Data pre-synchronization method and device for network controller switching and electronic equipment

Abstract

The application relates to a data pre-synchronization method and device for network controller switching and electronic equipment, the method comprising: obtaining historical data of network operation, and extracting features including traffic peak period and node fault history to form a feature set representing network state; identifying the network state based on the feature set and outputting a prediction result of the network state; in response to the prediction result reaching a switching threshold, outputting a pre-warning signal and triggering a pre-synchronization mechanism; and in response to the network state being within a normal range or controller switching not actually occurring, triggering a rollback mechanism. The application can reduce the delay and risk of data inconsistency during network controller switching by intelligently predicting network state changes and performing data synchronization in advance, thereby improving the stability and reliability of the network. Meanwhile, by providing a remedial rollback mechanism to restore the state of the backup controller to that before synchronization, the data consistency and stability of the system can be ensured.

Description

Technical Field

[0001] This invention relates to the field of network controllers, and in particular to a data pre-synchronization method, apparatus, and electronic device for network controller switching. Background Technology

[0002] In current redundant network controller systems, when the network state changes and controller switching is required, there is often a delay in data synchronization, which may lead to the risk of data inconsistency and affect the stability and reliability of the network. At the same time, traditional network controller switching is usually triggered only after a fault occurs, which cannot effectively reduce the delay and data inconsistency problems during switching. Summary of the Invention

[0003] Therefore, it is necessary to provide a data pre-synchronization method, device, and electronic device for network controller switching, which is necessary when the network status changes and controller switching is required. This may lead to data inconsistency risks and affect the stability and reliability of the network.

[0004] This invention provides a data pre-synchronization method for network controller switching, the method comprising:

[0005] Historical data of network operation is acquired, and features including peak traffic periods and node failure history are extracted to form a feature set representing the network status. The historical data includes information on network traffic patterns, data transmission latency, and error rate.

[0006] Based on the feature set, the network state is identified, and the predicted network state is output.

[0007] In response to the prediction result reaching the switching threshold, an early warning signal is output and a pre-synchronization mechanism is triggered;

[0008] The rollback mechanism is triggered in response to the network status being within the normal range or the controller switching not actually occurring.

[0009] In one embodiment, the step of acquiring historical network operation data and extracting features including peak traffic periods and node failure history includes:

[0010] Obtain performance metrics data of key network nodes under monitoring;

[0011] The historical data is cleaned and formatted to obtain preprocessed historical data.

[0012] Based on preprocessed historical data, traffic patterns are analyzed and peak traffic periods are identified.

[0013] Analyze the node failure history and output possible future failure points;

[0014] Perform mathematical transformations on the preprocessed historical data.

[0015] In one embodiment, the mathematical transformation of the preprocessed historical data includes:

[0016] Identifying periodic signals in preprocessed historical data based on Fourier transform techniques;

[0017] Alternatively, calculate the basic statistics of the preprocessed historical data, including the mean and variance.

[0018] In one embodiment, the step of identifying the network state based on the feature set and outputting the predicted network state includes:

[0019] Obtain the feature set representing the network state;

[0020] The feature set is input into the AI ​​prediction model, which outputs the prediction result of the network state. The AI ​​prediction model is trained using normal network state samples and abnormal network state samples as training data.

[0021] In one embodiment, the AI ​​prediction model is a time series model or a deep learning model, wherein the time series model is used to process linear and highly periodic data, and the deep learning model is used to process complex data with long-term dependencies and nonlinear relationships.

[0022] In one embodiment, the pre-synchronization triggering mechanism includes:

[0023] Determine the data and status information that need to be synchronized;

[0024] The calculation formula for performing data synchronization is as follows:

[0025] Data synchronization = f(master node data, backup node),

[0026] Where f represents the synchronization function;

[0027] Verify the data on the backup nodes.

[0028] In one embodiment, the trigger rollback mechanism includes:

[0029] Stop the data synchronization process and roll back the backup database to the specified point in time;

[0030] Update internal status management information and mark data on backup nodes as invalid or inactive;

[0031] The network components and controllers associated with the instruction will rescind any switching operations triggered due to incorrect predictions;

[0032] Record detailed information about the rollback operation, including the triggering reason, execution steps, and results;

[0033] Update the AI ​​prediction model based on the cause of the error.

[0034] The present invention also provides a data pre-synchronization device for network controller switching, comprising:

[0035] The acquisition module is used to acquire historical data of network operation and extract features including peak traffic periods and node failure history to form a feature set representing the network status. The historical data includes information on network traffic patterns, data transmission latency, and error rate.

[0036] The identification module is used to identify the network state based on the feature set and output the prediction result of the network state.

[0037] The response module is used to output an early warning signal and trigger a pre-synchronization mechanism when the prediction result reaches the switching threshold.

[0038] The trigger module is used to trigger the rollback mechanism in response to network conditions being within the normal range or the controller switching not actually occurring.

[0039] The present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the data pre-synchronization method for network controller switching as described above.

[0040] The present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the data pre-synchronization method for network controller switching as described above.

[0041] The aforementioned data pre-synchronization method, apparatus, and electronic equipment for network controller switching intelligently predict network state changes and synchronize data in advance, thereby reducing the risk of delay and data inconsistency during network controller switching, improving network stability and reliability. At the same time, by determining whether network controller switching has actually occurred, a remedial rollback mechanism is provided to restore the state of the backup controller to before synchronization, ensuring system data consistency and stability. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0043] Figure 1 This is a schematic diagram of a data pre-synchronization method for network controller switching in one embodiment.

[0044] Figure 2 This is a schematic diagram of the feature extraction process in one embodiment;

[0045] Figure 3 This is a flowchart illustrating the mathematical transformation of historical data in one embodiment.

[0046] Figure 4 This is a schematic diagram of the process for identifying network status in one embodiment;

[0047] Figure 5 This is a flowchart illustrating the triggering of the pre-synchronization mechanism in one embodiment;

[0048] Figure 6 This is a flowchart illustrating the triggering rollback mechanism in one embodiment;

[0049] Figure 7 This is a schematic diagram of the data pre-synchronization device for network controller switching in one embodiment.

[0050] Figure 8 This is an internal structural diagram of an electronic device according to one embodiment. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] The following is combined with Figures 1-8 The present invention describes a data pre-synchronization method, apparatus, and electronic device for network controller switching.

[0053] like Figure 1 As shown, in one embodiment, a data pre-synchronization method for network controller switching includes the following steps:

[0054] Step S110: Obtain historical network operation data and extract features including peak traffic periods and node failure history to form a feature set representing the network status. The historical data includes information on network traffic patterns, data transmission latency, and error rate.

[0055] Among them, network traffic patterns are helpful for understanding the patterns of data flow within a specific time period, while data transmission latency and error rate can reflect the real-time health status of the network.

[0056] Step S120: Based on the feature set, identify the network state and output the prediction result of the network state.

[0057] By intelligently predicting changes in network status, it is convenient to synchronize data in advance.

[0058] In step S130, in response to the prediction result reaching the switching threshold, an early warning signal is output and a pre-synchronization mechanism is triggered.

[0059] By monitoring and predicting results, it is easier to react in advance, thereby reducing latency during network controller switching.

[0060] Step S140: In response to the network status being within the normal range or the controller switching not actually occurring, the rollback mechanism is triggered.

[0061] By providing a remedial rollback mechanism to determine whether a network controller switchover has actually occurred, the backup controller's state can be restored to its state before synchronization, ensuring system data consistency and stability.

[0062] This data pre-synchronization method for network controller switching intelligently predicts network state changes and synchronizes data in advance, thereby reducing the risk of latency and data inconsistency during network controller switching and improving network stability and reliability. At the same time, by determining whether the network controller switching has actually occurred, it provides a remedial rollback mechanism to restore the backup controller to its state before synchronization, ensuring system data consistency and stability.

[0063] In this embodiment, see Figure 2 To obtain historical network operation data and extract features including peak traffic periods and node failure history, the following steps are included:

[0064] Step S111: Obtain performance indicator data of key network nodes under monitoring.

[0065] By monitoring key nodes in the network, a series of performance metrics data are collected, including but not limited to information on network traffic patterns, data transmission latency, and error rates. Network traffic patterns help to understand the patterns of data flow within a specific time period, while data transmission latency and error rates can reflect the real-time health status of the network.

[0066] Step S112: Clean and format the historical data to obtain preprocessed historical data.

[0067] Preprocessing historical data helps ensure the quality of the data input into AI prediction models.

[0068] Step S113: Based on the preprocessed historical data, analyze the traffic patterns and identify peak traffic periods.

[0069] This helps predict cyclical changes in network load.

[0070] Step S114: Analyze the node failure history and output the possible future failure points.

[0071] Predicting potential future failure points using historical failure data can effectively reduce latency during network controller switching.

[0072] Step S115: Perform mathematical transformation on the preprocessed historical data.

[0073] It facilitates the transformation of raw data into a format that AI prediction models can recognize and learn.

[0074] It should be noted that, see [link / reference] Figure 3 The preprocessed historical data undergoes mathematical transformation, including the following steps:

[0075] Step S116: Identify periodic signals in the preprocessed historical data based on Fourier transform technology.

[0076] The Fourier transform is a mathematical transformation that converts a function from the time domain to the frequency domain. By decomposing a complex time-domain signal into a sum of sine and cosine functions at different frequencies, the Fourier transform allows analysis of the signal's distribution across these frequencies. This is crucial for signal processing and image processing. For example, in signal processing, the Fourier transform can help identify noise components in a signal and remove this noise through filtering.

[0077] Alternatively, in step S117, calculate the basic statistics of the preprocessed historical data, including the mean and variance.

[0078] In the feature extraction process, it is necessary to pay attention not only to the quantity of data, but also to its quality and representativeness. Using the feature extraction methods described above, a set of features representing the network state can be obtained. This feature set will serve as input to the AI ​​prediction model for training and predicting changes in the network state.

[0079] For example, suppose we collect hourly traffic data for a network over the past month. By performing time-series analysis on this data, we can identify that weekly traffic peaks typically occur on Wednesday and Friday afternoons. Simultaneously, by analyzing node failure history, we find that failures of specific nodes are often associated with peak traffic periods. This information will be transformed into features and fed into an AI prediction model to improve the model's accuracy in predicting potential changes in network state.

[0080] In this embodiment, see Figure 4 Based on the feature set, the network state is identified, and the predicted network state is output, including the following steps:

[0081] Step S121: Obtain the feature set representing the network state.

[0082] It should be noted that these feature sets are historical data that has undergone preprocessing.

[0083] Step S122: Input the feature set into the AI ​​prediction model and output the prediction result of the network state. The AI ​​prediction model is trained using normal network state samples and abnormal network state samples as training data.

[0084] It should be noted that the AI ​​prediction model is either a time series model or a deep learning model. Time series models are used to handle data with strong linearity and periodicity, while deep learning models are used to handle complex data with long-term dependencies and non-linear relationships.

[0085] Time series models capture trends and patterns in data over time, while deep learning models learn complex data relationships through their multi-layered feature extraction and abstraction capabilities. The key to choosing these models lies in their predictive power—the ability to accurately predict future network state changes based on historical data, thereby providing decision support for subsequent data pre-synchronization and controller switching.

[0086] Based on the characteristics of network data, the applicability and prediction accuracy of different models are evaluated, thereby selecting a suitable AI prediction model.

[0087] Time series models, such as ARIMA (AutoRegressive Integrated Moving Average) and SARIMA (Seasonal AutoRegressive Integrated Moving Average), are suitable for linear and highly periodic data.

[0088] Deep learning models, such as LSTM (Long Short-Term Memory) and GRU (Gated Recurrent Unit), are suitable for processing complex data with long-term dependencies and nonlinear relationships.

[0089] Taking the ARIMA model as an example, the ARIMA model is a classic statistical model used for time series forecasting. It consists of three parts: autoregression (AR), differencing (I), and moving average (MA).

[0090] Autoregressive (AR): The model uses past values ​​in a time series to predict future values. The AR part specifies the number of past values ​​the model should consider and the impact of those values.

[0091] Difference (I): This step is to make a non-stationary time series stationary. A non-stationary time series is a series whose statistical properties (such as mean and variance) change over time. By differencing the series, it can be made more stationary, thus making it easier to predict.

[0092] Moving Average (MA): The model uses past prediction errors to predict future values, and the MA part specifies the impact of past prediction errors.

[0093] An ARIMA model is typically represented as ARIMA(p,d,q), where p is the order of the autoregressive term, d is the difference degree, and q is the order of the moving average term.

[0094] Choosing appropriate p, d, and q values ​​is crucial for building an effective ARIMA model and is typically determined through a model identification process. This involves using statistical methods (such as ACF and PACF plots) to analyze time series data to determine the model parameters.

[0095]

[0096] Where: y t This represents the value of the time series at time point t; L is the lag operator, i.e., Lt. k y t =y t-k ; θ1, θ2, ..., θ3 are the coefficients of the autoregressive term; p is the order of the autoregressive term; d is the difference degree, used to make the time series stationary; θ1, θ2, ..., θ3 are the coefficients of the autoregressive term; θ4 is the order of the autoregressive term; d is the difference degree, used to make the time series stationary; θ1, θ2, ..., θ3 are the coefficients of the q is the coefficient of the moving average term; q is the order of the moving average term; ∈ t is the white noise error term; c is the constant term.

[0097] The following is an example of an ARIMA model used to predict some time series data (e.g., monthly peak traffic):

[0098] Data collection: Collect monthly peak traffic data over a period of time, for example, collect monthly peak traffic data for the past 3 years.

[0099] Data preprocessing: Ensure the time series data is stationary. If the data is not stationary, differencing can be performed using the following steps:

[0100] Calculate the first-order difference: y t ′=y t -y t-1 If the data is still not stationary after the first-order difference, the second-order or higher-order differences can be calculated.

[0101] Model identification: The parameters (p, d, q) of the ARIMA model are determined using the autocorrelation function (ACF) and the partial autocorrelation function (PACF).

[0102] Model building: The model is built based on the following ARIMA model formula:

[0103]

[0104] Parameter estimation: Estimating model parameters using maximum likelihood estimation or other statistical methods. θ1, θ2, ..., θ q and c.

[0105] Model validation: The effectiveness of the model is verified by performing a white noise test on the model residuals.

[0106] Prediction: Using an established ARIMA model to predict future values, for example:

[0107] Suppose we have an ARIMA(1,1,1) model, the prediction formula might be:

[0108]

[0109] Among them, y t ′ is the data after first-order difference, ∈ t This is the error term from the previous period.

[0110] Results evaluation: The predictive performance of the model is evaluated by comparing the predicted values ​​with the actual observed values.

[0111] To ensure that the AI ​​prediction model can reliably predict network controller switching scenarios, the following detailed training and validation process needs to be performed:

[0112] The model was trained as follows:

[0113] Dataset preparation: First, the collected historical data of network operation is preprocessed and divided into training set and validation set. The training set is used for the model training process, while the validation set is used to evaluate the model's predictive performance.

[0114] Model Configuration: Based on the characteristics of the network data, configure the parameters of the AI ​​prediction model, including the learning rate, batch size, and number of network layers, to optimize the model's training performance. The following are the specific steps for model training:

[0115] Input feature processing: Standardize or normalize the feature data to adapt to the input requirements of the model.

[0116] Model iterative training: The model is trained iteratively using the following formula:

[0117]

[0118] Where θ represents the model parameters, α is the learning rate, and J(θ) is the loss function. It is the gradient of the loss function with respect to the model parameters.

[0119] Loss function optimization: The loss function is used for iterative training of the model. If the iterative training is not good, other appropriate loss functions (such as mean squared error (MSE) or cross-entropy loss) can be selected to measure the difference between the predicted value and the actual value, and the model parameters can be optimized to minimize the loss.

[0120] The model is validated as follows:

[0121] Predictive performance evaluation: Validate the trained model using a validation set.

[0122] The evaluation steps are as follows:

[0123] Model prediction: Using a trained model to predict data in the validation set.

[0124] Performance metrics calculation: Calculate the following performance metrics to evaluate the accuracy of the model:

[0125] Accuracy = Number of correct predictions / Total number of predictions

[0126] Recall = Number of correctly predicted positive samples / Actual number of positive samples

[0127] F1 score = 2(precision·recall) / (precision + recall).

[0128] Results analysis: Analyze the model's prediction results to ensure that the model's accuracy, recall, and F1 score reach the predetermined thresholds to confirm the model's reliability.

[0129] For example, a deep learning model was trained using a training set containing network state data from the past year. During training, the learning rate was adjusted to 0.001, and mean squared error was used as the loss function. After 100 training epochs, the model's performance was evaluated on the validation set. The results showed that the model achieved an accuracy of 95%, a recall of 90%, and an F1 score of 92%, indicating that the model has high predictive reliability and can be used for practical network state prediction.

[0130] After training and validating the AI ​​prediction model, the model is deployed to the network environment to achieve real-time monitoring of the network status and prediction of future state changes. The following are the specific implementation steps for real-time monitoring and prediction:

[0131] Model deployment: Integrate the trained AI prediction model into the network monitoring system to ensure that the model can continuously receive and process real-time network data streams.

[0132] Data flow monitoring: Captures data flow in the network in real time, including but not limited to key performance indicators such as traffic, latency, and error rate.

[0133] State Analysis: The AI ​​prediction model analyzes the captured data stream and makes state predictions through the following process:

[0134] Real-time data feature extraction: Extracting key features from real-time data, including preprocessing of the real-time data, and ensuring that these features are consistent with those used when training the model.

[0135] State prediction: Prediction is performed using the following formula:

[0136]

[0137] in, θ represents the network state predicted by the model, x is the feature vector of the real-time data, and θ is the model parameters.

[0138] Prediction result processing: The model outputs the prediction results and determines whether there is a potential controller switching requirement based on preset thresholds.

[0139] For example, an AI prediction model receives network performance metric updates every minute. The model immediately extracts features from this data and predicts changes in network status within the next five minutes. If the prediction indicates that the network status will exceed normal operating limits, the model outputs a warning signal, suggesting that a controller switchover may be necessary. This real-time monitoring and prediction mechanism enables pre-synchronization measures to be taken before potential network problems occur, thereby improving network stability and reliability.

[0140] In this embodiment, see Figure 5This triggers the pre-synchronization mechanism, which includes the following steps:

[0141] Step S131: Determine the data and status information that need to be synchronized.

[0142] These are typically the minimum datasets necessary to ensure the continuous operation of the network.

[0143] Step S132, perform data synchronization, the calculation formula is as follows:

[0144] Data synchronization = f(master node data, backup node),

[0145] Here, f represents the synchronization function.

[0146] This ensures that the data on the primary node is replicated to the backup node.

[0147] Step S133: Verify the data of the backup node.

[0148] After synchronization is complete, the data integrity and consistency are ensured by verifying the data on the backup nodes.

[0149] The pre-synchronization mechanism is triggered when the AI ​​prediction model predicts that the network state is about to reach the switching threshold, and immediately sends a signal to trigger the pre-synchronization mechanism.

[0150] In this embodiment, see Figure 6 This triggers the rollback mechanism, including the following steps:

[0151] Step S141: Stop the data synchronization process and roll back the backup database to the specified point in time.

[0152] By utilizing previously created data snapshots or logs, the data on the backup node can be restored to its state before pre-synchronization.

[0153] Step S142: Update the internal status management information and mark the data on the backup node as invalid or inactive.

[0154] This facilitates ensuring data consistency and system stability.

[0155] Step S143 instructs the relevant network components and controllers to revoke any switching operations triggered due to incorrect predictions.

[0156] It facilitates the cancellation of pre-synchronization and restoration to a stable state.

[0157] Step S144: Record detailed information about the rollback operation, including the triggering reason, execution steps, and results.

[0158] This facilitates subsequent analysis and troubleshooting.

[0159] Step S145: Update the AI ​​prediction model based on the cause of the error.

[0160] By updating AI prediction models, similar prediction errors can be avoided in the future.

[0161] Monitoring and switching decisions: The system continuously monitors whether a controller switch has actually been triggered.

[0162] Determine rollback conditions: If it is determined that no switch is needed (e.g., because the network status has returned to normal), then the rollback mechanism is triggered.

[0163] For example, if the AI ​​prediction model predicts that the network load will exceed the main controller's processing capacity within the next 5 minutes, the system will initiate a pre-synchronization mechanism. At this time, the main controller will synchronize all critical configuration files and real-time data to the backup controller. If, after synchronization is complete, the network load decreases for some reason, and the predicted switchover does not occur, the system will initiate a rollback mechanism to restore the backup controller's state to its state before synchronization, ensuring system data consistency and stability.

[0164] The data pre-synchronization device for network controller switching provided by the present invention is described below. The data pre-synchronization device for network controller switching described below and the data pre-synchronization method for network controller switching described above can be referred to in correspondence with each other.

[0165] like Figure 7 As shown, in one embodiment, a data pre-synchronization device for network controller switching includes an acquisition module 710, an identification module 720, a response module 730, and a triggering module 740.

[0166] The acquisition module 710 is used to acquire historical data of network operation and extract features including peak traffic periods and node failure history to form a feature set representing the network status. The historical data includes information on network traffic patterns, data transmission latency, and error rate.

[0167] The recognition module 720 is used to identify the network state based on the feature set and output the prediction result of the network state.

[0168] The response module 730 is used to respond to the prediction result reaching the switching threshold, output a warning signal, and trigger a pre-synchronization mechanism.

[0169] The trigger module 740 is used to trigger the rollback mechanism in response to the network status being within the normal range or the controller switching not actually occurring.

[0170] In this embodiment, the acquisition module 710 is specifically used for:

[0171] Obtain performance metrics data of key network nodes under monitoring;

[0172] The historical data is cleaned and formatted to obtain preprocessed historical data.

[0173] Based on preprocessed historical data, traffic patterns are analyzed and peak traffic periods are identified.

[0174] Analyze the node failure history and output possible future failure points;

[0175] Perform mathematical transformations on the preprocessed historical data.

[0176] In this embodiment, the preprocessed historical data undergoes mathematical transformation, specifically for:

[0177] Identifying periodic signals in preprocessed historical data based on Fourier transform techniques;

[0178] Alternatively, calculate the basic statistics of the preprocessed historical data, including the mean and variance.

[0179] In this embodiment, the identification module 720 is specifically used for:

[0180] Obtain the feature set representing the network state;

[0181] The feature set is input into the AI ​​prediction model, which outputs the prediction result of the network state. The AI ​​prediction model is trained using normal network state samples and abnormal network state samples as training data.

[0182] In this embodiment, the pre-synchronization mechanism is triggered, specifically for:

[0183] Determine the data and status information that need to be synchronized;

[0184] The calculation formula for performing data synchronization is as follows:

[0185] Data synchronization = f(master node data, backup node),

[0186] Where f represents the synchronization function;

[0187] Verify the data on the backup nodes.

[0188] In this embodiment, the rollback mechanism is triggered, specifically for:

[0189] Stop the data synchronization process and roll back the backup database to the specified point in time;

[0190] Update internal status management information and mark data on backup nodes as invalid or inactive;

[0191] The network components and controllers associated with the instruction will rescind any switching operations triggered due to incorrect predictions;

[0192] Record detailed information about the rollback operation, including the triggering reason, execution steps, and results;

[0193] Update the AI ​​prediction model based on the cause of the error.

[0194] This network controller switching data pre-synchronization device intelligently predicts network state changes and synchronizes data in advance, thereby reducing the risk of latency and data inconsistency during network controller switching, and improving network stability and reliability. At the same time, by determining whether the network controller switching has actually occurred, it provides a remedial rollback mechanism to restore the backup controller to the state before synchronization, ensuring system data consistency and stability.

[0195] Figure 8 This example illustrates a schematic diagram of the physical structure of an electronic device, which can be a smart terminal. Its internal structure diagram can be as follows: Figure 8 As shown. The electronic device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, a data pre-synchronization method for implementing network controller switching is implemented, the method including:

[0196] Historical network operation data is acquired, and features including peak traffic periods and node failure history are extracted to form a feature set representing the network status. The historical data includes information on network traffic patterns, data transmission latency, and error rate.

[0197] Based on the feature set, the network state is identified, and the predicted network state is output.

[0198] In response to the prediction result reaching the switching threshold, an early warning signal is output and a pre-synchronization mechanism is triggered;

[0199] The rollback mechanism is triggered in response to the network status being within the normal range or the controller switching not actually occurring.

[0200] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the electronic device to which the present invention is applied. A specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0201] On the other hand, the present invention also provides a computer storage medium storing a computer program, wherein when the computer program is executed by a processor, a data pre-synchronization method for network controller switching is implemented, the method comprising:

[0202] Historical network operation data is acquired, and features including peak traffic periods and node failure history are extracted to form a feature set representing the network status. The historical data includes information on network traffic patterns, data transmission latency, and error rate.

[0203] Based on the feature set, the network state is identified, and the predicted network state is output.

[0204] In response to the prediction result reaching the switching threshold, an early warning signal is output and a pre-synchronization mechanism is triggered;

[0205] The rollback mechanism is triggered in response to the network status being within the normal range or the controller switching not actually occurring.

[0206] In another aspect, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and when the processor executes the computer instructions, it implements a data pre-synchronization method for network controller switching, the method comprising:

[0207] Historical network operation data is acquired, and features including peak traffic periods and node failure history are extracted to form a feature set representing the network status. The historical data includes information on network traffic patterns, data transmission latency, and error rate.

[0208] Based on the feature set, the network state is identified, and the predicted network state is output.

[0209] In response to the prediction result reaching the switching threshold, an early warning signal is output and a pre-synchronization mechanism is triggered;

[0210] The rollback mechanism is triggered in response to the network status being within the normal range or the controller switching not actually occurring.

[0211] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory.

[0212] By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0213] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0214] The above-described embodiments are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the appended claims.

Claims

1. A data pre-synchronization method for network controller switching, characterized in that, The method includes: Historical data of network operation is acquired, and features including peak traffic periods and node failure history are extracted to form a feature set representing the network status. The historical data includes information on network traffic patterns, data transmission latency, and error rate. Based on the feature set, the feature set is input into the AI ​​prediction model, and the prediction result of the network state is output. The AI ​​prediction model is trained using normal network state samples and abnormal network state samples as training data. The AI ​​prediction model is a time series model or a deep learning model. In response to the prediction result reaching the switching threshold, an early warning signal is output, and a pre-synchronization mechanism is triggered. The pre-synchronization mechanism includes: determining the data and status information that need to be synchronized; performing data synchronization, calculated using the following formula: data synchronization = f (master node data, backup node), where f represents the synchronization function; verifying the data of the backup node; the triggering condition for the pre-synchronization mechanism is: when the AI ​​prediction model predicts that the network status is about to reach the switching threshold, a signal is immediately sent to trigger the pre-synchronization mechanism. In response to the network status being within the normal range or the controller switching not actually occurring, a rollback mechanism is triggered. The rollback mechanism includes: stopping the data synchronization process and rolling back the backup database to a specified point in time; updating internal status management information and marking the data on the backup node as invalid or inactive; instructing relevant network components and controllers to revert any switching operations triggered due to erroneous predictions; recording detailed information about the rollback operation, including the triggering reason, execution steps, and results; and updating the AI ​​prediction model based on the cause of the error.

2. The data pre-synchronization method for network controller switching according to claim 1, characterized in that, The acquisition of historical network operation data and the extraction of features including peak traffic periods and node failure history include: Obtain performance metrics data of key network nodes under monitoring; The historical data is cleaned and formatted to obtain preprocessed historical data. Based on preprocessed historical data, traffic patterns are analyzed and peak traffic periods are identified. Analyze the node failure history and output possible future failure points; Perform mathematical transformations on the preprocessed historical data.

3. The data pre-synchronization method for network controller switching according to claim 2, characterized in that, The mathematical transformation of the preprocessed historical data includes: Identifying periodic signals in preprocessed historical data based on Fourier transform techniques; Alternatively, calculate the basic statistics of the preprocessed historical data, including the mean and variance.

4. The data pre-synchronization method for network controller switching according to claim 1, characterized in that, The time series model is used to process data with strong linearity and periodicity, while the deep learning model is used to process complex data with long-term dependencies and nonlinear relationships.

5. A data pre-synchronization device for network controller switching, characterized in that, include: The acquisition module is used to acquire historical data of network operation and extract features including peak traffic periods and node failure history to form a feature set representing the network status. The historical data includes information on network traffic patterns, data transmission latency, and error rate. The identification module is used to input the feature set into the AI ​​prediction model based on the feature set, identify the network state, and output the prediction result of the network state. The AI ​​prediction model is trained using normal network state samples and abnormal network state samples as training data. The AI ​​prediction model is a time series model or a deep learning model. The response module is used to respond to the prediction result reaching the switching threshold, output a warning signal, and trigger a pre-synchronization mechanism. The pre-synchronization mechanism includes: determining the data and status information that need to be synchronized; performing data synchronization, calculated using the following formula: data synchronization = f (master node data, backup node), where f represents the synchronization function; verifying the data of the backup node; the trigger condition for the pre-synchronization mechanism is: when the AI ​​prediction model predicts that the network status is about to reach the switching threshold, it immediately sends a signal to trigger the pre-synchronization mechanism. The triggering module is used to trigger a rollback mechanism in response to the network status being within the normal range or the controller switching not actually occurring. The rollback mechanism includes: stopping the data synchronization process and rolling back the backup database to a specified point in time; updating internal status management information and marking the data on the backup node as invalid or inactive; instructing relevant network components and controllers to revert any switching operations triggered due to erroneous predictions; recording detailed information about the rollback operation, including the triggering reason, execution steps, and results; and updating the AI ​​prediction model based on the cause of the error.

6. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images