Network traffic optimization method and device, equipment, storage medium and product

Abstract

The invention relates to the technical field of network communication, and discloses a network traffic optimization method and device, equipment, a storage medium and a product, and the method comprises the steps: obtaining a traffic feature data set through analyzing real-time traffic, obtaining a prediction result based on a time sequence model according to a historical traffic data set and the traffic feature data set, and obtaining a prediction result according to the prediction result. The real-time flow is optimized; according to the method, the traffic characteristic data set is obtained by analyzing the real-time traffic, and prediction is performed in combination with the traffic characteristic data set and the historical traffic data set so as to deal with potential traffic fluctuation, so that the network traffic is optimized, the congestion risk is reduced, dynamic adjustment optimization and high-precision prediction are realized by using the time sequence model, and the prediction efficiency is improved. The processing effect of different characteristic flows is improved, and the data transmission efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of network communication technology, and in particular to a network traffic optimization method, device, equipment, storage medium and product. Background Art

[0002] At present, most of the existing methods for solving network congestion problems are based on fixed or simple dynamic algorithms to adjust the discard weights, which are difficult to cope with complex and changeable network traffic. On the one hand, it is impossible to make fine distinctions and processes for different traffic types, resulting in a high packet loss rate for some high-priority traffic; on the other hand, it relies on real-time status adjustment, with limited response speed, making it difficult to predict burst traffic, and the algorithm has a large amount of calculation, which affects device performance. Summary of the invention

[0003] The main purpose of this application is to provide a network traffic optimization method, device, equipment, storage medium and product, aiming to solve the technical problems that the existing technology cannot perform fine processing of different traffic types and lacks the ability to predict traffic trends.

[0004] To achieve the above objectives, the present application proposes a network traffic optimization method, the method comprising: Obtain traffic characteristic data set by analyzing real-time traffic; Based on the time series model, a prediction result is obtained according to the historical traffic data set and the traffic characteristic data set; The real-time traffic is optimized according to the prediction result.

[0005] In one embodiment, the step of obtaining a prediction result based on a time series model according to a historical traffic data set and the traffic feature data set includes: Acquire a historical traffic data set, and preprocess the historical traffic data set to obtain a preprocessed historical traffic data set; Inputting the preprocessed historical traffic data set into a time series model for fitting to obtain a target prediction model; The traffic feature data set is input into the target prediction model for prediction to obtain a prediction result.

[0006] In one embodiment, the target prediction model includes: rolling prediction and confidence interval prediction; The step of inputting the traffic feature data set into the target prediction model for prediction to obtain a prediction result includes: Inputting the traffic characteristic data set into the target prediction model for prediction to obtain a preliminary prediction result; Based on the rolling forecast, the preliminary forecast result is updated in combination with the latest traffic data obtained to obtain an updated forecast result; Obtaining the confidence interval by calculating the residual of the updated prediction result; A prediction result is obtained by integrating the updated prediction result and the confidence interval.

[0007] In one embodiment, the step of obtaining a traffic feature data set by analyzing real-time traffic includes: Extract key information of real-time traffic by parsing real-time traffic; Classify the real-time traffic categories based on the real-time traffic key information; According to the real-time traffic category, traffic features are extracted from the real-time traffic, and a traffic feature data set is obtained by integrating the traffic features.

[0008] In one embodiment, the step of optimizing the real-time traffic according to the prediction result includes: When the prediction result is that the future traffic exceeds the preset traffic threshold, optimizing the real-time traffic by increasing the probability of packet loss; When the prediction result is that the future traffic does not exceed the preset traffic threshold, the real-time traffic is optimized by reducing the probability of packet loss.

[0009] In one embodiment, after the step of optimizing the real-time traffic according to the prediction result, the method further includes: Obtaining correlation data of optimized real-time traffic, and extracting key optimization parameters from the correlation data; Based on the multi-dimensional traffic performance and the key optimization parameters, evaluating the effectiveness of the preset traffic threshold and obtaining an evaluation result; The preset flow threshold is updated based on the evaluation result.

[0010] In addition, to achieve the above purpose, the present application also proposes a network traffic optimization device, which includes: A data acquisition module, used to obtain a traffic feature data set by analyzing real-time traffic; A traffic prediction module, used to obtain a prediction result based on a time series model according to a historical traffic data set and the traffic feature data set; The traffic optimization module is used to optimize the real-time traffic according to the prediction result.

[0011] In addition, to achieve the above-mentioned purpose, the present application also proposes a network traffic optimization device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the network traffic optimization method described above.

[0012] In addition, to achieve the above objectives, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the network traffic optimization method described above are implemented.

[0013] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the network traffic optimization method described above are implemented.

[0014] The technical solution proposed in the present application obtains a traffic feature data set by analyzing real-time traffic, obtains prediction results based on a historical traffic data set and a traffic feature data set based on a time series model, and optimizes the real-time traffic based on the prediction results; since the present application obtains a traffic feature data set by analyzing real-time traffic, and combines the traffic feature data set and the historical traffic data set for prediction to cope with potential traffic fluctuations, thereby optimizing network traffic and reducing congestion risks, the time series model is used to achieve dynamic adjustment optimization and high-precision prediction, thereby improving the processing effect of different characteristic traffic, which is conducive to improving data transmission efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0016] 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 or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0017] Figure 1 A flowchart of the first embodiment of the network traffic optimization method of the present application is provided; Figure 2 This is a schematic diagram of the network traffic optimization process for this application; Figure 3 A flowchart of the second embodiment of the network traffic optimization method of the present application is provided; Figure 4 A flowchart of the third embodiment of the network traffic optimization method of the present application is provided; Figure 5 This is a schematic diagram of the module structure of the network traffic optimization device according to an embodiment of the present application; Figure 6 This is a schematic diagram of the device structure of the hardware operating environment involved in the network traffic optimization method in the embodiment of the present application.

[0018] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0019] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0020] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0021] The current traditional network traffic optimization technology mainly relies on manual configuration and script automation. Manual configuration is suitable for simple and small networks, but it is prone to errors and inefficient. Using predefined scripts to automate the configuration process is suitable for repetitive tasks, but it is more complicated to maintain and update the scripts, and has high requirements for script writing and debugging.

[0022] Therefore, in order to overcome the above-mentioned defects, the present application provides a solution by analyzing real-time traffic to obtain a traffic feature data set, combining the traffic feature data set and the historical traffic data set for prediction to cope with potential traffic fluctuations, thereby optimizing network traffic and reducing congestion risks. The time series model is used to achieve dynamic adjustment optimization and high-precision prediction, which improves the processing effect of different characteristic traffic and is conducive to improving data transmission efficiency.

[0023] It should be noted that the execution subject of each embodiment of the present application may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a network traffic optimization device, etc. The following embodiments are described below taking a network traffic optimization device as an example.

[0024] Based on this, the present application embodiment provides a network traffic optimization method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the network traffic optimization method of the present application.

[0025] In this embodiment, the network traffic optimization method includes steps S10 to S30: Step S10, obtaining a traffic feature data set by analyzing real-time traffic.

[0026] It should be noted that the real-time traffic refers to the data traffic generated in real time in the network. These data traffic can be data packets entering or leaving the network. Real-time traffic is dynamic and changes over time. Traffic feature data sets refer to information extracted from real-time traffic that can describe certain characteristics of the traffic. These characteristics can be traffic rate, data packet size, protocol type, source address, destination address, etc.

[0027] It is understandable that the traffic feature dataset obtained by analyzing real-time traffic aims to extract useful feature information from complex network traffic, and the traffic feature dataset will be used as a test set for the prediction model.

[0028] It should be noted that building a prediction model requires a training set and a test set. The training set is mainly used for model training and learning. Through the data in it, the model can extract features and rules and adjust internal parameters to achieve the best prediction effect. The test set is an independent data set. It is used to evaluate the generalization ability of the model on new data after the model training is completed, providing an objective and unbiased performance evaluation.

[0029] Furthermore, in order to improve the accuracy of the traffic feature data set, the step S10 may include: Extract key information of real-time traffic by parsing real-time traffic.

[0030] The real-time traffic categories are divided based on the real-time traffic key information.

[0031] According to the real-time traffic category, traffic features are extracted from the real-time traffic, and a traffic feature data set is obtained by integrating the traffic features.

[0032] It should be noted that the real-time traffic key information refers to information extracted from the real-time traffic that is of great value to subsequent processing, such as source IP address, destination IP address, data packet size, transmission rate, etc.

[0033] It is understandable that key information can be extracted by parsing real-time traffic, and the real-time traffic can be divided into different categories based on the key information. Traffic features can be extracted from the real-time traffic according to the divided categories, and these features can be integrated into a traffic feature data set.

[0034] Step S20, based on the time series model, obtain a prediction result according to the historical traffic data set and the traffic feature data set.

[0035] It should be noted that the time series model is a statistical method for analyzing and predicting data that changes over time. In traffic forecasting, the time series model can capture the time dependency of traffic, that is, the changing trend and periodicity of traffic at different time points. The historical traffic data set refers to the traffic data recorded over a period of time in the past. This data contains the historical values ​​of traffic and is the basis for the time series model to make predictions.

[0036] It is understandable that the historical traffic data set and the traffic feature data set can be preprocessed before obtaining the prediction results, which can include steps such as data cleaning (removing outliers, filling missing values, etc.), feature selection (selecting features that are useful for prediction) and feature scaling (standardizing or normalizing feature values).

[0037] It should be understood that the time series model is trained using preprocessed data. During the training process, the model learns the temporal dependencies in the historical traffic data and the correlation between traffic features, thereby building a model that can predict future traffic. The trained model is applied to the traffic feature dataset (or feature dataset containing future time points) to generate prediction results. These prediction results can include traffic values, traffic change trends, or traffic anomaly detection over a period of time in the future.

[0038] Step S30: optimizing the real-time traffic according to the prediction result.

[0039] It is understandable that in order to evaluate the accuracy and reliability of the prediction results, it is usually necessary to compare the predicted values ​​with the actual observed values ​​and calculate some statistical indicators (such as mean square error, mean absolute error, accuracy, etc.) to quantify the prediction performance.

[0040] It should be understood that the analysis of the forecast results generated by the time series model can include understanding key information such as future traffic trends, peak hours, possible congestion points, etc. Based on the analysis of the forecast results, identify which network parameters need to be adjusted to optimize real-time traffic. These parameters may include weighted random early detection (WRED) parameters (such as drop threshold, drop probability), queue management parameters (such as queue length limit), traffic shaping parameters (such as rate limit), etc.

[0041] It is understandable that a specific parameter adjustment strategy is formulated based on the identified parameter requirements. This includes determining the parameter value to be adjusted, the time point or time period for adjustment, and the method of adjustment (such as gradual adjustment, one-time adjustment, etc.). The formulated parameter adjustment strategy is applied to the network device to optimize the real-time traffic.

[0042] For ease of understanding, the following references Figure 2 This invention is provided for illustration, but is not intended to limit the present application. Figure 2 This is a schematic diagram of the network traffic optimization process. The specific steps of network traffic optimization are as follows: 1. Traffic characteristics analysis module (1) Obtaining traffic data Capture all network data through network devices (such as routers, switches) or special tools (such as tcpdump or Wireshark). These data include IP addresses, protocol types and data packet sizes, and extract key information (source address, destination address, protocol type, data packet size, etc.) by parsing these data.

[0043] (2) Data packet analysis and extraction Use machine learning algorithms to analyze real-time traffic, extract key real-time traffic information such as traffic rate, packet size distribution and timing, and organize this data in a unified format (for example, store each packet information as a row in a table).

[0044] (3) Traffic classification and feature extraction Define traffic categories based on business needs and security policies, and classify traffic using machine learning algorithms (such as decision trees, random forests, support vector machines, neural networks, etc.) Based on the traffic category, extract features related to the category from real-time traffic.

[0045] (4) Storage of traffic characteristic data The data generated above is stored in a relational database (MySQL), for example, and multiple tables are created according to different categories to facilitate subsequent data extraction.

[0046] (5) Provide data to subsequent modules 2. Historical data prediction module (1) Predict traffic trends and fluctuation ranges The time series forecasting autoregressive integrated moving average model (ARIMA) is mainly used to analyze historical traffic. This model predicts future traffic through methods such as autoregression and moving average.

[0047] a) First, you need to obtain historical traffic data for prediction. Usually, this data is stored in the database in the form of time series, and the data points include traffic values ​​and corresponding timestamps. For example, the data can be the traffic rate per minute (unit: Mbps). These historical data will be used as input to the ARIMA model.

[0048] Data example: Time: 2024-09-01 12:00:00 Traffic rate: 50Mbps b) Data preprocessing Before training the ARIMA model, you must ensure that the data is stationary. Non-stationary data (with trends or seasonal changes) will affect the accuracy of the model. Preprocessing includes the following steps: Check data stationarity: observe trends and fluctuations in data by plotting time series graphs; Difference processing: If there is a trend in the data, the trend can be eliminated by difference (i.e. the change in the previous and next data). The d parameter in the ARIMA model represents the number of differences; Denoising: If there are obvious anomalies in the data (such as traffic anomalies caused by emergencies), the outliers can be appropriately removed to achieve a smoothing effect.

[0049] c) ARIMA model parameter selection ARIMA model has three important parameters p (autoregressive term): represents the impact of historical data itself on the current value, that is, predicting the current value through previous data points.

[0050] d (number of differences): indicates how many times the data needs to be differentiated to become a stationary series.

[0051] q (moving average term): represents the impact of the forecast error on the current value.

[0052] Among them, the p value can be determined by the autocorrelation function (ACF) to observe the autocorrelation of the data; the q value is determined by the partial autocorrelation function (PACF) to observe the correlation of the prediction error; the d value is determined by observing the stationarity of the data after difference, and is generally 1 or 2. ACF measures the correlation between the sequence's own value and its past values. Specifically, it calculates the autocorrelation coefficient of the sequence at lag k, and the calculation formula is: (1) In the formula, It represents the value of the time series at time t, k is the lag order. Simply put, ACF at lag k represents the linear relationship between the current time and the previous k time.

[0053] PACF measures the direct correlation between the series at lag k and the current value, rather than the indirect effect through lags 1 to k−1.

[0054] d) Model training Using historical traffic data as input, the model will fit the data through autoregression and moving average according to the set parameters. The model will adjust various parameters to minimize the prediction error and generate the final prediction model.

[0055] e) Traffic prediction The trained ARIMA model can be used to predict future traffic based on historical data. Suppose you want to predict traffic in the next 10 minutes, the model will make inferences based on previous traffic patterns.

[0056] Rolling Forecast: ARIMA will predict the traffic volume for the next time period based on the most recent historical data. The predicted values ​​will be used as input for future time periods, and then the traffic volume for subsequent time periods will be predicted in turn.

[0057] Confidence interval: The ARIMA model not only provides specific forecast values, but also gives a confidence interval, which indicates the upper and lower fluctuation range of the forecast value. The smaller the confidence interval, the more reliable the forecast.

[0058] (2) Adjust WRED parameters based on prediction results The prediction results are used to set and optimize WRED parameters. Based on different traffic prediction results, the WRED packet loss policy in the network device can be adjusted to achieve intelligent management and optimization of traffic.

[0059] High traffic prediction: When ARIMA predicts that future traffic will reach or exceed a certain threshold, the WRED packet loss probability can be appropriately increased. This can prevent network congestion and maintain overall network health.

[0060] Low traffic prediction: When ARIMA predicts that future traffic will reach or exceed a certain threshold, the WRED packet loss probability can be appropriately increased. This can prevent network congestion and maintain overall network health.

[0061] If ARIMA predicts that future traffic will reach or exceed a certain threshold, the WRED packet loss probability can be appropriately increased. This can prevent network congestion and maintain overall network health. If ARIMA predicts that future traffic will reach or exceed a certain threshold, the WRED packet loss probability can be appropriately increased.

[0062] (3) The updated WRED parameters are applied to the network 3. Decision-making and adjustment module (1) Data input: receiving traffic characteristic data and prediction results.

[0063] (2) Decision-making logic: Analyze traffic status and predict trends, and formulate adjustment strategies.

[0064] (3) Parameter update: Calculate and set the new WRED packet loss probability and threshold.

[0065] (4) Parameter application: The updated WRED parameters are passed to the parameter optimization module for real-time application.

[0066] This embodiment provides a network traffic optimization method, which obtains a traffic feature data set by analyzing real-time traffic, obtains prediction results based on a historical traffic data set and a traffic feature data set based on a time series model, and optimizes real-time traffic based on the prediction results; since this application obtains a traffic feature data set by analyzing real-time traffic, and combines the traffic feature data set and the historical traffic data set for prediction to cope with potential traffic fluctuations, thereby optimizing network traffic and reducing congestion risks, the time series model is used to achieve dynamic adjustment optimization and high-precision prediction, thereby improving the processing effect of different feature traffic, which is conducive to improving data transmission efficiency.

[0067] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 3 , the step S20 may include steps S201 to S203: Step S201, obtaining a historical traffic data set, and preprocessing the historical traffic data set to obtain a preprocessed historical traffic data set.

[0068] It should be noted that the preprocessed historical traffic data set refers to the historical traffic data set after a series of preprocessing steps (such as cleaning, conversion, merging, etc.). The purpose of preprocessing is usually to improve the data quality and make it more suitable for subsequent analysis or modeling.

[0069] It is understandable that historical traffic data sets can be obtained from databases, files, APIs, etc.

[0070] Step S202: input the preprocessed historical traffic data set into a time series model for fitting to obtain a target prediction model.

[0071] It should be noted that fitting refers to the process of using a model to approximate or simulate actual data. By adjusting the parameters of the model, the predicted value output by the model can be made as close as possible to the actual observed value. The target prediction model is a model obtained after fitting that can be used to predict future data points. It is based on the preprocessed historical traffic data set and time series model training, and is used to predict future traffic trends or values.

[0072] It can be understood that a time series model is trained using the preprocessed historical traffic data set to obtain a target prediction model that can be used to predict future traffic trends.

[0073] Step S203: input the traffic feature data set into the target prediction model for prediction to obtain a prediction result.

[0074] It should be understood that the traffic feature data set is input into the target prediction model as a test set. After the model receives the input features, it calculates the corresponding prediction results based on the rules and patterns learned internally.

[0075] In order to make the prediction result more accurate, the target prediction model includes: rolling prediction and confidence interval prediction, and step S203 may include: Inputting the traffic characteristic data set into the target prediction model for prediction to obtain a preliminary prediction result; Based on the rolling forecast, the preliminary forecast result is updated in combination with the latest traffic data obtained to obtain an updated forecast result; Obtaining the confidence interval by calculating the residual of the updated prediction result; A prediction result is obtained by integrating the updated prediction result and the confidence interval.

[0076] It should be noted that the traffic feature dataset is input into the trained target prediction model, and the model calculates a preliminary prediction result based on the input feature dataset. This preliminary prediction result is based on historical data and the rules learned by the model, but may be affected by many factors, such as the timeliness of the data and the generalization ability of the model.

[0077] It is understandable that the method based on rolling forecast, that is, the latest data is continuously used to update the forecast results over time, combining the latest traffic data and preliminary forecast results to update the forecast and obtain the updated forecast results. Rolling forecast helps to capture the latest trends and changes in the data and improve the accuracy and timeliness of the forecast.

[0078] It should be understood that the confidence interval is a quantitative representation of the uncertainty of the forecast results. The uncertainty of the forecast is assessed by calculating the residual of the updated forecast results (i.e. the difference between the predicted value and the actual value). Based on the residual analysis, the confidence interval at a certain confidence level can be calculated to represent the reliability range of the forecast results.

[0079] It is understandable that the updated forecast results and confidence intervals are integrated to form a complete forecast report or output. The integrated forecast results include not only the forecast value itself, but also the uncertainty information of the forecast.

[0080] This embodiment trains a time series model through historical traffic data sets, inputs the traffic feature data set into the trained model for prediction, combines rolling prediction and confidence interval prediction, continuously updates the prediction results and calculates confidence intervals, and can achieve accurate prediction of future traffic trends and uncertainty assessment.

[0081] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 4 , the step S30 may include steps S301-S302: Step S301, when the prediction result is that the future traffic exceeds the preset traffic threshold, the real-time traffic is optimized by increasing the packet loss probability.

[0082] It should be noted that the packet loss probability refers to the proportion of data packets lost during data transmission. Specifically, it refers to the difference in the ratio of sent data packets to successfully received data packets. If a certain number of data packets are sent, but the receiving end does not receive all of them, then the ratio of the number of unsuccessfully received data packets to the total number of sent data packets is the packet loss probability.

[0083] It is understandable that the prediction results are compared with the preset traffic threshold. If the prediction results show that the future traffic may exceed the threshold, the system determines that optimization measures need to be taken. The increase in the probability of packet loss limits the growth of real-time traffic. The increase in the probability of packet loss means that some data packets will be discarded during network transmission, thereby reducing the traffic load in the network, which can alleviate network congestion to a certain extent and protect the quality of network services. By increasing the probability of packet loss, the system optimizes real-time traffic.

[0084] It should be understood that the packet loss rate can be affected by adjusting parameters. For example, in the Transmission Control Protocol (TCP), the data transmission rate and packet loss rate can be affected by adjusting parameters such as window size and timeout. Flow control policies can also be configured on network devices such as routers and switches, such as setting parameters of queue management algorithms (such as RED, WRED, etc.) to drop packets under certain conditions.

[0085] Step S302, when the prediction result is that the future traffic does not exceed the preset traffic threshold, the real-time traffic is optimized by reducing the packet loss probability.

[0086] It is understandable that based on the prediction results, it is judged that the current network condition is good and there is no need to limit traffic by increasing the probability of packet loss. In order to optimize real-time traffic, the probability of packet loss is reduced to reduce the loss of data packets during network transmission.

[0087] This embodiment judges the prediction results based on a preset traffic threshold and optimizes real-time traffic by affecting the probability of packet loss, aiming to improve the efficiency and reliability of network transmission, help reduce the delay and jitter of data transmission, and ensure that the network always remains in the best state.

[0088] In the third embodiment, the step S30 may include steps S311 to S313: Step S311: Obtaining correlation data of optimized real-time traffic, and extracting key optimization parameters from the correlation data.

[0089] It should be noted that the associated data refers to the relevant data of the optimized real-time traffic obtained through monitoring tools or log collection, which may include information in multiple dimensions such as traffic size, traffic rate, packet loss rate, delay, etc.

[0090] It is understandable that from the correlation data, the system extracts key parameters directly related to traffic optimization. These parameters may include the packet loss rate after optimization, the improvement of network delay, the balance of traffic distribution, etc.

[0091] Step S312: Based on the multi-dimensional traffic performance and the key optimization parameters, the effectiveness of the preset traffic threshold is evaluated to obtain an evaluation result.

[0092] It should be noted that the multi-dimensional traffic performance is a performance indicator that comprehensively considers multiple dimensions such as traffic size, rate, packet loss rate, delay, etc., to comprehensively evaluate the overall status of network traffic.

[0093] It should be understood that the system evaluates the effectiveness of the preset traffic thresholds based on multi-dimensional traffic performance and key optimization parameters. The evaluation may involve comparing the gap between actual traffic and thresholds, analyzing whether the threshold settings are too conservative or too loose, etc. After the evaluation is completed, a conclusion is drawn about the effectiveness of the preset traffic thresholds, which may include information such as whether the thresholds need to be adjusted, the direction and magnitude of the adjustment, etc.

[0094] Step S313: Update the preset flow threshold based on the evaluation result.

[0095] It should be understood that the preset traffic threshold is updated according to the evaluation results. If the evaluation results show that the threshold setting is unreasonable, the system will adjust the threshold according to the actual situation to ensure that it can better reflect the actual situation of network traffic and future changes. The updated preset traffic threshold will be applied to the subsequent traffic prediction and optimization process.

[0096] This embodiment continuously optimizes its network traffic management strategy by obtaining correlation data of optimized real-time traffic, extracting key optimization parameters, evaluating the effectiveness of preset traffic thresholds, and updating the thresholds according to the evaluation results. It not only improves the efficiency and stability of network transmission, but also constructs a dynamic adaptation mechanism, which enables the system to flexibly respond to various changes in the network environment and ensure that network performance is always at the optimal level.

[0097] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the network traffic optimization method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0098] This application also provides a network traffic optimization device, please refer to Figure 5 , the network traffic optimization device comprises: A data acquisition module 10 is used to obtain a traffic characteristic data set by analyzing real-time traffic; A traffic prediction module 20, configured to obtain a prediction result based on a time series model and a historical traffic data set and the traffic feature data set; The traffic optimization module 30 is used to optimize the real-time traffic according to the prediction result.

[0099] The network traffic optimization device provided by the present application adopts the network traffic optimization method in the above-mentioned embodiment, which can solve the technical problems that the prior art cannot perform fine processing on different traffic types and lacks the ability to predict traffic trends. Compared with the prior art, the beneficial effects of the network traffic optimization device provided by the present application are the same as the beneficial effects of the network traffic optimization method provided by the above-mentioned embodiment, and the other technical features in the network traffic optimization device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0100] The present application provides a network traffic optimization device, which includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the network traffic optimization method in the above-mentioned embodiment one.

[0101] Reference below Figure 6 , which shows a schematic diagram of the structure of a network traffic optimization device suitable for implementing the embodiment of the present application. The network traffic optimization device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Desctions: tablet computers), PMPs (Portable Media Players: portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The network traffic optimization device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0102] like Figure 6 As shown, the network traffic optimization device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the network traffic optimization device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the network traffic optimization device to communicate with other devices wirelessly or wired to exchange data. Although the figure shows a network traffic optimization device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0103] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0104] The network traffic optimization device provided by the present application adopts the network traffic optimization method in the above embodiment, which can solve the technical problems that the prior art cannot perform fine processing on different traffic types and lacks the ability to predict traffic trends. Compared with the prior art, the beneficial effects of the network traffic optimization device provided by the present application are the same as the beneficial effects of the network traffic optimization method provided by the above embodiment, and the other technical features in the network traffic optimization device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0105] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0106] 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.

[0107] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, wherein the computer-readable program instructions are used to execute the network traffic optimization method in the above-mentioned embodiment.

[0108] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0109] The computer-readable storage medium may be included in the network traffic optimization device; or may exist independently without being assembled into the network traffic optimization device.

[0110] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the network traffic optimization device, the network traffic optimization device: obtains a traffic feature data set by analyzing real-time traffic, obtains prediction results based on historical traffic data sets and traffic feature data sets based on a time series model, and optimizes the real-time traffic according to the prediction results.

[0111] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0112] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0113] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0114] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned network traffic optimization method, and can solve the technical problems that the prior art cannot perform refined processing on different traffic types and lacks the ability to predict traffic trends. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the network traffic optimization method provided by the above-mentioned embodiment, and will not be elaborated here.

[0115] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned network traffic optimization method when executed by a processor.

[0116] The computer program product provided by this application can solve the technical problems that the prior art cannot perform refined processing on different traffic types and lacks the ability to predict traffic trends. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as those of the network traffic optimization method provided by the above embodiment, and will not be elaborated here.

[0117] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A network traffic optimization method, characterized in that: The method comprises the following steps: Obtain traffic characteristic data set by analyzing real-time traffic; Based on the time series model, a prediction result is obtained according to the historical traffic data set and the traffic characteristic data set; The real-time traffic is optimized according to the prediction result.

2. The network traffic optimization method according to claim 1, characterized in that: The step of obtaining a prediction result based on the time series model according to the historical traffic data set and the traffic feature data set includes: Acquire a historical traffic data set, and preprocess the historical traffic data set to obtain a preprocessed historical traffic data set; Inputting the preprocessed historical traffic data set into a time series model for fitting to obtain a target prediction model; The traffic feature data set is input into the target prediction model for prediction to obtain a prediction result.

3. The network traffic optimization method according to claim 2, characterized in that: The target prediction model includes: rolling prediction and confidence interval prediction; The step of inputting the traffic feature data set into the target prediction model for prediction to obtain a prediction result includes: Inputting the traffic characteristic data set into the target prediction model for prediction to obtain a preliminary prediction result; Based on the rolling forecast, the preliminary forecast result is updated in combination with the latest traffic data obtained to obtain an updated forecast result; Obtaining the confidence interval by calculating the residual of the updated prediction result; A prediction result is obtained by integrating the updated prediction result and the confidence interval.

4. The network traffic optimization method according to any one of claims 1 to 3, characterized in that: The step of obtaining a traffic feature data set by analyzing real-time traffic includes: Extract key information of real-time traffic by parsing real-time traffic; Classify the real-time traffic categories based on the real-time traffic key information; According to the real-time traffic category, traffic features are extracted from the real-time traffic, and a traffic feature data set is obtained by integrating the traffic features.

5. The network traffic optimization method according to any one of claims 1 to 3, characterized in that: The step of optimizing the real-time traffic according to the prediction result includes: When the prediction result is that the future traffic exceeds the preset traffic threshold, optimizing the real-time traffic by increasing the probability of packet loss; When the prediction result is that the future traffic does not exceed the preset traffic threshold, the real-time traffic is optimized by reducing the probability of packet loss.

6. The network traffic optimization method according to any one of claims 1 to 3, characterized in that: After the step of optimizing the real-time traffic according to the prediction result, the method further includes: Obtaining correlation data of optimized real-time traffic, and extracting key optimization parameters from the correlation data; Based on the multi-dimensional traffic performance and the key optimization parameters, evaluating the effectiveness of the preset traffic threshold and obtaining an evaluation result; The preset flow threshold is updated based on the evaluation result.

7. A network traffic optimization device, characterized in that: The network traffic optimization device comprises: A data acquisition module, used to obtain a traffic feature data set by analyzing real-time traffic; A traffic prediction module, used to obtain a prediction result based on a time series model according to a historical traffic data set and the traffic feature data set; The traffic optimization module is used to optimize the real-time traffic according to the prediction result.

8. A network traffic optimization device, characterized in that: The network traffic optimization device comprises: a memory, a processor, and a network traffic optimization program stored in the memory and executable on the processor. When the network traffic optimization program is executed by the processor, the network traffic optimization method according to any one of claims 1 to 6 is implemented.

9. A storage medium, characterized in that: The storage medium stores a network traffic optimization program, and when the network traffic optimization program is executed by the processor, the network traffic optimization method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product comprises a network traffic optimization program, and when the network traffic optimization program is executed by a processor, the network traffic optimization method according to any one of claims 1 to 6 is implemented.

Images