only memory (EPROM), the electrically erasable programmable read only memory (EEPROM), the compact disk (CD), the digital versatile disk (DVD), the Blu-ray disk, the hard disk drive (HDD), or any other storage medium. The processor reads information in the storage medium, and performs the steps of the above-described methods with the aid of hardware.

[0105] The storage medium can be the memory, for example, the volatile memory or the non-volatile memory, or can include both the volatile and non-volatile memory.

[0106] The non-volatile memory can be the read only memory (ROM), the programmable read only memory (PROM), the erasable programmable read only memory (EPROM), the electrically erasable programmable read only memory (EEPROM), or the flash memory.

[0107] The volatile memory can be the random access memory (RAM) used as the external cache. By way of example, and not limitation, many forms of RAM are available, for example, the static random access memory (SRAM), the dynamic random access memory (DRAM), the synchronous dynamic random access memory (SDRAM), the double data rate SDRAM (DDR SDRAM), the enhanced SDRAM (ESDRAM), the Synchlink DRAM (SLDRAM), and the direct Rambus RAM (DRRAM).

[0108] The storage medium described in the embodiments of the present application is intended to include, but not limited to, these and any other suitable types of memory.

[0109] Those skilled in the art should be aware that, in one or more examples described above, functions described by the present application can be implemented in combination of hardware and software. When the software is applied, the corresponding functions can be stored in a computer readable medium or transmitted as one or more instructions or codes on the computer readable medium. The computer readable medium includes computer storage medium and communication medium, wherein the communication medium includes any medium that facilitates transfer of computer program from one place to another. The storage medium can be any available medium accessible by a general or special purpose computer.

[0110] The above detailed description of the specific implementation of the present application further explains the purpose, technical solution and beneficial effects of the present application. It should be understood that the above description is only a specific implementation of the present application and is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made on the basis of the technical solution of the present application should be included in the protection scope of the present application.

[0111] The specific implementation of the present application is described in detail above in combination with the drawings, but the present application is not limited to the above implementation. Various changes can be made within the knowledge of those skilled in the art without departing from the purpose of the present application.

Claims

1. An SRv6 explicit path intelligent scheduling method based on critical flow, characterized in that: The method includes: Collect multi-dimensional dynamic features of traffic, perform keyness scoring through a semi-supervised-transfer hybrid learning model, and output key flows carrying latency tolerance thresholds; Collect fine-grained network status data, construct a full-dimensional network twin model, predict congestion risk trends, and verify link path survival rate; Based on the critical flow and link path survival rate, a low-latency source node list is generated through a critical flow path enhancement algorithm. Parse the list of low-latency source nodes to create a micro-segmentation queue, reserve resources for critical flows, and guide non-critical flows to low-load links; When the digital twin detects that the actual state deviates from the predicted value, it calls the pre-verified backup path identifier chain to complete the path switching in real time. By utilizing a dual-channel learning model, a semi-supervised-transfer hybrid learning model, a full-dimensional network twin model, and a key flow path enhancement algorithm are optimized based on closed-loop optimization of key operational status data.

2. The SRv6 explicit path intelligent scheduling method based on critical flow according to claim 1, characterized in that, The system collects multi-dimensional dynamic features of traffic, performs keyness scoring using a semi-supervised-transfer hybrid learning model, and outputs key flows carrying latency tolerance thresholds, including: The multi-dimensional dynamic features of collected traffic are input into a semi-supervised-transfer hybrid learning model to perform preliminary criticality scoring and identify potential critical flows. Based on the scoring results and the latency tolerance threshold, the key flow carrying the threshold is output, and the key flow is filtered through dynamic optimization of a semi-supervised-transfer hybrid learning model.

3. The SRv6 explicit path intelligent scheduling method based on critical flow according to claim 1, characterized in that, Collect fine-grained network status data, construct a full-dimensional network twin model, predict congestion risk trends, and verify link path survival rates, including: Collect fine-grained network state data, construct a full-dimensional network twin model, and create a high-precision digital mapping through multi-dimensional data fusion; By using a full-dimensional network twin model, we can predict congestion risk trends and verify link path survival rates. Through real-time simulation and predictive analysis, we can output reliability indicators to guide path selection.

4. The SRv6 explicit path intelligent scheduling method based on critical flow according to claim 1, characterized in that, Based on critical flow and link path survival rates, a list of low-latency source nodes is generated using a critical flow path enhancement algorithm, including: By integrating the latency tolerance threshold of critical flows with the link path survival rate, a weighted directed graph model is constructed, and a topology mining algorithm is used to filter effective source nodes; The critical flow path enhancement algorithm is triggered by the source node, and backtracking pruning is performed in the weighted directed graph model to generate a list of low-latency source nodes that meet the critical flow service level protocol.

5. The SRv6 explicit path intelligent scheduling method based on critical flow according to claim 1, characterized in that, Parse the list of low-latency source nodes to create a micro-segmentation queue, reserve resources for critical flows, and guide non-critical flows to low-load links, including: Parse the list of low-latency source nodes, construct a micro-segmentation queue container at the ingress node, and inject a priority forwarding identifier into the segment route header to reserve bandwidth and time slot resources; Based on real-time link load data, a non-critical flow redirection strategy is generated, and non-critical flows are redirected to low-load paths by combining the entropy value of equivalent multipath.

6. The SRv6 explicit path intelligent scheduling method based on critical flow according to claim 1, characterized in that, When the digital twin detects that the actual state deviates from the predicted value, it invokes the pre-verified backup path identifier chain to complete the path switch in real time, including: By continuously comparing the actual network status with the predicted value using a digital twin, when key indicators exceed dynamic thresholds, a path switching command based on the network service chain is activated. Retrieve the pre-stored backup path identifier chain and perform a segment route identifier stack switching operation to complete traffic rerouting.

7. The SRv6 explicit path intelligent scheduling method based on critical flow according to claim 2, characterized in that, Multi-dimensional dynamic features of collected traffic are input into a semi-supervised-transfer hybrid learning model to perform preliminary criticality scoring and identify potential critical flows; specifically including: Multi-dimensional dynamic features of traffic are collected, including bandwidth fluctuations, transmission latency changes, protocol types, application identifiers, and interaction frequencies. These features are then standardized and preprocessed to form a feature matrix. This feature matrix is ​​input into a semi-supervised-transfer hybrid learning model. The semi-supervised module constructs a feature space mapping using a small number of labeled samples and a large amount of unlabeled traffic data, and uses clustering algorithms to uncover inherent correlation patterns within the traffic. The transfer learning module introduces key flow identification knowledge from similar network scenarios and adjusts model parameters through a domain adaptation mechanism to suit the current network environment. The semi-supervised-transfer hybrid learning model performs hierarchical processing on the input features. First, a feature extraction layer captures key feature vectors, and then a scoring layer outputs a preliminary key score for each traffic flow. The key score K is calculated using the following formula: ； in, and Define the time window boundaries for traffic feature collection. It is the start time of data collection. It is the end time of data collection, used to limit the observation duration of the dynamic characteristics of the flow. It reflects the instantaneous rate of change of bandwidth fluctuation, where B represents bandwidth, which is the amount of data that can be transmitted per unit time, and t represents the current time t; The rate of change of transmission delay; It is a key coefficient of the protocol; Represents application priority; Interaction frequency; It is the feature space mapping distance; The standard deviation of the feature space; middle, It is a matrix trace operation. To label the confidence matrix of the samples, It is the transpose of the domain fitness coefficient matrix M. It is the bandwidth fluctuation Laplace operator; Truncate the order of the series expansion; It represents the application priority standard deviation; n represents the nth order of the series expansion stage; Based on the initial criticality score distribution, an initial threshold is set, and traffic with scores exceeding the threshold is filtered out and marked as potential critical traffic.

8. The SRv6 explicit path intelligent scheduling method based on critical flow according to claim 3, characterized in that, This approach utilizes a full-dimensional network twin model to predict congestion risk trends and verify link path survivability. Real-time simulation and predictive analysis are used to output reliability metrics, guiding path selection. Specifically, this includes: The system invokes a full-dimensional network twin model, inputs real-time collected fine-grained network status data and traffic change trends, and starts a dynamic simulation engine. Time series analysis algorithms are used to extrapolate trends in link bandwidth and node load indicators, predicting the congestion risk level and propagation path of each link in the future. Simultaneously, based on graph theory-based reachability analysis, the system simulates link connectivity under various fault scenarios in the full-dimensional network twin model, calculates the survival probability of different paths within a preset time window, and verifies the link path survival rate. Among them, link path survival rate The formula is: ； Where T represents the total duration of the time window used to analyze the link path status; m represents the number of links that make up the path; Let represent the instantaneous reliability of the i-th link at time t, reflecting the stability of the link over time; n1 is the number of time steps after discretization. It is the interval between adjacent time steps; Let f be the failure rate of the path at the k-1th time step; It is the matrix trace operation, which sums the elements on the main diagonal of a matrix. This is a topology connectivity matrix, used to describe the connectivity relationships between links and nodes in the network topology; It is a node processing capability matrix; It is its inverse matrix; This is the Hadamard product, which integrates topological connectivity information with node processing capability information through this operation; It is the fault recovery rate at the path endpoint L; It is the fault recovery rate at the starting point of the path; This reflects changes in the path fault recovery capability; It is an approximate calculation of the integral of the standard normal distribution, used to quantify the probabilistic characteristics of risks such as path congestion; x is the standardized risk statistic, derived from the path congestion probability. Mean congestion probability Standard deviation The calculation shows that u is the integral variable of the standard normal distribution. The simulation results are integrated with the predicted data, and statistical analysis is used to generate reliability indicators such as path availability time, fault recovery probability, and congestion probability. These indicators are then quantified into evaluation parameters that can be directly used for path decision-making.

9. The SRv6 explicit path intelligent scheduling method based on critical flow according to claim 4, characterized in that, By integrating the latency tolerance threshold of critical flows with the link path survival rate, a weighted directed graph model is constructed, and a topology mining algorithm is used to filter effective source nodes; specifically including: The system receives critical flows and their criticality scores, integrates link data and link path survival rates, and constructs a weighted directed graph model after correlation calibration and standardization. In the weighted directed graph model, nodes correspond to network source nodes and forwarding nodes, edges represent physical links, and edge weights are generated by a weighted fusion algorithm of critical flow criticality scores and link survival rates. Simultaneously, potential source nodes are inferred based on network topology features. Combining the communication characteristics of critical flows and the reachability constraints of network topology, a topology mining algorithm is used to identify candidate source nodes that match the critical flows. By verifying the link path survival rate and criticality scores of the nodes, effective source nodes with the ability to carry critical flows are selected, and their latency sensitivity level and initial path weight values ​​are labeled. The source node selection formula is as follows: ； Where K is the criticality score of the critical flow, used to measure the criticality of the traffic; R represents the node resource reserve, reflecting the remaining resources of the node to handle traffic; and U is the node resource utilization rate. Ψ(t) is the resource sensitivity coefficient; S is the link path survival rate; T represents the length of the time observation window for source node screening; Ψ(t) is the node time-varying availability function, which is the availability of the source node at time t; D is the link delay jitter, which reflects the fluctuation of link transmission delay. Node association matrix With path stability matrix The largest eigenvalue of the matrix after transpose and multiplication is a comprehensive eigenvalue that reflects node association and path stability; For time delay jitter variance; It is the path length. Used to quantify the negative impact of factors such as link latency jitter on source node selection; Historical failure rate of the node; It is the vector of topological coupling coefficients; It is the topological coupling index; is the Fourier transform of the distance attenuation factor; j is the imaginary unit; f is the frequency variable; r is the distance variable.

10. An SRv6 explicit path intelligent scheduling system based on critical flow, characterized in that, The system includes a module for executing the critical flow-based SRv6 explicit path intelligent scheduling method as described in any one of claims 1 to 9.

Images