A blockchain-based power data security management and control system

Abstract

The application relates to a blockchain-based power data security management and control system, which comprises a data acquisition module for acquiring operation data of a power system in real time; a rule mining module for mining frequent item sets in the processed operation data, generating initial association rules corresponding to the frequent item sets, constructing a variable space according to the initial association rules, determining a target path in the variable space, and determining an abnormal condition of the power system according to a target association rule corresponding to the target path. The system can improve the detection capability of the power system security hidden danger.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power safety, in particular to a power data security management and control system based on block chain. BACKGROUND

[0002] In the modernization process of the power system, the security and reliability of data are key factors to ensure the stable operation of the power system. With the gradual development of the power system towards intelligence and interconnection, the scale and complexity of power data are increasing, and the security challenges faced by power data management are becoming increasingly severe. The stable operation of the power system depends on real-time monitoring, accurate fault diagnosis and efficient security management, and the security and integrity of power data become particularly important, especially in the face of natural disasters, cyber attacks and system failures. The traditional power data management system is susceptible to data tampering, leakage and single-point failure due to the limitations of centralized storage, and cannot meet the high requirements of modern power systems for data security.

[0003] In the prior art, power data can be intelligently collected and transmitted to a cloud management platform for security management and control. However, this method has low potential security risk detection capability, more false positives, and cannot quickly respond to changes in the power system, and has low sensitivity to security risks.

[0004] Therefore, there is a problem of low security risk detection capability in the current power data security management and control technology. SUMMARY

[0005] Therefore, it is necessary to provide a power data security management and control system based on block chain which can improve the security risk detection capability.

[0006] In a first aspect, the present application provides a power data security management and control system based on block chain, comprising:

[0007] a data acquisition module, configured to acquire running data of a power system in real time;

[0008] a rule mining module, configured to mine frequent item sets in the processed running data, generate initial association rules corresponding to the frequent item sets, construct a variable space according to the initial association rules, determine a target path in the variable space, and determine an abnormal situation of the power system according to a target association rule corresponding to the target path.

[0009] In one of the embodiments, the rule mining module is further configured to determine an initial value of pheromone corresponding to the selected body, determine heuristic information according to the confidence and support of the initial association rule, determine a path selection probability of the variable space according to the initial value of pheromone and the heuristic information, and determine the target path according to the path selection probability.

[0010] The rule mining module is further configured to update the pheromone according to the target path, return the obtained updated value of pheromone as the initial value of pheromone to the step of determining the path selection probability of the variable space according to the initial value of pheromone and the heuristic information, and determining the target path according to the path selection probability, until a preset termination condition is met, and determine the target association rule according to the finally determined target path.

[0011] In one of the embodiments, the system further comprises a data preprocessing module configured to preprocess the operation data to obtain the processed operation data.

[0012] In one of the embodiments, the system further comprises a block storage module configured to store the processed operation data to a block chain.

[0013] In one of the embodiments, the system further comprises a hybrid consensus module configured to perform a hash transformation on the processed operation data, and upload the obtained block to the block chain.

[0014] In one of the embodiments, the system further comprises an access control module configured to set user access permissions and control user access according to the user access permissions.

[0015] In one of the embodiments, the system further comprises a prediction decision module configured to determine a search tree according to the current state and executable operations of the power system, determine a return value corresponding to each node of the search tree by simulating the power system, and determine a fault condition of the power system according to the return value.

[0016] In one of the embodiments, the system further comprises a management optimization module configured to determine a state transition probability of the power system, determine a target state transition strategy of the power system according to a reward value associated with the state transition of the power system according to the state transition probability.

[0017] In one of the embodiments, the system further comprises a security audit module and a security configuration evaluation module, the security audit module is configured to audit the security management of the power system, and the security configuration evaluation module is configured to determine the security and efficiency of the power system.

[0018] In one of the embodiments, the system further comprises a modeling simulation module for simulating the power system.

[0019] In a second aspect, the application further provides a power data security management method based on a block chain, comprising:

[0020] Mining frequent item sets in the processed operation data, and generating initial association rules corresponding to the frequent item sets;

[0021] Constructing a variable space according to the initial association rules, and determining a target path in the variable space;

[0022] Determining an abnormal situation of the power system according to a target association rule corresponding to the target path.

[0023] In a third aspect, the application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0024] Mining frequent item sets in the processed operation data, and generating initial association rules corresponding to the frequent item sets;

[0025] Constructing a variable space according to the initial association rules, and determining a target path in the variable space;

[0026] Determining an abnormal situation of the power system according to a target association rule corresponding to the target path.

[0027] In a fourth aspect, the application further provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the following steps:

[0028] Mining frequent item sets in the processed operation data, and generating initial association rules corresponding to the frequent item sets;

[0029] Constructing a variable space according to the initial association rules, and determining a target path in the variable space;

[0030] Determining an abnormal situation of the power system according to a target association rule corresponding to the target path.

[0031] In a fifth aspect, the application further provides a computer program product comprising a computer program, wherein the computer program is executed by a processor to implement the following steps:

[0032] Mining frequent item sets in the processed operation data, and generating initial association rules corresponding to the frequent item sets;

[0033] Constructing a variable space according to the initial association rules, and determining a target path in the variable space;

[0034] determine the abnormal situation of the power system according to the target association rule corresponding to the target path.

[0035] The blockchain-based power data security management system, method, computer device, computer readable storage medium and computer program product can obtain the operation data of the power system in real time through the data acquisition module, mine the frequent item set in the processed operation data through the rule mining module, generate the initial association rule corresponding to the frequent item set, construct the variable space according to the initial association rule, determine the target path in the variable space, and determine the abnormal situation of the power system according to the target association rule corresponding to the target path. The frequent item set can be mined from the operation data of the power system, and the association rule corresponding to the frequent item set can be determined. The high-quality target association rule is screened from the association rule, the potential security risks existing in the power system are identified based on the target association rule, and the detection capability of the security risks of the power system is improved. BRIEF DESCRIPTION OF DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other related drawings can be obtained by those skilled in the art without creative labor.

[0037] Figure 1 is a structural block diagram of a blockchain-based power data security management system in an embodiment;

[0038] Figure 2 is a structural block diagram of a blockchain-based power data security management system in another embodiment;

[0039] Figure 3 is a flowchart of a blockchain-based power data security management method in an embodiment;

[0040] Figure 4 is an internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0042] It should be noted that the terms "first", "second", and the like in the description and in the claims of the present disclosure and above-described accompanying drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Rather, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0043] In one exemplary embodiment, as shown in Figure 1 A blockchain-based power data security management system is provided, comprising:

[0044] The data acquisition module 102 is configured to acquire real-time operation data of the power system.

[0045] The rule mining module 104 is configured to mine frequent item sets from the processed operation data, generate initial association rules corresponding to the frequent item sets, construct a variable space according to the initial association rules, determine a target path in the variable space, and determine an abnormal situation of the power system according to a target association rule corresponding to the target path.

[0046] The blockchain-based power data security management system can be a terminal, a server, or other equipment for securely managing power data, and the present application does not limit this. The data acquisition module and the rule mining module can be functional modules integrated in the blockchain-based power data security management system, and can be computer programs or physical devices, and the present application does not limit this.

[0047] The power system refers to a unified whole of power generation, transmission, transformation, distribution, and use of electric energy, composed of power generation, power transmission, power transformation, power distribution, power equipment, users, and corresponding auxiliary systems. The operation data can be voltage, current, power, and other data generated during the operation of the power system. The frequent item set refers to a set of several items that frequently appear in the operation data. The initial association rule can be the association relationship between each item in the frequent item set obtained under the initial condition. The variable space can be a data space composed of variables. The target path can be a selected path in the variable space. The target association rule can be an association relationship corresponding to the target path. The abnormal situation can be a potential safety hazard and other situations existing in the power system.

[0048] In the specific implementation, sensors can be arranged in the power system, the data acquisition module is connected with the sensors, the sensors collect the operation data of the power system in real time, and the collected operation data is sent to the data acquisition module, so that the data acquisition module obtains the operation data of the power system in real time. After the operation data is preprocessed, it is sent to the rule mining module, the rule mining module mines frequent item sets from the preprocessed operation data, and takes the association rules of any two subsets in the frequent item sets as initial association rules. The confidence and support of each initial association rule are calculated, wherein the confidence is the ratio of the support of the union of the frequent item and a certain item to the support of the frequent item set, and the support is the number of sets containing the frequent item set. The path selection probability in the variable space is determined according to the confidence and support, the target path is determined according to the path selection probability, the association rule corresponding to the target path is taken as the target association rule, and the potential security risks existing in the power system are determined according to the target association rule.

[0049] In actual application, based on the frequent pattern growth (FP-Growth) algorithm, frequent item sets are mined in the power data set, and association rules of any two subsets in each frequent item set are generated to obtain the association relationship between variables in the power data, and the confidence and support of each association rule are calculated. Then, the ant colony algorithm can be referred to, the volatility factor, the number of selected bodies (the number of ant colonies), and the initial value of the pheromone are initialized, the heuristic information corresponding to each association rule is calculated according to the calculated confidence and support of each association rule (for example, the heuristic information is obtained according to the product of the confidence and the support), each selected body is randomly initialized, each selected body is mapped to each association rule to form a variable space, the path selection probability corresponding to each selected body is calculated according to the initial value of the pheromone and the heuristic information, and path selection is performed in the variable space based on the path selection probability. According to the selected high-probability path, an association rule combination is formed (for example, for the path with a path selection probability higher than a preset threshold, the association rules corresponding to each selected body on the path are combined to form an association rule combination), each path is comprehensively evaluated according to the total support and total confidence corresponding to the association rule combination, the pheromone is updated according to the evaluation value (a parameter reflecting the quality of the path) of the path, the path selection and pheromone updating process is repeated until a preset iteration number is reached, the association rule combination with the highest evaluation value is screened out, and each problem in the power system is identified according to the association rule combination.

[0050] The path selection probability can be represented as

[0051]

[0052]

[0053] wherein, representative path heuristic information; representative association rule confidence; representative association rule support; representative selection body selection path probability; representative path pheromone concentration; representative pheromone influence coefficient; representative heuristic information influence coefficient; representative set of all paths selectable in the current variable space.

[0054] In this way, according to the real-time operation of the power system, the frequent item set can be continuously mined, and the association relationship between each subset in the frequent item set is updated again, and the operation mode of the power system is judged in real time through the latest association relationship.

[0055] The above-mentioned power data security management and control system based on blockchain can obtain the operation data of the power system in real time through the data acquisition module, mine the frequent item set in the processed operation data through the rule mining module, generate the initial association rule corresponding to the frequent item set, construct the variable space according to the initial association rule, determine the target path in the variable space, and determine the abnormal situation of the power system according to the target association rule corresponding to the target path. The frequent item set can be mined from the operation data of the power system, and the association rule corresponding to the frequent item set is determined, the high-quality target association rule is screened from the association rule, the potential safety hidden danger existing in the power system is identified based on the target association rule, and the detection ability of the safety hidden danger of the power system is improved.

[0056] In an exemplary embodiment, the rule mining module 104 is further configured to determine a pheromone initial value of the pheromone corresponding to the selection body, determine heuristic information according to the confidence and support of the initial association rule, determine a path selection probability of the variable space according to the pheromone initial value and the heuristic information, and determine the target path according to the path selection probability; update the pheromone according to the target path, take the obtained pheromone update value as the pheromone initial value, return to the step of determining the path selection probability of the variable space according to the pheromone initial value and the heuristic information, determine the target path according to the path selection probability, until a preset termination condition is met, and determine the target association rule according to the finally determined target path.

[0057] Here, the selector can be a node corresponding to an association rule. Pheromones can be parameters generated during the selector's movement. Heuristic information can be parameters obtained based on confidence and support. Path selection probability is the probability that the selector will choose a particular path. The preset termination condition is reaching a preset number of iterations.

[0058] In specific implementation, the rule mining module can associate each association rule with a selector and randomly initialize the position of each selector to form a variable space. The initial values ​​of the pheromones corresponding to each selector in the variable space are set manually or automatically. Heuristic information is calculated based on the credibility and support of each association rule. The path selection probability corresponding to each selector in the variable space is determined based on the initial pheromone values ​​and the heuristic information. A target path is selected in the variable space based on the path selection probability; for example, paths with a path selection probability higher than a preset threshold are selected as target paths. Here, a path refers to a connection between at least two selectors. Evaluation parameters for at least two association rules (association rule combinations) corresponding to the target path are determined. These evaluation parameters reflect the quality of the target path. The pheromones of the selectors are updated based on the evaluation parameters, and the updated pheromone values ​​are used as new initial pheromone values. This process is repeated until a preset number of iterations is reached. Among the target paths determined during the iteration process, the one with the highest evaluation parameter is selected, and the association rules in the association rule combination corresponding to that target path are determined as the target association rules. Thus, the FP-Growth algorithm is used to efficiently extract frequent itemsets, and then the ant colony algorithm is used to further evaluate and optimize the association rules between these frequent itemsets.

[0059] In this embodiment, by determining the initial pheromone value of the pheromone corresponding to the selected entity, determining heuristic information based on the credibility and support of the initial association rule, determining the path selection probability of the variable space based on the initial pheromone value and the heuristic information, determining the target path based on the path selection probability, updating the pheromone according to the target path, using the obtained updated pheromone value as the initial pheromone value, and returning to the steps of determining the path selection probability of the variable space based on the initial pheromone value and the heuristic information, and determining the target path based on the path selection probability, until a preset termination condition is met, and determining the target association rule based on the finally determined target path, safety hazards in the power system can be accurately identified, so that corresponding measures can be taken in a timely manner to ensure the safety of the power system.

[0060] In one exemplary embodiment, the aforementioned blockchain-based power data security management and control system further includes a data preprocessing module for preprocessing operational data to obtain processed operational data.

[0061] The data preprocessing module can be a functional module integrated in the power data security management system based on the blockchain.

[0062] In specific implementation, the data collection module can be connected with the data preprocessing module, and the data preprocessing module is further connected with the rule mining module and the block storage module. The data collection module inputs the real-time acquired operation data into the data preprocessing module, and the data preprocessing module performs data cleaning, standardization and other processing to obtain processed operation data. The processed operation data is sent to the rule mining module for frequent item set mining or to the block storage module for on-chain storage.

[0063] In this embodiment, the operation data is preprocessed to obtain processed operation data, which can ensure the integrity and accuracy of the data and improve the reliability of identifying the security risks of the power system.

[0064] In one exemplary embodiment, the power data security management system based on the blockchain further includes a block storage module for storing the processed operation data to the blockchain.

[0065] The block storage module can be a functional module integrated in the power data security management system based on the blockchain.

[0066] In specific implementation, the block storage module can store the processed operation data to the blockchain.

[0067] In this embodiment, the processed operation data is stored to the blockchain, which can avoid data tampering and ensure the security of the power data.

[0068] In one exemplary embodiment, the power data security management system based on the blockchain further includes a hybrid consensus module for performing hash transformation on the processed operation data and uploading the obtained block to the blockchain.

[0069] The hybrid consensus module can be a functional module integrated in the power data security management system based on the blockchain.

[0070] In a specific implementation, the hybrid consensus module can be connected with the block storage module. The hybrid consensus module can package the processed operation data, and when packaging, convert each data entry into a hash value through a hash function, and then merge each group of hash values two by two in turn, and hash again until the final Merkle root is formed to form a block. Then, the miner nodes in the block chain use different Nonce values (random numbers) in turn until the hash value of the block header is less than the preset target value, and then broadcast the formed block to the network. A group of nodes holding rights are randomly selected to verify the legality and integrity of the data in the block, and sign for confirmation. The nodes calculate the hash value of each data entry in the block, and verify the Merkle tree structure level by level. If the recalculated Merkle root is the same as the Merkle root in the block header and passes the verification, it is considered that the data is complete and true, and the block that passes the double verification is added to the block chain for storage.

[0071] In the embodiment, by performing hash transformation on the processed operation data, and uploading the obtained block to the block chain, it can be ensured that the power data stored on the chain is real and reliable.

[0072] In an exemplary embodiment, the above-mentioned blockchain-based power data security management system further comprises an access control module for setting user access permissions and controlling user access according to user access permissions.

[0073] The access control module can be a functional module integrated in the blockchain-based power data security management system.

[0074] In a specific implementation, the access control module can be connected with the block storage module. The access control module can set user access permissions and control user access to the block storage module according to user access permissions.

[0075] In the embodiment, by setting user access permissions and controlling user access according to user access permissions, the security of block chain access can be ensured.

[0076] In an exemplary embodiment, the above-mentioned blockchain-based power data security management system further comprises a prediction decision module for determining a search tree according to the current state of the power system and executable operations, determining the return value corresponding to each node of the search tree by simulating the power system, and determining the fault condition of the power system according to the return value.

[0077] The prediction decision module can be a functional module integrated in the blockchain-based power data security management system. The current state can be the normal or fault state of the power system. The executable operation can be each operation that can be performed on the power system. The return value can be a parameter reflecting the fault condition of the power system obtained by simulation.

[0078] In a specific implementation, the prediction and decision module can be connected with the rule mining module, and used for predicting and deciding the operation data security event, analyzing the expected results of different strategies, and optimizing the security management decision. Specifically, the prediction and decision module can collect the processed operation data, extract time sequence features, spatial features, and historical event features from the processed operation data, take the current state of the power system as a root node, and set a maximum search depth and an iteration number. Starting from the root node, an action is selected based on the UCB (Upper Confidence Bound) selection strategy according to the executable operation of the power system, and the state is transferred to the next state. The value of each action is evaluated based on the statistical model of the historical data, and the optimal action is selected to expand the state, so as to gradually expand the nodes of the search tree until the maximum search depth is reached, and a search tree is formed. The search tree is simulated to predict the possible security events of the power system in the future, and the results of each simulation are evaluated to calculate the total return from the current node to the terminal node, and the node value in the search tree is updated. The process of selection, expansion, simulation, and backtracking is repeated until the maximum iteration number is reached. Based on the current cumulative expected return, the action with the highest return value is selected at each node, and the optimal path and state transition with the highest cumulative expected return are analyzed to identify the key nodes and actions that lead to the failure or unsafe state of the power system, generate a warning for these potential problems, and suggest corresponding preventive measures or coping strategies. In this way, the MCST (Minimum Cost Spanning Tree) algorithm can be used to simulate different operating states and fault propagation paths of the power system to identify nodes that may fail and their potential impact on the overall system safety, so as to predict possible failure conditions in advance.

[0079] In the embodiment, the search tree is determined according to the current state and executable operation of the power system, the return value corresponding to each node of the search tree is determined by simulating the power system, and the failure condition of the power system is determined according to the return value, so that the potential problems of the power system can be accurately predicted, and corresponding measures can be taken in time to increase the reliability of the power system.

[0080] In one exemplary embodiment, the above-mentioned blockchain-based power data security management and control system further comprises a management optimization module for determining the state transition probability of the power system, determining the target state transition strategy of the power system according to the reward value associated with the state transition of the power system according to the state transition probability.

[0081] The management optimization module can be a functional module integrated in the blockchain-based power data security management system. The state transition probability can be the probability of transition between different states of the power system. The reward value can be a parameter of the reward generated by the control strategy of the power system. The target state transition strategy can be the selected state transition strategy.

[0082] In a specific implementation, the management optimization module can be connected with the prediction decision module, and used for modeling and optimizing the safety management of the power system. Specifically, the management optimization module can collect all state information of the power system at different times based on historical data, and construct a corresponding state space. An action space is constructed based on each action or decision that can be taken under each state. Then, the transition probability between states under any action is obtained according to the constructed state space and action space. An initial strategy is randomly selected according to each original control strategy of the power system under the current state, and the expected cumulative reward value starting from the current state under the initial strategy is calculated. The value function is iteratively calculated and the strategy is updated until the change value of the value function of the strategy is within a preset convergence threshold. The iteration is stopped, the action that maximizes the value function is selected to generate an optimal strategy (target state transition strategy), and the optimal action is taken in each state according to the optimal strategy. In this way, after modeling the safety management of the power system as an MDP (Markov Decision Process), the optimal decision strategy is learned through continuous exploration and learning under different fault scenarios through reinforcement learning.

[0083] In this embodiment, by determining the state transition probability of the power system, determining the target state transition strategy of the power system according to the reward value associated with the state transition probability of the power system, the potential safety hazards of the power system can be optimized, the operation efficiency of the power system can be optimized, and emergency management can be performed when a fault occurs.

[0084] In an exemplary embodiment, the blockchain-based power data security management system described above further includes a security audit module and a security configuration evaluation module. The security audit module is used to audit the safety management of the power system, and the security configuration evaluation module is used to determine the safety and efficiency of the power system.

[0085] The security audit module and the security configuration evaluation module can be functional modules integrated in the blockchain-based power data security management system.

[0086] In a specific implementation, the security audit module and the security configuration evaluation module can be connected with the modeling simulation module. The security configuration evaluation module can be used to evaluate the safety and efficiency of the current security configuration scheme, and the security audit module can be used to audit the security management process and record all operations and events.

[0087] In this embodiment, the security audit module is used to audit the security management of the power system, and the security configuration evaluation module is used to determine the security and efficiency of the power system, so as to ensure the security and efficiency of the power data security management, and facilitate the finding of the cause when problems occur.

[0088] In one exemplary embodiment, the above-mentioned blockchain-based power data security management system further comprises a modeling simulation module for simulating the power system.

[0089] The modeling simulation module can be a functional module integrated in the blockchain-based power data security management system.

[0090] In a specific implementation, the modeling simulation module can be connected to the management optimization module, and the modeling simulation module can construct a virtual power system environment to simulate and test the security configuration of the power system.

[0091] In this embodiment, the security configuration of the power system can be simulated by simulating the power system, which facilitates the prediction of potential safety hazards of the power system and improves the security of the power system.

[0092] In order for those skilled in the art to have a better understanding of the embodiments of the present application, the following will be described in conjunction with a specific example.

[0093] Reference Figure 2 The present application proposes a blockchain-based power data security management system, comprising a sensor acquisition module, a data preprocessing module, a block storage module, a hybrid consensus module, an access control module, a rule mining module, a prediction decision module, a management optimization module, a security configuration evaluation module, a security audit module and a modeling simulation module; wherein,

[0094] The sensor acquisition module is used to connect various sensors in the power system and acquire real-time operation data of the power system;

[0095] The data preprocessing module is used to process real-time data obtained from the sensor;

[0096] The block storage module is used to store the preprocessed power data into the block chain;

[0097] The hybrid consensus module is used to verify the blocks stored in the block chain;

[0098] The access control module is used to set user access rights and control user access;

[0099] The rule mining module is used to analyze the patterns and problems in the power system;

[0100] A prediction decision module is configured to make predictions and decisions on the power data security events, analyze the expected results of different strategies, and optimize the security management decisions.

[0101] A management optimization module is configured to model and optimize the security management of the power system.

[0102] A security configuration evaluation module is configured to evaluate the security and efficiency of the current security configuration scheme.

[0103] A security audit module is configured to audit the security management process and record all operations and events.

[0104] A modeling simulation module is configured to build a virtual power system environment and simulate and test the security configuration of the power system.

[0105] In a specific implementation, after the sensor collection module collects data from various sensors of the power system in real time, the raw power data collected is preprocessed by the data preprocessing module, and then the data is transmitted to the block storage module and the hybrid consensus module. The block storage module verifies the preprocessed power data according to the consensus mechanism preset by the hybrid consensus module and stores it on the blockchain. The access control module restricts user access according to the smart contract rules of the blockchain. Then the rule mining module uses the FP-Growth algorithm to mine frequent item sets from the latest power data and evaluates the association between each frequent item set. The prediction decision module predicts the security events in the power data according to the evaluation results and identifies potential security risks and abnormal behaviors through the MCST algorithm. Meanwhile, the management optimization module and the evaluation results and prediction results develop the optimal security configuration scheme. Then the security configuration evaluation module evaluates and adjusts the existing security management strategy, and the security audit module monitors and audits the overall operation of the system. According to the operation of the power system, a virtual model is established by the modeling simulation module for administrators to view.

[0106] The specific steps of the hybrid consensus module verifying the data blocks stored on the blockchain are as follows:

[0107] Step S201, the preprocessed power data is packaged, and when packaging, each data entry is converted into a hash value by a hash function, and then each group of hash values is merged two by two, and hashed again until the final Merkle root is formed to form a block.

[0108] Step S202, after the block is generated, the miner nodes in the blockchain use different Nonce values in turn until the hash value of the block header is less than the preset target value, then the new block is broadcast to the network, and a group of nodes holding rights are randomly selected to verify the legality and integrity of the data in the block and sign for confirmation.

[0109] Step S203, the node calculates the hash value of each data entry in the block, and verifies the Merkel tree structure level by level, if the recalculated Merkel root is the same as the Merkel root in the block header, and the verification is passed, it is considered that the data is complete and true, and the block passed by the double verification is added to the block chain for storage.

[0110] The specific steps of the rule mining module analyzing the mode and problem in the power system are as follows:

[0111] Step S211, the frequent item set is mined from the power data set by the FP-Growth algorithm, the set of frequent item sets is generated, and then the association rules of any two subsets in each frequent item set are generated to obtain the association relationship between variables in the power data, and the confidence and support of each association rule are calculated to construct the corresponding variable space;

[0112] Step S212, the volatility factor, the number of selectors, and the initial value of pheromone are initialized, the heuristic information corresponding to the confidence and support of each association rule is calculated according to the calculation, each selector is randomly initialized to a position, and then the path selection probability in each variable space is calculated according to the initial value of pheromone and the heuristic information, and the selector selects the path based on the path selection probability;

[0113] Step S213, according to the selected high probability path, the combination of association rules is formed, the rule combination of each path is comprehensively evaluated according to the total support and confidence, the pheromone is updated according to the quality of the constructed path, the path selection and pheromone updating are repeated, and until the iteration times reach the preset threshold, the association rule combination with the highest evaluation value is screened out, and the mode analysis is carried out based on the high quality rule to identify each problem in the power system.

[0114] The path selection probability is as follows:

[0115]

[0116]

[0117] Wherein, represents the heuristic information of the path . represents the confidence of the association rule . represents the support of the association rule . represents the probability of the selector selecting the path . represents the pheromone concentration of the path . represents the influence coefficient of pheromone. influence coefficients representing heuristic information; a set representing all paths selectable in the current variable space.

[0118] The specific steps of predicting and deciding the power data security event by the prediction decision module are as follows:

[0119] In step S221, real-time data after preprocessing is collected, time sequence features, spatial features and historical event features are extracted from the preprocessed power data, the state of the current power system is taken as a root node, and the maximum search depth and iteration number are set.

[0120] In step S222, starting from the current node, an action is selected based on the UCB selection strategy and transferred to the next state according to the executable operation of the power system, the value of each action is evaluated based on the statistical model of historical data, and the optimal action is selected to expand the state, so as to gradually expand the nodes of the search tree until the maximum search depth is reached.

[0121] In step S223, simulation is performed according to the constructed path to predict possible future security events, the results of each simulation are evaluated, the total return from the current node to the terminal node is calculated, and the node value in the search tree is updated, and the selection, expansion, simulation and backtracking process is repeated until the maximum iteration number is reached.

[0122] In step S224, based on the current cumulative expected return, the action with the highest return is selected at each node, the optimal path and state transition with the highest cumulative expected return are analyzed to identify the key nodes and actions that lead to power system failure or unsafe state, and a warning is generated for these potential problems and corresponding preventive measures or coping strategies are suggested.

[0123] The specific steps of modeling and optimizing the security management of the power system by the management optimization module are as follows:

[0124] In step S231, all state information of the power system at different times is collected based on historical data, and a corresponding state space is constructed, an action space is constructed based on the actions or decisions that can be taken in each state, and then the transition probability between states under any action is obtained according to the constructed state space and action space.

[0125] In step S232, an initial strategy is randomly selected according to the original control strategy of the power system in the current state, the expected cumulative reward starting from the current state under the initial strategy is calculated, the value function is iteratively calculated and the strategy is updated until the change value of the value function of the strategy is within the preset convergence threshold, and the iteration is stopped.

[0126] In step S233, an action that maximizes the value function is selected to generate an optimal policy, and the optimal action in each state is taken according to the optimal policy to potentially eliminate security risks of the power system, optimize the operation efficiency of the power system, and perform emergency management when a fault occurs.

[0127] Compared with the prior art, the blockchain-based power data security management system has the beneficial effects that the FP-Growth algorithm is used to mine frequent item sets from the power data set, a set of frequent item sets is generated, association rules of any two subsets in each frequent item set are generated to obtain the association relationship between variables in the power data, the confidence and support of each association rule are calculated to construct a corresponding variable space, the volatility factor, the number of selectors, and the initial value of the pheromone are initialized, the heuristic information corresponding to each association rule is calculated according to the calculated confidence and support, the positions of the selectors are randomly initialized, the path selection probability in each variable space is calculated according to the initial value of the pheromone and the heuristic information, the selectors select paths based on the path selection probability, the combination of association rules is formed according to the selected high-probability paths, the rule combination of each path is comprehensively evaluated according to the total support and confidence, the pheromone is updated according to the quality of the constructed path, the path selection and the pheromone updating are repeatedly performed, the association rule combination with the highest evaluation value is screened out after the iteration number reaches a preset threshold, and the high-quality rules are used for pattern analysis to identify various problems in the power system, improve the detection capability of potential security risks of the system, reduce false positives, quickly respond to changes in the power system, have high sensitivity to security risks, and improve the depth and breadth of the security management of the power system.

[0128] Moreover, the system collects pre-processed real-time data, extracts feature data from the pre-processed power data, takes the current state of the power system as the root node, sets the maximum search depth and the number of iterations, starts from the current node, selects an action based on the UCB selection strategy according to the executable operations of the power system, and moves to the next state, evaluates the value of each action based on the statistical model of historical data, selects the optimal action to expand the state, gradually expands the nodes of the search tree, until the maximum search depth is reached, simulates according to the constructed path to predict possible future safety incidents, evaluates the results of each simulation, calculates the total return from the current node to the terminal node, and updates the node values in the search tree, repeats the selection, expansion, simulation, and backtracking process until the maximum number of iterations is reached, selects the action with the highest return at each node based on the current cumulative expected return, analyzes the optimal path and state transition with the highest cumulative expected return to identify the key nodes and actions that lead to power system failure or unsafe state, generates warnings for these potential problems, and suggests corresponding preventive measures or coping strategies, enhancing the prediction ability of the system, reducing the probability of accidents, reducing the risk of wrong decisions, and improving the decision-making quality of the system.

[0129] In one embodiment, as shown in Figure 3 , a blockchain-based power data security management method is provided, which is applied to the rule mining module 104 in Figure 1 for example, including the following steps:

[0130] Step S302, mining frequent item sets in the processed operation data, generating initial association rules corresponding to the frequent item sets;

[0131] Step S304, constructing a variable space according to the initial association rules, and determining a target path in the variable space;

[0132] Step S306, determining the abnormal situation of the power system according to the target association rules corresponding to the target path.

[0133] In a specific implementation, the rule mining module mines frequent item sets in the pre-processed operation data, takes the association rules of any two subsets in the frequent item sets as initial association rules, calculates the confidence and support of each initial association rule, wherein the confidence is the ratio of the support of the union of the frequent item and a certain item to the support of the frequent item set, and the support is the number of sets containing the frequent item set. According to the confidence and support, the path selection probability in the variable space is determined, the target path is determined according to the path selection probability, the association rules corresponding to the target path are taken as the target association rules, and the potential safety hazards existing in the power system are determined according to the target association rules.

[0134] The power data security management method based on the blockchain can mine frequent item sets from the processed operation data, generate initial association rules corresponding to the frequent item sets, construct a variable space according to the initial association rules, determine a target path in the variable space, and determine an abnormal condition of the power system according to a target association rule corresponding to the target path. The frequent item sets can be mined from the operation data of the power system, the association rules corresponding to the frequent item sets are determined, high-quality target association rules are screened from the association rules, potential safety hazards existing in the power system are identified based on the target association rules, and the detection capability of the safety hazards of the power system is improved.

[0135] It should be understood that, although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless explicitly stated herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps.

[0136] In an exemplary embodiment, a computer device, which can be a terminal, is provided, and an internal structure diagram of the computer device can be as shown in FIG. 1. Figure 4As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control ability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be realized through WIFI, mobile cellular network, near field communication (Near Field Communication, NFC) or other technologies. The computer program is executed by the processor to realize a power data security management method based on block chain. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0137] Those skilled in the art can understand that, Figure 4 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0138] In one embodiment, a computer device is also provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to realize the steps in each of the above method embodiments.

[0139] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to realize the steps in each of the above method embodiments.

[0140] In one embodiment, a computer program product is provided, including a computer program, and the computer program is executed by a processor to realize the steps in each of the above method embodiments.

[0141] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0142] It can be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments of each method. In the embodiments provided in the present application, any reference to memory, database or other medium can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0143] Any technical features in the above embodiments can be combined, and for the sake of brevity, not all possible combinations are described above, however, any combination of these technical features is deemed to be within the scope of the present application.

[0144] The above embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the patent scope of the present application. It should be pointed out that, for ordinary skilled persons in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A blockchain-based power data security management and control system, characterized in that, The system includes: a data acquisition module, a data preprocessing module, a block storage module, a hybrid consensus module, an access control module, a rule mining module, a prediction and decision-making module, a management optimization module, a security audit module, a security configuration evaluation module, and a modeling and simulation module; the block storage module is connected to both the hybrid consensus module and the access control module, the rule mining module is connected to the prediction and decision-making module, the prediction and decision-making module is connected to the management optimization module, the management optimization module is connected to the modeling and simulation module, and the modeling and simulation module is connected to both the security audit module and the security configuration evaluation module; The data acquisition module is used to acquire the operating data of the power system in real time; The rule mining module is used to mine frequent itemsets in the processed running data, generate initial association rules corresponding to the frequent itemsets, construct a variable space based on the initial association rules, determine a target path in the variable space, and determine the abnormal situation of the power system based on the target association rules corresponding to the target path. The hybrid consensus module is used to perform hash transformation on the processed running data and upload the resulting blocks to the blockchain; The prediction and decision-making module is used to collect the processed operational data, extract time series features, spatial features, and historical event features from the processed operational data, take the current state of the power system as the root node, and set the maximum search depth and number of iterations. Starting from the root node, based on the executable operations of the power system, an action is selected based on the upper confidence boundary selection strategy and the system moves to the next state. The value of each action is evaluated based on the statistical model of historical data, and the optimal action is selected to expand the state, so as to gradually expand the nodes of the search tree until the maximum search depth is reached, forming the search tree. Simulation is performed based on the search tree to predict possible future security events of the power system. The management optimization module is used to determine the state transition probability of the power system, and based on the reward value associated with the state transition probability of the power system, determine the target state transition strategy of the power system according to the reward value.

2. The system according to claim 1, characterized in that, The rule mining module is further configured to determine the initial pheromone value of the pheromone corresponding to the selector, determine heuristic information based on the credibility and support of the initial association rule, determine the path selection probability of the variable space based on the initial pheromone value and the heuristic information, and determine the target path based on the path selection probability. The rule mining module is further configured to update the pheromone according to the target path, use the obtained pheromone update value as the pheromone initial value, return to the steps of determining the path selection probability of the variable space according to the pheromone initial value and the heuristic information, and determining the target path according to the path selection probability, until a preset termination condition is met, and determine the target association rule according to the finally determined target path.

3. The system according to claim 1, characterized in that, The data preprocessing module is used to preprocess the running data to obtain the processed running data.

4. The system according to claim 1, characterized in that, The block storage module is used to store the processed running data in the blockchain.

5. The system according to claim 1, characterized in that, The hybrid consensus module is also used to package the processed running data, convert each data entry into a hash value through a hash function, merge each group of hash values ​​in pairs, and hash again until the final Merkle root is formed to obtain the block.

6. The system according to claim 1, characterized in that, The access control module is used to set user access permissions and control user access based on the user access permissions.

7. The system according to claim 1, characterized in that, The prediction and decision module is also used to determine the reward value corresponding to each node of the search tree, and to determine the fault status of the power system based on the reward value.

8. The system according to claim 1, characterized in that, The management optimization module is also used to collect all state information of the power system at different times based on historical data to construct a corresponding state space, construct an action space based on each action or decision that can be taken in each state, and obtain the transition probability between each state under any action based on the constructed state space and the action space.

9. The system according to claim 1, characterized in that, The security audit module is used to audit the security management of the power system, and the security configuration assessment module is used to determine the security and efficiency of the power system.

10. The system according to claim 1, characterized in that, The modeling and simulation module is used to simulate the power system.

Images