Digital power grid total factor data management method and system

Abstract

The invention discloses a digital power grid total factor data management method and system. The method comprises the steps that total element data are obtained in a digital power grid, power supply indexes of a current area are obtained, and the total element data at least comprise the power grid equipment operation state, the user power consumption behavior and the market supply and demand condition of the current area; fusing the total element data and the power supply indexes to obtain fused power grid data; the fused power grid data is input into a pre-trained data management model, a power grid management adjustment strategy for the current area is output based on the data management model, and the data management model is obtained by training a random forest model according to historical fused power grid data and historical power grid management adjustment strategies; the historical fusion power grid data comprises historical total element data and historical power supply indexes, and the power grid management adjustment strategy of the current area is used for adjusting equipment in a power grid of the current area.

Description

Technical Field

[0001] The present application relates to the field of electrical technology, and more specifically, to a method and system for managing all-factor data of a digital power grid. Background Art

[0002] With the rapid development of the power industry, digital transformation has become an important trend in the development of power companies. As an important part of digitalization, the core of digital grid is data collection, processing and application.

[0003] Most of the existing digital power grid management systems mainly collect power grid operation data through various sensors and monitoring equipment, and then store and manage them through data centers. However, these systems can only manage part of the data and cannot fully cover all aspects of the power grid, resulting in the inability to cover data management in all aspects of the power grid, unable to meet different management needs, and resulting in low accuracy of power grid management. Summary of the invention

[0004] The embodiments of the present application provide a method and system for managing all-factor data of a digital power grid, so as to at least solve the technical problem of low accuracy in power grid equipment management in related technologies.

[0005] According to one aspect of an embodiment of the present application, a method for managing full-factor data of a digital power grid is provided, comprising: obtaining full-factor data in a digital power grid and obtaining power supply indicators of a current area, wherein the full-factor data at least includes an operating status of power grid equipment, power consumption behavior of users, and market supply and demand conditions in the current area; fusing the full-factor data and the power supply indicators to obtain fused power grid data; inputting the fused power grid data into a pre-trained data management model, and outputting a power grid management adjustment strategy for the current area based on the data management model; wherein the data management model is obtained by training a random forest model according to historical fused power grid data and historical power grid management adjustment strategies, and the historical fused power grid data includes historical full-factor data and historical power supply indicators.

[0006] Optionally, obtaining full-factor data in the digital power grid includes: obtaining various basic data from multiple data sources of the digital power grid, the basic data including the following data: equipment operation data and fault data of power equipment, external environment data of the deployed power equipment, power generation and consumption of the power operation system, and power user load data; integrating and standardizing the various basic data to obtain full-factor data.

[0007] Optionally, after acquiring various types of basic data from multiple data sources of the digital power grid, the method further includes: for each type of basic data, if the basic data has been protected by a homomorphic encryption function, decrypting the basic data to obtain decrypted basic data.

[0008] Optionally, the process of decrypting the basic data to obtain the decrypted basic data is as follows:

[0009] Dec(D i )=c i -kmod(m)

[0010] In the formula, Dec(D i ) is the basic data after decryption, c i is the number of power equipment, m is the homomorphic encryption key, and k is a constant.

[0011] Optionally, the training process of the data management model includes: obtaining historical full-factor data and historical power supply indicators in the digital power grid; fusing the historical full-factor data and the historical power supply indicators to obtain historical fused power grid data; determining a training set based on the historical fused power grid data; randomly constructing multiple trees, each tree is used to predict each sample data in the training set; inputting the prediction results of the multiple trees for each sample data into a random forest model, and outputting a final prediction result based on the random forest model; based on the final prediction result, iteratively training the random forest model to obtain a pre-trained data management model.

[0012] Optionally, the iterative training of the random forest model according to the final prediction result to obtain a pre-trained data management model includes: judging whether the random forest model reaches the convergence condition according to the final prediction result; if the convergence condition is reached, determining the random forest model as the data management model; if the convergence condition is not reached, adjusting the number of trees in the random forest, the maximum depth of each tree, and the number of nodes of each tree, and continuing to use each adjusted tree to predict each sample data in the training set, until the final prediction result based on the output of the random forest model reaches the convergence condition, and determining the adjusted random forest model as the data management model.

[0013] Optionally, the process of adjusting the number of nodes of each tree includes: for each tree, determining a node in each tree that exceeds the maximum depth of the tree as a target node, and removing the target node.

[0014] According to another aspect of an embodiment of the present application, a digital power grid full-factor data management system is also provided, including: an acquisition module, used to acquire full-factor data in the digital power grid and acquire power supply indicators of the current area, wherein the full-factor data at least includes the operating status of power grid equipment in the current area, user power consumption behavior, and market supply and demand conditions; a fusion module, used to fuse the full-factor data and the power supply indicators to obtain fused power grid data; a management module, used to input the fused power grid data into a pre-trained data management model, and output a power grid management adjustment strategy for the current area based on the data management model, wherein the data management model is obtained by training a random forest model based on historical fused power grid data and historical power grid management adjustment strategies, and the historical fused power grid data includes historical full-factor data and historical power supply indicators.

[0015] According to another aspect of the embodiment of the present application, a computer device is also provided, including: a memory and a processor, wherein the memory is used to store program instructions; the processor is connected to the memory and is used to execute the above-mentioned digital grid full-element data management method.

[0016] According to another aspect of the embodiment of the present application, a non-volatile storage medium is also provided, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the above-mentioned digital grid full-factor data management method by running the computer program.

[0017] According to another aspect of the embodiments of the present application, a computer program product is also provided, including computer instructions, which, when executed by a processor, implement the above-mentioned digital power grid full-factor data management method.

[0018] In an embodiment of the present application, by obtaining full-factor data in a digital power grid and obtaining power supply indicators for the current area, the full-factor data includes at least the operating status of power grid equipment in the current area, user power consumption behavior, and market supply and demand; the full-factor data and the power supply indicators are integrated to obtain integrated power grid data; the integrated power grid data is input into a pre-trained data management model, and based on the data management model, a power grid management adjustment strategy for the current area is output; wherein the data management model is obtained by training a random forest model based on historical integrated power grid data and historical power grid management adjustment strategies, the historical integrated power grid data includes historical full-factor data and historical power supply indicators, and the power grid management adjustment strategy for the current area is used to adjust the equipment in the power grid in the current area, thereby achieving the purpose of integrating full-factor data and power supply indicators in the digital power grid, thereby covering data management in all aspects of the power grid, meeting different management needs, and improving the accuracy of data management. The technical effect, thereby solving the technical problem of low accuracy of power grid equipment management in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0020] Figure 1 It is a hardware structure block diagram of a computer terminal for implementing a digital power grid full-factor data management method according to an embodiment of the present application;

[0021] Figure 2 is a flow chart of a digital power grid full-factor data management method according to an embodiment of the present application;

[0022] Figure 3 It is a structural diagram of a digital power grid full-factor data management system according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] The information collected in the embodiments of the present application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or reject automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered.

[0026] In order to solve the problems existing in the related art, the embodiment of the present application provides a digital power grid full-factor data management method, which can be run on Figure 1 In the computer terminal shown, the computer terminal is explained below.

[0027] The digital grid full-factor data management method embodiment provided in the embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal for implementing a digital power grid full-factor data management method is shown. Figure 1 As shown, the computer terminal 10 may include one or more (102a, 102b, ..., 102n are used to illustrate) processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission module 106 for communication functions connected via a wired and / or wireless network. In addition, it may also include: a display, a keyboard, a cursor control device, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, and a BUS bus. Those skilled in the art can understand that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0028] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0029] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the digital power grid full-factor data management method in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the above-mentioned digital power grid full-factor data management method is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0030] The transmission module 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission module 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission module 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0031] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 .

[0032] It should be noted that, in some optional embodiments, the above Figure 1 The computer terminal shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of hardware elements and software elements. It should be noted that Figure 1 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the computer terminal described above.

[0033] In the above-mentioned operating environment, an embodiment of the present application provides an embodiment of a method for managing all-factor data of a digital power grid. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0034] Figure 2 is a flow chart of a digital power grid full-factor data management method according to an embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0035] Step S102, obtaining full-factor data in the digital power grid and obtaining power supply indicators of the current area, wherein the full-factor data at least includes the operation status of power grid equipment, user power consumption behavior, and market supply and demand conditions in the current area;

[0036] Step S104, integrating all factor data and power supply indicators to obtain integrated power grid data;

[0037] Step S106, input the fused power grid data into a pre-trained data management model, and output a power grid management adjustment strategy for the current area based on the data management model; wherein the data management model is obtained by training a random forest model based on historical fused power grid data and historical power grid management adjustment strategies, the historical fused power grid data includes historical full-factor data and historical power supply indicators, and the power grid management adjustment strategy for the current area is used to adjust the equipment in the power grid in the current area.

[0038] Through the above steps S102 to S106, by obtaining full-factor data in the digital power grid and obtaining the power supply index of the current area, the full-factor data at least includes the operation status of the power grid equipment in the current area, the user's power consumption behavior, and the market supply and demand; the full-factor data and the power supply index are integrated to obtain integrated power grid data; the integrated power grid data is input into a pre-trained data management model, and based on the data management model, a power grid management adjustment strategy for the current area is output; wherein the data management model is obtained by training a random forest model according to historical integrated power grid data and historical power grid management adjustment strategies, and the historical integrated power grid data includes historical full-factor data and historical power supply indicators, achieving the purpose of integrating full-factor data and power supply indicators in the digital power grid, thereby covering the data management of each link of the power grid, meeting different management needs, and improving the accuracy of data management. The technical effect, thereby solving the technical problem of low accuracy of power grid equipment management in related technologies. The following is a detailed description.

[0039] The digital grid full-factor data management method provided in the embodiment of the present invention is applied to a digital grid full-factor data management system, which may be an electronic device, specifically a smart terminal, a PC, a tablet computer, or other device.

[0040] In one implementation, when the above S102 acquires the full-factor data in the digital power grid, various basic data may be acquired from multiple data sources of the digital power grid, and then the various basic data are used as the full-factor data.

[0041] In another implementation, when the above S102 obtains all-factor data in the digital power grid, various basic data are obtained from multiple data sources of the digital power grid; various basic data are integrated and standardized to obtain all-factor data. In this implementation, considering that the formats and standards of various basic data in multiple data sources are not unified, which brings difficulties to the integration and utilization of data, in this implementation, by managing all-factor data, the format and standard of data are unified, the problem of inconsistent data formats and standards is solved, the utilization efficiency of data is improved, and the problems of large data volume, diverse data sources, uneven data quality, etc. are solved, and the efficient integration and utilization of data are realized, and the reliability and efficiency of power grid operation are improved.

[0042] The above-mentioned multiple data sources include power equipment, power operation system, power user system, etc. Various basic data obtained from multiple data sources include the following data: equipment operation data and fault data of power equipment, external environment data deployed by power equipment, power generation and power consumption of power operation system, and power user load data. As an important part of digitalization, the core of digital grid is data collection, processing and application. In this process, the management of all-factor data is crucial, which involves all aspects of the power grid, including equipment operation status, user power consumption behavior, market supply and demand, etc. The integration and standardization of these data can provide strong support for the operation and management of the power grid. By integrating and standardizing all-factor data, not only equipment operation data, but also user power consumption behavior, market supply and demand, etc., it is possible to achieve comprehensive management of all-factor data of the power grid. At the same time, these data can be deeply mined and analyzed to obtain valuable information, thereby optimizing the operation efficiency and service quality of the power grid.

[0043] All-factor data covers all aspects of power grid operation and management. These data are the basis for the digital power grid to achieve intelligent and efficient operation. Through integration, standardization and big data analysis, power grid data management adjustment strategies can be obtained to improve power grid operation efficiency, reduce operating costs, and enhance the safety and stability of the power grid. Among them, the equipment operation data of power equipment can reflect the real-time operation of various equipment in the power grid, such as the operating status and parameters of transformers, circuit breakers, lines, etc. Fault data can help quickly locate and solve faults and problems in the power grid. The external environment data deployed by power equipment includes environmental information such as temperature, humidity, wind speed, etc., which is of great significance to the safe operation of the power grid and the maintenance of equipment. The power generation and power consumption of the power operation system record the generation, transmission and consumption of electric energy in the power grid, which is helpful for power balance and scheduling. The power user load data reflects the power load in different areas and different time periods in the power grid, providing a basis for load forecasting and scheduling.

[0044] The specific method of integrating and standardizing the various basic data to obtain the full-factor data is as follows: Step 1, data cleaning: removing duplicate data, correcting erroneous data, filling missing values, etc. in various basic data;

[0045] Step 2, data conversion: convert the cleaned basic data into a unified format, such as date format, number format, etc.; Step 3, data mapping: map various basic data fields from different sources to a unified model or architecture to ensure data consistency; Step 4, data normalization: normalize the data so that data of different magnitudes can be compared under the same standard, such as using Z-score normalization or minimum-maximum normalization; Step 4, data integration: merge data from different sources into a unified data warehouse or data lake.

[0046] It should be noted that a data log is created to record the source, structure, quality and other information of various basic data, and the data quality is checked regularly to ensure the accuracy and consistency of the data. The unified data model at least includes: entities, attributes, relationships and constraints of various basic data. For example, in the embodiment of the present invention, a full-factor data management platform is constructed, which is developed in Java language, the operating environment is Windows Server 2012, and the database uses MySQL 5.7. The platform mainly includes a data acquisition module, a data cleaning module, a data storage module and a data access module. The data acquisition module is responsible for collecting data from various data sources, the data cleaning module is responsible for cleaning the collected data, removing noise and outliers, the data storage module is responsible for storing the cleaned data in the database, and the data access module is responsible for providing a data access interface for other modules to call. Optionally, big data technology can be applied to manage full-factor data, such as using the Hadoop ecosystem, including components such as HDFS, MapReduce, and Hive. Through these components, full-factor data can be distributedly stored and standardized, and the efficiency and accuracy of data analysis can be improved, which is of great significance to improving the operating efficiency and service quality of the power grid. This method can solve problems such as inconsistent data formats, difficulty in ensuring data quality, and difficulty in sharing data, and achieve efficient use and integrated application of data.

[0047] In one scenario, the data in the digital power grid is private and may be protected. Therefore, after obtaining various basic data from multiple data sources of the digital power grid, it also includes: for various basic data, if the basic data has been protected by homomorphic encryption functions, the basic data is decrypted to obtain the decrypted basic data. Then, the decrypted basic data is integrated and standardized to obtain full-factor data. Homomorphic encryption technology allows power companies to store sensitive information in remote servers, which not only avoids leaks from the local host, but also ensures the use and search of information; users can also use search engines to query and obtain results without worrying that the search engine will leave their own query records, thereby further ensuring the security of the data.

[0048] For example, the process of decrypting the basic data to obtain the decrypted basic data satisfies the following process: Dec(D i )=c i -kmod(m), where Dec(D i ) is the basic data after decryption, c i is the number of power equipment, m is the homomorphic encryption key, and k is a constant. Accordingly, the expression of the homomorphic encryption function satisfies: Enc(D i )=mod(m)+c i , where Enc(D i ) is the basic data after decryption.

[0049] In the above S102, the power supply index of the current area is obtained. The power supply index represents the power supply demand of the current area, such as which indicators need to be monitored, managed and optimized, the calculation method and threshold range of these indicators, and the relationship between them and the full factor data. For example, the power supply index includes one or more of power supply reliability, power supply quality, power supply efficiency, power supply economy, etc. The power supply reliability index may involve equipment failure rate, power outage time, etc., while the power supply economy index may involve power loss, operating cost, etc. For example, for equipment status data, it may be necessary to collect data in real time through sensors and perform data cleaning and outlier processing; for power information data, it may be necessary to perform data aggregation and calculation to obtain specific power indicators. In one implementation method, the power supply index is also related to the data service needs of various departments in the current area, for example, customized data services are provided according to the needs of different business departments, such as dispatching, operation, and maintenance. For example, the dispatching department needs to monitor the operating status of the power grid in real time, so it needs high-frequency and high-precision data; the operation department needs to understand the user's power consumption behavior, so it needs user-level data; the operation and maintenance department needs to understand the operating status of the equipment, so it needs equipment-level data. The present invention integrates power supply indicators with all-factor data for management, which can meet the needs of different business departments, such as user power consumption behavior data required by the operation department and equipment operation status data required by the dispatching department, thereby improving the applicability and flexibility of the system.

[0050] In the above S104, the power supply index and the full-factor data are integrated and managed, which can achieve comprehensive coverage and in-depth utilization of data and solve the problem of data management that cannot fully cover all aspects of the power grid. In one example, the relationship between the power supply index and the full-factor data, such as causality, correlation, etc., is determined, and the power supply index and the full-factor data are mapped based on the causality and correlation to obtain the fused data, forming a complete data view, so as to better understand and utilize the data. In another example, a fusion model of the power supply index and the full-factor data can be established, and the fused power grid data can be obtained based on the model. This model can comprehensively consider various factors, including equipment status, power information, load data, fault records, and environmental conditions, so as to obtain more accurate and comprehensive power supply index calculation results. The specific modeling method can be selected according to the actual situation. For example, a machine learning algorithm can be used for model training and optimization, and the model can be trained by historical data and actual operation data, and the model parameters can be continuously adjusted to improve the prediction accuracy. At the same time, the model can also be further optimized and improved in combination with the experience and knowledge of experts. In this step, the power supply indicators are integrated with all-factor data for management, which can solve problems such as data isolation, difficulty in data association, and low data utilization, and realize efficient integration and comprehensive analysis of power supply indicators and all-factor data.

[0051] In the above S106, based on big data analysis, the adjustment strategy of power grid data management is formulated, which can solve the problems of low data management efficiency, low data utilization, and difficulty in fully mining data value, and optimize the power grid data management process. In addition, deep mining and analysis of all-factor data can obtain valuable information, improve the accuracy and practicality of data analysis, and provide more reliable decision support for the operation and management of the power grid. In addition, the data management model can be optimized and updated regularly, including software upgrades, data cleaning, etc., to improve the real-time and accuracy of the data. The goal of the update is to adapt to the needs of power grid development.

[0052] The training process of the data management model involved in the above S106 includes the following steps:

[0053] Obtain historical full-factor data and historical power supply indicators in the digital power grid;

[0054] The historical full-factor data and the historical power supply indicators are integrated to obtain the historical integrated power grid data; the training set is determined based on the historical integrated power grid data;

[0055] Multiple trees are randomly constructed, and each tree is used to predict each sample data in the training set;

[0056] Input the prediction results of multiple trees for each sample data into the random forest model, and output the final prediction results based on the random forest model;

[0057] According to the final prediction results, the random forest model is iteratively trained to obtain a pre-trained data management model.

[0058] Random forest is an ensemble learning model composed of multiple decision trees (such as the multiple trees constructed above), which can improve the accuracy and stability of the model. For example, the steps for using random forest include:

[0059] Step 1, data preparation: Prepare the data set required for the random forest model, such as a training set and a test set.

[0060] Step 2, data selection: In the process of building each tree, a part of the features will be randomly selected instead of all the features.

[0061] Step 3, Building Trees: For each data point, each tree in the random forest will make a prediction for it.

[0062] Step 4, result integration: Finally, the random forest will comprehensively consider the prediction results of all individual trees to obtain the final prediction result.

[0063] Step 5, optional steps include evaluating the model: you can use cross-validation or evaluate the performance of the model on an independent test set.

[0064] A key advantage of the random forest model is that it can handle large datasets and handles overfitting well. In addition, random forests can be easily extended to more datasets and larger datasets.

[0065] In one implementation, the random forest model is iteratively trained according to the final prediction result to obtain a pre-trained data management model including:

[0066] According to the final prediction results, determine whether the random forest model has reached the convergence condition;

[0067] If the convergence condition is met, the random forest model is determined as the data management model;

[0068] If the convergence condition is not met, the number of trees in the random forest, the maximum depth of each tree, and the number of nodes of each tree are adjusted, and each adjusted tree is used to continue to predict each sample data in the training set until the final prediction result based on the output of the random forest model meets the convergence condition, and the adjusted random forest model is determined as the data management model.

[0069] The use of the random forest model in this implementation includes tuning parameters: according to the performance of the model, some parameters of the random forest can be adjusted, such as the number of trees, the maximum depth of each tree, the number of nodes per tree, etc.

[0070] Generally, in the random forest algorithm, due to the use of bootstrap sampling and random feature selection, each tree is independent and trained on different data sets, so the random forest itself has a certain degree of randomness and diversity, which reduces the risk of overfitting to a certain extent. Therefore, the random forest algorithm usually does not need to be post-pruned because it has avoided overfitting through randomness. In the embodiment of the present invention, considering the particularity of the full-element data in the data grid, the amount of data grid data is huge, there are too many features to be analyzed, and there are also many features considered in the generated power grid management adjustment strategy, as well as the differences in power supply indicators and power grid management adjustment strategies in different regions, it is still possible that the feature space is very large and causes overfitting. Therefore, in the embodiment of the present invention, post-pruning is used to further prevent overfitting. Post-pruning refers to checking non-leaf nodes from the bottom up after the decision tree is fully constructed. If removing a node can improve the performance of the decision tree on the validation set, it is replaced with a leaf node. Specifically, in the embodiment of the present invention, the process of adjusting the number of nodes of each tree includes: for each tree, if there is a target node that exceeds the maximum depth of the tree, the target node is removed. This implementation can remove nodes that contribute less to model prediction, reduce the complexity of the model, prevent overfitting, and improve the generalization ability of the model.

[0071] This process uses big data technology to deeply mine and analyze the integrated power grid data to obtain valuable information, which is of great reference value for the decision-making and management of power companies. In addition, this technical solution can also meet the needs of different regions and different business departments, such as user power behavior data required by the operation department and equipment operation status data required by the dispatching department. Therefore, this technical solution has broad market demand and good application prospects.

[0072] Figure 3 A schematic diagram of the structure of a digital power grid full-factor data management system provided by an embodiment of the present invention, the device includes:

[0073] The acquisition module 201 is used to acquire all-factor data in the digital power grid and acquire power supply indicators in the current area;

[0074] A fusion module 202 is used to fuse all factor data and power supply indicators to obtain fused power grid data;

[0075] Management module 203, used to input the integrated power grid data into a pre-trained data management model, and output a power grid management adjustment strategy for the current area based on the data management model;

[0076] Among them, the data management model is obtained by training the random forest model according to the historical integrated power grid data and the historical power grid management adjustment strategy. The historical integrated power grid data includes historical full-factor data and historical power supply indicators. The power grid management adjustment strategy of the current area is used to adjust the equipment in the power grid of the current area.

[0077] Furthermore, the acquisition module 201 is specifically used to acquire various basic data from multiple data sources of the digital power grid. The basic data include the following data: equipment operation data and fault data of power equipment, external environment data deployed by the power equipment, power generation and consumption of the power operation system, and power user load data; various basic data are integrated and standardized to obtain full-factor data.

[0078] Furthermore, the acquisition module 201 is also used to decrypt various basic data to obtain decrypted basic data if the basic data has been protected by a homomorphic encryption function.

[0079] Furthermore, the acquisition module 201 is specifically used to decrypt the data to obtain the decrypted basic data, and the process satisfies the following process: Dec(D i )=c i -kmod(m), where Dec(D i ) is the basic data after decryption, c i is the number of power equipment, m is the homomorphic encryption key, and k is a constant.

[0080] Furthermore, it also includes:

[0081] A training module for acquiring historical full-factor data and historical power supply indicators in the digital power grid;

[0082] The historical full-factor data and the historical power supply indicators are integrated to obtain the historical integrated power grid data; the training set is determined based on the historical integrated power grid data;

[0083] Multiple trees are randomly constructed, and each tree is used to predict each sample data in the training set;

[0084] Input the prediction results of multiple trees for each sample data into the random forest model, and output the final prediction results based on the random forest model;

[0085] According to the final prediction results, the random forest model is iteratively trained to obtain a pre-trained data management model.

[0086] Furthermore, the training module is specifically used to determine whether the random forest model has reached the convergence condition based on the final prediction result; if the convergence condition is reached, the random forest model is determined as the data management model; if the convergence condition is not reached, the number of trees in the random forest, the maximum depth of each tree, and the number of nodes of each tree are adjusted, and each adjusted tree is used to continue to predict each sample data in the training set until the final prediction result based on the output of the random forest model reaches the convergence condition, and the adjusted random forest model is determined as the data management model.

[0087] Furthermore, the training module is specifically used to remove the target node for each tree if there is a target node that exceeds the maximum depth of the tree.

[0088] On the basis of the above embodiments, an electronic device is also provided in an embodiment of the present invention, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; a computer program is stored in the memory, and when the program is executed by the processor, the processor executes the steps of the digital grid full-element data management method as in the above embodiments.

[0089] For the specific implementation process, please refer to the above embodiment, and the similarities are not repeated here.

[0090] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0091] The communication interface is used for communication between the above electronic device and other devices.

[0092] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0093] The above-mentioned processor can be a general-purpose processor, including a central processing unit, a network processor (Network Processor, NP), etc.; it can also be a digital signal processing processor (Digital Signal Processing, DSP), an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc.

[0094] It should be noted that Figure 3 The digital grid full-element data management system shown is used to execute Figure 2 The digital grid full-factor data management method shown in the figure, therefore the relevant explanations in the above digital grid full-factor data management method are also applicable to the digital grid full-factor data management system, and will not be repeated here.

[0095] An embodiment of the present application also provides a computer device, including: a memory and a processor, wherein the memory is used to store program instructions; the processor is connected to the memory and is used to execute the above-mentioned digital power grid full-factor data management method.

[0096] An embodiment of the present application also provides a non-volatile storage medium, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the above-mentioned digital power grid full-factor data management method by running the computer program.

[0097] An embodiment of the present application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the digital grid full-element data management method in the present application.

[0098] An embodiment of the present application also provides a computer program, which, when executed by a processor, implements the steps of the digital grid full-factor data management method in the present application.

[0099] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0100] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0101] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0102] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0103] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0104] 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 application, 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, and the computer software product is stored in a storage medium, including a number of instructions to enable 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 application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0105] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for managing all-factor data of a digital power grid, characterized in that: The method comprises: Obtaining full-factor data in the digital power grid and obtaining power supply indicators in the current area, wherein the full-factor data at least includes the operation status of power grid equipment in the current area, user power consumption behavior, and market supply and demand conditions; Fusion the all-factor data and the power supply index to obtain fused power grid data; The fused power grid data is input into a pre-trained data management model, and based on the data management model, a power grid management adjustment strategy for the current area is output, wherein the data management model is obtained by training a random forest model based on historical fused power grid data and historical power grid management adjustment strategies, the historical fused power grid data includes historical full-factor data and historical power supply indicators, and the power grid management adjustment strategy for the current area is used to adjust equipment in the power grid in the current area.

2. The method according to claim 1, characterized in that The acquisition of all-factor data in the digital power grid includes: Acquire various basic data from multiple data sources of the digital power grid, the basic data including the following data: equipment operation data and fault data of power equipment, external environment data where the power equipment is deployed, power generation and power consumption of the power operation system, and power user load data; The various basic data are integrated and standardized to obtain full-factor data.

3. The method according to claim 2, characterized in that After obtaining various basic data from multiple data sources of the digital power grid, the method further includes: For various basic data, if such basic data has been protected by a homomorphic encryption function, such basic data is decrypted to obtain the decrypted basic data.

4. The method according to claim 3, characterized in that The process of decrypting the basic data to obtain the decrypted basic data is as follows: Dec(D i )=c i -kmod(m) In the formula, Dec(D i ) is the basic data after decryption, c i is the number of power equipment, m is the homomorphic encryption key, and k is a constant.

5. The method according to claim 1, characterized in that The training process of the data management model includes: Obtain historical full-factor data and historical power supply indicators in the digital power grid; The historical full-factor data and the historical power supply index are integrated to obtain historical integrated power grid data; and a training set is determined based on the historical integrated power grid data; Multiple trees are randomly constructed, and each tree is used to predict each sample data in the training set; Inputting the prediction results of the multiple trees for each sample data into a random forest model, and outputting a final prediction result based on the random forest model; According to the final prediction result, the random forest model is iteratively trained to obtain a pre-trained data management model.

6. The method according to claim 5, characterized in that The iterative training of the random forest model according to the final prediction result to obtain a pre-trained data management model includes: According to the final prediction result, judging whether the random forest model has reached a convergence condition; If the convergence condition is met, determining the random forest model as the data management model; If the convergence condition is not met, the number of trees in the random forest, the maximum depth of each tree, and the number of nodes of each tree are adjusted, and each adjusted tree is used to continue to predict each sample data in the training set until the final prediction result based on the output of the random forest model meets the convergence condition, and the adjusted random forest model is determined as the data management model.

7. The method according to claim 6, characterized in that The process of adjusting the number of nodes of each tree includes: For each tree, a node in each tree that exceeds the maximum depth of the tree is determined as a target node, and the target node is removed.

8. A digital power grid full-factor data management system, characterized in that: The system comprises: An acquisition module is used to acquire full-factor data in the digital power grid and to acquire power supply indicators in the current area, wherein the full-factor data at least includes the operation status of power grid equipment, user power consumption behavior, and market supply and demand conditions in the current area; A fusion module, used for fusing the full-factor data and the power supply index to obtain fused power grid data; A management module is used to input the fused power grid data into a pre-trained data management model, and based on the data management model, output a power grid management adjustment strategy for the current area, wherein the data management model is obtained by training a random forest model based on historical fused power grid data and historical power grid management adjustment strategies, the historical fused power grid data includes historical full-factor data and historical power supply indicators, and the power grid management adjustment strategy for the current area is used to adjust equipment in the power grid in the current area.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory is used to store program instructions; The processor is connected to the memory and is used to execute the digital grid full-factor data management method as described in any one of claims 1 to 7.

10. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by a processor, the digital grid full-factor data management method described in any one of claims 1 to 7 is implemented.

Images