Broadcast suppression method used in flat networking, control device and storage medium

Abstract

The invention discloses a broadcast suppression method for flat networking, a control device and a storage medium, and belongs to the technical field of communication, and the method comprises the following steps: monitoring data related to broadcast traffic in a target network; identifying whether the monitored data has potential broadcast storm features or not by using a preset traffic feature identification model; when it is identified that the potential broadcast storm feature exists, predicting the flow trend of the target network and the degree of the broadcast storm by using a time sequence analysis technology; and based on the predicted flow trend and the degree of the broadcast storm, adjusting parameters for suppressing the broadcast storm in the target network according to a preset adjustment strategy. According to the method and the device, the broadcast storm can be suppressed by adjusting the mode of suppressing the broadcast storm parameters, so that the influence of broadcast traffic on the network is reduced, the stability and the performance of the network are improved, and reasonable utilization of network resources is ensured.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a broadcast suppression method, a control device and a storage medium for flat networking. Background Art

[0002] Under the flat networking architecture, due to the reduction of the network hierarchy, the broadcast domain range in the network tends to become larger than that of the traditional multi-layer network. When there is a large amount of broadcast traffic in the network, broadcast storms are prone to occur, resulting in reduced network performance and impaired stability.

[0003] In order to effectively suppress broadcast storms, existing technologies usually configure network devices more finely, such as implementing VLAN division strategies. However, the efficiency of implementing such strategies is low. In short, if the configuration is improper, it will bring greater burden to the network and fail to ensure the rational use of network resources. Summary of the invention

[0004] The present invention provides a broadcast suppression method for flat networking, which is used to solve the defect of lacking an effective method for suppressing broadcast storms in the prior art.

[0005] In one aspect, the present invention provides a broadcast suppression method for flat networking, comprising: Monitor data related to broadcast traffic in a target network; use a preset traffic feature recognition model to identify whether the monitored data has potential broadcast storm features; use timing analysis technology to predict the traffic trend of the target network and identify potential broadcast storms in the monitored data; and based on whether the monitored data has potential broadcast storm features, the predicted traffic trend and the identified potential broadcast storms, and using a preset adjustment strategy, adjust the parameters for suppressing broadcast storms in the target network.

[0006] Preferably, the step of monitoring data related to broadcast traffic in the target network includes: deploying a traffic monitoring system to capture data related to broadcast traffic; creating a database to store the captured data related to broadcast traffic; counting data related to broadcast traffic and storing the results in the database.

[0007] Preferably, the data related to the broadcast traffic includes at least: the amount of broadcast traffic, the number of forwarding times, the frequency of broadcast traffic, and the source IP address.

[0008] Preferably, before using the preset traffic feature recognition model to identify whether the monitored data has potential broadcast storm features, the broadcast suppression method also includes: obtaining historical data related to broadcast traffic in the target network to construct a training set and a verification set; constructing a long short-term memory network for identifying traffic features, and setting an activation function and a loss function; training the long short-term memory network for identifying traffic features through the training set, and verifying the training of the long short-term memory network for identifying traffic features through the verification set; and using the trained model as the preset traffic feature recognition model.

[0009] Preferably, the use of time series analysis technology to predict the traffic trend of the target network and identify broadcast storms in the monitored data includes: acquiring historical data and real-time data related to the broadcast traffic of the target network in chronological order to obtain time series data; extracting features in the time series data that are helpful for prediction, and constructing a training set and a verification set, and the features at least include moving average, seasonal decomposition, and autocorrelation; using a long short-term memory network to construct a time series prediction model; training the time series prediction model through the training set, and verifying the training of the time series prediction model through the verification set; and using the trained time series prediction model to predict the traffic trend of the target network and identify broadcast storms in the monitored data.

[0010] Preferably, the method of utilizing the trained time series prediction model to identify broadcast storms in the monitored data includes: setting a preset threshold for broadcast traffic based on historical data related to broadcast traffic in the monitored target network; and marking the monitored data related to broadcast traffic as a potential broadcast storm when it exceeds the preset threshold.

[0011] Preferably, the parameters for suppressing broadcast storms in the target network are adjusted based on whether the identified monitored data has potential broadcast storm characteristics, the predicted traffic trends and the identified potential broadcast storms, and according to a preset adjustment strategy, including: setting dynamic thresholds based on whether the identified monitored data has potential broadcast storm characteristics, the predicted traffic trends and the identified potential broadcast storms; determining key parameters related to broadcast suppression; when the monitored data related to the broadcast traffic is not within the dynamic threshold, adjusting the key parameters related to broadcast suppression; when the monitored data related to the broadcast traffic is within the dynamic threshold range, gradually calling back to the initial parameter settings to maintain normal operation of the network.

[0012] Preferably, the key parameters related to broadcast suppression include at least: the maximum number of forwarding times allowed for each broadcast data packet in the network and the broadcast traffic rate.

[0013] Preferably, when the monitored data related to the broadcast traffic is not within the dynamic threshold range, the key parameters related to broadcast suppression are adjusted, including: when the monitored data related to the broadcast traffic is continuously higher than the dynamic threshold, the maximum forwarding number and / or the broadcast traffic rate is gradually reduced.

[0014] Preferably, after adjusting the parameters for suppressing broadcast storms in the target network, the broadcast suppression method further includes: based on a feedback mechanism, monitoring data related to broadcast traffic in the target network, and optimizing a preset adjustment strategy according to the monitoring results.

[0015] Preferably, the optimization of the preset adjustment strategy includes: performing data analysis on the stored data related to the broadcast traffic; performing feedback adjustment based on the analysis results; and updating the preset traffic feature recognition model within a preset period based on the data analysis results and the feedback adjustment results.

[0016] On the other hand, the present invention further provides a control device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned broadcast suppression method.

[0017] On the other hand, the present invention further provides a machine-readable storage medium, on which instructions are stored, and the instructions enable the machine to execute the above-mentioned broadcast suppression method.

[0018] The broadcast suppression method for flat networking provided by the present invention monitors data related to broadcast traffic in a target network, and then uses a preset traffic feature recognition model to identify whether the monitored data has potential broadcast storm features, and based on the potential broadcast storm features, uses timing analysis technology to predict the traffic trend of the target network and the degree of the broadcast storm, and then adjusts the parameters for suppressing the broadcast storm in the target network according to a preset adjustment strategy, thereby solving the problem of lack of effective methods for predicting and suppressing broadcast storms in the prior art and achieving the beneficial effect of ensuring the rational use of network resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1It is a flowchart of a broadcast suppression method for flat networking provided by an embodiment of the present invention; Figure 2 It is a flowchart of a broadcast suppression method for flat networking provided by another embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0022] As mentioned above, in order to effectively suppress broadcast storms, existing technologies usually configure network devices more finely, such as implementing VLAN division strategies. However, the efficiency of implementing such strategies is low. In short, if the configuration is improper, it will bring a greater burden to the network and fail to ensure the rational use of network resources.

[0023] To this end, the present invention provides a broadcast suppression method for flat networking, which uses a preset traffic feature recognition model to identify potential broadcast storm features, and then adjusts the parameters for suppressing the broadcast storm according to a preset adjustment strategy, thereby suppressing the occurrence of broadcast storms.

[0024] Combine the following Figure 1 , Figure 2 The present invention is described in detail.

[0025] Figure 1 It is a flowchart of a broadcast suppression method for flat networking provided by an embodiment of the present invention.

[0026] like Figure 1 As shown, an embodiment of the present invention provides a broadcast suppression method for flat networking, the execution subject may be a controller, and the method mainly includes the following steps: S101. Monitor data related to broadcast traffic in a target network.

[0027] S102: Using a preset traffic feature recognition model, identify whether the monitored data has potential broadcast storm features.

[0028] S103: Using time series analysis technology, predict the traffic trend of the target network and identify potential broadcast storms in the monitored data.

[0029] S104: Based on whether the identified monitored data has potential broadcast storm characteristics, the predicted traffic trend and the identified potential broadcast storm, and using a preset adjustment strategy, adjust the parameters for suppressing the broadcast storm in the target network.

[0030] Based on the above steps, the present invention provides a broadcast suppression method for flat networking, which monitors the data related to broadcast traffic in the target network; uses a preset traffic feature recognition model to identify whether the monitored data has potential broadcast storm features, and based on the potential broadcast storm features; uses timing analysis technology to predict the traffic trend of the target network and the degree of the broadcast storm; and then adjusts the parameters used to suppress broadcast storms in the target network according to a preset adjustment strategy. The embodiment of the present invention can suppress broadcast storms by adjusting the broadcast storm suppression parameters, thereby reducing the impact of broadcast traffic on the network, improving the stability and performance of the network, and ensuring the rational use of network resources.

[0031] In order to explain the technical solution provided by the above embodiment in more detail, the present invention also provides another preferred embodiment, such as Figure 2 As shown, Figure 2 It is a flowchart of a broadcast suppression method for flat networking provided by another embodiment of the present invention. In this figure, the broadcast suppression method can also be executed by a controller.

[0032] like Figure 2 As shown, in another embodiment of the present invention, step S101 can utilize a traffic monitoring and analysis module to monitor data related to broadcast traffic in the target network. In step S101, the broadcast suppression method may include, step S1011, deploying a traffic monitoring system, capturing data related to broadcast traffic, and creating a database; step S1012, storing the captured data related to broadcast traffic; step S1013, counting data related to broadcast traffic and storing the results in a database.

[0033] For example, the traffic monitoring and analysis module can have real-time data capture and storage capabilities. For example, a network traffic analysis tool (such as Wireshark or custom-developed network monitoring software) can be used to capture all filtered broadcast packets passing through the network device. The tool needs to be configured to be able to identify and filter broadcast packets. Usually, the target MAC address of the filtered broadcast packet can be FF:FF:FF:FF:FF:FF. By setting filtering rules, the system can focus on collecting relevant data on broadcast traffic.

[0034] In the embodiment of the present invention, the data related to the broadcast traffic may preferably include at least: the amount of broadcast traffic, the number of forwarding times, the frequency of broadcast traffic, the source IP address, etc.

[0035] The above-mentioned traffic monitoring and analysis module can also have a data statistics function. For example, the system needs to regularly (for example, every minute) count the data related to the broadcast traffic in the target network. In another embodiment of the present invention, the data related to the broadcast traffic in the target network includes at least: the number of broadcast traffic (that is, calculating the total number of broadcast data packets captured in a specified time period), the frequency of broadcast traffic (that is, calculating the frequency of sending broadcast data packets per unit time) and the source IP address (recording the source IP address of each broadcast data packet, and counting the number of broadcast data packets sent by each source IP address to identify potential abnormal traffic sources).

[0036] Among them, the broadcast traffic frequency can be expressed by the following formula: , In order to achieve the above functions, the traffic monitoring module can use a database (such as MySQL or MongoDB) to store the collected data, and the data table structure can be designed as: timestamp (i.e., recording the time of data collection), source IP address (i.e., storing the source IP that sends the broadcast data packet), number of broadcast data packets (i.e., recording the number of broadcast data packets captured within the time period), frequency (i.e., the calculated broadcast traffic frequency).

[0037] The traffic monitoring and analysis module can also have visualization functions so that network administrators can view traffic data intuitively. Chart tools (such as Grafana or a customized web interface) can be used to display real-time traffic data, including the number and frequency trends of broadcast traffic.

[0038] The traffic monitoring and analysis module can be connected to the subsequent pattern recognition and prediction modules so that the collected data can be used for further analysis and decision making. By passing the traffic data to the pattern recognition algorithm, the system can identify normal broadcast traffic patterns and potential broadcast storm characteristics, etc.

[0039] Therefore, through the above steps, the traffic monitoring and analysis module can effectively collect and analyze broadcast traffic data in the network, providing reliable data support for subsequent broadcast suppression strategies.

[0040] In another embodiment of the present invention, before step S102, it can also include step S1021, obtaining historical data related to broadcast traffic in the target network to construct a training set and a verification set; S1022, constructing a long short-term memory network for identifying traffic characteristics, and setting activation functions and loss functions; S1023, training the long short-term memory network for identifying traffic characteristics through the training set, and verifying the training of the long short-term memory network for identifying traffic characteristics through the verification set; S1024, using the trained model as the preset traffic feature recognition model.

[0041] For example, steps S1021-S1024 further include the following steps: Obtain and process historical data related to broadcast traffic in the target network, the steps are as follows: Data cleaning to remove duplicate and invalid data records to ensure data accuracy and completeness. Extract key features from historical data, such as the number of broadcast traffic packets (i.e., the total number of broadcast data packets in a specific time period), the diversity of source IP addresses (i.e., the number of different source IP addresses that send broadcast data packets in a time period), the time interval (i.e., the time interval between broadcast data packets, calculating the average and standard deviation), and traffic burstiness (i.e., this indicator can identify abnormal fluctuations in traffic), etc. Traffic burstiness is calculated using the following formula: , A machine learning algorithm is selected to train the model. Considering the timing characteristics and complexity of broadcast traffic, in another embodiment of the present invention, a long short-term memory network (LSTM) is selected, which is a recurrent neural network suitable for processing time series data. LSTM can capture long-term dependencies in time series and is suitable for identifying broadcast traffic patterns.

[0042] Subsequently, the long short-term memory network model is trained, and the steps are as follows: the historical data related to the broadcast traffic in the target network collected is divided into a training set and a test set, for example, 70% can be used as a training set and 30% as a test set; then a deep learning framework (which can be TensorFlow or PyTorch) is used to build an LSTM model. The model structure can be designed as an input layer (i.e., receiving the extracted feature data), an LSTM layer (i.e., setting an appropriate number of LSTM units such as 64 or 128 to capture time series features), a fully connected layer (i.e., mapping the output of the LSTM layer to the classification result), and an output layer (i.e., the probability of normal traffic and broadcast storms can be output using a softmax activation function).

[0043] Then, you can choose cross entropy as the loss function, for example, you can use the Adam optimizer to train the model. During the training process, monitor the training loss and validation loss to prevent overfitting; and optimize the above model.

[0044] After training is completed, the model is evaluated based on indicators such as accuracy (i.e., the proportion of samples correctly classified by the computing model), recall (i.e., the ability of the computing model to identify positive classes such as broadcast storms), and F1-score (i.e., an indicator that takes into account both accuracy and recall).

[0045] The trained model is used as a traffic feature recognition model and deployed in the pattern recognition and prediction module configured according to step S102. The real-time data collected by the traffic monitoring and analysis module is input into the above-mentioned traffic feature recognition model. According to the output result of the traffic feature recognition model, it is judged whether the current traffic belongs to the normal mode or a potential broadcast storm.

[0046] Through the above steps, the pattern recognition and prediction module can effectively train the traffic feature recognition model, identify normal broadcast traffic patterns and potential broadcast storm characteristics, and provide important decision support for subsequent broadcast suppression strategies.

[0047] In another embodiment of the present invention, in step S103, the method of using time series analysis technology to predict the traffic trend of the target network and the degree of broadcast storm may include: step S1031, obtaining historical and real-time data related to the broadcast traffic of the target network in chronological order to obtain time series data; S1032, extracting features in the time series data that are helpful for prediction, and constructing a training set and a verification set, and the features at least include moving average, seasonal decomposition, and autocorrelation; S1033, using a long short-term memory network to construct a time series prediction model; S1034, training the time series prediction model through the training set, and verifying the training of the time series prediction model through the verification set; S1035, using the trained time series prediction model to predict the traffic trend and broadcast storm of the target network.

[0048] In step S1035, it can also include S10351: setting a preset threshold of broadcast traffic based on historical data related to broadcast traffic in the monitored target network; S10352: when the monitored data related to broadcast traffic exceeds the preset threshold, marking it as a potential broadcast storm.

[0049] For example, steps S1031-S1035 further include the following steps: The broadcast storm prediction module can be deployed, and the real-time and historical network traffic data, i.e., data related to broadcast traffic in the target network, can be collected from the traffic monitoring and analysis module; data cleaning can be performed on these data to remove missing values ​​and outliers, and then the time series can be constructed. For example, the collected traffic data can be organized into a time series format by timestamp for subsequent analysis. The data at each time point should include the timestamp (i.e., the time when the data was recorded), the number of broadcast packets (i.e., the total number of broadcast packets at that time point), and the traffic rate (i.e., the broadcast traffic rate per unit time).

[0050] Features that are helpful for prediction are extracted from the above time series. These features can be moving average (i.e., calculating the average number of broadcast data packets at the past N time points to smooth data fluctuations), seasonal decomposition (i.e., analyzing seasonal changes in data and identifying periodic patterns), and autocorrelation (i.e., using autocorrelation functions and partial autocorrelation functions to analyze the autocorrelation of data to determine appropriate model parameters).

[0051] Select a time series prediction model. Considering the dynamic characteristics of broadcast traffic, in another embodiment of the present invention, according to data characteristics, LSTM or autoregressive integrated moving average model (ARIMA) can be used. Among them, LSTM is suitable for processing complex nonlinear time series data, while ARIMA is suitable for linear time series data.

[0052] The steps for training the model are as follows: divide the time series into training set and test set, for example, 80% can be used as training set and 20% as test set, and then choose to use the deep learning framework to build the LSTM network. The model structure can be designed as follows: input layer (receive time series data), LSTM layer (set the appropriate number of LSTM units, which can be 64 or 128 to capture time series features), fully connected layer (map the output of the LSTM layer to the prediction result), output layer (output the prediction of the number of broadcast packets at future time points).

[0053] Next, you can choose mean squared error (MSE) as the loss function and use the Adam optimizer for model training. During training, monitor the training loss and validation loss to prevent overfitting. Evaluate the trained model based on mean squared error (i.e., the average of the squared differences between the predicted and actual values), mean absolute error (i.e., the average of the absolute differences between the predicted and actual values), and R² coefficient of determination (i.e., used to evaluate the model's ability to explain data variation).

[0054] The trained model is used as the preset time series prediction model to predict the input real-time data, so as to set the preset threshold of broadcast traffic according to the monitored data related to broadcast traffic. When the predicted number of broadcast data packets exceeds the preset threshold, it is marked as a potential broadcast storm.

[0055] Through the above steps, the broadcast storm prediction module can effectively apply timing analysis technology to identify possible broadcast storms in advance and provide important decision support for subsequent broadcast suppression strategies.

[0056] In another embodiment of the present invention, step S104 may also include step S1041: setting a dynamic threshold based on the predicted traffic trend, the degree of broadcast storm and whether the identified monitored data has potential broadcast storm characteristics; step S1042: determining key parameters related to broadcast suppression; step S1043: when the monitored data related to broadcast traffic is not within the dynamic threshold, adjusting the key parameters related to broadcast suppression; step S1044: when the monitored data related to broadcast traffic is within the dynamic threshold range, gradually calling back to the initial parameter settings to maintain normal operation of the network.

[0057] Wherein, the step S1043 may further include: step S10431: when the monitored data related to the broadcast traffic is continuously higher than the dynamic threshold, gradually reducing the maximum forwarding times and / or the broadcast traffic rate.

[0058] For example, steps S1041 to S1044 further include the following steps: A dynamic parameter adjustment module can be deployed, and the maximum forwarding times (i.e., the maximum number of times each broadcast data packet is allowed to be forwarded in the network. Broadcast data packets exceeding this number will be discarded) and the broadcast traffic rate (i.e., the number of broadcast data packets allowed to be sent per unit time, usually expressed in packets per second (pps)) can be set as key parameters for broadcast suppression. For example, the initial maximum forwarding times can be set to 5 times and the traffic rate to 100 pps. The broadcast traffic in the network can be continuously monitored, and data such as the current number of broadcast data packets, forwarding times, and traffic rate can be collected. A preset threshold (e.g., 80 pps) can be set. Based on historical data and prediction results, it can be determined whether the current broadcast traffic exceeds the preset dynamic threshold (e.g., when the current broadcast traffic reaches 90 pps) to trigger the parameter adjustment mechanism.

[0059] According to the results of real-time monitoring and preset threshold judgment, a dynamic adjustment strategy is implemented. That is, if the broadcast traffic is detected to be continuously higher than the dynamic threshold, the maximum forwarding times and broadcast traffic rate can be gradually reduced. For example, the maximum forwarding times can be reduced from 5 to 3 times, and the traffic rate can be reduced from 100pps to 80pps. When the broadcast traffic falls back to the dynamic threshold range, the previous parameter settings are gradually restored to maintain the normal operation of the network.

[0060] Implement a feedback control mechanism to ensure that the adjusted parameters can effectively control broadcast traffic. That is, after adjusting the parameters, monitor the changes in broadcast traffic in real time, record the number of broadcast packets and traffic rate before and after the adjustment, and evaluate the adjustment effect based on the monitoring results. If it is found that the adjusted parameters still fail to effectively suppress broadcast traffic, it is necessary to further optimize the adjustment strategy. For example, if the traffic after adjustment is still higher than the dynamic threshold, further reduce the maximum number of forwarding times to 2 times and the traffic rate to 60pps, and monitor the effect again.

[0061] Through the above steps, the dynamic parameter adjustment module can flexibly adjust the broadcast suppression parameters according to the traffic analysis and prediction results, effectively control the broadcast traffic, prevent the occurrence of broadcast storms, and ensure the stability and performance of the network.

[0062] In another embodiment of the present invention, after step S104, the method may further include step S105: based on a feedback mechanism, monitoring data related to broadcast traffic in the target network, and optimizing the preset adjustment strategy according to the monitoring result.

[0063] In step S105, it can also include S1051: performing data analysis on the stored data related to the broadcast traffic; S1052: performing feedback adjustment according to the analysis results; S1053: updating the preset traffic feature recognition model within a preset period according to the data analysis results and the feedback adjustment results.

[0064] For example, step S105 further includes the following steps: Deploy a real-time monitoring and feedback module to continuously track the broadcast traffic in the network. The real-time monitoring and feedback module should have the functions of data collection and data storage.

[0065] On the basis of real-time monitoring, establish an effect evaluation mechanism to determine whether the adjusted parameters are effective. That is, set evaluation indicators: define key performance indicators, such as the rate of change of the number of broadcast packets, the stability of the traffic rate, etc. Set a target range, such as the number of broadcast packets should be kept below 80 per second. Regularly analyze the stored data, calculate the average and standard deviation of the number of broadcast packets and traffic rate, to evaluate whether the current broadcast traffic is within a reasonable range.

[0066] According to the results of the effect evaluation, a feedback adjustment strategy is implemented. That is, if the monitoring data shows that the broadcast traffic is still higher than the set dynamic threshold, the broadcast suppression parameters need to be further adjusted. For example, if the number of broadcast packets continues to be above 90, you can consider reducing the maximum number of forwarding times from 3 to 2 and the traffic rate from 80pps to 60pps. In addition, an automatic response mechanism is set in the monitoring system. When the broadcast traffic exceeds the preset threshold, the system can automatically trigger parameter adjustment without manual intervention.

[0067] Regularly review (for example, once a week) and analyze feedback data to evaluate the long-term effects of adjustment strategies to ensure continued stability of network performance, and regularly update traffic analysis and prediction models based on historical data and new traffic patterns to improve their accuracy and adaptability.

[0068] Through the above steps, the real-time monitoring feedback module can effectively monitor and evaluate the adjustment effect of broadcast traffic, ensure that the broadcast traffic remains within a reasonable range, thereby preventing the occurrence of broadcast storms and maintaining the stability and performance of the network.

[0069] Based on the same general inventive concept, the present invention also protects a control device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the above-mentioned broadcast suppression method.

[0070] Based on the same general inventive concept, the present invention also protects a machine-readable storage medium, on which instructions are stored, and the instructions enable the machine to execute the above-mentioned broadcast suppression method.

[0071] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0072] In addition, the terms "system" and "network" are often used interchangeably in this article. The term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0073] It should be understood that in the embodiment of the present invention, "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0074] 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, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. 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 the present invention.

[0075] 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.

[0076] 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 a logical function division. 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. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.

[0077] 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 embodiments of the present invention.

[0078] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0079] Through the description of the above embodiments, it can be clearly understood by those skilled in the art that the present invention can be implemented in hardware, firmware, or a combination thereof. When implemented using software, the above functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein the communication media include any medium that facilitates the transmission of computer programs from one place to another. The storage medium can be any available medium that can be accessed by a computer. Taking this as an example but not limited to: a computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer. In addition. Any connection can be appropriately a computer-readable medium. For example, if the software is transmitted from a website, server or other remote source using a coaxial cable, optical fiber cable, twisted pair, digital subscriber line (DSL) or wireless technologies such as infrared, radio and microwave, then the coaxial cable, optical fiber cable, twisted pair, DSL or wireless technologies such as infrared, wireless and microwave are included in the fixing of the medium. As used in the present invention, disk and disc include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and blue-ray disc, wherein disk usually reproduces data magnetically, while disc uses laser to reproduce data optically. The above combination should also be included in the scope of protection of computer-readable media.

[0080] In short, the above is only a preferred embodiment of the technical solution of the present invention, and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A broadcast suppression method for flat networking, characterized in that: The broadcast suppression method comprises: Monitor data related to broadcast traffic in the target network; Use the preset traffic feature recognition model to identify whether the monitored data has potential broadcast storm features; Using time series analysis techniques, predict traffic trends on the target network and identify potential broadcast storms in the monitored data; and Based on whether the identified monitored data has potential broadcast storm characteristics, the predicted traffic trend and the identified potential broadcast storm, and using a preset adjustment strategy, the parameters for suppressing the broadcast storm in the target network are adjusted.

2. The broadcast suppression method according to claim 1, characterized in that: The step of monitoring data related to broadcast traffic in the target network includes: Deploy a traffic monitoring system to capture data related to broadcast traffic; Creating a database to store captured data related to broadcast traffic; Collect statistics related to broadcast traffic and store the results in the database.

3. The method according to claim 1, characterized in that The data related to the broadcast traffic includes at least: the amount of broadcast traffic, the number of forwarding times, the frequency of broadcast traffic, and the source IP address.

4. The broadcast suppression method according to claim 1, characterized in that: Before using the preset traffic feature recognition model to identify whether the monitored data has potential broadcast storm features, the broadcast suppression method further includes: Acquire historical data related to broadcast traffic in the target network to construct a training set and a validation set; Construct a long short-term memory network for identifying traffic characteristics and set the activation function and loss function; The long short-term memory network for identifying traffic characteristics is trained by the training set, and the long short-term memory network for identifying traffic characteristics is trained and verified by the verification set; The trained model is used as the preset traffic feature recognition model.

5. The broadcast suppression method according to claim 1, characterized in that: The method of using the timing analysis technology to predict the traffic trend of the target network and identify broadcast storms in the monitored data includes: Acquire historical data and real-time data related to broadcast traffic of the target network in chronological order to obtain time series data; Extracting features from the time series data that are helpful for prediction, and constructing a training set and a validation set, wherein the features at least include moving average, seasonal decomposition, and autocorrelation; Use long short-term memory networks to build time series prediction models; The time series prediction model is trained by the training set, and the training of the time series prediction model is verified by the verification set; and The trained time series prediction model is used to predict the traffic trend of the target network and identify broadcast storms in the monitored data.

6. The broadcast suppression method according to claim 1, characterized in that: The method of using the trained time series prediction model to identify broadcast storms in the monitored data includes: Setting a preset threshold for broadcast traffic based on historical data related to broadcast traffic in the monitored target network; When the monitored data related to broadcast traffic exceeds a preset threshold, it is marked as a potential broadcast storm.

7. The broadcast suppression method according to claim 1, characterized in that: The step of adjusting the parameters for suppressing the broadcast storm in the target network based on whether the identified monitored data has potential broadcast storm characteristics, the predicted traffic trend, and the identified potential broadcast storm, and according to a preset adjustment strategy, includes: Dynamic thresholds are set based on whether the monitored data identified have potential broadcast storm characteristics, predicted traffic trends, and identified potential broadcast storms; Identify key parameters related to broadcast suppression; When the monitored data related to the broadcast traffic is not within the dynamic threshold, adjusting the key parameters related to broadcast suppression; When the monitored data related to broadcast traffic is within the dynamic threshold range, the parameters are gradually called back to the initial settings to maintain the normal operation of the network.

8. The broadcast suppression method according to claim 7, characterized in that: The key parameters related to broadcast suppression include at least: the maximum number of forwarding times allowed for each broadcast data packet in the network and the broadcast traffic rate.

9. The broadcast suppression method according to claim 7, characterized in that: When the monitored data related to the broadcast traffic is not within the dynamic threshold range, adjusting the key parameters related to the broadcast suppression includes: When the monitored data related to the broadcast traffic is continuously higher than the dynamic threshold, the maximum forwarding times and / or the broadcast traffic rate are gradually reduced.

10. The broadcast suppression method according to claim 1, characterized in that: After adjusting the parameters for suppressing broadcast storms in the target network, the broadcast suppression method further includes: Based on the feedback mechanism, the data related to the broadcast traffic in the target network is monitored, and the preset adjustment strategy is optimized according to the monitoring results.

11. The broadcast suppression method according to claim 10, characterized in that: The optimization of the preset adjustment strategy includes: Performing data analysis on stored data related to broadcast traffic; Make feedback adjustments based on the results of the analysis; Within a preset period, the preset traffic feature recognition model is updated based on the data analysis results and feedback adjustment results.

12. A control device, characterized in that: The control device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the broadcast suppression method according to any one of claims 1-11.

13. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions, which enable the machine to execute the broadcast suppression method according to any one of claims 1-11.

Images