Construction system of power grid health degree evaluation model

Abstract

The invention is suitable for the technical field of model construction, and provides a construction system for a power grid health degree evaluation model, and the system comprises a data quality management module which carries out the cleaning, denoising, difference and anomaly detection of data, and processing of the data; the data integration and consistency management module is used for performing format consistency processing on the multi-source data and integrating the data; the self-adaptability and flexibility enhancing module is used for setting configurable algorithms and model parameters to automatically adjust and optimize the model; the security and privacy protection module is used for matching a power grid data processing standard through an encryption technology, data desensitization, access control and security audit, and ensuring the security of the data in the processes of acquisition, transmission, storage and processing; and the continuous maintenance and update management module is used for regularly updating the model and the algorithm by implementing an automatic monitoring and feedback mechanism so as to ensure that the model performance is continuously optimized and adapts to new technology and data optimization. Misjudgment caused by a data quality problem is avoided, and the accuracy of the evaluation model is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of model construction, and in particular to a system for constructing a power grid health evaluation model. Background Art

[0002] The grid health evaluation model construction system is a tool or system used to analyze and evaluate the health status of the power system. It is mainly used to monitor, diagnose and predict the operating status of the power grid to help power operators and managers optimize grid operation and improve the reliability, safety and economy of the grid. This system usually integrates multiple technologies and methods, including data acquisition, signal processing, mathematical modeling, statistical analysis, artificial intelligence, power system simulation and optimization.

[0003] In the prior art, the accuracy and reliability of the power grid health assessment model are highly dependent on the quality and real-time nature of the data. However, power grid data usually comes from multiple different sensors, devices and systems, and these data may be inconsistent, noisy or missing. In addition, there may be problems with different data formats, data heterogeneity and data transmission delays. In the process of processing these data, the accuracy of the assessment model output may be affected, resulting in errors in the assessment. Summary of the invention

[0004] The embodiment of the present application provides a system for constructing a power grid health evaluation model, which is used to solve the problem of errors in evaluation of the evaluation model.

[0005] A first aspect of an embodiment of the present application provides a system for constructing a power grid health evaluation model, including:

[0006] Data quality management module, which is used to clean, denoise, differenciate and detect anomalies of data, and process data using machine learning algorithms and statistical algorithms;

[0007] Data integration and consistency management module, which is used to process the format consistency of multi-source data and integrate data using data lake or data warehouse technology combined with data stream processing and ETL tools;

[0008] Adaptability and flexibility enhancement module, which is used to set configurable algorithms and model parameters to automatically adjust and optimize the model so that the model can adapt to the characteristics and needs of different regions and power grid structures;

[0009] Security and privacy protection module, which is used to match the standards of power grid data processing through encryption technology, data desensitization, access control and security audit, and ensure the security of data during collection, transmission, storage and processing;

[0010] The continuous maintenance and update management module is used to regularly update models and algorithms by implementing automated monitoring and feedback mechanisms to ensure that the model's performance is continuously optimized and adapted to new technologies and data optimization.

[0011] Furthermore, the data quality management module includes:

[0012] Data cleaning and preprocessing: Identify and correct outliers, missing values, and duplicate values ​​in the data;

[0013] Data standardization and formatting: set standardized units for data and set a unified format for timestamps;

[0014] Anomaly detection and anomaly repair: Detect abnormal data, including equipment failure data, equipment transmission interruption or abnormal point data, and perform data repair based on the detected abnormal data;

[0015] Data quality monitoring: Regularly evaluate data quality indicators and monitor data in real time by implementing metrics and dashboards for data quality measurement.

[0016] Furthermore, the anomaly detection and anomaly repair include:

[0017] Build an abnormal data prediction model and train the abnormal data prediction model through normalization processing;

[0018] The detected data set is input into the abnormal data prediction model, and the prediction result is obtained according to the detection rules.

[0019] Furthermore, the expression of the abnormal data prediction model trained by normalization processing is as follows:

[0020] The normalization formula is as follows:

[0021]

[0022] Where: x t is the actual detection value of the power grid at time t, x min and x max are the minimum and maximum detection values ​​in the detection sequence, respectively;

[0023] The calculation formula of the neural network loss function in the training model is as follows:

[0024]

[0025] Where: x′ t is the predicted value, and n is the number of samples in the training set.

[0026] Furthermore, the data integration and consistency management module includes:

[0027] Multi-source data processing and adapters: Set up adapters and interfaces that support multiple data sources to handle data input in different formats and structures;

[0028] Data stream processing and batch processing: Data at different data rates and time intervals can be processed in stages through data stream processing and batch processing.

[0029] Furthermore, the data integration and consistency management module includes:

[0030] Data quality control and verification: Control the accuracy and completeness of the data introduced at each stage;

[0031] Data synchronization and version control: Manage data synchronization and version control to ensure that data versions and updates of all data sources are consistent in the system;

[0032] Real-time data stream processing and caching: Introducing real-time data stream processing and caching mechanisms;

[0033] Data governance and metadata management: Establish a data governance framework and metadata management system to track and manage the origin, changes, and usage of data.

[0034] Furthermore, the adaptability and flexibility enhancement module includes:

[0035] Configure model parameters and select algorithms: Set up an interface for users to configure model parameters and select algorithms, which can adapt to the specific needs and conditions of different regions and power grid structures;

[0036] Multi-model integration and comparative analysis: Integrate multiple different types of models or algorithms and determine the target model based on model performance comparison;

[0037] Regional and grid structure specific model optimization: Optimize model parameters and input data processing methods according to the characteristics of different regions and grid structures, and adjust the applicability and performance of the model in specific environments;

[0038] Real-time strategy adjustment and response: Adjust model parameters and decision rules according to the immediate situation and respond to decision changes.

[0039] Furthermore, the region and grid structure specific model optimization includes:

[0040] Based on the requirements and conditions of different regions and power grid structures, the sampled data are processed with coarse values ​​and zero initial values ​​to obtain the model target parameters;

[0041] The improved particle swarm algorithm is used to optimize the model parameters.

[0042] Furthermore, the optimization of model parameters by using the improved particle swarm algorithm includes:

[0043] Initialize the particle population and set the corresponding parameters;

[0044] Calculate particle fitness and update individual optimum and global optimum through particle fusion algorithm;

[0045] After each iteration, the inertia weight is adjusted to update the particle's velocity and position;

[0046] Determine whether the iteration requirements are met. If the iteration limit is reached, the search process will stop, the global optimal solution and the local optimal solution will be output, the fitness function will be calculated, and the model target parameters will be determined.

[0047] Furthermore, the security and privacy protection module includes:

[0048] Data encryption and secure transmission: Set up end-to-end encryption technology for transmitted power grid data;

[0049] Identity authentication and access control: Set up identity authentication and access control, and set permissions for authorized users and systems to access and operate sensitive data;

[0050] Data auditing and monitoring: Set up data auditing and monitoring mechanisms to track and record access, modification, and sharing of sensitive data, and respond to potential security issues in a timely manner;

[0051] Anonymization and data desensitization: Anonymize the stored and analyzed data to remove and obfuscate sensitive information that may identify individuals.

[0052] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0053] This application sets up a data quality management module, a data integration and consistency management module, an adaptability and flexibility enhancement module, a security and privacy protection module, and a continuous maintenance and update management module. Through the data quality management module and the data integration and consistency management module, it can ensure that the power grid data can be pre-processed to improve the accuracy and integrity of the data, avoid misjudgments and wrong decisions caused by data quality problems, and improve data utilization. In addition, the adaptability and flexibility enhancement module can improve the applicability of the evaluation model; the security and privacy protection module ensures the security and privacy protection of power grid data during collection, transmission, storage and processing, avoids sensitive data leakage, and improves the overall credibility and compliance of the system; the continuous maintenance and update management module can promptly discover and repair problems in the model to maintain the efficiency and accuracy of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a structural block diagram of an embodiment of a system for constructing a power grid health evaluation model in the present invention;

[0055] Figure 2 It is a structural block diagram of the data quality management module in the present invention;

[0056] Figure 3 It is a structural block diagram of the data integration and consistency management module in the present invention;

[0057] Figure 4 It is a structural block diagram of the adaptability and flexibility enhancement module in the present invention;

[0058] Figure 5 This is a structural block diagram of the security and privacy protection module in the present invention. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0060] The construction system of the power grid health evaluation model in this embodiment is used to improve the evaluation efficiency and accuracy of the evaluation model. The implementation method in this embodiment can be implemented in the system, can be implemented in the server, and can also be implemented in the terminal, without specific limitation.

[0061] Embodiment 1

[0062] See also Figures 1 to 5 , an embodiment of a system for constructing a power grid health assessment model in the present invention includes the following steps:

[0063] The data quality management module 101 is used to clean, denoise, differenciate and detect anomalies of the data, and process the data using machine learning algorithms and statistical algorithms;

[0064] Specifically, the data quality management module also includes:

[0065] Data cleaning and preprocessing: Identify and correct outliers, missing values, and duplicate values ​​in the data;

[0066] Data standardization and formatting: set standardized units for data and set a unified format for timestamps;

[0067] Anomaly detection and anomaly repair: Detect abnormal data, including equipment failure data, equipment transmission interruption or abnormal point data, and perform data repair based on the detected abnormal data;

[0068] Data quality monitoring: Regularly evaluate data quality indicators and monitor data in real time by implementing metrics and dashboards for data quality measurement.

[0069] Specifically, anomaly detection and anomaly repair include:

[0070] Build an abnormal data prediction model and train the abnormal data prediction model through normalization processing;

[0071] The detected data set is input into the abnormal data prediction model, and the prediction result is obtained according to the detection rules.

[0072] Among them, the normalization formula is as follows:

[0073]

[0074] Where: x t is the actual detection value of the power grid at time t, x min and x max are the minimum and maximum detection values ​​in the detection sequence, respectively.

[0075] The calculation formula of the neural network loss function in the training model is as follows:

[0076]

[0077] Where: x′ t is the predicted value, and n is the number of samples in the training set.

[0078] By monitoring and repairing abnormal data, data accuracy and integrity can be ensured, power grid data flow can be monitored in real time, and any abnormal situations can be identified and handled.

[0079] Data standardization and formatting ensure that data from different sources can be uniformly processed and analyzed by the system, all electric power uses the same international system of units, all data timestamps have uniform time accuracy, and all timestamps are converted into a unified machine-readable format. Through these standardized units and unified formatting methods of timestamps, it can be ensured that power grid data from different sources can be accurately captured, processed and analyzed by the system, thereby improving the reliability, consistency and real-time performance of the data.

[0080] The data integration and consistency management module 102 is used to process the format consistency of multi-source data and integrate the data by using data lake or data warehouse technology in combination with data stream processing and ETL tools;

[0081] Specifically, the data integration and consistency management module includes:

[0082] Multi-source data processing and adapters: Set up adapters and interfaces that support multiple data sources to handle data input in different formats and structures;

[0083] Data stream processing and batch processing: Data at different data rates and time intervals can be processed in stages through data stream processing and batch processing.

[0084] Also includes:

[0085] Data quality control and verification: Control the accuracy and completeness of the data introduced at each stage;

[0086] Data synchronization and version control: Manage data synchronization and version control to ensure that data versions and updates of all data sources are consistent in the system;

[0087] Real-time data stream processing and caching: Introducing real-time data stream processing and caching mechanisms;

[0088] Data governance and metadata management: Establish a data governance framework and metadata management system to track and manage the origin, changes, and usage of data.

[0089] The data integration and consistency management module can realize real-time processing and integration of data.

[0090] The adaptability and flexibility enhancement module 103 is used to set configurable algorithms and model parameters to automatically adjust and optimize the model so that the model can adapt to the characteristics and requirements of different regions and power grid structures;

[0091] Adaptability and flexibility enhancement modules, including:

[0092] Configure model parameters and select algorithms: Set up an interface for users to configure model parameters and select algorithms, which can adapt to the specific needs and conditions of different regions and power grid structures;

[0093] Multi-model integration and comparative analysis: Integrate multiple different types of models or algorithms and determine the target model based on model performance comparison;

[0094] Regional and grid structure specific model optimization: Optimize model parameters and input data processing methods according to the characteristics of different regions and grid structures, and adjust the applicability and performance of the model in specific environments;

[0095] Real-time strategy adjustment and response: Adjust model parameters and decision rules according to the immediate situation and respond to decision changes.

[0096] Among them, regional and grid structure specific model optimization includes:

[0097] Based on the requirements and conditions of different regions and power grid structures, the sampled data are processed with coarse values ​​and zero initial values ​​to obtain the model target parameters;

[0098] The improved particle swarm algorithm is used to optimize the model parameters.

[0099] Specifically, the expression for coarse value processing is as follows:

[0100]

[0101] Where: y is the sampling data of a specific environmental model, and N is the number of samples.

[0102] The optimization of model parameters using improved particle swarm algorithm includes:

[0103] Initialize the particle population and set the corresponding parameters;

[0104] Calculate particle fitness and update individual optimum and global optimum through particle fusion algorithm;

[0105] After each iteration, the inertia weight is adjusted to update the particle's velocity and position;

[0106] Determine whether the iteration requirements are met. If the iteration limit is reached, the search process will stop, the global optimal solution and the local optimal solution will be output, the fitness function will be calculated, and the model target parameters will be determined.

[0107] The security and privacy protection module 104 is used to match the standards of power grid data processing through encryption technology, data desensitization, access control and security auditing, and ensure the security of data during collection, transmission, storage and processing;

[0108] Specifically, the security and privacy protection modules include:

[0109] Data encryption and secure transmission: Set up end-to-end encryption technology for transmitted power grid data;

[0110] Identity authentication and access control: Set up identity authentication and access control, and set permissions for authorized users and systems to access and operate sensitive data;

[0111] Data auditing and monitoring: Set up data auditing and monitoring mechanisms to track and record access, modification, and sharing of sensitive data, and respond to potential security issues in a timely manner;

[0112] Anonymization and data desensitization: Anonymize the stored and analyzed data to remove and obfuscate sensitive information that may identify individuals.

[0113] Specifically, the encryption method is to select a strong random number generator to generate the 256-bit (32-byte) key required by AES-256. The key should be generated, stored and distributed in a secure key management system to ensure that only authorized users and systems can access it. Data encryption: Use the AES-256 encryption algorithm and the generated key to encrypt the power grid data. The encryption process can be implemented through block cipher modes (such as CBC, ECB, CTR, GCM, etc.). The encrypted data will become a ciphertext that cannot be directly understood. Only authorized users with the correct key can decrypt it; Data transmission: Transmit the encrypted power grid data (ciphertext) to the destination through a secure channel (such as SSL / TLS encrypted TCP / IP connection), ensuring that end-to-end encryption is also implemented during the transmission process to prevent man-in-the-middle attacks. Data reception and decryption: At the receiving end, use the same key and encryption algorithm to decrypt the received ciphertext, restore it to the original power grid data, and verify the integrity of the decrypted data; Key update and rotation: Regularly replace encryption keys to reduce the risk of key leakage. Key updates should be carried out in a secure environment and ensure a smooth transition between new and old keys.

[0114] The continuous maintenance and update management module 105 is used to regularly update the model and algorithm by implementing an automated monitoring and feedback mechanism to ensure that the performance of the model is continuously optimized and adapted to new technologies and data optimization.

[0115] Specifically, provide continuous maintenance and update management of the model to ensure that the model's performance is continuously optimized and adapts to new technologies and data changes, implement automated monitoring and feedback mechanisms, regularly update models and algorithms, and promptly repair and optimize models.

[0116] The above-mentioned embodiment constructs an evaluation model by integrating a data quality management module, a data integration and consistency management module, an adaptability and flexibility enhancement module, a security and privacy protection module, and a continuous maintenance and update management module, so as to realize real-time processing and integration of data, optimize the model, and adjust the operating efficiency and reliability of the model.

[0117] Those of ordinary skill in the art will appreciate that the units of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0118] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored. In addition, each functional unit in each embodiment of the present invention can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0119] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes 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 method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-0nlyMemory), random access memory (RAM, RandomAccessMemory), mobile hard disk, magnetic disk or optical disk, etc., which can store program code.

[0120] It can be understood 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 above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A system for constructing a power grid health evaluation model, characterized in that: include: Data quality management module, which is used to clean, denoise, differenciate and detect anomalies of data, and process data using machine learning algorithms and statistical algorithms; Data integration and consistency management module, which is used to process the format consistency of multi-source data and integrate data using data lake or data warehouse technology combined with data stream processing and ETL tools; Adaptability and flexibility enhancement module, which is used to set configurable algorithms and model parameters to automatically adjust and optimize the model so that the model can adapt to the characteristics and needs of different regions and power grid structures; Security and privacy protection module, which is used to match the standards of power grid data processing through encryption technology, data desensitization, access control and security audit, and ensure the security of data during collection, transmission, storage and processing; The continuous maintenance and update management module is used to regularly update models and algorithms by implementing automated monitoring and feedback mechanisms to ensure that the model's performance is continuously optimized and adapted to new technologies and data optimization.

2. The system for constructing a power grid health evaluation model according to claim 1, characterized in that: The data quality management module includes: Data cleaning and preprocessing: Identify and correct outliers, missing values, and duplicate values ​​in the data; Data standardization and formatting: set standardized units for data and set a unified format for timestamps; Anomaly detection and anomaly repair: Detect abnormal data, including equipment failure data, equipment transmission interruption or abnormal point data, and perform data repair based on the detected abnormal data; Data quality monitoring: Regularly evaluate data quality indicators and monitor data in real time by implementing metrics and dashboards for data quality measurement.

3. The system for constructing a power grid health evaluation model according to claim 2, characterized in that: The anomaly detection and anomaly repair include: Build an abnormal data prediction model and train the abnormal data prediction model through normalization processing; The detected data set is input into the abnormal data prediction model, and the prediction result is obtained according to the detection rules.

4. The system for constructing a power grid health evaluation model according to claim 3, characterized in that: The expression of the abnormal data prediction model trained by normalization is as follows: The normalization formula is as follows: Where: x t is the actual detection value of the power grid at time t, x min and x max are the minimum and maximum detection values ​​in the detection sequence, respectively; The calculation formula of the neural network loss function in the training model is as follows: Where: x′ t is the predicted value, and n is the number of samples in the training set.

5. The system for constructing a power grid health evaluation model according to claim 1, characterized in that: The data integration and consistency management module includes: Multi-source data processing and adapters: Set up adapters and interfaces that support multiple data sources to handle data input in different formats and structures; Data stream processing and batch processing: Data at different data rates and time intervals can be processed in stages through data stream processing and batch processing.

6. The power grid health evaluation model construction system according to claim 5, characterized in that: The data integration and consistency management module includes: Data quality control and verification: Control the accuracy and completeness of the data introduced at each stage; Data synchronization and version control: Manage data synchronization and version control to ensure that data versions and updates of all data sources are consistent in the system; Real-time data stream processing and caching: Introducing real-time data stream processing and caching mechanisms; Data governance and metadata management: Establish a data governance framework and metadata management system to track and manage the origin, changes, and usage of data.

7. The system for constructing a power grid health evaluation model according to claim 1, characterized in that: The adaptability and flexibility enhancement module includes: Configure model parameters and select algorithms: Set up an interface for users to configure model parameters and select algorithms, which can adapt to the specific needs and conditions of different regions and power grid structures; Multi-model integration and comparative analysis: Integrate multiple different types of models or algorithms and determine the target model based on model performance comparison; Regional and grid structure specific model optimization: Optimize model parameters and input data processing methods according to the characteristics of different regions and grid structures, and adjust the applicability and performance of the model in specific environments; Real-time strategy adjustment and response: Adjust model parameters and decision rules according to the immediate situation and respond to decision changes.

8. The system for constructing a power grid health evaluation model according to claim 7, characterized in that: The region and grid structure specific model optimization includes: Based on the requirements and conditions of different regions and power grid structures, the sampled data are processed with coarse values ​​and zero initial values ​​to obtain the model target parameters; The improved particle swarm algorithm is used to optimize the model parameters.

9. The system for constructing a power grid health evaluation model according to claim 8, characterized in that: The method of optimizing the model parameters by using the improved particle swarm algorithm includes: Initialize the particle population and set the corresponding parameters; Calculate particle fitness and update individual optimum and global optimum through particle fusion algorithm; After each iteration, the inertia weight is adjusted to update the particle's velocity and position; Determine whether the iteration requirements are met. If the iteration limit is reached, the search process will stop, the global optimal solution and the local optimal solution will be output, the fitness function will be calculated, and the model target parameters will be determined.

10. The system for constructing a power grid health evaluation model according to claim 1, characterized in that: The security and privacy protection module includes: Data encryption and secure transmission: Set up end-to-end encryption technology for transmitted power grid data; Identity authentication and access control: Set up identity authentication and access control, and set permissions for authorized users and systems to access and operate sensitive data; Data auditing and monitoring: Set up data auditing and monitoring mechanisms to track and record access, modification, and sharing of sensitive data, and respond to potential security issues in a timely manner; Anonymization and data desensitization: Anonymize the stored and analyzed data to remove and obfuscate sensitive information that may identify individuals.

Images