Two-layer wide area network flow management system

By analyzing the coefficient of variation of data flows in the second-layer wide area network traffic management system, optimizing traffic allocation and resource allocation, the problems of network congestion and performance degradation in the existing technology are solved, and more efficient and flexible traffic management is achieved to ensure data transmission stability and response speed.

CN118921334APending Publication Date: 2024-11-08GUIZHOU QIANYUN NETWORK INFORMATION TECHNOLOGY CO LTD
View PDF 0 Cites 4 Cited by

Patent Information

Application Number
CN202411140748.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-20
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The existing layer 2 WAN traffic management system is difficult to accurately predict and deal with traffic fluctuations in a short time when processing large amounts of data flows, resulting in network congestion and performance degradation, and lacks flexibility in resource allocation, making it difficult to achieve rapid response to high-priority tasks. .

Method used

The traffic stability analysis module is used to calculate the coefficient of variation of the data flow, generate the traffic stability measurement results, divide the priority traffic queue through the traffic sorting adjustment module, the resource allocation optimization module allocates network resources according to the priority, and the transmission efficiency monitoring module monitors the data flow transmission Rate and network quality, stop point decision module evaluates the continued transmission or stop of data flow, and network performance analysis module continuously monitors and identifies potential performance problems.

Benefits of technology

By dynamically analyzing the coefficient of variation of data flows, optimizing traffic allocation, improving network resource utilization and response speed, reducing the risks of congestion and performance bottlenecks, ensuring that critical tasks obtain the necessary bandwidth, and improving the decision-making efficiency and execution quality of data transmission.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118921334A_ABST
    Figure CN118921334A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of network flow management, in particular to a two-layer wide area network flow management system, which comprises a flow stability analysis module, a flow stability analysis module, a flow stability analysis module, a flow stability analysis module, a flow stability analysis module, a flow stability analysis module, a flow stability analysis module and a flow stability analysis module, and generating a flow stability measurement result. According to the invention, the utilization rate and the response speed of network resources are improved by dynamically analyzing the variable coefficient of each data stream and adjusting the flow distribution according to the volatility of the variable coefficient. A network administrator is allowed to accurately manage and predict the traffic peak on the real-time basis, and the risks of congestion and performance bottleneck are reduced. And it is ensured that the key task can obtain the necessary bandwidth in the burst traffic event. By optimizing scheduling of the data flow, resource waste under an unstable network condition is reduced, and decision efficiency and execution quality of data transmission are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of network traffic management, and in particular to a layer 2 wide area network traffic management system. Background Art

[0002] Network traffic management monitors, regulates, and optimizes data flows in the network. The field focuses on how to effectively allocate network resources to meet the needs of different types of data traffic, including identifying and classifying network traffic types, implementing traffic regulation strategies, and dynamically allocating network bandwidth. The core purpose of network traffic management is to maintain the basic operation of the network through these means and to maximize the efficiency of data transmission.

[0003] Among them, the Layer 2 WAN traffic management system refers to the management of data link layer (Layer 2) traffic in a WAN environment. The main function is to monitor and control data transmission on the Layer 2 of the WAN, and to achieve rapid detection and analysis of network lines. By detecting the status of network lines, adjusting and managing data packets flowing through these lines, data can be correctly routed and transmitted on physical or logical links. In this way, communication on the data link layer is processed and optimized to ensure that data can be effectively transmitted between various network nodes.

[0004] The current Layer 2 WAN traffic management method focuses on traffic monitoring and control at the data link layer. When processing large amounts of data flows, it is difficult to accurately predict and respond to traffic fluctuations in a short period of time, resulting in network congestion and performance degradation. In addition, there is a lack of flexibility in resource allocation, making it difficult to achieve a rapid response to high-priority tasks. This limits the overall performance of the network, and it is difficult to ensure efficient and stable data transmission in high-demand and complex network environments. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose a two-layer wide area network traffic management system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a layer 2 wide area network traffic management system, the system comprising:

[0007] The traffic stability analysis module collects the data flow information transmitted in the Layer 2 WAN, calculates the ratio of the standard deviation of each data flow to the average value, extracts the coefficient of variation of each data flow, and generates the traffic stability measurement result;

[0008] The traffic sorting adjustment module divides the processing order of the data stream according to the sorting result based on the coefficient of variation in the traffic stability measurement result, and generates a priority traffic queue;

[0009] The resource allocation optimization module uses the priority traffic queue to adjust the network bandwidth, allocates network resources according to the priority of each data flow, and generates adjusted resource allocation data;

[0010] The transmission efficiency monitoring module monitors the transmission rate and data volume of active data flows, collects network quality indicators corresponding to transmission, extracts key performance indicators, and generates data flow transmission information;

[0011] The stopping point decision module evaluates the continued transmission or stopping of the data flow based on the data flow transmission information, selects the resource use switching point, and generates a resource reconfiguration result;

[0012] The network performance analysis module integrates the adjusted resource allocation data and resource reconfiguration results, continuously monitors network performance, identifies potential performance issues, and generates real-time network performance data.

[0013] The present invention has improvements in that the flow stability measurement result includes the average volatility of the data flow, the highest volatility record and the volatility distribution diagram, the priority flow queue includes the priority number of the data flow, the priority level classification and the queue sorting diagram associated with the priority, the adjusted resource allocation data includes the resource allocation value, the resource utilization rate of the data flow after allocation and the resource allocation optimization, the data flow transmission information includes the real-time data transmission rate table, data volume statistics and key network indicators, the resource reconfiguration result includes the time node of the resource configuration adjustment and the resource allocation comparison information before and after the configuration, and the real-time network performance data includes the real-time monitoring chart of the network performance, the network performance rating and the real-time data of the network status.

[0014] The present invention is improved in that the flow stability analysis module comprises:

[0015] The data receiving submodule receives the data flow information transmitted in the Layer 2 WAN, including the size, transmission interval and time stamp of each data packet, extracts key transmission features, and generates basic traffic data;

[0016] The volatility analysis submodule adopts a weighted round-robin method to calculate the ratio of the standard deviation to the average value of each data flow from the basic flow data, obtains the volatility index of each data flow, and generates a volatility index table;

[0017] The stability assessment submodule uses the volatility index table to perform quantitative analysis on the stability of each data flow, identify data flows whose volatility exceeds a predetermined threshold, and generate flow stability measurement results.

[0018] The present invention is improved in that the weighted polling method is according to the formula:

[0019]

[0020] and

[0021]

[0022] Calculate the adjusted standard deviation σ′ and the adjusted mean packet size μ′;

[0023] Among them, S i is the size of the ith packet, n is the total number of packets, P j is the priority of data stream j, T j is the duration of data stream j, M j is the peak value of data flow j, and B represents the network bandwidth used by the data flow;

[0024] According to the formula:

[0025]

[0026] Calculate the volatility index V′;

[0027] Among them, V′ is used to measure the stability of the data flow under the adjusted conditions.

[0028] The present invention is improved in that the flow sorting adjustment module comprises:

[0029] The volatility sorting submodule sorts the data streams according to the volatility index in the flow stability measurement result, and generates a sorted data stream list;

[0030] The priority setting submodule analyzes the sorted data stream list, sets priorities for the data streams, assigns a processing order label to each data stream, and generates a priority setting result;

[0031] The queue configuration submodule forms a data flow processing queue according to the priority setting result, arranges the data flows in the set priority order, and generates a priority traffic queue.

[0032] The present invention is improved in that the resource allocation optimization module includes:

[0033] The network demand analysis submodule analyzes the resource usage of data flows in the network based on the priority traffic queue, including current bandwidth consumption and expected traffic growth, performs resource demand prediction, and generates resource demand analysis results;

[0034] The bandwidth allocation submodule adjusts the bandwidth configuration to match the requirements of multiple data flows according to the resource requirement analysis result and generates a bandwidth configuration record;

[0035] The resource optimization submodule uses the bandwidth configuration record to perform resource allocation operations, configures network resources among data flows according to priorities, and generates adjusted resource allocation data.

[0036] The present invention is improved in that the transmission efficiency monitoring module comprises:

[0037] The traffic monitoring submodule monitors active data flows, records the current transmission rate and total data volume of the data flows, and generates active data flow records;

[0038] The performance data extraction submodule extracts key network performance indicators from the active data flow records, including real-time delay and packet loss, evaluates key network performance indicators, and generates key performance indicator data;

[0039] The efficiency information summary submodule uses the key performance indicator data to analyze the transmission efficiency and status of the entire network, evaluate the overall network performance, and generate data flow transmission information.

[0040] The present invention is improved in that the stopping point decision module comprises:

[0041] The transmission status evaluation submodule analyzes the current transmission status and resource usage of each data stream based on the data stream transmission information, determines the transmission parameters to be evaluated, and generates a transmission parameter analysis result;

[0042] The decision point calibration submodule uses the transmission parameter analysis result to evaluate the necessity of continuing transmission or stopping of each data stream through the optimal stopping theory, determines the resource use switching point, and generates switching point decision data;

[0043] The resource configuration adjustment submodule adjusts the network resource configuration according to the switching point decision data and generates a resource reconfiguration result.

[0044] The present invention is improved in that the optimal stopping theory is according to the formula:

[0045]

[0046] Analyze the need to continue or stop each data flow;

[0047] Among them, C′ j is the decision value, indicating the decision to continue transmission or stop the jth data stream, ω C,E Efficiency E eff,j The weight coefficient, ω C,M is the data flow peak value M j For the weight coefficient of the total bandwidth B, E eff,j is the efficiency of the jth data stream, M j is the peak value of the jth data stream, B is the total bandwidth of the network, γ C,U is the resource utilization U j The weight coefficient, γ C,D is the average delay D jThe weight coefficient, U j is the resource utilization of the jth data stream, D j is the average delay of the jth data flow.

[0048] The present invention is improved in that the network performance analysis module comprises:

[0049] The performance data integration submodule integrates the adjusted resource allocation data and resource reconfiguration results, analyzes the overall resource allocation and utilization efficiency, and generates resource utilization analysis results;

[0050] The problem diagnosis submodule identifies network performance bottlenecks and potential problems based on the resource usage analysis results, analyzes key factors affecting network performance, and generates network problem diagnosis results;

[0051] The performance monitoring submodule applies the network problem diagnosis results to continuously monitor network performance, re-judge the network operation status, and generate real-time network performance data.

[0052] Compared with the prior art, the advantages and positive effects of the present invention are:

[0053] In the present invention, by dynamically analyzing the coefficient of variation of each data flow and adjusting the flow distribution according to its volatility, the utilization rate and response speed of network resources are improved. It allows network administrators to accurately manage and predict flow peaks on a real-time basis, reducing the risk of congestion and performance bottlenecks. It ensures that critical tasks can obtain the necessary bandwidth during sudden flow events. By optimizing the scheduling of data flows, the waste of resources under unstable network conditions is reduced, and the decision-making efficiency and execution quality of data transmission are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A module diagram of a layer 2 wide area network traffic management system is proposed for the present invention;

[0055] Figure 2 A system framework diagram of a layer 2 wide area network traffic management system is proposed for the present invention;

[0056] Figure 3 is a schematic diagram of a flow stability analysis module of the present invention;

[0057] Figure 4 A schematic diagram of a flow sorting and adjusting module of the present invention;

[0058] Figure 5 It is a schematic diagram of the resource allocation optimization module of the present invention;

[0059] Figure 6 is a schematic diagram of a transmission efficiency monitoring module of the present invention;

[0060] Figure 7 is a schematic diagram of a stopping point decision module of the present invention;

[0061] Figure 8 Schematic diagram of the network performance analysis module of the present invention. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0063] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0064] See also Figure 1 The present invention provides a technical solution: a layer 2 wide area network traffic management system, the system comprising:

[0065] The traffic stability analysis module collects the data flow information transmitted in the Layer 2 WAN, calculates the ratio of the standard deviation of each data flow to the average value, extracts the coefficient of variation of each data flow, and generates the traffic stability measurement result;

[0066] The traffic sorting adjustment module divides the processing order of data flows according to the sorting results based on the coefficient of variation in the traffic stability measurement results and generates priority traffic queues;

[0067] The resource allocation optimization module uses priority traffic queues to adjust network bandwidth, allocates network resources according to the priority of each data flow, and generates adjusted resource allocation data;

[0068] The transmission efficiency monitoring module monitors the transmission rate and data volume of active data flows, collects network quality indicators corresponding to transmission, extracts key performance indicators, and generates data flow transmission information;

[0069] The stop point decision module evaluates the continuation or stop of data flow transmission based on data flow transmission information, selects the resource use switching point, and generates resource reconfiguration results;

[0070] The network performance analysis module integrates the adjusted resource allocation data and resource reconfiguration results, continuously monitors network performance, identifies potential performance issues, and generates real-time network performance data.

[0071] The traffic stability measurement results include the average volatility of the data flow, the highest volatility record and the volatility distribution diagram; the priority traffic queue includes the priority number of the data flow, the priority level classification and the queue sorting diagram associated with the priority; the adjusted resource allocation data includes the resource allocation value, the resource utilization rate of the data flow after allocation and the resource allocation optimization; the data flow transmission information includes the real-time data transmission rate table, data volume statistics and key network indicators; the resource reconfiguration results include the time node of the resource configuration adjustment and the resource allocation comparison information before and after the configuration; the real-time network performance data includes the real-time monitoring chart of the network performance, the network performance rating and the real-time data of the network status.

[0072] See also Figure 2 and Figure 3 , the flow stability analysis module includes:

[0073] The data receiving submodule receives the data flow information transmitted in the Layer 2 WAN, including the size, sending interval and time stamp of each data packet, extracts key transmission features, and generates basic traffic data in the following process;

[0074] Collect data flow information transmitted in the Layer 2 WAN, record the size, sending interval and time stamp of each data packet, and provide basic data for subsequent analysis. Calculate using the following formula: and S represents the sum of all data packet sizes. i represents the size of the ith data packet. n represents the total number of data packets. I represents the average value of the intervals between all data packets sent. i Represents the sending interval of the i-th data packet.

[0075] The volatility analysis submodule uses a weighted round-robin method to calculate the ratio of the standard deviation to the mean value of each data flow from the basic traffic data to obtain the volatility index of each data flow. The process of generating the volatility index table is as follows;

[0076] The weighted round-robin method is used to evaluate the stability of each data flow, and the standard deviation and average value and volatility index are calculated to further process the basic flow data;

[0077] The weighted round robin method is based on the formula:

[0078]

[0079] and

[0080]

[0081] Calculate the adjusted standard deviation σ′ and the adjusted mean packet size μ′;

[0082] Among them, S i is the size of the ith packet, n is the total number of packets, used for normalization calculation, P j is the priority of data flow j, which affects the importance of data flow in the network and resource allocation, T j is the duration of data stream j, which is used to measure the active period of data stream, M j is the peak value of data stream j, indicating the maximum load capacity of the data stream. B represents the network bandwidth used by the data stream and is related to the priority P of the data stream. j and peak value M j Combined, this determines the adjustment factor for the average packet size;

[0083] According to the formula:

[0084]

[0085] Calculate the volatility index V′;

[0086] Among them, V′ is used to measure the stability of the data flow under the adjusted conditions.

[0087] The calculation process is as follows:

[0088] In order to combine the bandwidth utilization and priority of the data flow, the size S of each data packet is i Weighted processing is performed. The weight is determined by the bandwidth ratio of the data flow. Decide, Consider bandwidth B and priority P j and data flow peak M j The importance factor of the data packet. The formula is:

[0089]

[0090] The size of each data packet is S i Multiply it by its importance factor, add up all the results and divide by the total number of packets n.

[0091] Calculate the adjusted standard deviation σ′:

[0092] Calculate the size S of each data packet i The deviation from the adjusted mean μ′ is then multiplied by the priority P of the data flow. j Duration T j and divided by the peak value M j To adjust the influence of the deviation. The formula is:

[0093]

[0094] The adjusted standard deviation σ′ is obtained by summing the squares of each adjusted deviation, dividing it by the total number of packets n and taking the square root.

[0095] Calculate the volatility index V′:

[0096] The modified volatility index is calculated by dividing the adjusted standard deviation σ′ by the adjusted mean μ′. The formula is:

[0097]

[0098] The final volatility index V′ provides a more comprehensive assessment of data flow stability. By considering the priority, duration, and peak value of data flows, the stability assessment is more in line with the dynamic conditions of the actual network.

[0099] The stability assessment submodule uses the volatility index table to quantitatively analyze the stability of each data flow, identify data flows whose volatility exceeds a predetermined threshold, and generate the flow stability measurement results in the following process;

[0100] The volatility index table obtained from the volatility analysis is used to quantitatively analyze the stability of each data stream. A predetermined threshold T is set and the volatility index V of each data stream is checked to see if it exceeds this threshold. Data streams that exceed the threshold T are considered unstable and will be marked. The unstable marking process is completed by comparing the relationship between the volatility index V and the threshold T.

[0101] See also Figure 2 and Figure 4 , the traffic sorting adjustment module includes:

[0102] The volatility sorting submodule sorts the data streams according to the volatility index in the flow stability measurement result, and the process of generating the sorted data stream list is as follows;

[0103] Using the collected volatility index V j Sort the data streams. This module uses the following sorting algorithm to sort the data streams according to the volatility index V j , determine its sort position P in the list j : P j Indicates the sorting position of data stream j. V j and V r are the volatility indices of data streams j and r, respectively. m is the total number of data streams. r is the index of the data stream used for comparison. 1(·) is the indicator function, which is j >V rThe value is 1 if true, otherwise 0.

[0104] The priority setting submodule analyzes the sorted data stream list, sets priorities for the data streams, and assigns a processing order label to each data stream. The process of generating the priority setting result is as follows;

[0105] Analyze the sorted data stream list and set a priority for each data stream. j , calculate the processing order label L j :L j =mP j , L j Indicates the priority label of data flow j, which is used to indicate the priority in the processing queue. m is the total number of data flows. j is the sorting position of data stream j.

[0106] The queue configuration submodule forms a data flow processing queue based on the priority setting result, arranges the data flow in the set priority order, and generates a priority traffic queue in the following process:

[0107] According to the priority setting results, a data stream processing queue is established. The data streams are sorted in the set priority order. j Arrange,create a priority traffic queue Q, where the position of each data flow is determined by its priority label: Q k =D argminx(Lx) , Q k Indicates the kth data flow position in the priority queue. x is the data stream x. x is the priority label of data stream x. argmin is a mathematical function used to select the x The smallest data stream index is x, which indicates that x represents the highest priority data stream.

[0108] See 2 and Figure 5 , the resource allocation optimization module includes:

[0109] The network demand analysis submodule analyzes the resource usage of data flows in the network based on the priority traffic queue, including the current bandwidth consumption and expected traffic growth, and makes resource demand predictions. The process of generating resource demand analysis results is as follows;

[0110] Based on the priority traffic queue, analyze the resource usage of data flows in the network, including the current bandwidth consumption cur and expected traffic growth G. The formula for computing resource demand prediction is redefined as follows: B req Indicates the predicted bandwidth demand. curIndicates the current bandwidth consumption. G indicates the expected traffic growth coefficient. α B,j It represents the growth sensitivity coefficient of data flow j, which is specifically used for bandwidth calculation. j represents the current bandwidth usage of the jth data flow in the queue. m is the total number of data flows in the queue.

[0111] The bandwidth allocation submodule adjusts the bandwidth configuration to match the requirements of multiple data streams according to the resource demand analysis results, and generates the bandwidth configuration record in the following process:

[0112] Adjust bandwidth configuration based on resource demand analysis results to match the needs of multiple data flows. Bandwidth allocation calculation is redefined as follows: B new,j represents the bandwidth of the jth data stream after adjustment. base is the basic bandwidth allocation. B It is an adjustment factor used to balance bandwidth allocation for different data streams and is specifically used for bandwidth adjustment.

[0113] The resource optimization submodule uses the bandwidth configuration record to perform resource allocation operations, configures network resources between data streams according to priority, and generates the adjusted resource allocation data in the following process:

[0114] Use bandwidth configuration records to perform resource allocation operations and allocate network resources between data flows according to priority. The resource optimization calculation is updated as follows: R alloc,j Indicates the amount of resources allocated to the jth data flow. new,j The adjusted bandwidth is defined as above. B total is the total bandwidth of the network. total is the total amount of network resources.

[0115] See also Figure 2 and Figure 6 , the transmission efficiency monitoring module includes:

[0116] The traffic monitoring submodule monitors active data flows, records the current transmission rate and total data volume of the data flows, and the process of generating active data flow records is as follows;

[0117] Monitor active data flows and record the current transmission rate V of each data flow rate,j and the total data volume V total,j In order to calculate the overall transmission efficiency E of active data flows eff , using the following formula: V rate,j V represents the transmission rate of the jth data stream. total,j represents the total data volume of the jth data stream. q is the number of active data streams. eff Represents overall efficiency.

[0118] The performance data extraction submodule extracts key network performance indicators from active data flow records, including real-time delay and packet loss, and evaluates key network performance indicators. The process of generating key performance indicator data is as follows;

[0119] Extract key network performance indicators from active data flow records, including real-time latency real,j And packet loss P loss,j . To evaluate the network performance of each data flow, use the formula: D real,j P represents the real-time delay of the jth data stream. loss,j Indicates the number of packet losses of the jth data stream. ∈ K is the packet loss impact coefficient, specifically for K j The calculation setting is used to adjust the weight of the impact of delay and packet loss on performance indicators. j represents the key performance indicator of the jth data stream.

[0120] The efficiency information summary submodule uses key performance indicator data to analyze the transmission efficiency and status of the entire network, evaluate the overall network performance, and generate data flow transmission information in the following process:

[0121] Using key performance indicator data K j Analyze the transmission efficiency and status of the entire network. The overall performance index of the network is P net Calculated by the following formula: K j is the key performance indicator of the jth data flow calculated from the performance data extraction submodule. q is the number of active data flows. P net Represents the average performance indicator of the entire network.

[0122] See also Figure 2 and Figure 7 , the stopping point decision module includes:

[0123] The transmission status evaluation submodule analyzes the current transmission status and resource usage of each data stream based on the data stream transmission information, determines the transmission parameters to be evaluated, and generates the transmission parameter analysis results in the following process:

[0124] Analyze the current transmission status and resource usage of each data flow. The evaluation includes transmission efficiency E eff,j and resource utilization U j : E eff,j represents the transmission efficiency of the jth data stream. j V represents the resource utilization of the jth data stream. rate,j is the transmission rate of the jth data stream. V total,jis the total data volume of the jth data stream. total,j is the total amount of resources allocated to the jth data flow.

[0125] The decision point calibration submodule uses the transmission parameter analysis results to evaluate the necessity of continuing transmission or stopping each data stream through the optimal stopping theory, determines the resource usage switching point, and generates the switching point decision data in the following process;

[0126] Using the transmission parameter analysis results, the necessity of continuing transmission or stopping of each data flow is evaluated through the optimal stopping theory.

[0127] The optimal stopping theory is based on the formula:

[0128]

[0129] Analyze the need to continue or stop each data flow;

[0130] Among them, C′ j is the decision value, which indicates the decision of continuing transmission or stopping of the jth data stream, and is used to evaluate whether the data stream should continue to be transmitted or stopped. C,E Efficiency E eff,j The weight coefficient is used to strengthen or weaken the influence of efficiency in the decision-making process, ω C,M is the data flow peak value M j The weight coefficient relative to the total bandwidth B is used to adjust the importance of the peak in the decision, E eff,j is the efficiency of the jth data stream, which is usually determined by factors such as the transmission rate and error rate of the data stream. j is the peak value of the jth data flow, indicating the maximum data transmission volume of the data flow at any given moment. B is the total bandwidth of the network, which is used to normalize the data flow peak value to make it suitable for comparison of different network capacities. C,U is the resource utilization U j The weight coefficient adjusts the influence of resource utilization in decision making, γ C,D is the average delay D j The weight coefficient reflects the importance of delay in data flow management decisions, U j is the resource utilization of the jth data stream, which is usually determined by the resource demand and resource allocation ratio. j is the average delay of the jth data stream, which affects the performance of the data stream and the user experience.

[0131] The calculation process is as follows:

[0132] Calculate the efficiency E of the data flow eff,j :

[0133] Assume V rate,j represents the rate of the jth data stream, Vtotal,j Indicates the total amount of data. Efficiency E eff,j Determined by the ratio of data flow rate to total data volume:

[0134]

[0135] Calculate the resource utilization U of the data flow j :

[0136] Assume R alloc,j is the resource allocated to data flow j. Resource utilization U j It is expressed by the ratio of resources used by a data flow to allocated resources:

[0137]

[0138] Import and calculate the data flow peak to bandwidth ratio

[0139] M j is the maximum transmission volume of data stream j at any time. B is the total network bandwidth. The ratio reflects the proportion of the peak value of the data stream to the entire network bandwidth, which helps to evaluate the pressure of a single data stream on network resources.

[0140] Calculate the average delay D of the data flow j :

[0141] Assumption D j It can be obtained from the network monitoring system and represents the average response time of the data flow. This parameter directly affects the user experience and the service quality of the data flow.

[0142] Determination of weight coefficient:

[0143] Weight coefficient ω C,E ,ω C,M , γ C,U and γ C,D It should be determined based on network policies, historical performance data, or through optimization algorithms (such as linear regression, machine learning, etc.), reflecting the network's operational priorities and management goals.

[0144] By comprehensively considering the efficiency, peak ratio, resource utilization and average delay of the data flow, the decision value C′ j Comprehensive metrics are provided to determine whether each data flow should continue to transmit or stop.

[0145] The resource configuration adjustment submodule adjusts the network resource configuration according to the switching point decision data, and the process of generating the resource reconfiguration result is as follows;

[0146] Based on decision point data C j , adjust network resource configuration, including calculation of resource reallocation: R new,j Represents the resource configuration of the jth data stream after adjustment. R It is the adjustment sensitivity coefficient, which is specially designed for resource allocation R new,j Adjustment design. is the decision value of all data flows C j The average value of .

[0147] See also Figure 2 and Figure 8 , the network performance analysis module includes:

[0148] The performance data integration submodule integrates the adjusted resource allocation data and resource reconfiguration results, analyzes the overall resource allocation and utilization efficiency, and generates resource utilization analysis results in the following process:

[0149] Integrate the adjusted resource allocation data and resource reconfiguration results to analyze the overall resource allocation and utilization efficiency: E util,h Represents the resource utilization after integration. new,j is the resource configuration after adjustment for the jth data stream. total is the total amount of network resources. t is the total number of data flows involved in the calculation.

[0150] The problem diagnosis submodule identifies network performance bottlenecks and potential problems based on the resource usage analysis results, analyzes the key factors affecting network performance, and generates network problem diagnosis results in the following process:

[0151] Based on the resource usage analysis results, identify network performance bottlenecks and potential problems, and calculate resource configuration deviations: D diag,j Indicates the network problem diagnosis result and reflects the variability of resource allocation. D is the coefficient of variability. R new,j is the resource configuration of the jth data stream. R YesR new t represents the total number of data flows involved in the calculation.

[0152] The performance monitoring submodule applies the network problem diagnosis results to continuously monitor network performance, re-judge the network operation status, and generate real-time network performance data.

[0153] Apply network problem diagnosis results to continuously monitor network performance and generate real-time network performance data: P mon,k Represents real-time network performance indicators. P is the monitoring sensitivity coefficient. D diag,j is the problem diagnosis result of the jth data stream. t is the total number of data streams.

[0154] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A Layer 2 WAN traffic management system, characterized by: The system comprises: The traffic stability analysis module collects the data flow information transmitted in the Layer 2 WAN, calculates the ratio of the standard deviation of each data flow to the average value, extracts the coefficient of variation of each data flow, and generates the traffic stability measurement result; The traffic sorting adjustment module divides the processing order of the data stream according to the sorting result based on the coefficient of variation in the traffic stability measurement result, and generates a priority traffic queue; The resource allocation optimization module uses the priority traffic queue to adjust the network bandwidth, allocates network resources according to the priority of each data flow, and generates adjusted resource allocation data; The transmission efficiency monitoring module monitors the transmission rate and data volume of active data flows, collects network quality indicators corresponding to transmission, extracts key performance indicators, and generates data flow transmission information; The stopping point decision module evaluates the continued transmission or stopping of the data flow based on the data flow transmission information, selects the resource use switching point, and generates a resource reconfiguration result; The network performance analysis module integrates the adjusted resource allocation data and resource reconfiguration results, continuously monitors network performance, identifies potential performance issues, and generates real-time network performance data.

2. The layer 2 wide area network traffic management system according to claim 1, characterized in that: The traffic stability measurement results include the average volatility of the data flow, the highest volatility record and the volatility distribution diagram; the priority traffic queue includes the priority number of the data flow, the priority level classification and the queue sorting diagram associated with the priority; the adjusted resource allocation data includes the resource allocation value, the resource utilization rate of the data flow after allocation and the resource allocation optimization; the data flow transmission information includes the real-time data transmission rate table, data volume statistics and key network indicators; the resource reconfiguration results include the time node of the resource configuration adjustment and the resource allocation comparison information before and after the configuration; the real-time network performance data includes the real-time monitoring chart of the network performance, the network performance rating and the real-time data of the network status.

3. The layer 2 wide area network traffic management system according to claim 1, characterized in that: The flow stability analysis module includes: The data receiving submodule receives the data flow information transmitted in the Layer 2 WAN, including the size, transmission interval and time stamp of each data packet, extracts key transmission features, and generates basic traffic data; The volatility analysis submodule adopts a weighted round-robin method to calculate the ratio of the standard deviation to the average value of each data flow from the basic flow data, obtains the volatility index of each data flow, and generates a volatility index table; The stability assessment submodule uses the volatility index table to perform quantitative analysis on the stability of each data flow, identify data flows whose volatility exceeds a predetermined threshold, and generate flow stability measurement results.

4. The layer 2 wide area network traffic management system according to claim 3, characterized in that: The weighted round robin method is based on the formula: and Calculate the adjusted standard deviation σ′ and the adjusted mean packet size μ′; Among them, S i is the size of the ith packet, n is the total number of packets, P j is the priority of data stream j, T j is the duration of data stream j, M j is the peak value of data flow j, and B represents the network bandwidth used by the data flow; According to the formula: Calculate the volatility index V′; Among them, V′ is used to measure the stability of the data flow under the adjusted conditions.

5. The layer 2 wide area network traffic management system according to claim 1, characterized in that: The flow sorting adjustment module includes: The volatility sorting submodule sorts the data streams according to the volatility index in the flow stability measurement result, and generates a sorted data stream list; The priority setting submodule analyzes the sorted data stream list, sets priorities for the data streams, assigns a processing order label to each data stream, and generates a priority setting result; The queue configuration submodule forms a data flow processing queue according to the priority setting result, arranges the data flows in the set priority order, and generates a priority traffic queue.

6. The layer 2 wide area network traffic management system according to claim 1, characterized in that: The resource allocation optimization module includes: The network demand analysis submodule analyzes the resource usage of data flows in the network based on the priority traffic queue, including current bandwidth consumption and expected traffic growth, performs resource demand prediction, and generates resource demand analysis results; The bandwidth allocation submodule adjusts the bandwidth configuration to match the requirements of multiple data flows according to the resource requirement analysis result and generates a bandwidth configuration record; The resource optimization submodule uses the bandwidth configuration record to perform resource allocation operations, configures network resources among data flows according to priorities, and generates adjusted resource allocation data.

7. The layer 2 wide area network traffic management system according to claim 1, characterized in that: The transmission efficiency monitoring module includes: The traffic monitoring submodule monitors active data flows, records the current transmission rate and total data volume of the data flows, and generates active data flow records; The performance data extraction submodule extracts key network performance indicators from the active data flow records, including real-time delay and packet loss, evaluates key network performance indicators, and generates key performance indicator data; The efficiency information summary submodule uses the key performance indicator data to analyze the transmission efficiency and status of the entire network, evaluate the overall network performance, and generate data flow transmission information.

8. The layer 2 wide area network traffic management system according to claim 1, characterized in that: The stopping point decision module includes: The transmission status evaluation submodule analyzes the current transmission status and resource usage of each data stream based on the data stream transmission information, determines the transmission parameters to be evaluated, and generates a transmission parameter analysis result; The decision point calibration submodule uses the transmission parameter analysis result to evaluate the necessity of continuing transmission or stopping of each data stream through the optimal stopping theory, determines the resource use switching point, and generates switching point decision data; The resource configuration adjustment submodule adjusts the network resource configuration according to the switching point decision data and generates a resource reconfiguration result.

9. The layer 2 wide area network traffic management system according to claim 8, characterized in that: The optimal stopping theory is according to the formula: Analyze the need to continue or stop each data flow; Among them, C′ j is the decision value, indicating the decision to continue transmission or stop the jth data stream, ω C,E Efficiency E eff,j The weight coefficient, ω C,M is the data flow peak value M j For the weight coefficient of the total bandwidth B, E eff,j is the efficiency of the jth data stream, M j is the peak value of the jth data stream, B is the total bandwidth of the network, γ C,U is the resource utilization U j The weight coefficient, γ C,D is the average delay D j The weight coefficient, U j is the resource utilization of the jth data stream, D j is the average delay of the jth data flow.

10. The layer 2 wide area network traffic management system according to claim 1, characterized in that: The network performance analysis module includes: The performance data integration submodule integrates the adjusted resource allocation data and resource reconfiguration results, analyzes the overall resource allocation and utilization efficiency, and generates resource utilization analysis results; The problem diagnosis submodule identifies network performance bottlenecks and potential problems based on the resource usage analysis results, analyzes key factors affecting network performance, and generates network problem diagnosis results; The performance monitoring submodule applies the network problem diagnosis results to continuously monitor network performance, re-judge the network operation status, and generate real-time network performance data.

Citation Information

Cited By

  • Monitoring management platform based on digital operation

    CN119623826A

  • Digitalized operation monitoring management platform

    CN119623826B

  • Flow bandwidth intelligent distribution optimization method and system

    CN119835162A

  • Physical environment lightweight data acquisition method

    CN119984410A