Electric power data protection method and device based on industrial internet, and storage medium

Abstract

The invention relates to the technical field of power system data security protection, in particular to a power data protection method and device based on the industrial internet and a storage medium, and the method comprises the following steps: S1, data collection and preprocessing: collecting power data of a power system in real time through various sensors, preprocessing the collected power data at an edge computing node; s2, data transmission and storage: recording storage and access logs of the power data by using a block chain technology; s3, data backup and recovery: backing up the power data regularly; s4, data analysis: identifying potential security threats and abnormal behaviors; s5, a real-time self-healing mechanism: realizing a self-healing function of the power system; and S6, data protection: automatically triggering safety protection measures. According to the invention, the system is rapidly repaired after a fault occurs, the normal operation state is recovered, and the self-healing capability of the power system is enhanced.

Description

Technical Field

[0001] The present invention relates to the field of power system data security protection technology, and in particular to an industrial Internet-based power data protection method, device and storage medium. Background Art

[0002] With the development of industrial Internet technology, the operation and management of power systems have become more intelligent and data-driven. A large amount of power data in the power system is collected in real time through sensors and transmitted to the industrial Internet platform through the network for storage, analysis and management. These data include multiple parameters such as current, voltage, temperature, frequency, etc., which are the key to the stable operation and optimized management of the power system. However, with the increase in data volume and the complexity of the network environment, the security, integrity and reliability of power data are facing increasing challenges.

[0003] At present, the protection of power data mainly relies on traditional security measures, such as firewalls, encrypted transmission and access control. Although these measures can protect power data to a certain extent, they are still insufficient in dealing with complex network environments and changing security threats. Traditional protection methods lack the ability to monitor and dynamically adjust data in real time, and cannot effectively identify and handle potential security threats and abnormal behaviors. In addition, existing technologies also have certain limitations in the recovery speed and accuracy after data loss or damage, resulting in the power system being unable to quickly resume normal operation when encountering a fault, thus affecting the stability and reliability of the system.

[0004] In order to solve the above problems, the present invention proposes a power data protection method based on industrial Internet, which effectively prevents potential security threats and abnormal behaviors through comprehensive security protection and response mechanisms, and ensures the integrity of power data and the continuous and stable operation of the system. Summary of the invention

[0005] Based on the above objectives, the present invention provides an industrial Internet-based power data protection method, device and storage medium.

[0006] The power data protection method based on the industrial Internet includes the following steps:

[0007] S1, data collection and preprocessing: collect power data of the power system in real time through a variety of sensors, and preprocess the collected power data at the edge computing node;

[0008] S2, data transmission and storage: the pre-processed power data is sent to the industrial Internet platform and stored in multiple nodes using distributed storage technology, and the storage and access logs of power data are recorded using blockchain technology;

[0009] S3, data backup and recovery: regularly back up power data and quickly restore power data when it is lost or damaged;

[0010] S4, data analysis: Analyze the stored power data to identify potential security threats and abnormal behaviors;

[0011] S5, real-time self-healing mechanism: real-time monitoring of the power system operating status, prediction of potential faults, and realization of the self-healing function of the power system, including:

[0012] S51, Fault prediction: Real-time monitoring of the power system operation status through fault prediction models to detect anomalies and potential faults;

[0013] S52, early warning and adjustment: Based on the predicted faults, early warning is issued in advance, and the power system parameters are automatically adjusted or the operation mode is switched before the fault occurs to avoid the actual occurrence of the fault;

[0014] S53, fault repair: After a fault occurs, the system will quickly perform self-repair and resume normal operation;

[0015] S6, Data Protection: Automatically trigger security protection measures based on the results of data analysis and real-time self-healing mechanisms, including access control, anomaly detection and response mechanisms.

[0016] Optionally, the data collection and preprocessing in S1 includes:

[0017] S11, data collection: real-time power data including current, voltage, temperature and frequency are collected through current sensors, voltage sensors, temperature sensors and frequency sensors;

[0018] S12, data preprocessing: On the edge computing node, the collected power data is preprocessed, including data cleaning, format conversion and preliminary encryption.

[0019] Optionally, the data backup and recovery in S3 includes:

[0020] S31, regular data backup: Regularly back up the power data of the power system, including:

[0021] Backup plan formulation: formulate a data backup plan and determine the backup time interval and data volume;

[0022] Data snapshot: At a predetermined time point, the data snapshot technology is used to capture the current status of power data;

[0023] Backup storage: transfer and store data snapshots to multiple backup storage nodes;

[0024] S32, fast data recovery: when power data is lost or damaged, fast recovery of power data, including:

[0025] Data restoration: Extract lost or damaged power data shards from backup storage nodes and restore them to the power system’s data storage;

[0026] Data verification: Use hash function to verify the restored data.

[0027] Optionally, the data analysis in S4 includes:

[0028] S41, security threat identification: Use Gaussian mixture models to analyze stored power data to identify potential security threats and abnormal behaviors, including:

[0029] S411, define the data set: Let the data set be The parameters of the Gaussian mixture model include the mean vector μ k , covariance matrix∑ k and the mixing coefficient π k , where k is the number of Gaussian distributions;

[0030] S412, parameter initialization: Initialize parameter μ k ,∑ k and π k ;

[0031] S413, EM algorithm update parameters:

[0032] Step E:

[0033] M-step:

[0034] Among them, γ ik is the data point X i The probability of belonging to the kth Gaussian distribution, (X i |μ k ,∑ k ) is the probability density function of the kth Gaussian distribution;

[0035] S414, calculate anomaly score: for each data point X, calculate its anomaly score, expressed as:

[0036]

[0037] S415, outlier identification: if the anomaly score is higher than a preset threshold, the data point is considered to be an outlier;

[0038] S42, abnormal behavior detection: combining historical power data and real-time power data, using the autoregressive integrated moving average (ARIMA) model to detect abnormal behavior;

[0039] S43, security threat warning: Based on the Gaussian mixture model and time series analysis results, it identifies potential security threats and abnormal behaviors and issues a warning signal.

[0040] Optionally, the fault prediction model in S51 adopts a recursive neural network (RNN) model, and the recursive neural network (RNN) model includes:

[0041] S511, construct a multivariate RNN structure: Assume that the input data is a multivariate time series, expressed as:

[0042]

[0043] in, is the value of the 1st, 2nd, ..., nth variable at time t;

[0044] S512, Attention Mechanism: Introduce the attention mechanism to dynamically adjust the attention to different time steps in the input sequence at each time step, expressed as:

[0045] Calculate the attention weight α t，t ′:

[0046] e t，t′ =tanh(W e h t-1 +UeX t′ +b e );

[0047]

[0048] Among them, e t，t′ is the intermediate representation of the attention weight, W e and U e is the weight matrix, b e is the bias vector;

[0049] Calculate the attention weighted input:

[0050] Update hidden state h t :h t =σ(W h c t +U h h t-1 +b h );

[0051] Among them, c t is the attention-weighted input, σ is the activation function, W h and U h is the weight matrix, b h is the bias vector;

[0052] S513, loss function optimization: introduce a penalty term to enhance the model's sensitivity to abnormal data, expressed as:

[0053]

[0054] Among them, y t is the true value, is the predicted value, λ is the penalty coefficient, δ is the fault threshold, is the indicator function;

[0055] S514, model training: using the optimized loss function to train the recursive neural network (RNN) model, and using the gradient descent method to optimize the model parameters, expressed as:

[0056]

[0057] Where η is the learning rate;

[0058] S515, real-time monitoring and fault prediction: Apply the trained model to monitor the operating status of the power system in real time, input the current multivariate time series data, predict the state of the next time step, and detect abnormal conditions, expressed as:

[0059]

[0060] Among them, f is the optimized recursive neural network function and θ is the model parameter.

[0061] Optionally, the early warning and adjustment in S52 include:

[0062] S521, Fault prediction: Use the recurrent neural network (RNN) model to perform real-time monitoring and fault prediction on the multivariate time series data of the power system. Suppose the predicted fault state is

[0063] S522, warning signal is issued: when the predicted fault state When the preset fault threshold δ is exceeded, an early warning signal is automatically issued;

[0064] S523, parameter adjustment: according to the early warning signal, automatically adjust the operating parameters of the power system, the operating parameters include voltage, current and frequency, expressed as:

[0065] P t+1 =P t +ΔP;

[0066] Among them, P t is the current operating parameter, ΔP is the incremental operating parameter after adjustment;

[0067] S524, operation mode switching: when a fault is detected, the operation mode is automatically switched, including switching from high load mode to low load mode or enabling backup power supply.

[0068] Optionally, the fault repair in S53 includes:

[0069] S531, fault detection: real-time monitoring of faults in the power system and identification of the type and location of the faults;

[0070] S532, data isolation: after a fault occurs, isolate the affected power data area;

[0071] S533, automatic repair: automatic repair of detected anomalies and potential faults, including reconfiguring power system parameters and switching backup equipment;

[0072] S534, system recovery: after the fault is repaired, gradually restore the power supply to the faulty area and monitor the stability during the recovery process;

[0073] S535, power data repair: After the power system is restored, the power data during the fault period is repaired, including data integrity check, data consistency check, data cleaning, interpolation and reconstruction.

[0074] Optionally, the data protection in S6 includes:

[0075] S61, Analysis Results Integration: Integrate the analysis results of data analysis and real-time self-healing mechanisms to identify potential security threats and abnormal behaviors;

[0076] S62, access control: dynamically adjusting access rights to power data in the power system based on the integrated analysis results;

[0077] S63, anomaly detection: using the z-score method to detect abnormal data in the integrated analysis results in real time, identifying and marking abnormal data points;

[0078] S64, response mechanism: automatically trigger corresponding security response measures based on the abnormal detection results.

[0079] The power data protection device based on the industrial Internet is used to implement the above-mentioned power data protection method based on the industrial Internet, including:

[0080] Data acquisition and preprocessing module: collects power data of the power system in real time through a variety of sensors, and preprocesses the collected power data at the edge computing node;

[0081] Data transmission and storage module: sends the pre-processed power data to the industrial Internet platform, and uses distributed storage technology to store it in multiple nodes, and uses blockchain technology to record the storage and access logs of power data;

[0082] Data backup and recovery module: regularly back up power data and quickly restore power data when it is lost or damaged;

[0083] Data analysis module: Analyzes stored power data to identify potential security threats and abnormal behaviors;

[0084] Real-time self-healing mechanism module: monitors the operating status of the power system in real time, predicts potential faults, and automatically adjusts the parameters of the power system or switches the operating mode before a fault occurs, thus realizing the self-healing function of the power system;

[0085] Data protection module: automatically triggers security protection measures, including access control, anomaly detection and response mechanisms, based on the results of the data analysis module and the real-time self-healing mechanism module.

[0086] A storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above-mentioned method for protecting power data based on industrial Internet.

[0087] Beneficial effects of the present invention:

[0088] The present invention realizes the real-time and accurate collection and preprocessing of power data through the combination of multiple sensors and edge computing nodes. It adopts distributed storage and blockchain technology to ensure the confidentiality, integrity and non-tamperability of data during transmission and storage. The regular backup and rapid recovery mechanism ensures that power data can be quickly restored when lost or damaged, thereby improving the data security and reliability of the power system.

[0089] The present invention, by introducing a recursive neural network model, realizes real-time monitoring and fault prediction of the power system. By dynamically adjusting the attention paid to different time steps, long-term dependencies can be better captured, thereby improving the accuracy of fault prediction. Combined with the early warning and adjustment mechanism, it can issue an early warning before a fault occurs and automatically adjust the power system parameters or switch the operating mode, thereby effectively avoiding the actual occurrence of the fault. In addition, the automatic repair mechanism ensures that the system is quickly repaired after the fault occurs and the normal operating state is restored, further enhancing the self-healing ability of the power system.

[0090] The present invention detects and marks abnormal data in real time through the z-score method, dynamically adjusts access permissions, and prevents unauthorized access. After abnormality detection, it automatically triggers a variety of response measures including data isolation, abnormality handling, system restart or switching, data backup and recovery, network security measures, log recording and auditing, as well as notifications and alarms to ensure the continuous and stable operation of the system. The detailed log recording and auditing functions facilitate post-analysis and optimization, thereby improving the overall security and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0091] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0092] Figure 1 A schematic diagram of a protection method flow chart of an embodiment of the present invention;

[0093] Figure 2 Schematic diagram of a protective device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0094] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0095] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0096] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0097] like Figure 1 As shown, the power data protection method based on the industrial Internet includes the following steps:

[0098] S1, data collection and preprocessing: The power data of the power system is collected in real time through a variety of sensors, and the collected power data is preprocessed at the edge computing node to improve the accuracy and security of the data;

[0099] S2, data transmission and storage: The pre-processed power data is sent to the industrial Internet platform and stored in multiple nodes using distributed storage technology. Blockchain technology is used to record the storage and access logs of power data to ensure the data is tamper-proof and traceable, and to ensure the confidentiality and integrity of the data during transmission and storage;

[0100] S3, data backup and recovery: regularly back up power data and quickly restore power data when it is lost or damaged to ensure the stable operation of the power system;

[0101] S4, data analysis: Analyze the stored power data to identify potential security threats and abnormal behaviors;

[0102] S5, real-time self-healing mechanism: real-time monitoring of the power system operating status, prediction of potential faults, and realization of the self-healing function of the power system, including:

[0103] S51, Fault prediction: Real-time monitoring of the power system operation status through fault prediction models to detect anomalies and potential faults;

[0104] S52, early warning and adjustment: Based on the predicted faults, early warning is issued in advance, and the power system parameters are automatically adjusted or the operation mode is switched before the fault occurs to avoid the actual occurrence of the fault;

[0105] S53, fault repair: After a fault occurs, the system will quickly perform self-repair and resume normal operation;

[0106] S6, Data Protection: Based on the results of data analysis and real-time self-healing mechanisms, security protection measures are automatically triggered, including access control, anomaly detection and response mechanisms, to protect power data in real time;

[0107] Through the above steps, the security, reliability and stability of power data are comprehensively improved, effectively preventing potential security threats and abnormal behaviors, and ensuring the continuous and stable operation of the power system.

[0108] Data collection and preprocessing in S1 include:

[0109] S11, data collection: real-time power data including current, voltage, temperature and frequency are collected through current sensors, voltage sensors, temperature sensors and frequency sensors;

[0110] S12, data preprocessing: on the edge computing node, the collected power data is preprocessed, including data cleaning, format conversion and preliminary encryption;

[0111] Data cleaning uses the standard deviation method to detect and remove noise and outliers in power data. Suppose data D contains n data points d i , the data cleaning process is expressed as:

[0112] D clean ={d i ∈D|d i is not an outlier};

[0113] Outliers = {d i |d i >μ+3σord i <μ-3σ};

[0114] Among them, μ is the mean of the data, σ is the standard deviation of the data;

[0115] Format conversion: converting data from the original acquisition format to a standardized format for subsequent processing;

[0116] Preliminary encryption: Use the AES encryption algorithm to perform preliminary encryption on the data to ensure data security during transmission, as shown in the following figure:

[0117] E(D clean )=AES K (D clean );

[0118] Among them, AES K represents the AES encryption function using key K, D clean is the cleaned data;

[0119] Through the above steps, it is possible to ensure that the power data of the power system is collected in real time and accurately, and perform necessary preprocessing before transmission to improve the accuracy and security of the data, providing a solid foundation for subsequent data transmission, storage, analysis and protection.

[0120] Data backup and recovery in S3 include:

[0121] S31, regular data backup: Regularly back up the power data of the power system, including:

[0122] Backup plan formulation: formulate a data backup plan and determine the backup time interval and data volume;

[0123] Data snapshot: At a predetermined time point, the data snapshot technology is used to capture the current status of power data;

[0124] Backup storage: transfer and store data snapshots to multiple backup storage nodes to ensure data redundancy and storage security;

[0125] S32, fast data recovery: when power data is lost or damaged, fast recovery of power data, including:

[0126] Data restoration: Extract lost or damaged power data shards from backup storage nodes and restore them to the power system’s data storage;

[0127] Data verification: Use hash functions to verify the restored data to ensure data integrity and consistency;

[0128] Through the above steps, the method can regularly back up power data and quickly and accurately restore power data when data is lost or damaged, thereby ensuring the stable operation of the power system and the integrity of the data.

[0129] The data analysis in S4 includes:

[0130] S41, security threat identification: Use Gaussian mixture models to analyze stored power data to identify potential security threats and abnormal behaviors, including:

[0131] S411, define the data set: Let the data set be The parameters of the Gaussian mixture model include the mean vector μ k , covariance matrix∑ k and the mixing coefficient π k , where k is the number of Gaussian distributions;

[0132] S412, parameter initialization: Initialize parameter μ k ,∑ k and π k ;

[0133] S413, EM algorithm update parameters:

[0134] Step E:

[0135] M-step:

[0136] Among them, γ ik is the data point X i The probability of belonging to the kth Gaussian distribution, (X i |μ k ,∑ k ) is the probability density function of the kth Gaussian distribution;

[0137] S414, calculate anomaly score: for each data point X, calculate its anomaly score, expressed as:

[0138]

[0139] S415, outlier identification: if the anomaly score is higher than a preset threshold, the data point is considered to be an outlier;

[0140] The preset threshold is set using the percentile method, and the threshold is set to the pth percentile (such as the 95th or 99th percentile) of the abnormal score of the normal data, expressed as:

[0141] Threshold = Percentile(s(X), p);

[0142] Where s(X) is the anomaly score of normal data, and Percentile(s(X), p) represents the value of the anomaly score at percentile p;

[0143] S42, abnormal behavior detection: combining historical power data and real-time power data, using the autoregressive integrated moving average (ARIMA) model to detect abnormal behavior, expressed as:

[0144]

[0145] Among them, X t is the data at time t, and θ are model parameters, ∈ t is the error term;

[0146] S43, security threat warning: Based on the Gaussian mixture model and time series analysis results, it identifies potential security threats and abnormal behaviors and issues warning signals;

[0147] Through the above steps, the stored power data can be deeply analyzed to identify potential security threats and abnormal behaviors, thus ensuring the safety and stability of the power system.

[0148] The fault prediction model in S51 adopts a recurrent neural network (RNN) model, which includes:

[0149] S511, construct a multivariate RNN structure: Assume that the input data is a multivariate time series, expressed as:

[0150]

[0151] in, is the value of the 1st, 2nd, ..., nth variable at time t;

[0152] S512, Attention Mechanism: The attention mechanism is introduced to dynamically adjust the attention to different time steps in the input sequence in each time step, so as to better capture long-term dependencies, expressed as:

[0153] Calculate the attention weight α t，t′ :

[0154] e t，t′ =tanh(W e h t-1 +U e X t′ +b e );

[0155]

[0156] Among them, e t，t′ is the intermediate representation of the attention weight, used to calculate the attention weight between time steps t and t′, W e and U e is the weight matrix, b e is the bias vector;

[0157] Calculate the attention weighted input:

[0158] Update hidden state h t :h t =σ(W h c t +U h h t-1 +b h );

[0159] Among them, c t is the attention-weighted input, σ is the activation function, W h and U h is the weight matrix, b h is the bias vector;

[0160] S513, loss function optimization: introduce a penalty term to enhance the model's sensitivity to abnormal data, expressed as:

[0161]

[0162] Among them, yt is the true value, is the predicted value, λ is the penalty coefficient, δ is the fault threshold, is the indicator function. When the prediction error exceeds the fault threshold δ, the indicator function takes the value of 1, otherwise it takes the value of 0;

[0163] The fault threshold δ is set based on the mean and standard deviation method, expressed as:

[0164] δ=μ+kσ;

[0165]

[0166]

[0167]

[0168] Where μ is the mean of the prediction error, σ is the standard deviation of the prediction error, k is a constant (such as 2 or 3) used to control the looseness of the threshold, ∈ is the prediction error ∈, and N is the number of samples;

[0169] S514, model training: using the optimized loss function to train the recursive neural network (RNN) model, and using the gradient descent method to optimize the model parameters, expressed as:

[0170]

[0171] Where η is the learning rate;

[0172] S515, real-time monitoring and fault prediction: Apply the trained model to monitor the operating status of the power system in real time, input the current multivariate time series data, predict the state of the next time step, and detect abnormal conditions, expressed as:

[0173]

[0174] Among them, f is the optimized recursive neural network function, and θ is the model parameter;

[0175] Through the above content, we can better handle the multivariate time series characteristics of power system data, improve the accuracy of fault prediction, and use the attention mechanism to dynamically adjust the attention to different time steps, so that the model can more accurately reflect the actual operating status of the power system and provide reliable fault prediction and early warning functions.

[0176] The early warning and adjustment in S52 include:

[0177] S521, Fault prediction: Use the recurrent neural network (RNN) model to perform real-time monitoring and fault prediction on the multivariate time series data of the power system. Suppose the predicted fault state is

[0178] S522, warning signal is issued: when the predicted fault state When the preset fault threshold δ is exceeded, an early warning signal is automatically issued;

[0179] S523, parameter adjustment: according to the early warning signal, automatically adjust the operating parameters of the power system to prevent the occurrence of faults. The operating parameters include voltage, current and frequency, which are expressed as:

[0180] P t+1 =P t +ΔP;

[0181] Among them, P t is the current operating parameter, ΔP is the incremental operating parameter after adjustment;

[0182] S524, operation mode switching: when a fault is detected, automatically switching the operation mode, including switching from a high load mode to a low load mode or enabling a backup power source, to ensure stable operation of the power system;

[0183] Through the above steps, it is possible to automatically adjust the parameters of the power system or switch the operating mode through prediction and early warning before a fault occurs, thereby effectively avoiding the actual occurrence of the fault and ensuring the stable operation of the power system.

[0184] Bug fixes in S53 include:

[0185] S531, fault detection: real-time monitoring of faults in the power system and identification of the type and location of the faults;

[0186] S532, data isolation: after a fault occurs, isolate the affected power data area to prevent the fault data from affecting system decision-making;

[0187] S533, automatic repair: automatic repair of detected anomalies and potential faults, including reconfiguring power system parameters and switching backup equipment;

[0188] S534, system recovery: after the fault is repaired, gradually restore the power supply to the faulty area and monitor the stability during the recovery process;

[0189] S535, power data repair: after the power system is restored, the power data during the fault period is repaired, including data integrity check, data consistency check, data cleaning, interpolation and reconstruction to ensure data integrity and consistency;

[0190] Through the above steps, after a fault occurs, the power system fault can be automatically repaired to ensure that the system returns to normal operation, and the power data during the fault can be repaired to ensure the integrity and consistency of the data, thereby ensuring the stable and reliable operation of the power system.

[0191] Data protection in S6 includes:

[0192] S61, Analysis Results Integration: Integrate the analysis results of data analysis and real-time self-healing mechanisms to identify potential security threats and abnormal behaviors;

[0193] S62, access control: dynamically adjust access rights to power data in the power system based on the integrated analysis results to prevent unauthorized access;

[0194] S63, anomaly detection: using the z-score method to detect abnormal data in the integrated analysis results in real time, identifying and marking abnormal data points;

[0195] S64, Response Mechanism: Automatically trigger corresponding security response measures based on the abnormal detection results to prevent or mitigate potential threats;

[0196] Specific security response measures include:

[0197] Access control: limit access to critical systems and data, adjust user permissions in real time, block unauthorized access, enable two-factor authentication, and increase access security;

[0198] Data isolation: Isolate the affected systems or data to prevent the spread of faults, create isolation zones, and limit the spread of affected data;

[0199] Exception handling: block and handle abnormal data input in real time, start abnormal data repair program, correct data errors, trigger alarm system, and notify administrators or relevant personnel;

[0200] System restart or switch: Automatically restart affected system components to restore normal operation and switch to backup systems or backup paths to ensure uninterrupted services.

[0201] Data backup and recovery: Start the data backup program, save the current system status, and restore the affected data or system from the backup;

[0202] Network security measures: monitor network traffic in real time to prevent malicious attacks and intrusions, enable firewalls and intrusion detection systems to protect systems from external threats, implement security patches and updates, and fix known vulnerabilities;

[0203] Logging and auditing: Record all security incidents and response measures in detail, maintain log integrity, facilitate post-analysis and auditing, analyze log data, and identify potential security risks;

[0204] Notifications and Alerts: Send instant alerts and notifications to relevant personnel, provide detailed fault and response information for quick processing, and activate automated notification systems to ensure timely communication.

[0205] Through the above steps, it is possible to quickly respond to and handle exceptions, prevent faults from spreading, and ensure the continuous and stable operation of the system. At the same time, detailed logging and auditing functions are provided to facilitate post-analysis and optimization, thereby improving the overall security and reliability of the system.

[0206] like Figure 2 As shown, the power data protection device based on the industrial Internet is used to implement the above-mentioned power data protection method based on the industrial Internet, including:

[0207] Data acquisition and preprocessing module: collects power data of the power system in real time through a variety of sensors, and preprocesses the collected power data at the edge computing node;

[0208] Data transmission and storage module: sends the pre-processed power data to the industrial Internet platform, and uses distributed storage technology to store it in multiple nodes, and uses blockchain technology to record the storage and access logs of power data;

[0209] Data backup and recovery module: regularly back up power data and quickly restore power data when it is lost or damaged;

[0210] Data analysis module: Analyzes stored power data to identify potential security threats and abnormal behaviors;

[0211] Real-time self-healing mechanism module: monitors the operating status of the power system in real time, predicts potential faults, and automatically adjusts the parameters of the power system or switches the operating mode before a fault occurs, thus realizing the self-healing function of the power system;

[0212] Data protection module: automatically triggers security protection measures, including access control, anomaly detection and response mechanisms, based on the results of the data analysis module and the real-time self-healing mechanism module.

[0213] A storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method for protecting power data based on the industrial Internet.

[0214] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0215] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. The power data protection method based on the industrial Internet is characterized by: The following steps are involved: S1, data collection and preprocessing: collect power data of the power system in real time through a variety of sensors, and preprocess the collected power data at the edge computing node; S2, data transmission and storage: the pre-processed power data is sent to the industrial Internet platform and stored in multiple nodes using distributed storage technology, and the storage and access logs of power data are recorded using blockchain technology; S3, data backup and recovery: regularly back up power data and quickly restore power data when it is lost or damaged; S4, data analysis: analyze the stored power data to identify potential security threats and abnormal behaviors; S5, real-time self-healing mechanism: real-time monitoring of the power system operating status, prediction of potential faults, and realization of the self-healing function of the power system, including: S51, Fault prediction: Real-time monitoring of the power system operation status through fault prediction models to detect anomalies and potential faults; S52, early warning and adjustment: Based on the predicted faults, early warning is issued in advance, and the power system parameters are automatically adjusted or the operation mode is switched before the fault occurs to avoid the actual occurrence of the fault; S53, fault repair: After a fault occurs, the system will quickly perform self-repair and resume normal operation; S6, Data Protection: Automatically trigger security protection measures based on the results of data analysis and real-time self-healing mechanisms, including access control, anomaly detection and response mechanisms.

2. The power data protection method based on industrial Internet according to claim 1 is characterized in that: The data collection and preprocessing in S1 include: S11, data collection: real-time power data including current, voltage, temperature and frequency are collected through current sensors, voltage sensors, temperature sensors and frequency sensors; S12, data preprocessing: On the edge computing node, the collected power data is preprocessed, including data cleaning, format conversion and preliminary encryption.

3. The power data protection method based on industrial Internet according to claim 1 is characterized in that: The data backup and recovery in S3 includes: S31, regular data backup: Regularly back up the power data of the power system, including: Backup plan formulation: formulate a data backup plan and determine the backup time interval and data volume; Data snapshot: At a predetermined time point, the data snapshot technology is used to capture the current status of power data; Backup storage: transfer and store data snapshots to multiple backup storage nodes; S32, fast data recovery: when power data is lost or damaged, fast recovery of power data, including: Data restoration: Extract lost or damaged power data shards from backup storage nodes and restore them to the power system’s data storage; Data verification: Use hash function to verify the restored data.

4. The power data protection method based on industrial Internet according to claim 1 is characterized in that: The data analysis in S4 includes: S41, security threat identification: Use Gaussian mixture models to analyze stored power data to identify potential security threats and abnormal behaviors, including: S411, define the data set: Let the data set be The parameters of the Gaussian mixture model include the mean vector μ k , covariance matrix∑ k and the mixing coefficient π k , where k is the number of Gaussian distributions; S412, parameter initialization: Initialize parameter μ k ,∑ k and π k ; S413, EM algorithm update parameters: Step E: M-step: Among them, γ ik is the data point X i The probability of belonging to the kth Gaussian distribution, (X i |μ k ,Σ k ) is the probability density function of the kth Gaussian distribution; S414, calculate anomaly score: for each data point X, calculate its anomaly score, expressed as: Anomaly score S415, outlier identification: if the anomaly score is higher than a preset threshold, the data point is considered to be an outlier; S42, abnormal behavior detection: combining historical power data and real-time power data, using the autoregressive integrated moving average model to detect abnormal behavior; S43, security threat warning: Based on the Gaussian mixture model and time series analysis results, it identifies potential security threats and abnormal behaviors and issues a warning signal.

5. The power data protection method based on industrial Internet according to claim 1 is characterized in that: The fault prediction model in S51 adopts a recursive neural network model, and the recursive neural network model includes: S511, construct a multivariate RNN structure: Assume that the input data is a multivariate time series, expressed as: in, is the value of the 1st, 2nd, ..., nth variable at time t; S512, Attention Mechanism: Introduce the attention mechanism to dynamically adjust the attention to different time steps in the input sequence at each time step, expressed as: Calculate the attention weight α t,t′ : e t,t′ =tanh(W e h t-1 +U e X t′ +b e ); Among them, e t,t′ is the intermediate representation of the attention weight, W e and U e is the weight matrix, b e is the bias vector; Calculate the attention weighted input: Update hidden state h t :h t =σ(W h c t +U h h t-1 +b h ); Among them, c t is the attention-weighted input, σ is the activation function, W h and U n is the weight matrix, b h is the bias vector; S513, loss function optimization: introduce a penalty term to enhance the model's sensitivity to abnormal data, expressed as: Among them, y t is the true value, is the predicted value, λ is the penalty coefficient, δ is the fault threshold, is the indicator function; S514, model training: use the optimized loss function to train the recursive neural network model, and use the gradient descent method to optimize the model parameters, expressed as: Where η is the learning rate; S515, real-time monitoring and fault prediction: Apply the trained model to monitor the operating status of the power system in real time, input the current multivariate time series data, predict the state of the next time step, and detect abnormal conditions, expressed as: Among them, f is the optimized recursive neural network function and θ is the model parameter.

6. The power data protection method based on industrial Internet according to claim 5 is characterized in that: The early warning and adjustment in S52 include: S521, Fault prediction: Use the recurrent neural network model to perform real-time monitoring and fault prediction on the multivariate time series data of the power system. Suppose the predicted fault state is S522, warning signal is issued: when the predicted fault state When the preset fault threshold δ is exceeded, an early warning signal is automatically issued; S523, parameter adjustment: according to the early warning signal, automatically adjust the operating parameters of the power system, the operating parameters include voltage, current and frequency, expressed as: P t+1 =P t +ΔP; Among them, P t is the current operating parameter, ΔP is the incremental operating parameter after adjustment; S524, operation mode switching: when a fault is detected, the operation mode is automatically switched, including switching from high load mode to low load mode or enabling backup power supply.

7. The power data protection method based on industrial Internet according to claim 6 is characterized in that: The fault repair in S53 includes: S531, fault detection: real-time monitoring of faults in the power system and identification of the type and location of the faults; S532, data isolation: after a fault occurs, isolate the affected power data area; S533, automatic repair: automatic repair of detected anomalies and potential faults, including reconfiguring power system parameters and switching backup equipment; S534, system recovery: after the fault is repaired, gradually restore the power supply to the faulty area and monitor the stability during the recovery process; S535, power data repair: After the power system is restored, the power data during the fault period is repaired, including data integrity check, data consistency check, data cleaning, interpolation and reconstruction.

8. The power data protection method based on industrial Internet according to claim 1 is characterized in that: The data protection in S6 includes: S61, Analysis Results Integration: Integrate the analysis results of data analysis and real-time self-healing mechanisms to identify potential security threats and abnormal behaviors; S62, access control: dynamically adjusting access rights to power data in the power system based on the integrated analysis results; S63, anomaly detection: using the z-score method to detect abnormal data in the integrated analysis results in real time, identifying and marking abnormal data points; S64, response mechanism: automatically trigger corresponding security response measures based on the abnormal detection results.

9. An industrial Internet-based power data protection device, used to implement the industrial Internet-based power data protection method as described in any one of claims 1 to 8, characterized in that: include: Data acquisition and preprocessing module: collects power data of the power system in real time through a variety of sensors, and preprocesses the collected power data at the edge computing node; Data transmission and storage module: sends the pre-processed power data to the industrial Internet platform, and uses distributed storage technology to store it in multiple nodes, and uses blockchain technology to record the storage and access logs of power data; Data backup and recovery module: regularly back up power data and quickly restore power data when it is lost or damaged; Data analysis module: Analyzes stored power data to identify potential security threats and abnormal behaviors; Real-time self-healing mechanism module: monitors the operating status of the power system in real time, predicts potential faults, and automatically adjusts the parameters of the power system or switches the operating mode before a fault occurs, thus realizing the self-healing function of the power system; Data protection module: automatically triggers security protection measures, including access control, anomaly detection and response mechanisms, based on the results of the data analysis module and the real-time self-healing mechanism module.

10. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the steps of the power data protection method based on industrial Internet as described in any one of claims 1 to 8.

Images