Intelligent analysis and optimization method based on network traffic

Abstract

The invention relates to the technical field of network flow optimization, in particular to an intelligent analysis and optimization method based on network flow. The method comprises the following steps: acquiring a network flow log in a management time period, acquiring an actual current-carrying value and a preset current-carrying value of network equipment based on the network flow log, and marking a ratio of the actual current-carrying value to the preset current-carrying value as a network flow index WL in the management time period; judging whether the operation situation of the network equipment in the management time period meets an anomaly analysis requirement or not through the network flow index WL; under the condition that the operation situation of the network equipment meets the exception analysis requirement, obtaining a network equipment operation situation index in the management time period, and obtaining a network equipment operation risk index based on the network equipment operation situation index; and judging whether to activate a network flow optimization model based on the network equipment operation risk index, and if yes, activating the network flow optimization model and optimizing the network flow in the management time period. According to the invention, the optimization efficiency of the network flow can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of network traffic optimization, and in particular to an intelligent analysis and optimization method based on network traffic. Background Art

[0002] With the rapid development of the Internet, network traffic has shown an explosive growth trend. Network traffic refers to the amount of data transmitted in the network, which reflects the busyness of the network and the utilization of resources. However, a large amount of network traffic also brings a series of problems, such as network congestion, delay, packet loss, etc., which seriously affect the performance of the network and user experience.

[0003] Traditional network traffic management mainly relies on manual monitoring and manual configuration, but this approach often fails to respond to network changes in a timely manner and is inefficient.

[0004] Therefore, an intelligent network traffic analysis and optimization method is needed that can automatically sense the network status, make decisions based on real-time traffic data, and take corresponding optimization measures. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent analysis and optimization method based on network traffic: at least to solve the problems of weak timeliness and low management efficiency caused by relying on manual monitoring and manual configuration to manage network traffic in existing solutions.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] An intelligent analysis and optimization method based on network traffic, the method comprising:

[0008] Obtaining a network traffic log within a management period, obtaining an actual load current value and a preset load current value of a network device based on the network traffic log, and marking a ratio of the actual load current value to the preset load current value as a network traffic index WL within the management period;

[0009] The network traffic index WL is used to determine whether the operation status of network devices within the management period meets the requirements of abnormal analysis;

[0010] When the operation status of the network device meets the abnormal analysis requirements, the network device operation status indicators within the management period are obtained, and the network device operation risk index is obtained based on the network device operation status indicators;

[0011] Based on the network equipment operation risk index, it is determined whether to activate the network traffic optimization model. If so, the network traffic optimization model is activated and the network traffic within the management period is optimized.

[0012] Furthermore, obtaining the actual current value and the preset current value of the network device based on the network traffic log specifically includes the following process:

[0013] Based on the network traffic log, the upload traffic speed and download traffic speed of the network device at each detection moment within the management period are obtained, and the total value of the upload traffic and download traffic of the network device is obtained at the end of the management period. The total value is marked as the actual carrying current value, and the execution time of the management period is used as the X-axis to calculate the average speed of the upload traffic and download traffic speed within the management period. A rectangular coordinate system is established with the average speed as the Y-axis to generate a curve for the management period, and the graphic area enclosed by the curve and the coordinate axis is calculated, and the graphic area is marked as the preset carrying current value.

[0014] Furthermore, judging whether the operation status of the network equipment in the management period meets the abnormal analysis requirements through the network traffic index WL specifically includes the following process:

[0015] Get the preset threshold index WL max , W.L. min , among which WL max , W.L. min is the preset threshold;

[0016] If WL≤WL min , it is determined that the operation status of the network device within the management period does not meet the abnormal analysis requirements, and a network device no operation status signal is generated and sent to the intelligent analysis center, wherein the intelligent analysis center is used to receive the network device operation status signal;

[0017] If WL min <WL<WL max , determine whether the operation status of network equipment within the management period meets the requirements of abnormal analysis;

[0018] If WL>WL max , determine that the operation status of the network equipment within the management period does not meet the abnormal analysis requirements, generate a network equipment operation status abnormality signal and send it to the intelligent analysis center.

[0019] Furthermore, obtaining the network equipment operation risk index based on the network equipment operation status indicator specifically includes the following process:

[0020] Network equipment operation status indicators include: CPU utilization LY, memory utilization NC, bandwidth utilization DK, and vulnerability number S;

[0021] Substitute the CPU utilization LY, memory utilization NC, bandwidth utilization DK, and vulnerability number S into the correlation calculation formula to obtain the network equipment operation risk index LFX. The correlation calculation formula is as follows:

[0022]

[0023] Wherein, 0≤γ≤1, 0≤θ≤1, 0≤DK≤1, γ and θ are weights, C is a constant correction coefficient, and its specific value can be adjusted and set by the user according to the degree of influence of network equipment on the transmission of network traffic, and P is the network status coefficient.

[0024] Furthermore, judging whether to activate the network traffic optimization model based on the network device operation risk index specifically includes the following process:

[0025] The network equipment operation risk index is input into a recurrent neural network, which uses the recurrent connection between neurons to store the historical network equipment operation risk index of the network equipment, and outputs the predicted value based on the currently input network equipment operation risk index and the network equipment operation risk index, and determines whether the predicted value exceeds the preset threshold. If so, the network traffic optimization model is activated, otherwise, the network traffic optimization model is not activated.

[0026] Furthermore, activating the network traffic optimization model and optimizing the network traffic during the management period includes the following processes:

[0027] Get the dataset Among them, the vector x i =(f 1 , f 2 ..., f k ) T represents the input vector of the i-th network traffic, f j , j∈[1,k], represents the K expert features of the current network traffic, y i ∈(0, M) represents the true label of the i-th network traffic, and M represents the total number of categories to be classified;

[0028] Input the data set D into the network traffic optimization model to get the output vector

[0029]

[0030] vector After the Softmax calculation, we get the probability distribution vector z for each category. i :

[0031]

[0032] Based on the probability distribution vector z i Determine optimization plans for each category, and optimize network traffic within the management period according to the optimization plans for each category.

[0033] Furthermore, the network traffic within the management period is optimized according to each classification optimization scheme, including:

[0034] Traffic analysis and monitoring: Use network traffic analysis tools to monitor and analyze network traffic data during management periods to identify high traffic periods, traffic sources, traffic types, and potential bottlenecks or problem areas;

[0035] Traffic shaping and priority setting: Implement traffic shaping strategies, reasonably allocate network bandwidth according to business needs and traffic types, set traffic priorities, and ensure that key businesses or applications have sufficient bandwidth resources;

[0036] Data compression and caching: Use data compression technology to reduce the size of transmitted data and reduce network bandwidth consumption. Use caching technology to store commonly used data or files locally or at the edge of the network to reduce remote access and transmission.

[0037] Load balancing and failover: Deploy a load balancer to evenly distribute network traffic to multiple servers to avoid single point overload, and set up a failover mechanism to ensure that when a server fails, traffic can be automatically transferred to other available servers;

[0038] Application optimization: Optimize the network usage of applications and use CDN to accelerate content delivery, reduce latency and improve user experience.

[0039] Compared with the existing solutions, the present invention achieves the following beneficial effects:

[0040] On the one hand, the present invention obtains the network traffic log within the management period, obtains the actual load current value and the preset load current value of the network device based on the network traffic log, and marks the ratio of the actual load current value to the preset load current value as the network traffic index WL within the management period; judges whether the operation status of the network device within the management period meets the abnormal analysis requirements through the network traffic index WL; can monitor the network traffic in real time without relying on manual monitoring and manual configuration, can automatically sense the network status, and improve the supervision efficiency of the network traffic.

[0041] On the other hand, by collecting and analyzing network traffic data, the present invention can identify bottlenecks and potential problems in the network, and then propose optimization solutions, providing a scientific basis for network planning and optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0043] Figure 1It is a workflow diagram of an intelligent analysis and optimization method based on network traffic according to an embodiment of the present invention;

[0044] Figure 2 It is a workflow diagram of another intelligent analysis and optimization method based on network traffic according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] In addition, the described features, structures or characteristics may be combined in one or more example embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the example embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, steps, etc. may be adopted. In other cases, well-known structures, methods, implementations or operations are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0047] This embodiment provides an intelligent analysis and optimization method based on network traffic. Figure 1 is a workflow diagram of an intelligent analysis and optimization method based on network traffic according to an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0048] Step S101: Obtain the network traffic log within the management period, obtain the actual load current value and the preset load current value of the network device based on the network traffic log, and mark the ratio of the actual load current value to the preset load current value as the network traffic index WL within the management period.

[0049] Specifically, obtaining the actual current value and the preset current value of the network device based on the network traffic log specifically includes the following process:

[0050] Based on the network traffic log, the upload traffic speed and download traffic speed of the network device at each detection moment within the management period are obtained, and the total value of the upload traffic and download traffic of the network device is obtained at the end of the management period. The total value is marked as the actual carrying current value, and the execution time of the management period is used as the X-axis to calculate the average speed of the upload traffic and download traffic speed within the management period. A rectangular coordinate system is established with the average speed as the Y-axis to generate a curve for the management period, and the graphic area enclosed by the curve and the coordinate axis is calculated, and the graphic area is marked as the preset carrying current value.

[0051] Step S102: judging whether the operation status of the network equipment within the management period meets the abnormality analysis requirements through the network traffic index WL.

[0052] It is worth noting that judging whether the operation status of network devices within the management period meets the abnormal analysis requirements through the network traffic index WL specifically includes the following process:

[0053] Get the preset threshold index WL max , W.L. min , among which WL max , W.L. min is the preset threshold;

[0054] If WL≤WL min , it is determined that the operation status of the network device within the management period does not meet the abnormal analysis requirements, and a network device no operation status signal is generated and sent to the intelligent analysis center, wherein the intelligent analysis center is used to receive the network device operation status signal;

[0055] If WL min <WL<WL max , determine whether the operation status of network equipment within the management period meets the requirements of abnormal analysis;

[0056] If WL>WL max , determine that the operation status of the network equipment within the management period does not meet the abnormal analysis requirements, generate a network equipment operation status abnormality signal and send it to the intelligent analysis center.

[0057] Step S103: When the operation status of the network device meets the abnormality analysis requirements, obtain the network device operation status index within the management period, and obtain the network device operation risk index based on the network device operation status index.

[0058] In some embodiments, obtaining the network device operation risk index based on the network device operation status indicator specifically includes the following process:

[0059] Network equipment operation status indicators include: CPU utilization LY, memory utilization NC, bandwidth utilization DK, and vulnerability number S;

[0060] Substitute the CPU utilization LY, memory utilization NC, bandwidth utilization DK, and vulnerability number S into the correlation calculation formula to obtain the network equipment operation risk index LFX. The correlation calculation formula is as follows:

[0061]

[0062] Wherein, 0≤γ≤1, 0≤θ≤1, 0≤DK≤1, γ and θ are weights, C is a constant correction coefficient, and its specific value can be adjusted and set by the user according to the degree of influence of network equipment on the transmission of network traffic, and P is the network status coefficient.

[0063] Step S104: Determine whether to activate the network traffic optimization model based on the network device operation risk index. If so, proceed to step S105; if not, proceed to step S106.

[0064] Step S105: Activate the network traffic optimization model and optimize the network traffic within the management period.

[0065] Step S106: deactivate the network traffic optimization model.

[0066] In summary, the embodiment of the present invention obtains the network traffic log within the management period, obtains the actual load current value and the preset load current value of the network device based on the network traffic log, and marks the ratio of the actual load current value to the preset load current value as the network traffic index WL within the management period; judges whether the operation status of the network device within the management period meets the abnormal analysis requirements through the network traffic index WL; when the operation status of the network device meets the abnormal analysis requirements, obtains the network device operation status index within the management period, and obtains the network device operation risk index based on the network device operation status index; judges whether to activate the network traffic optimization model based on the network device operation risk index, and if so, activates the network traffic optimization model and optimizes the network traffic within the management period, can monitor the network traffic in real time without relying on manual monitoring and manual configuration, can automatically sense the network status, improve the supervision efficiency of the network traffic, and can identify bottlenecks and potential problems in the network by collecting and analyzing network traffic data, and then propose optimization plans to provide a scientific basis for network planning and optimization.

[0067] In some embodiments, Figure 2 FIG. 1 is a flowchart of another intelligent analysis and optimization method based on network traffic according to an embodiment of the present invention. Figure 2 As shown, judging whether to activate the network traffic optimization model based on the network device operation risk index specifically includes the following steps:

[0068] Step S201: inputting the network device operation risk index into a recurrent neural network, wherein the recurrent neural network uses a recurrent connection between neurons to store the historical network device operation risk index of the network device;

[0069] Step S202: outputting a predicted value according to the currently input network device operation risk index and the network device operation risk index;

[0070] Step S203: determine whether the predicted value exceeds a preset threshold, if so, activate the network traffic optimization model, if not, do not activate the network traffic optimization model.

[0071] Among them, recurrent neural network (RNN) is a deep learning model that is particularly suitable for processing sequence data with time dependencies. In RNN, the recurrent connection between neurons allows the model to store historical information and use this information together with the current input to generate predicted values.

[0072] Here is a brief overview of how RNNs store historical information based on recurrent connections and output predictions based on current input and historical state data:

[0073] Loop connection:

[0074] Each neuron in the RNN receives not only the signal from the current input layer, but also the output signal from itself at the previous time step. This recurrent connection enables the RNN to capture the temporal dependencies in the sequence.

[0075] State transfer:

[0076] At each time step, the RNN updates its internal state. This state is a function of the current input and the state at the previous time step. Therefore, the state of the RNN can be seen as an encoding of the sequence information observed so far.

[0077] Weight Sharing:

[0078] RNNs use the same weights across all time steps. This means that the model performs the same operation at different time steps, only the input and state are different. This weight sharing enables RNNs to learn patterns in sequences without being limited by the length of the sequence.

[0079] Output prediction:

[0080] At each time step, the RNN generates an output based on the current input and internal state. This output can be a prediction of the next element in the sequence or some representation of the entire sequence.

[0081] Training and Optimization:

[0082] To train an RNN, we define a loss function that measures the difference between the model's predictions and the true values. We then use the backpropagation algorithm and gradient descent to optimize the model's weights to minimize the loss function.

[0083] In some embodiments, activating the network traffic optimization model and optimizing the network traffic during the management period includes the following process:

[0084] Get the dataset Among them, the vector x i =(f 1 , f 2 ..., f k ) T represents the input vector of the i-th network traffic, f j , j∈[1,k], represents the K expert features of the current network traffic, y i ∈(0, M) represents the true label of the i-th network traffic, and M represents the total number of categories to be classified;

[0085] Input the data set D into the network traffic optimization model to obtain the output vector

[0086]

[0087] vector After the Softmax calculation, we get the probability distribution vector z for each category. i :

[0088]

[0089] Based on the probability distribution vector z i Determine each classification optimization plan, and optimize the network traffic within the management period according to each classification optimization plan, wherein each probability distribution interval corresponds to a classification optimization plan, and the classification optimization plan is a preset optimization plan.

[0090] Furthermore, based on the probability distribution vector z i Determine each classification optimization plan, and optimize the network traffic within the management period according to each classification optimization plan, including:

[0091] Traffic analysis and monitoring: Use network traffic analysis tools to monitor and analyze network traffic data during management periods to identify high traffic periods, traffic sources, traffic types, and potential bottlenecks or problem areas;

[0092] Traffic shaping and priority setting: Implement traffic shaping strategies, reasonably allocate network bandwidth according to business needs and traffic types, set traffic priorities, and ensure that key businesses or applications have sufficient bandwidth resources;

[0093] Data compression and caching: Use data compression technology to reduce the size of transmitted data and reduce network bandwidth consumption. Use caching technology to store commonly used data or files locally or at the edge of the network to reduce remote access and transmission.

[0094] Load balancing and failover: Deploy a load balancer to evenly distribute network traffic to multiple servers to avoid single point overload, and set up a failover mechanism to ensure that when a server fails, traffic can be automatically transferred to other available servers;

[0095] Application optimization: Optimize the network usage of applications and use CDN (Content Delivery Network) to accelerate content delivery, reduce latency and improve user experience.

[0096] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0097] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0098] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0099] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0100] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0101] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0102] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An intelligent analysis and optimization method based on network traffic, characterized in that: Methods include: Obtaining a network traffic log within a management period, obtaining an actual load current value and a preset load current value of a network device based on the network traffic log, and marking a ratio of the actual load current value to the preset load current value as a network traffic index WL within the management period; The network traffic index WL is used to determine whether the operation status of network devices within the management period meets the requirements of abnormal analysis; When the operation status of the network device meets the abnormal analysis requirements, the network device operation status indicators within the management period are obtained, and the network device operation risk index is obtained based on the network device operation status indicators; Based on the network equipment operation risk index, it is determined whether to activate the network traffic optimization model. If so, the network traffic optimization model is activated and the network traffic within the management period is optimized.

2. According to claim 1, a method for intelligent analysis and optimization based on network traffic is characterized in that: Get the actual current value and preset current value of network devices based on network traffic logs The process includes: Based on the network traffic log, the upload traffic speed and download traffic speed of the network device at each detection moment within the management period are obtained, and the total value of the upload traffic and download traffic of the network device is obtained at the end of the management period. The total value is marked as the actual carrying current value, and the execution time of the management period is used as the X-axis to calculate the average speed of the upload traffic and download traffic speed within the management period. A rectangular coordinate system is established with the average speed as the Y-axis to generate a curve for the management period, and the graphic area enclosed by the curve and the coordinate axis is calculated, and the graphic area is marked as the preset carrying current value.

3. The intelligent analysis and optimization method based on network traffic according to claim 1 is characterized in that: The network traffic index WL is used to determine whether the operation status of network devices during the management period meets the abnormal analysis requirements. The specific process includes the following: Get the preset threshold index WL max , W.L. min , among which WL max , W.L. min is the preset threshold; If WL≤WL min , it is determined that the operation status of the network device within the management period does not meet the abnormal analysis requirements, and a network device no operation status signal is generated and sent to the intelligent analysis center, wherein the intelligent analysis center is used to receive the network device operation status signal; If WL min <WL<WL max , determine whether the operation status of network equipment within the management period meets the requirements of abnormal analysis; If WL>WL max , determine that the operation status of the network equipment within the management period does not meet the abnormal analysis requirements, generate a network equipment operation status abnormality signal and send it to the intelligent analysis center.

4. The intelligent analysis and optimization method based on network traffic according to claim 1 is characterized in that: The specific process of obtaining the network equipment operation risk index based on the network equipment operation status indicators is as follows: Network equipment operation status indicators include: CPU utilization LY, memory utilization NC, bandwidth utilization DK, and vulnerability number S; Substitute the CPU utilization LY, memory utilization NC, bandwidth utilization DK, and vulnerability number S into the correlation calculation formula to obtain the network equipment operation risk index LFX. The correlation calculation formula is as follows: Wherein, 0≤γ≤1, 0≤θ≤1, 0≤DK≤1, γ and θ are weights, C is a constant correction coefficient, and its specific value can be adjusted and set by the user according to the degree of influence of network equipment on the transmission of network traffic, and P is the network status coefficient.

5. The intelligent analysis and optimization method based on network traffic according to claim 1 is characterized in that: Judging whether to activate the network traffic optimization model based on the network equipment operation risk index specifically includes the following processes: The network equipment operation risk index is input into a recurrent neural network, which uses the recurrent connection between neurons to store the historical network equipment operation risk index of the network equipment, and outputs the predicted value based on the currently input network equipment operation risk index and the network equipment operation risk index, and determines whether the predicted value exceeds the preset threshold. If so, the network traffic optimization model is activated, otherwise, the network traffic optimization model is not activated.

6. The intelligent analysis and optimization method based on network traffic according to claim 1 is characterized in that: Activating the network traffic optimization model and optimizing network traffic during the management period includes the following processes: Get the dataset Among them, the vector x i =(f1, f2..., f k ) T represents the input vector of the i-th network traffic, f j , j∈[1,k], represents the K expert features of the current network traffic, y i ∈(0, M(represents the true label of the i-th network traffic, and M represents the total number of categories to be classified; Input the data set D into the network traffic optimization model to obtain the output vector vector After the Softmax calculation, we get the probability distribution vector z for each category. i : Based on the probability distribution vector z i Determine optimization plans for each category, and optimize network traffic within the management period according to the optimization plans for each category.

7. The intelligent analysis and optimization method based on network traffic according to claim 6 is characterized in that: Optimize network traffic during the management period according to various classification optimization plans, including: Traffic analysis and monitoring: Use network traffic analysis tools to monitor and analyze network traffic data during management periods to identify high traffic periods, traffic sources, traffic types, and potential bottlenecks or problem areas; Traffic shaping and priority setting: Implement traffic shaping strategies, reasonably allocate network bandwidth according to business needs and traffic types, set traffic priorities, and ensure that key businesses or applications have sufficient bandwidth resources; Data compression and caching: Use data compression technology to reduce the size of transmitted data and reduce network bandwidth consumption. Use caching technology to store commonly used data or files locally or at the edge of the network to reduce remote access and transmission. Load balancing and failover: Deploy a load balancer to evenly distribute network traffic to multiple servers to avoid single point overload, and set up a failover mechanism to ensure that when a server fails, traffic can be automatically transferred to other available servers; Application optimization: Optimize the network usage of applications and use CDN to accelerate content delivery, reduce latency and improve user experience.

Images