Communication processing method based on high-quality channel routing scheduling

Abstract

The invention relates to the technical field of communication processing, and discloses a communication processing method based on high-quality channel routing scheduling, which comprises the following steps: initialization and preparation: setting a group of input parameters, importing a pre-trained machine learning model, outputting an initialized parameter set, and setting a set of input parameters; and flow monitoring and early warning: collecting real-time flow statistical data from all network elements through a southbound interface, extracting key features based on historical data and the collected real-time flow statistical data, and defining upper and lower limit thresholds in a normal flow range. According to the invention, an optimal path suggestion for different application types and traffic modes is given, especially an effective coping scheme for burst traffic is given, the user can enjoy smoother and more reliable network service due to more intelligent traffic management and resource allocation, good experience can be kept even in the peak period of network traffic, and the user experience is improved. And adverse effects caused by service interruption due to congestion are avoided.

Description

Technical Field

[0001] The present invention relates to the field of communication processing, and more particularly to a communication processing method based on high-quality channel routing scheduling. Background Art

[0002] In today's era of information explosion, with the rapid development of Internet technology, traditional network architecture is facing unprecedented challenges. On the one hand, the growing data traffic has put forward higher requirements for network bandwidth; on the other hand, the diversified application requirements have also made network management complicated and difficult. Traditional hardware-based network equipment is difficult to adapt to the rapidly changing application environment. Its fixed functions and closed architecture limit the network flexibility and service innovation capabilities.

[0003] In the context of software-defined networking (SDN) combined with network function virtualization (NFV), certain events (such as live broadcasts of large-scale events and reporting of emergencies) can cause a surge in traffic during a specific time period. Links on conventional paths may not be able to withstand the sudden increase in load, resulting in congestion or even service interruption. Summary of the invention

[0004] The present invention provides a communication processing method based on high-quality channel routing scheduling to solve the technical problems in related technologies.

[0005] The present invention provides a communication processing method based on high-quality channel routing scheduling, comprising the following steps:

[0006] S100, initialization and preparation: set a set of input parameters, import a pre-trained machine learning model, and output the initialized parameter set;

[0007] S200, traffic monitoring and early warning: collects real-time traffic statistics from all network elements through southbound interfaces, extracts key features based on historical data and collected real-time traffic statistics, and defines upper and lower thresholds within the normal traffic range;

[0008] S300, Traffic surge detection and response: Once the link utilization in the key features of a link or area deviates from the set threshold, it is immediately marked as a potential traffic surge point, and the relevant edge computing nodes and other network devices are notified. Based on the current network status, one or more emergency paths are quickly calculated, and important traffic is detoured to avoid the congested area and directed to the emergency path;

[0009] S400, intelligent routing adjustment: predict the traffic flow at the next moment, and adjust the cost function to find the path combination that minimizes the total cost;

[0010] S500, instruction issuance and implementation: the calculated path combination with the minimum total cost is converted into a specific routing rule and sent to the corresponding network device through the southbound interface. The edge computing node further optimizes the traffic distribution according to the local situation.

[0011] Furthermore, the input parameters are , the expression is as follows:

[0012] ;

[0013] in represents the network topology matrix, is the link state vector at time t, is the application demand vector;

[0014] The network topology matrix represents the connection relationship between nodes in the network;

[0015] The application requirement vector represents the requirements of different applications for network performance;

[0016] The link state vector represents the status information of each link at the current moment, including bandwidth capacity, utilization, delay, jitter, and packet loss rate;

[0017] The initialized parameter set is .

[0018] Furthermore, the pre-trained machine learning model uses LSTM, which includes a forget gate, an input gate, a cell state, and an output gate. The tth output of the forget gate for:

[0019] ;

[0020] in, is the weight matrix of the forget gate, is the bias term of the forget gate, is the t-1th intermediate representation data and The splicing, is the sigmoid function;

[0021] ;

[0022] The tth output of the input gate and the tth candidate cell state The calculation method is:

[0023] ;

[0024] ;

[0025] in, is the weight matrix of the input gate, is the bias term of the input gate, is the hyperbolic tangent activation function, is the weight matrix for calculating candidate cell states, is the bias term of the candidate cell state;

[0026] The t-th cell state is the state of the t-1th cell and Weighted synthesis, the calculation method is:

[0027] ;

[0028] in, Represents element-by-element multiplication operation;

[0029] The tth activation value of the output gate and the parameter set after the tth initialization The calculation method is:

[0030] ;

[0031] ;

[0032] in, is the weight matrix of the output gate, is the bias term of the output gate.

[0033] Furthermore, historical data refers to network activity information recorded over a certain period of time in the past. Historical data is stored in a network management system or a dedicated log system, including traffic statistics, error reports, and configuration changes;

[0034] Real-time traffic statistics include bandwidth utilization, throughput, latency, jitter, packet loss, and error rates.

[0035] Furthermore, the process of establishing an emergency path is as follows:

[0036] S310, using an algorithm to find all possible paths from the source to the destination;

[0037] Each path is evaluated, considering the following factors: path length, path capacity, and path delay;

[0038] S320, obtaining a candidate path set , through the candidate path set and the corresponding weight vector to calculate the comprehensive score of each candidate path :

[0039] ;

[0040] in, is the path length, is the residual bandwidth of the path, is the total delay of the path, where , and is the corresponding weight parameter;

[0041] S330, and based on the comprehensive score of the selected path Select the optimal set of emergency paths ; According to the optimal emergency path set Update the routing table, redirect the affected traffic to the newly selected optimal emergency path, and output the updated routing rules .

[0042] Furthermore, the calculation formula for the traffic prediction at the next moment is as follows:

[0043] ;

[0044] Use current time point Key features of input and model parameters , combined with the sudden increase in traffic To predict the traffic distribution at the next moment t+1, represents the traffic forecast at the next time t+1, Indicates a sudden increase in traffic. Indicates the impact factor of the sudden increase in traffic, Represents the prediction function.

[0045] Furthermore, the calculation formula for cost function adjustment is as follows:

[0046] ;

[0047] in represents the peak load factor, where Indicates link The peak load, represents the adjusted cost to reflect the additional cost of the traffic surge. Represents the traffic weight factor, which is used to balance the impact of basic cost and predicted traffic. Yes Link The initial cost, Yes Link The maximum capacity.

[0048] Furthermore, the steps for solving the path combination that minimizes the total cost are as follows:

[0049] 1) Through the emergency path collection and the adjusted cost function , for each emergency path , calculate its total cost :

[0050] ;

[0051] in Indicates the link in the emergency path Costs;

[0052] 2) Generate new candidate paths using heuristic algorithms or linear programming methods ;

[0053] The optimization problem is as follows:

[0054] Minimize total cost:

[0055] ;

[0056] in represents the decision variable;

[0057] Flow conservation:

[0058] ;

[0059] in represents the traffic source node, Indicates the destination node; Indicates the amount of data sent. Indicates the amount of received data;

[0060] Link capacity limitation:

[0061] ;

[0062] in Indicates that the link Traffic volume;

[0063] Use heuristic algorithms or linear programming solvers to solve the above optimization problem and obtain a new set of candidate paths. ;

[0064] 3) Enter a new set of candidate paths and the adjusted cost function , for each candidate path , calculate its total cost ;

[0065] ;

[0066] in, is the link in the new candidate path Costs;

[0067] 4) Compare emergency path sets The total cost of the path in and the new set of candidate paths The total cost of the path in , replace the paths with higher total costs in the new candidate path set to form a replaced candidate path set ;

[0068] 5) Collect the optimal emergency paths The emergency path in Sort in ascending order, select the cost lower than the threshold The path is regarded as a set of paths close to the optimal path. ;

[0069] 6) Close to the optimal path and the set of candidate paths after replacement Merge to form a total path set , in the total set of paths Select the path combination that minimizes the total cost ;

[0070] ;

[0071] in is the total cost of the paths in the total path set;

[0072] 7) According to the progressive adjustment plan, gradually migrate the real-time traffic data to the path combination with the minimum total cost on the path in .

[0073] Furthermore, the progressive adjustment plan is as follows:

[0074] Set the migration time window and the proportion of each migration ;

[0075] At each time step In the current flow Migrate to the optimal path:

[0076] ;

[0077] in Indicates the current traffic distribution. Indicates the current traffic on the optimal path.

[0078] The present invention also proposes a storage medium storing non-temporary computer-readable instructions for executing one or more steps in the aforementioned communication processing method based on high-quality channel routing scheduling.

[0079] The beneficial effects of the present invention are:

[0080] The present invention provides an optimal path recommendation for different application types and traffic patterns, especially an effective response plan for burst traffic. Thanks to more intelligent traffic management and resource allocation, users can enjoy smoother and more reliable network services, and maintain a good experience even during peak network traffic periods, avoiding the adverse effects caused by service interruptions due to congestion. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] Figure 1 It is a flow chart of a communication processing method based on high-quality channel routing scheduling proposed by the present invention. DETAILED DESCRIPTION

[0082] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that the discussion of these embodiments is only to enable those skilled in the art to better understand and implement the subject matter described herein, and the functions and arrangements of the elements discussed may be changed without departing from the scope of protection of the contents of this specification. Each example may omit, replace or add various processes or components as needed. In addition, the features described relative to some examples may also be combined in other examples.

[0083] like Figure 1 As shown, a communication processing method based on high-quality channel routing scheduling includes the following steps:

[0084] S100, initialization and preparation:

[0085] Set a set of input parameters:

[0086] ;

[0087] in Represents the input parameters, represents the network topology matrix, is the link state vector at time t, is the application demand vector;

[0088] The network topology matrix represents the connection relationship between nodes (such as routers and switches) in the network;

[0089] The application requirement vector defines the requirements of different applications for network performance, such as minimum bandwidth, maximum latency, etc.

[0090] The link state vector It describes the status information of each link at the current moment, including bandwidth capacity, utilization, delay, jitter, packet loss rate, etc.

[0091] Load model: import a pre-trained machine learning model and output the initialized parameter set ;

[0092] In one embodiment of the present invention, the pre-trained machine learning model uses LSTM (Long Short-Term Memory Network), which includes a forget gate, an input gate, a cell state, and an output gate. The t-th output of the forget gate for:

[0093] ;

[0094] in, is the weight matrix of the forget gate, is the bias term of the forget gate, is the t-1th intermediate representation data and The splicing, is the sigmoid function;

[0095] ;

[0096] The tth output of the input gate and the tth candidate cell state The calculation method is:

[0097] ;

[0098] ;

[0099] in, is the weight matrix of the input gate, is the bias term of the input gate, is the hyperbolic tangent activation function, is the weight matrix for calculating candidate cell states, is the bias term of the candidate cell state;

[0100] The t-th cell state is the state of the t-1th cell and Weighted synthesis, the calculation method is:

[0101] ;

[0102] in, Represents element-by-element multiplication operation;

[0103] The tth activation value of the output gate and the parameter set after the tth initialization The calculation method is:

[0104] ;

[0105] ;

[0106] in, is the weight matrix of the output gate, is the bias term of the output gate.

[0107] S200, flow monitoring and early warning:

[0108] Collect real-time traffic statistics from all network elements through southbound interfaces, and then extract key features based on historical data and collected real-time traffic statistics , the key feature Used to predict future traffic;

[0109] Among them, historical data refers to the network activity information recorded in a certain period of time in the past. Historical data is stored in the network management system (NMS) or a dedicated log system, including traffic statistics, error reports, and configuration changes;

[0110] Real-time traffic statistics include bandwidth utilization, throughput, latency, jitter, packet loss rate, and error rate;

[0111] Threshold setting: define the upper and lower thresholds within the normal flow range and ;

[0112] In one embodiment of the present invention, a southbound interface refers to an interface for communication between a controller and underlying network devices (such as switches, routers, etc.) in a network architecture, especially in a software defined network (SDN) environment. It allows the SDN controller to directly program and configure these devices, thereby achieving centralized management and control of the entire network.

[0113] The main functions of the southbound interface include:

[0114] Configuration management: Through the southbound interface, the SDN controller can set and modify the rules or flow table entries on the network devices. For example, under the Open Flow protocol, the controller can specify how the data packet is forwarded, that is, the matching conditions (such as source IP address, destination IP address, port number, etc.) and the corresponding actions (such as forwarding to a specific port, discarding the data packet, etc.).

[0115] Status acquisition: The controller can collect real-time information from network devices through the southbound interface, such as link status, traffic statistics, error counts, etc. This helps monitor network performance and make corresponding routing decisions.

[0116] Event notification: When a network device detects certain specific events (such as port status changes, new data packets arriving but no matching rules), it can use the southbound interface to send notifications to the controller so that the controller can adjust the policy based on the latest situation.

[0117] Fault handling: In the event of a hardware failure or other abnormal situation, the southbound interface allows the controller to respond quickly and take measures to restore services or reconfigure paths to ensure high availability and reliability of the network.

[0118] S300, Traffic Surge Detection and Response: Once the key characteristics of a link or area are found

[0119] (Link utilization) deviates from the set threshold , , it is immediately marked as a potential traffic surge point, and the relevant edge computing nodes and other network devices are notified to prepare for emergency measures. Based on the current network status (including the status information of all links), one or more emergency paths are quickly calculated to divert important traffic away from the congested area and direct it to the emergency path;

[0120] In one embodiment of the present invention, the process of establishing an emergency path is as follows:

[0121] S310, finding all possible paths from the source to the destination using a breadth-first search (BFS) or depth-first search (DFS) algorithm;

[0122] Each path is evaluated, considering the following factors:

[0123] Path length: Shorter paths are generally better.

[0124] Path capacity: Select a path with sufficient remaining bandwidth.

[0125] Path delay: Select the path with lower delay to ensure service quality.

[0126] S320, obtaining a candidate path set , through the candidate path set and the corresponding weight vector (defining the weight of each evaluation factor), calculate the comprehensive score of each candidate path :

[0127] ;

[0128] in, is the path length, is the residual bandwidth of the path, is the total delay of the path, where , and is the corresponding weight parameter.

[0129] S330, and based on the comprehensive score of the selected path Select the optimal set of emergency paths ; According to the optimal emergency path set Update the routing table, redirect the affected traffic to the newly selected optimal emergency path, and output the updated routing rules ;

[0130] S400, intelligent routing adjustment:

[0131] S410, traffic prediction update, the calculation formula is as follows:

[0132] ;

[0133] Use current time point Key features of input and model parameters , combined with the sudden increase in traffic To predict the traffic distribution at the next moment t+1, represents the traffic forecast at the next time t+1, Indicates a sudden increase in traffic. Indicates the impact factor of the sudden increase in traffic, represents the prediction function;

[0134] S420, cost function adjustment, the calculation formula is as follows:

[0135]

[0136] in represents the peak load factor, where Indicates link The peak load, represents the adjusted cost to reflect the additional cost of the traffic surge. Represents the traffic weight factor, which is used to balance the impact of basic cost and predicted traffic. Yes Link The initial cost, Yes Link Maximum capacity;

[0137] S430, solving the optimal path: using heuristic algorithms or linear programming methods to find the path combination that minimizes the total cost .

[0138] 1) Through the emergency path collection and the adjusted cost function , for each emergency path , calculate its total cost :

[0139] ;

[0140] in Indicates the link in the emergency path Costs;

[0141] 2) Generate new candidate paths using heuristic algorithms or linear programming methods ;

[0142] The optimization problem is as follows:

[0143] Minimize total cost:

[0144] ;

[0145] in represents the decision variable;

[0146] Flow conservation:

[0147] ;

[0148] in represents the traffic source node, Indicates the destination node; Indicates the amount of data sent. Indicates the amount of received data;

[0149] Link capacity limitation:

[0150] ;

[0151] in Indicates that the link Traffic volume;

[0152] Use heuristic algorithms (such as genetic algorithms, simulated annealing) or linear programming solvers (such as Simplex algorithm, interior point method) to solve the above optimization problem and obtain a new set of candidate paths. ;

[0153] 3) Enter a new set of candidate paths and the adjusted cost function , for each candidate path , calculate its total cost ;

[0154] ;

[0155] in, is the link in the new candidate path Costs;

[0156] 4) Compare emergency path sets The total cost of the path in and the new set of candidate paths The total cost of the path in , replace the paths with higher total costs in the new candidate path set to form a replaced candidate path set ;

[0157] 5) Collect the optimal emergency paths The emergency path in Sort in ascending order, select the ones with cost lower than the threshold The path is regarded as a set of paths close to the optimal path. ;

[0158] 6) Close to the optimal path and the set of candidate paths after replacement Merge to form a total path set , in the total set of paths Select the path combination that minimizes the total cost ;

[0159] ;

[0160] in is the total cost of the paths in the total path set;

[0161] 7) According to the progressive adjustment plan, gradually migrate the real-time traffic data to the path combination with the minimum total cost on the path in;

[0162] The gradual adjustment plan is as follows:

[0163] 1. Set the migration time window and the proportion of each migration ;

[0164] 2. At each time step In the current flow Migrate to the optimal path:

[0165] ;

[0166] in Indicates the current traffic distribution. Indicates the current flow on the optimal path;

[0167] S500, instruction issuance and implementation: path combination that minimizes the calculated total cost Converted into specific routing rules and sent to the corresponding network devices through the southbound interface, the edge computing node can further optimize traffic distribution according to local conditions and reduce the pressure on the core network.

[0168] In one embodiment of the present invention, the following steps are specifically included:

[0169] S510, routing rule generation:

[0170] Convert each optimal path into specific routing rules and generate , verify the routing rules , to ensure its correctness and security, forming ;

[0171] S520, command issued:

[0172] Build control instructions , and send it to the corresponding network device through the southbound interface to collect the sending status report , confirm that the instruction was successfully executed;

[0173] S530, edge computing node optimization:

[0174] Edge computing nodes analyze local traffic data , generate analysis results , formulate and implement optimization strategies based on the analysis results , adjust local traffic distribution; monitor the optimization effect to ensure that the core network pressure is reduced and form an optimized local traffic distribution .

[0175] Develop optimization strategies based on the analysis results , such as caching hot content, adjusting service deployment locations, enabling load balancing, etc. For critical business traffic, consider setting higher priorities or dedicated channels.

[0176] An embodiment of the present invention further provides a storage medium storing non-transitory computer-readable instructions for executing one or more steps in the aforementioned communication processing method based on high-quality channel routing scheduling.

[0177] The computer program may be stored / distributed on suitable media, such as optical storage media or solid-state media supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems.

[0178] The above describes an embodiment of the present embodiment, but the present embodiment is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present embodiment, ordinary technicians in this field can also make many forms, all of which are within the protection of the present embodiment.

Claims

1. A communication processing method based on high-quality channel routing scheduling, characterized in that: The following steps are involved: S100, setting a set of input parameters, importing a pre-trained machine learning model, and outputting an initialized parameter set; S200, collects real-time traffic statistics from all network elements through southbound interfaces, extracts key features based on historical data and collected real-time traffic statistics, and defines upper and lower thresholds within the normal traffic range; S300: When the link utilization rate of a key feature of a link or region deviates from the set threshold, it is immediately marked as a potential traffic surge point, and the relevant edge computing nodes and network devices are notified. According to the current network status, at least one emergency path is calculated, and important traffic is detoured to avoid the congested area and directed to the emergency path. S400, predicting the traffic flow at the next moment, and adjusting the cost function to find a path combination that minimizes the total cost; S500 converts the calculated path combination with the minimum total cost into a routing rule and sends it to the corresponding network device through the southbound interface. The edge computing node further optimizes the traffic distribution according to the local situation.

2. A communication processing method based on high-quality channel routing scheduling according to claim 1, characterized in that: The input parameters include the network topology matrix, the link state vector at time t, and the demand vector; The network topology matrix represents the connection relationship between nodes in the network; The application requirement vector represents the requirements of different applications for network performance; The link state vector represents the status information of each link at the current moment, including bandwidth capacity, utilization, delay, jitter, and packet loss rate.

3. A communication processing method based on high-quality channel routing scheduling according to claim 2, characterized in that: The pre-trained machine learning model uses LSTM, which includes a forget gate, an input gate, a cell state, and an output gate.

4. A communication processing method based on high-quality channel routing scheduling according to claim 3, characterized in that: Historical data refers to network activity information recorded over a certain period of time in the past. Historical data is stored in network management systems and specialized log systems, including traffic statistics, error reports, and configuration changes. Real-time traffic statistics include bandwidth utilization, throughput, latency, jitter, packet loss, and error rates.

5. A communication processing method based on high-quality channel routing scheduling according to claim 4, characterized in that: The process of establishing an emergency path is as follows: S310, using an algorithm to find all possible paths from the source to the destination; Each path is evaluated, considering the following factors: path length, path capacity, and path delay; S320, obtaining a set of candidate paths, and calculating a comprehensive score of each candidate path through the set of candidate paths and a corresponding weight vector; S330, and select the optimal emergency path set according to the comprehensive score of the selected path; update the routing table according to the optimal emergency path set, redirect the affected traffic to the newly selected optimal emergency path, and output the updated routing rules.

6. A communication processing method based on high-quality channel routing scheduling according to claim 5, characterized in that: The calculation formula for the traffic prediction at the next moment is as follows: ； Use current time point Key features of input and model parameters , combined with the sudden increase in traffic To predict the traffic distribution at the next moment t+1, represents the traffic forecast at the next time t+1, Indicates a sudden increase in traffic. Indicates the impact factor of the sudden increase in traffic, Represents the prediction function.

7. A communication processing method based on high-quality channel routing scheduling according to claim 6, characterized in that: The calculation formula for cost function adjustment is as follows: ； in represents the peak load factor, where Indicates link The peak load, represents the adjusted cost to reflect the additional cost of the traffic surge. Represents the traffic weight factor, which is used to balance the impact of basic cost and predicted traffic. Yes Link The initial cost, Yes Link The maximum capacity.

8. A communication processing method based on high-quality channel routing scheduling according to claim 7, characterized in that: The steps to solve the path combination that minimizes the total cost are as follows: By using the emergency path set and the adjusted cost function, the total cost of each emergency path is calculated; Generate new candidate paths using heuristic algorithms and linear programming methods; The optimization problem involves minimizing total cost, flow conservation, and link capacity constraints; Use heuristic algorithms and linear programming solvers to solve the above optimization problem and obtain a new set of candidate paths; Input the new candidate path set and the adjusted cost function, and calculate the total cost of each candidate path; Compare the total cost of the paths in the emergency path set with the total cost of the paths in the new candidate path set, replace the paths with higher total costs in the new candidate path set, and form a replaced candidate path set; Sort the emergency paths in the optimal emergency path set in ascending order of cost, and select the paths with costs lower than a threshold as the near-optimal path set; The nearly optimal path is merged with the replaced candidate path set to form a total path set, and the path combination with the minimum total cost is selected from the total path set; According to the formulated progressive adjustment plan, the real-time traffic data is gradually migrated to the paths in the path combination with the minimized total cost.

9. A communication processing method based on high-quality channel routing scheduling according to claim 8, characterized in that: The gradual adjustment plan is as follows: Set the migration time window and the ratio of each migration; In each time step, the current flow Migrate to the optimal path: ； in Indicates the current traffic distribution. Indicates the current traffic on the optimal path.

10. A storage medium storing non-transitory computer-readable instructions for executing the steps in a communication processing method based on high-quality channel routing scheduling as described in any one of claims 1 to 9.

Images