Control method and system for real-time monitoring fusion of intelligent electric meter and power system

Abstract

The invention relates to the technical field of electric power systems and intelligent power grids, and discloses a control method and system for real-time monitoring fusion of an intelligent electric meter and an electric power system, and the method comprises the steps: collecting the operation data of the electric power system in real time through the intelligent electric meter, and transmitting the operation data to edge computing equipment for preprocessing; encrypting the preprocessed operation data of the power system, and storing the operation data through a block chain technology; the central control platform obtains the data stored in the block chain and performs real-time monitoring; and the central control platform dynamically adjusts the network structure of the power system according to the real-time monitoring result. The intelligent electric meter is combined with edge computing and block chain technologies, so that real-time acquisition, encrypted storage and efficient processing of operation data of the power system are realized. Data transmission delay is reduced through edge calculation, and the real-time response capability is improved; the block chain ensures the security and non-tampering property of the data; and the stability and the efficiency of the power system are optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems and smart grids, and specifically to a control method and system for integrating real-time monitoring of a smart meter with a power system. Background Art

[0002] In recent years, with the continuous increase in global electricity demand and the continuous development of energy management technology, the intelligence of power systems has become the key to improving energy utilization efficiency and ensuring power safety. As an important development direction of the power system, smart grid technology aims to achieve efficient dispatching and real-time monitoring of electricity through the comprehensive application of information technology, automation technology, communication technology, etc. Traditional power systems usually adopt a centralized monitoring mode. As the requirements for real-time, flexibility and efficiency of power systems continue to increase, distributed monitoring, data collection and analysis based on smart meters have become an important part of the intelligence of power systems. As an important device connecting power users and power companies, smart meters can collect real-time operating data of power systems, such as current, voltage, power, load, etc., thereby providing data support for real-time monitoring, load forecasting and optimal dispatching of power systems.

[0003] However, the integration of existing smart meters and power systems still faces many challenges. First, the existing power data collection methods usually rely on centralized management platforms for data storage and analysis, resulting in high data transmission delays and failure to meet real-time requirements, especially in large-scale and widely distributed power systems. The efficiency of real-time monitoring is greatly reduced. Secondly, security issues in the data transmission process are still a major challenge facing the intelligentization of power systems. Existing technologies often face the risk of tampering, leakage or loss during data storage and transmission, which seriously affects the stability and reliability of power systems. Furthermore, the existing power system network structure adjustment mostly relies on manual intervention and rule setting, and lacks a flexible, adaptive adjustment mechanism based on real-time data, which results in the power system not responding quickly enough to emergencies and load changes, reducing the dynamic stability of the system. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: the data transmission delay, security and adaptive adjustment of network structure in real-time monitoring of power systems. Through the combination of smart meters, edge computing and blockchain technology, efficient, real-time and secure data processing and dynamic control are achieved.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a control method for integrating smart meters with real-time monitoring of power systems, comprising: Collect power system operation data in real time through smart meters and transmit it to edge computing devices for preprocessing; Encrypt the pre-processed power system operation data and store it through blockchain technology; The central control platform obtains the data stored in the blockchain and conducts real-time monitoring; Based on the real-time monitoring results, the central control platform dynamically adjusts the network structure of the power system.

[0007] As a preferred solution of the control method for real-time monitoring integration of smart meters and power systems described in the present invention, the operation data of the power system includes voltage data, current data, power data, frequency data, energy data, power quality data, temperature and environmental monitoring data, equipment status and fault data, communication data, time synchronization data and user behavior and power consumption mode data; The preprocessing includes cleaning and filtering the collected power system operation data through edge computing devices to remove noise and outliers; compressing the power system operation data to reduce the amount of data; and extracting the peak load and load trend of the power system.

[0008] As a preferred solution of the control method for integrating the real-time monitoring of the smart meter and the power system according to the present invention, wherein: encrypting the pre-processed operation data of the power system includes encrypting the pre-processed data by an AES encryption algorithm; Adding additional information to the encrypted operation data of the power system; The additional information includes a timestamp, a data type, and an ID of the edge computing device; Encapsulating the encrypted operation data of the power system and additional information to form a data packet; The encryption keys for the operation data of the power system are stored and managed through the HSM hardware security module; Storage through blockchain technology includes encapsulating data packets into transaction units, defining upload rules in the Quorum blockchain network through smart contracts, and triggering upload operations when conditions are met; The upload rule is to upload data every hour; After the transaction unit is triggered by the smart contract, it is sent to the verification node in the Quorum blockchain network for verification; The verification node checks the validity of the transaction unit through additional information; After more than 3 / 4 of the verification nodes agree that the transaction unit is valid, the transaction is finally confirmed and the transaction unit is written into the Quorum blockchain network.

[0009] As a preferred solution of the control method for integrating the smart meter and the real-time monitoring of the power system described in the present invention, wherein: the central control platform obtains the data stored in the blockchain, including the central control platform inquiring the power system operation data stored in the blockchain by calling the smart contract, and preprocessing the power system operation data stored in the blockchain; Based on the preprocessed power system operation data, the steady-state operation characteristics, instantaneous change characteristics and historical data characteristics of the power system are extracted to form a feature set.

[0010] As a preferred solution of the control method for integrating the real-time monitoring of the smart meter and the power system described in the present invention, wherein: the central control platform obtains the data stored in the blockchain, and performs real-time monitoring and status analysis, including training the initial random forest model using historical power system data; Each tree uses the Bootstrap sampling method to randomly select a subset of features for training; Each tree is constructed using the CART algorithm, the optimal feature is selected for splitting, and the Gini index is calculated until the maximum tree depth is reached. The formula is expressed as: ; in, represents the left subset, represents the number of samples in the right subset; represents the left subset, represents the right subset; Indicates the total number of samples of the current node; represents the Gini index of the left subset, represents the Gini index of the right subset; For each tree, evaluate the contribution of each leaf node to the overall prediction result, and judge the contribution by calculating the error weight of the node. The formula is expressed as: ; in, Representation Node Contribution to the overall forecast, represents the prediction result of random forest, Representation Node The predicted value of Is a node The number of samples; When a leaf node Contribution Less than a certain threshold When , the pruning operation is performed to delete the node from the tree and update the tree structure. The formula is expressed as: ; in, represents the pruning operation, represents the minimum threshold of contribution, Indicates from the tree Delete a node ; After pruning, the depth of the tree will decrease; the depth of the tree is adjusted by dynamically changing the depth factor The implementation formula is: ; in, Indicates the depth of the current tree. represents the reduction in depth during pruning, Indicates the minimum depth limit; Periodically monitor the prediction error of the tree, using the incremental error function Conduct assessments; ; in, Indicates The error increment of each tree, represents the number of samples, represents the true value, represents the model prediction value; when When , the tree retraining is triggered; Repeat the training process to generate a trained random forest model.

[0011] As a preferred solution of the control method for integrating the real-time monitoring of the smart meter and the power system described in the present invention, the central control platform obtains the data stored in the blockchain, and the real-time monitoring also includes inputting the pre-processed power system operation data into the random forest model, calculating the contribution of each leaf node to the overall prediction result, and performing real-time monitoring. The formula is expressed as follows: ; ; in, Representation Node Contribution to the overall forecast; Representation Node For input samples The predicted value of represents the final prediction value of the random forest model, Representation Node The number of samples, Representation Node For samples Information entropy measurement of The value range of is 0 to positive infinity, indicating the contribution of the node to the prediction; The value range is , represents the uncertainty of the sample, Indicates the number of categories.

[0012] As a preferred solution of the control method for integrating the real-time monitoring of the smart meter and the power system described in the present invention, the central control platform obtains the data stored in the blockchain, and the real-time monitoring also includes load forecasting in combination with the online pruning and error weighting mechanism, which is expressed as follows: ; in, Indicates The weight of a tree is defined as: ; in, Indicates The prediction error increment of a tree is defined as: ; in, represents the final predicted value of power load, Indicates The predicted value of a tree, represents the total number of decision trees, Indicates The weight of a tree, Indicates The prediction error increment of each tree, represents the number of samples, Indicates the true load value, Indicates Tree pair The predicted value of samples; The value range of is 0 to 1; The range of is real numbers.

[0013] A preferred solution of a control method for integrating smart meter and power system real-time monitoring, wherein: The edge computing module collects the operation data of the power system in real time through smart meters and transmits it to the edge computing device for preprocessing; The blockchain module encrypts the pre-processed operation data of the power system and stores it through blockchain technology; Monitoring module: The central control platform obtains data stored in the blockchain and conducts real-time monitoring; Adjustment module, based on real-time monitoring results, the central control platform dynamically adjusts the network structure of the power system.

[0014] A computer device comprises: a memory and a processor; the memory stores a computer program, wherein the processor implements the steps of any one of the methods of the present invention when executing the computer program.

[0015] A computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of any one of the methods of the present invention.

[0016] Beneficial effects of the invention: The control method for integrating smart meters with real-time monitoring of power systems provided by the invention realizes real-time collection, encrypted storage and efficient processing of power system operation data by combining smart meters with edge computing and blockchain technology. Edge computing reduces data transmission delay and improves real-time response capabilities; blockchain ensures the security and non-tamperability of data; the central control platform optimizes the stability and efficiency of the power system through real-time monitoring and dynamic adjustment of the network structure, and improves the security, reliability and flexibility of the overall system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0018] Figure 1 An overall flow chart of a control method for integrating real-time monitoring of a smart meter and a power system provided in the first embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0020] Example 1, reference Figure 1 , is an embodiment of the present invention, and provides a control method for integrating a smart meter with real-time monitoring of a power system, comprising: S1: Collect the operation data of the power system in real time through smart meters and transmit it to edge computing devices for preprocessing.

[0021] The operating data of the power system includes voltage data, current data, power data, frequency data, energy data, power quality data, temperature and environmental monitoring data, equipment status and fault data, communication data, time synchronization data, and user behavior and power consumption pattern data.

[0022] The preprocessing includes cleaning and filtering the collected power system operation data through edge computing devices to remove noise and outliers; compressing the power system operation data to reduce the amount of data; and extracting the peak load and load trend of the power system.

[0023] Furthermore, the collected power system operation data is cleaned, filtered, compressed and feature extracted through edge computing devices to improve data processing efficiency and accuracy. Data cleaning and filtering can remove noise and outliers, ensure the quality of input data, and avoid interference with subsequent analysis; data compression helps to reduce the amount of data, optimize transmission efficiency, and reduce bandwidth pressure; and extracting peak loads and load trends can mine the key features of the power system from massive data, facilitate real-time monitoring and prediction, and improve the operational stability and responsiveness of the power system. Through this series of preprocessing operations, it can ensure that the subsequent analysis model obtains high-quality and streamlined data input, thereby achieving more efficient power load forecasting and real-time monitoring.

[0024] S2: Encrypt the pre-processed power system operation data and store it through blockchain technology.

[0025] Encrypting the pre-processed operation data of the power system includes encrypting the pre-processed data by using an AES encryption algorithm.

[0026] Add additional information to the encrypted power system operation data.

[0027] The additional information includes a timestamp, a data type, and an ID of the edge computing device.

[0028] The encrypted power system operation data and additional information are encapsulated to form a data packet.

[0029] The HSM hardware security module is used to store and manage the encryption keys for the power system's operating data.

[0030] Storage through blockchain technology includes encapsulating data packets into transaction units, defining upload rules in the Quorum blockchain network through smart contracts, and triggering upload operations when conditions are met.

[0031] The upload rule is to upload data every hour.

[0032] After the transaction unit is triggered by the smart contract, it is sent to the verification node in the Quorum blockchain network for verification.

[0033] Verification nodes check the validity of transaction units through additional information.

[0034] After more than 3 / 4 of the verification nodes agree that the transaction unit is valid, the transaction is finally confirmed and the transaction unit is written into the Quorum blockchain network.

[0035] Furthermore, through encryption, additional information encapsulation and blockchain storage technology, the security, integrity and immutability of power system operation data are ensured. The data is encrypted through the AES encryption algorithm, and additional information such as timestamp, data type and edge computing device ID is added to the data to improve the traceability and verifiability of the data. At the same time, the HSM hardware security module is used to manage encryption keys to ensure the safe storage and management of keys. Through the Quorum blockchain network and smart contract mechanism, the data upload process is strictly verified and confirmed to ensure the safe transmission and storage of each piece of data in the network, prevent data loss or tampering, and improve the trust and transparency of power system operation data.

[0036] S3: The central control platform obtains the data stored in the blockchain and conducts real-time monitoring.

[0037] The central control platform queries the power system operation data stored on the blockchain by calling smart contracts and pre-processes the power system operation data stored on the blockchain.

[0038] Based on the preprocessed power system operation data, the steady-state operation characteristics, instantaneous change characteristics and historical data characteristics of the power system are extracted to form a feature set.

[0039] The initial random forest model is trained using historical power system data.

[0040] Each tree uses the Bootstrap sampling method to randomly select a subset of features for training.

[0041] Each tree is constructed using the CART algorithm, the optimal feature is selected for splitting, and the Gini index is calculated until the maximum tree depth is reached. The formula is expressed as: ; in, represents the left subset, represents the number of samples in the right subset; represents the left subset, represents the right subset; Indicates the total number of samples of the current node; represents the Gini index of the left subset, represents the Gini index of the right subset.

[0042] For each tree, evaluate the contribution of each leaf node to the overall prediction result, and judge the contribution by calculating the error weight of the node. The formula is expressed as: ; in, Representation Node Contribution to the overall forecast, represents the prediction result of random forest, Representation Node The predicted value of Is a node The number of samples.

[0043] When a leaf node Contribution Less than a certain threshold When , the pruning operation is performed to delete the node from the tree and update the tree structure. The formula is expressed as: ; in, represents the pruning operation, represents the minimum threshold of contribution, Indicates from the tree Delete a node .

[0044] After pruning, the depth of the tree will decrease; the depth of the tree is adjusted by dynamically changing the depth factor The implementation formula is: ; in, Indicates the depth of the current tree. represents the reduction in depth during pruning, Indicates the minimum depth limit.

[0045] Periodically monitor the prediction error of the tree, using the incremental error function Conduct an assessment.

[0046] ; in, Indicates The error increment of each tree, represents the number of samples, represents the true value, Represents the model prediction value.

[0047] when , triggers the retraining of the tree.

[0048] Repeat the training process to generate a trained random forest model.

[0049] The preprocessed power system operation data is input into the random forest model, and the contribution of each leaf node to the overall prediction result is calculated for real-time monitoring. The formula is expressed as: ; ; in, Representation Node Contribution to the overall forecast; Representation Node For input samples The predicted value of represents the final prediction value of the random forest model, Representation Node The number of samples, Representation Node For samples The information entropy measure.

[0050] The value range is from 0 to positive infinity, indicating the contribution of the node to the prediction.

[0051] The value range is , represents the uncertainty of the sample, Indicates the number of categories.

[0052] Combining online pruning and error weighting mechanism, load forecasting is performed, and the formula is expressed as: , improve the accuracy of load forecasting: ; in, Indicates The weight of a tree is defined as: ; in, Indicates The prediction error increment of a tree is defined as: ; in, represents the final predicted value of power load, Indicates The predicted value of a tree, represents the total number of decision trees, Indicates The weight of a tree, Indicates The prediction error increment of each tree, represents the number of samples, Indicates the true load value, Indicates Tree pair The predicted value of samples;

[0053] The value range is 0 to 1.

[0054] The range of is real numbers.

[0055] Furthermore, the steady-state operation characteristics of the system include, but are not limited to, the voltage value of the line or node, the voltage level distribution, the current voltage amplitude, the current amplitude, and the grid frequency.

[0056] By using historical power system data to train the random forest model, and combining it with real-time monitoring data and load forecasting results, the operating status and network structure of the power system can be dynamically adjusted. Specifically, by preprocessing, feature extraction and model training of the power system operation data stored on the blockchain, the random forest model is used for real-time load forecasting and error weighted calculation to ensure that the system can accurately predict power load demand and optimize power flow. In addition, combined with online pruning and error weighting mechanisms, the prediction accuracy can be effectively improved. At the same time, through dynamic adjustment and real-time monitoring of the model, the optimal control of the power system can be achieved, power loss can be reduced, and system efficiency and stability can be improved.

[0057] S4: Based on the real-time monitoring results, the central control platform dynamically adjusts the network structure of the power system.

[0058] Redistribute loads through switchgear, especially when load forecasts show that some lines are overloaded, and transfer part of the load to lighter lines.

[0059] Based on the results of real-time monitoring and load forecasting, the control platform can selectively disconnect unnecessary power lines or temporarily connect backup lines to mitigate the risk of load overload and effectively reduce losses during power transmission.

[0060] The control platform optimizes the topology of the power grid and dynamically adjusts the current flow and voltage level in the power grid, thereby achieving lower power transmission losses.

[0061] Furthermore, through real-time monitoring and load forecasting results, the central control platform can intelligently adjust the network structure of the power system to ensure that the flow of electricity in the system is more balanced and efficient. By redistributing loads, disconnecting unnecessary lines, connecting backup lines, and topology optimization, the platform can effectively avoid load overloads, reduce losses during power transmission, and improve the stability and reliability of the power system. This not only reduces power transmission losses, but also improves the system's ability to adapt to sudden load changes, thereby achieving the optimal configuration of power resources.

[0062] Embodiment 2 is an embodiment of the present invention, which provides a control system for integrating real-time monitoring of a smart meter and a power system, including: The edge computing module collects the operating data of the power system in real time through smart meters and transmits it to the edge computing device for preprocessing.

[0063] The blockchain module encrypts the pre-processed operation data of the power system and stores it through blockchain technology.

[0064] Monitoring module, the central control platform obtains the data stored in the blockchain and conducts real-time monitoring.

[0065] Adjustment module, based on real-time monitoring results, the central control platform dynamically adjusts the network structure of the power system.

[0066] Embodiment 3, an embodiment of the present invention, is different from the first two embodiments in that: If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0067] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0068] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0069] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0070] Example 4 is an embodiment of the present invention, which provides a control method and system for integrating a smart meter with real-time monitoring of a power system. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0071] This embodiment aims to verify the effect of a control method that integrates smart meters and real-time monitoring of power systems in load forecasting and power system optimization and adjustment. The experiment deploys smart meters and edge computing devices in the actual power system, combines blockchain technology for data storage and management, to achieve real-time monitoring and dynamic adjustment of the power system. The power system used in the experiment includes 10 substations, 50 transmission lines, and 30 power load monitoring points, covering typical load demand conditions in urban areas.

[0072] All smart meters collect key operating data of the power system in real time, including voltage, current, power, frequency, equipment status, fault records, ambient temperature and user behavior data. The collected raw data is updated once a minute and preprocessed by edge computing devices. The preprocessing process includes data cleaning, noise and outlier removal, data compression processing to reduce data transmission volume, and extraction of peak load, load trend and other characteristics of the power system. This process achieves rapid response to real-time data and reasonable control of data volume, providing an efficient data foundation for subsequent data storage and analysis.

[0073] The pre-processed data will be encrypted using the AES encryption algorithm to ensure high security during data transmission. Each data packet will be attached with additional information such as timestamp, data type, and edge computing device ID, encapsulated into a transaction unit, and stored using the Quorum blockchain network. The data upload rule is triggered every hour, and the data is stored in the blockchain after being verified by the verification node. The upload and data verification process is controlled by smart contracts to ensure data integrity and tamper-proof.

[0074] The central control platform uses the random forest algorithm to train the initial model based on historical power system data. Each tree uses the Bootstrap sampling method to randomly select a feature subset for training, and uses the CART algorithm to build a decision tree and calculate the Gini index until the depth of the tree reaches the set value. In this process, the depth of the tree is dynamically adjusted through the error evaluation mechanism. The tree pruning operation is optimized based on the node contribution value and error weight to reduce unnecessary computing load and improve the accuracy of the prediction.

[0075] Combining online pruning and error weighting mechanisms for load forecasting, combined with real-time monitoring data and forecasting results, the central control platform dynamically adjusts the network structure of the power system. By redistributing the load, it avoids excessive load on certain lines and reduces power loss. In addition, based on real-time monitoring and load forecasting results, the control platform disconnects unnecessary power lines or temporarily connects backup lines to reduce the risk of load overload, ensuring stable operation of the power system.

[0076] This test was conducted in an actual operating environment, and the collected data covered the operating status of the power system under different load conditions, as follows: The frequency of data collection for power system operation is updated once every minute. The data collected by smart meters include voltage, current, power, frequency, temperature and other parameters.

[0077] Data volume: 300 data packets are uploaded per hour (each data packet contains multi-dimensional data from multiple monitoring points).

[0078] Load forecasting error: By comparing the load forecasting results based on the traditional method (such as linear regression model) and the method of the present invention (random forest model), the error rates are: Traditional method: 10.2% The method of the present invention: 6.4% Power transmission loss: Before power system optimization, the system's power transmission loss rate was 4.5%. After real-time monitoring and load adjustment, the power transmission loss rate was reduced to 3.1%.

[0079] The model trained by the random forest algorithm can predict the power load more accurately than the traditional linear regression model, and the error rate is reduced by 3.8 percentage points. This shows that the present invention can better capture the complexity and nonlinear characteristics of the load changes in the power system during the load forecasting process, and improve the accuracy of the prediction. By introducing multiple decision trees and error weighting mechanisms, the random forest model can effectively reduce the impact of local outliers on the overall prediction, thereby obtaining more stable and reliable prediction results. In the experiment, the power transmission loss was reduced from 4.5% to 3.1% through the dynamic adjustment of the central control platform. This improvement is mainly due to the combination of real-time monitoring and dynamic load adjustment. In traditional systems, lines with excessive loads often lead to increased power losses, while the present invention greatly optimizes the operating efficiency of the power grid and reduces power losses through reasonable load distribution, timely access to backup lines, and disconnection of unnecessary lines.

[0080] The present invention uses blockchain technology to ensure the security and transparency of data, and ensures the reliability and non-tamperability of power system data. In addition, the preprocessing function of edge computing devices enables the power system to respond quickly to abnormal situations and improve the stability of the system. Through these technical means, the system can monitor and dynamically adjust the network structure in real time, effectively reducing the probability of failure and improving the reliability of the overall power system.

[0081] Experimental data show that when the load is too high, the system can effectively avoid overload and increase of power transmission loss by dynamically adjusting the power lines (such as disconnecting unnecessary lines or connecting to backup lines), thus ensuring the smooth operation of the power system. Dynamic adjustment not only optimizes the structure of the power grid, but also improves the system's ability to respond to emergencies.

[0082] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A control method for integrating smart meter and power system real-time monitoring, characterized in that: include: Collect power system operation data in real time through smart meters and transmit it to edge computing devices for preprocessing; Encrypt the pre-processed power system operation data and store it through blockchain technology; The central control platform obtains the data stored in the blockchain and conducts real-time monitoring; Based on the real-time monitoring results, the central control platform dynamically adjusts the network structure of the power system.

2. The control method for integrating smart meter and power system real-time monitoring as claimed in claim 1, characterized in that: The operation data of the power system includes voltage data, current data, power data, frequency data, energy data, power quality data, temperature and environmental monitoring data, equipment status and fault data, communication data, time synchronization data and user behavior and power consumption pattern data; The preprocessing includes cleaning and filtering the collected power system operation data through edge computing devices to remove noise and outliers; Compress the power system operation data to reduce the data volume; Extract peak loads and load trends from power systems.

3. The control method for integrating smart meter and power system real-time monitoring as claimed in claim 2, characterized in that: Encrypting the pre-processed operation data of the power system includes encrypting the pre-processed data by using an AES encryption algorithm; Adding additional information to the encrypted operation data of the power system; The additional information includes a timestamp, a data type, and an ID of the edge computing device; Encapsulating the encrypted operation data of the power system and additional information to form a data packet; The encryption keys for the operation data of the power system are stored and managed through the HSM hardware security module; Storage through blockchain technology includes encapsulating data packets into transaction units, defining upload rules in the Quorum blockchain network through smart contracts, and triggering upload operations when conditions are met; The upload rule is to upload data every hour; After the transaction unit is triggered by the smart contract, it is sent to the verification node in the Quorum blockchain network for verification; The verification node checks the validity of the transaction unit through additional information; After more than 3 / 4 of the verification nodes agree that the transaction unit is valid, the transaction is finally confirmed and the transaction unit is written into the Quorum blockchain network.

4. The control method for integrating smart meter and power system real-time monitoring as claimed in claim 3 is characterized by: The central control platform obtains the data stored in the blockchain, including the central control platform inquiring the power system operation data stored in the blockchain by calling the smart contract, and preprocessing the power system operation data stored in the blockchain; Based on the preprocessed power system operation data, the steady-state operation characteristics, instantaneous change characteristics and historical data characteristics of the power system are extracted to form a feature set.

5. The control method for integrating smart meter and power system real-time monitoring as claimed in claim 4 is characterized by: The central control platform obtains data stored in the blockchain and conducts real-time monitoring and status analysis, including training the initial random forest model using historical power system data; Each tree uses the Bootstrap sampling method to randomly select a subset of features for training; Each tree is constructed using the CART algorithm, the optimal feature is selected for splitting, and the Gini index is calculated until the maximum tree depth is reached. The formula is expressed as: ； in, represents the left subset, represents the number of samples in the right subset; represents the left subset, represents the right subset; Indicates the total number of samples of the current node; represents the Gini index of the left subset, represents the Gini index of the right subset; For each tree, evaluate the contribution of each leaf node to the overall prediction result, and judge the contribution by calculating the error weight of the node. The formula is expressed as: ； in, Representation Node Contribution to the overall forecast, represents the prediction result of random forest, Representation Node The predicted value of Is a node The number of samples; When a leaf node Contribution Less than a certain threshold When , the pruning operation is performed to delete the node from the tree and update the tree structure. The formula is expressed as: ； in, represents the pruning operation, represents the minimum threshold of contribution, Indicates from the tree Delete a node ; After pruning, the depth of the tree will decrease; the depth of the tree is adjusted by dynamically changing the depth factor The implementation formula is: ； in, Indicates the depth of the current tree. represents the reduction in depth during pruning, Indicates the minimum depth limit; Periodically monitor the prediction error of the tree, using the incremental error function Conduct assessments; ； in, Indicates The error increment of each tree, represents the number of samples, represents the true value, represents the model prediction value; when When , the tree retraining is triggered; Repeat the training process to generate a trained random forest model.

6. The control method for integrating smart meter and power system real-time monitoring as claimed in claim 5, characterized in that: The central control platform obtains the data stored in the blockchain for real-time monitoring, and also includes inputting the pre-processed power system operation data into the random forest model, calculating the contribution of each leaf node to the overall prediction result, and performing real-time monitoring. The formula is expressed as: ； ； in, Representation Node Contribution to the overall forecast; Representation Node For input samples The predicted value of represents the final prediction value of the random forest model, Representation Node The number of samples, Representation Node For samples Information entropy measurement of The value range of is 0 to positive infinity, indicating the contribution of the node to the prediction; The value range is , represents the uncertainty of the sample, Indicates the number of categories.

7. The control method for integrating smart meter and power system real-time monitoring as claimed in claim 6, characterized in that: The central control platform obtains the data stored in the blockchain for real-time monitoring and also combines online pruning and error weighting mechanisms to perform load forecasting. The formula is expressed as: ； in, Indicates The weight of a tree is defined as: ； in, Indicates The prediction error increment of a tree is defined as: ； in, represents the final predicted value of power load, Indicates The predicted value of a tree, represents the total number of decision trees, Indicates The weight of a tree, Indicates The prediction error increment of each tree, represents the number of samples, Indicates the true load value, Indicates Tree pair The predicted value of samples; The value range of is 0 to 1; The range of is real numbers.

8. A control system integrating smart meter and power system real-time monitoring, characterized in that: The edge computing module collects the operation data of the power system in real time through smart meters and transmits it to the edge computing device for preprocessing; The blockchain module encrypts the pre-processed operation data of the power system and stores it through blockchain technology; Monitoring module: The central control platform obtains data stored in the blockchain and conducts real-time monitoring; Adjustment module, based on real-time monitoring results, the central control platform dynamically adjusts the network structure of the power system.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the control method for integrating the real-time monitoring of the smart meter and the power system as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the control method for integrating the real-time monitoring of the smart meter and the power system as described in any one of claims 1 to 7 are implemented.

Images