Power grid bearing capacity assessment method, device, equipment, medium and program

Abstract

The invention belongs to the technical field of information management, and particularly relates to a power grid bearing capacity evaluation method, device and equipment, a medium and a program. The method comprises the steps of obtaining power grid parameters based on a digital twin platform; wherein the data of the digital twin platform is subjected to distributed storage and / or encryption based on a block chain network after being synchronized through an Internet of Things sensor; calculating the bearing capacity of the power grid according to the fusion weight and the power grid parameters; wherein the fusion weight is the weight of each power grid parameter, which is obtained by fusing a first weight and a second weight based on a nonlinear model. The method not only optimizes the efficiency of data processing, but also improves the accuracy, real-time performance and safety of monitoring and managing the carrying capacity of the power grid, thereby further improving the reliability of evaluation.

Description

Technical Field

[0001] The present application belongs to the field of information management technology, and in particular, relates to a method, device, equipment, medium and program for evaluating the carrying capacity of a power grid. Background Art

[0002] At present, the evaluation of grid carrying capacity involves multiple complex factors, and these indicators often have complex relationships, including maximum injected power, network security constraints, power balance constraints and other indicators, mainly involving current, power, voltage, power factor, voltage harmonics, etc., but the selected status indicators are generally not comprehensive enough. In order to ensure the stability and reliability of the power system, to improve the efficiency of grid operation and the life of power equipment, evaluating the state of grid carrying capacity has become the focus of current electrical equipment research. Summary of the invention

[0003] The embodiments of the present application provide a method, device, equipment, medium and program for evaluating the carrying capacity of a power grid, which can improve the stability and reliability of the power system.

[0004] In a first aspect, an embodiment of the present application provides a method for evaluating power grid carrying capacity, characterized by comprising:

[0005] Obtaining power grid parameters based on a digital twin platform; wherein the data of the digital twin platform is synchronized through IoT sensors and then distributedly stored and / or encrypted based on a blockchain network;

[0006] The carrying capacity of the power grid is calculated based on the fusion weight and the power grid parameters; wherein the fusion weight is the weight of each of the power grid parameters obtained by fusing the first weight and the second weight based on a nonlinear model.

[0007] In a possible implementation manner of the first aspect, the first weight is a subjective weight based on human evaluation, and the second weight is an objective weight based on the power grid parameter.

[0008] In a possible implementation manner of the first aspect, the fusion weight includes a linear part, a nonlinear part, a balance parameter β, and a mixing parameter γ;

[0009] Among them, the linear part is a function associated with the first weight and the second weight; the nonlinear part is a function associated with the first weight and the second weight; the balance parameter β is used to adjust the contribution of the linear part and the nonlinear part to the fusion weight; the mixing parameter γ is used to adjust the contribution of the first weight and the second weight to the nonlinear part.

[0010] In a possible implementation manner of the first aspect, the step of calculating the first weight includes:

[0011] Constructing the judgment matrix A based on human evaluation ij ) n×n ; Among them, a ij is the importance of the ith parameter in the power grid parameters relative to the jth parameter, i and j are both positive integers not greater than n, n is the number of the power grid parameters, and for any i and j, the elements of the judgment matrix A simultaneously satisfy the following three formulas:

[0012] a ii =1;

[0013] a ij >0;

[0014]

[0015] Setting an initial weight, wherein the initial weight is associated with: the importance of the power grid parameter based on human evaluation, and the quantitative impact of historical data on the importance of the power grid parameter; wherein the importance is associated with the judgment matrix A;

[0016] The first weight is obtained based on the dynamic update of the initial weight; wherein the dynamic update is used to smooth short-term fluctuations.

[0017] In a possible implementation manner of the first aspect, the step of calculating the second weight includes:

[0018] Standardizing the power grid parameters to obtain standard parameters; the standard parameters are the power grid parameters at the same level after data adjustment;

[0019] Construct the time weight function W(t i ), where W(t i ) is negatively correlated to the time difference Δt=Tt i , T is the preset standard time label;

[0020] According to the standard parameters and the time weight function W(t i ) calculates the second weight; wherein the second weight is positively correlated to the standard parameter and the time weight function W(t i ) value.

[0021] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0022] It not only optimizes the efficiency of data processing, but also improves the accuracy, real-time and security of monitoring and managing the grid's carrying capacity, thereby further enhancing the reliability of the assessment.

[0023] In a second aspect, an embodiment of the present application provides a power grid carrying capacity evaluation device, including an information processing system, wherein the information processing system includes:

[0024] A parameter module, used to obtain power grid parameters based on a digital twin platform; wherein the data of the digital twin platform is synchronized through IoT sensors and then distributedly stored and / or encrypted based on a blockchain network;

[0025] The operation module is used to calculate the carrying capacity of the power grid according to the fusion weight and the power grid parameters; wherein the fusion weight is the weight of each of the power grid parameters obtained by fusing the first weight and the second weight based on a nonlinear model.

[0026] In a possible implementation manner of the second aspect, the device further includes a digital twin system, and the digital twin system includes:

[0027] A twin mapping module for mapping static and dynamic properties of physical entities in the power grid into virtual copies;

[0028] A model building module, configured to receive real-time data and / or virtual data of the virtual replica, and generate, update and maintain a virtual model corresponding to a physical entity in the power grid generated according to the virtual replica;

[0029] A data storage module is used to collect, archive and protect the data of the power grid; wherein the operations performed on the data of the power grid are verified and recorded through a blockchain network; the smart contracts of the blockchain network include a power grid maintenance scheduling protocol and a power grid load balancing protocol.

[0030] In a third aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for evaluating the power grid carrying capacity described in any one of the first aspects above is implemented.

[0031] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the power grid carrying capacity assessment method described in any one of the first aspects above is implemented.

[0032] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on a terminal device, the terminal device executes the power grid carrying capacity assessment method described in any one of the first aspects above.

[0033] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0035] Figure 1 It is a flow chart of the power grid carrying capacity evaluation method provided in the embodiment of the present application.

[0036] Figure 2 It is a structural schematic diagram of a power grid carrying capacity assessment device provided in an embodiment of the present application.

[0037] Figure 3 It is a schematic diagram of the structure of the terminal device provided in an embodiment of the present application.

[0038] Figure 4 This is a digital twin model architecture diagram provided in an embodiment of the present application.

[0039] Figure 5 This is an architecture diagram of the information collection system provided in an embodiment of the present application.

[0040] Figure 6 This is an architecture diagram of the information processing system provided in an embodiment of the present application.

[0041] Figure 7 This is a diagram of the hardware composition architecture of the entire machine provided in the embodiment of the present application.

[0042] Figure 8 It is a schematic diagram of the main control software design provided in the embodiment of the present application.

[0043] Fig. 9 It is a schematic diagram of the main control software platform provided in the embodiment of the present application.

[0044] Reference numerals:

[0045] Terminal device 30;

[0046] Processor 301;

[0047] Memory 302;

[0048] Computer program 303. DETAILED DESCRIPTION

[0049] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0050] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0051] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0052] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0053] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0054] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0055] The present application provides a method for evaluating power grid carrying capacity, including:

[0056] Step 102, obtaining power grid parameters based on the digital twin platform; wherein the data of the digital twin platform is synchronized through the Internet of Things sensors and distributedly stored and / or encrypted based on the blockchain network;

[0057] Step 104, calculating the carrying capacity of the power grid according to the fusion weight and the power grid parameters; wherein the fusion weight is the weight of each of the power grid parameters obtained by fusing the first weight and the second weight based on a nonlinear model.

[0058] Among them, the grid parameters may include multi-level indicators, for example, including maximum injection power, network security constraints, power balance constraints and other indicators, which further involve specific parameters such as current, power, voltage, power factor, voltage harmonics and so on.

[0059] Although at least part of the data used to model the digital twin platform and at least part of the raw data synchronized from the power grid by the digital twin platform are the aforementioned specific parameters, the core of the digital twin technology is to establish a virtual model corresponding to the real-world power grid system. This model contains various physical entities in the power grid, including power stations, substations, transmission lines, distribution equipment, etc. Each entity needs to be accurately modeled to reflect its physical characteristics and operating status.

[0060] The digital twin model needs to rely on a large amount of data support to achieve accurate modeling and simulation analysis of the power system. The data platform of the digital twin model needs to realize real-time collection, processing and storage of power system data to provide support for the establishment and optimization of the digital twin model.

[0061] Therefore, the power grid parameters obtained by the execution entity of this embodiment from the digital twin platform are not limited to the aforementioned specific parameters, but may also include the aforementioned indicators obtained by digital twin modeling and simulation analysis.

[0062] The executor of this embodiment may be predetermined hardware with computing capabilities, such as computers, servers, etc. More specifically, the aforementioned computers, servers, and other hardware may be used as sub-components of the power grid and its management and evaluation system to ensure the operation of the power grid.

[0063] In an optional implementation, the method of this embodiment is implemented based on computer software (in other optional implementations, at least a portion of the method of this embodiment can be implemented by hardware such as a logic circuit, a switch circuit, or other specified methods). In this implementation based on computer software execution method, the present application additionally provides an apparatus embodiment, specifically:

[0064] The present application embodiment provides a power grid carrying capacity evaluation device, such as Figure 2As shown, an information processing system is included, and the information processing system includes:

[0065] Parameter module 201, used to obtain power grid parameters based on the digital twin platform; wherein the data of the digital twin platform is synchronized through the Internet of Things sensors and distributedly stored and / or encrypted based on the blockchain network;

[0066] The operation module 202 is used to calculate the carrying capacity of the power grid according to the fusion weight and the power grid parameters; wherein the fusion weight is the weight of each of the power grid parameters obtained by fusing the first weight and the second weight based on a nonlinear model.

[0067] In a preferred implementation of the device embodiment, the device further includes a digital twin system, and the digital twin system includes:

[0068] A twin mapping module for mapping static and dynamic properties of physical entities in the power grid into virtual copies;

[0069] A model building module, configured to receive real-time data and / or virtual data of the virtual replica, and generate, update and maintain a virtual model corresponding to a physical entity in the power grid generated according to the virtual replica;

[0070] A data storage module is used to collect, archive and protect the data of the power grid; wherein the operations performed on the data of the power grid are verified and recorded through a blockchain network; the smart contracts of the blockchain network include a power grid maintenance scheduling protocol and a power grid load balancing protocol.

[0071] Correspondingly, the embodiment of the present application also provides a terminal device, such as Figure 3 As shown, the terminal device 30 includes: at least one processor 301, a memory 302, and a computer program 303 stored in the memory and executable on the at least one processor, and the processor implements the steps in any of the above-mentioned method embodiments when executing the computer program.

[0072] Regardless of the specific implementation method of the above embodiments, the digital twin model therein needs to rely on a large amount of data support to achieve accurate modeling and simulation analysis of the power system. In an optional implementation, the data platform of the digital twin model needs to realize real-time collection, processing and storage of power system data to provide support for the establishment and optimization of the digital twin model.

[0073] Figure 4 An exemplary (but not limiting) digital twin model architecture diagram is provided.

[0074] exist Figure 4 In the example provided, the functions of each module are as follows.

[0075] The twin mapping module is the core of the digital twin power grid system. It is responsible for accurately mapping each physical entity in the power grid into a virtual copy, including the static and dynamic properties of the equipment. It involves accurate mapping and continuous monitoring of multiple key entities. These include power stations, substations, transmission lines, distribution equipment, control centers, and protection equipment. As the core of the energy supply of the power grid, the efficiency and reliability of the power station directly affect the entire system; substations and transmission lines ensure that electric energy is converted and transmitted under high efficiency and safety conditions; distribution equipment is directly related to the quality of power supply to end users; the control center regulates the operation of the entire power grid through real-time data monitoring and analysis to ensure the efficiency and safety of the system; protection equipment responds quickly when a fault occurs to prevent the spread of problems and protect the entire power grid and its users. This module updates the status of each virtual entity in real time by connecting to the real-time data stream of sensors and monitoring systems to ensure that the model accurately reflects the operating status of physical entities. It also provides feedback mechanisms and prediction support, reveals system risks or optimization opportunities through analysis and simulation, and feeds this information back to operators to process and integrate large amounts of data from different sources and ensure the real-time and reliability of the system.

[0076] The backend management module is the core of the system, responsible for user management, configuration management, and monitoring and alarm functions. This module ensures that only authorized users can access key system data and management functions through strict user permission settings, thereby ensuring data security and system stability. In terms of configuration management, administrators can flexibly adjust system settings according to the needs of power grid operations, such as parameter settings and enabling or disabling functions. At the same time, the backend management module also includes a comprehensive monitoring system to monitor the operating status and system performance of the power grid in real time. Once an abnormality or performance degradation is detected, the alarm mechanism is immediately activated to respond quickly to prevent potential risks.

[0077] The model building module generates accurate power grid models based on real-time and historical data. Its core task is to generate, update and maintain virtual models that represent physical entities to ensure that the models can accurately reflect the current state of the entities and predict future behavior. It supports dynamic updates and simulation tests of models. This module uses algorithms and technologies to build models to ensure that each model can accurately reflect the physical characteristics of power grid entities and their operating status. Figure 4 Already given.

[0078] The data storage module is the foundation of the digital twin system, responsible for collecting, archiving and protecting all key data of the power grid operation. This includes real-time data from sensors and historical operation data. The module is also responsible for communication and data synchronization with other systems to analyze the transmitted data. Moreover, the powerful data protection and recovery mechanism built into the module ensures the integrity and security of the data under any circumstances. Blockchain technology plays an important role here. The data storage module is responsible for ensuring the operation data of the power grid, real-time monitoring data and historical data, while the regional chain technology ensures that the data is not modified without authorization. Each data update is verified and recorded through the blockchain, forming a permanent and traceable data chain. Through distributed ledger technology, all participating nodes retain an identical copy of the ledger, and any record on the blockchain requires verification and confirmation by the majority of nodes in the network. In addition, through smart contract technology, blockchain can automatically execute defined rules and protocols, automated maintenance scheduling and load balancing strategies, all of which are based on real-time data analysis and preset conditions.

[0079] The data connection module processes data received from various external and internal sources. It not only integrates real-time data from various parts of the power grid, but also manages the data exchange interface with external systems. In addition, the module ensures the consistency and real-time update of data within the system. This example is to communicate with the STM32F103RCT6, mainly to transfer the stored data to the chip through the data connection module.

[0080] The model library stores all generated models and their versions. This not only facilitates the management and tracking of model changes, but also facilitates the sharing and reuse of models between different users and systems. Through the model library, the twin mapping module can build a digital twin model based on the existing models in the model library.

[0081] Furthermore, in the above embodiments, the collection of grid carrying capacity information is still one of the difficulties. In an optional implementation, the data collection design framework is as follows: Figure 5 As shown. By establishing a digital twin platform for the power grid, the data connection module communicates with the information acquisition system, simulates and analyzes the acquired power grid data including current, voltage, power flow, equipment status, etc., and uses the conditioning circuit to power the sensor. Then the power grid carrying capacity status information is converted into an analog signal through the corresponding sensor, and the AD conversion module converts it into a digital signal. The data processing module uses the CPU to analyze and process the data, and the network communication module is used to upload the collected data to the host computer for data storage and display.

[0082] In addition, in an optional embodiment, the hardware architecture of the information processing system is as follows: Figure 6As shown, the ARM main control module is responsible for data collection, reception, calculation, analysis, etc.; and realizes human-computer interaction through external interfaces to display and store data; it is used to better analyze the results; and the collected data can also be sent to the host computer through the network interface. According to this project, the STM32F103RCT6 series microprocessor with ARMCortex-M3 core should be selected. It is composed of memory, key processing, LCD, USB and network interface drivers, accepts the operation instructions of the key response module, receives the control instructions of the host computer remote control software from the network interface, stores them in the memory module, and then reads the test data from the memory module to the LCD screen for display, and can also be transmitted to the computer remote control software through the network. Test data can also be transmitted or read out through the USB interface.

[0083] As an example but not a limitation, the combination of this embodiment and other embodiments of the present application can be used to build a large-scale, complete real-time evaluation and information management system for power grid carrying capacity.

[0084] The real-time assessment and information management system of power grid carrying capacity is a large-scale hierarchical system, which contains multiple subsystems, including the aforementioned digital twin system, the aforementioned information acquisition system, the aforementioned information processing (and management) system, etc. Each system is closely connected and works in coordination through data flow.

[0085] As a top-level system, the digital twin system uses real-time data from the physical power grid to build a virtual model to achieve real-time monitoring and simulation analysis of the power grid status. The information acquisition system is responsible for real-time data acquisition of key nodes of the power grid (such as power stations, substations, and transmission lines) through sensors and IoT devices, including parameters such as current, voltage, power, and temperature, and uploads these data to the information processing system through a data link. The data is transmitted from the sensor to the signal conditioning and amplification module, and enters the ARM processor after analog-to-digital conversion (ADC). The processed digital signal is transmitted to the host computer or the cloud through the network communication module for subsequent storage and display.

[0086] The software modules are deployed on each hardware platform. Specifically, the data acquisition module and processing module run in the embedded system to complete the preliminary processing and analysis of the data. The digital twin system software is deployed on the cloud or server, using real-time and historical data to dynamically update the virtual model and predict the potential risks of the power grid through simulation analysis. The data storage and management module is combined with blockchain technology and deployed in a distributed network to ensure the immutability and security of the data. The user interaction module displays real-time monitoring information through the host computer or mobile terminal to support user operations and policy adjustments. The entire data link starts with the underlying sensors and information acquisition equipment. Through conditioning, conversion, processing, transmission and other steps, the analysis results are fed back to the digital twin and user interface, forming a real-time, efficient and stable closed loop of power grid carrying capacity assessment and management.

[0087] In the new energy grid carrying capacity status assessment and information management architecture, grid carrying capacity information is collected in real time through sensors and data acquisition devices, that is, the voltage, current and frequency are collected. After processing and analysis, the data is uploaded to the host computer for display to realize the monitoring of the basic data of the grid carrying capacity. The processed data is to analyze and calculate the basic data using the status assessment algorithm, which can realize the grid carrying capacity status assessment. The grid carrying capacity main control system is realized by the ADC+ARM hardware platform. The system mainly consists of AD conversion module, data acquisition module, data processing and storage module, data calculation and display module, and data transmission. Among them, the signal sensor module is used to sense and transmit the real-time conditions of voltage / current and voltage / current on the DC side and the AC side into corresponding suitable weak-current signals; the signal conditioning and amplification module is used to filter, adjust and amplify the weak-current signals corresponding to the sensor and the transmitter to meet the needs of ADC conversion; the function of the ADC conversion module is to convert the analog signals that have been conditioned and amplified into corresponding digital signals; ARM is used to process and calculate the acquired data, and then upload it to the host computer for display using the network communication module to integrate and analyze the data, manage the relevant information in a unified manner, and control the entire machine in a unified manner.

[0088] Under this architecture, the hardware block diagram of the whole machine is as follows: Figure 7 shown.

[0089] In terms of software, the main control software of the new energy grid carrying capacity mainly includes the following aspects: platform main control software, host computer remote control software and database. The platform main control software runs on the host of the test instrument. The test instrument establishes a communication connection with the host computer remote control software through the RS485 module. Figure 8 shown.

[0090] The system can establish a communication connection with the host computer remote control software through a USB or serial interface, send corresponding test instructions according to the corresponding categories, set various test parameters of the instrument through network communication, obtain measurement data and perform corresponding data analysis and processing, and save the test data in the database.

[0091] As a preferred embodiment, the system platform uses ARM as the core platform, and the embedded software design uses the FreeRTOS operating system, which has good compatibility and can achieve full compatibility with the STM32 platform. The transplantation process is simple, lightweight, and takes up less system memory. Supporting preemptive scheduling algorithms can improve the real-time performance of software operation. In the software system and algorithm, it is necessary to consider the real-time collection of power grid carrying capacity data and voltage, current, and power data, the use of data to effectively evaluate the state of regional power grid carrying capacity, the real-time dynamic display of stable state indicator parameters, and the storage and reading management of large amounts of data. Therefore, it is necessary to use digital twin technology and regional chain technology combined with improved hierarchical analysis method and entropy weight method to evaluate the state of regional power grid carrying capacity, and use the fuzzy membership of the model to solve the problems of fuzziness of level boundaries and uncertainty in data collection, and establish a regional power grid carrying capacity state evaluation and information management system. Finally, the relevant power grid data is evaluated according to the established model to verify the feasibility and reliability of the model. Its main control software platform is as follows: Fig. 9 shown.

[0092] The test parameters of the main control software can be set manually and obtained through the network communication module when TCP communication is established with the host computer software. The test control module controls and collects the processed data according to the set test parameters; and establishes a connection with the data through the host computer software, and then transmits the data to the host computer through the network interface module and displays it.

[0093] In general, the real-time state assessment and information management system for power grid carrying capacity integrates a variety of hardware and software modules to form an efficient and reliable comprehensive system. The hardware modules include sensors, analog-to-digital converters (ADCs), ARM processors, and network communication modules, which work together to realize data acquisition, processing, storage, and transmission. Sensors and IoT devices are responsible for real-time acquisition of data such as current, voltage, temperature, power flow, and equipment status at key nodes of the power grid (such as power stations, substations, and transmission lines). The collected analog signals are converted into digital signals through the ADC module, and the ARM processor analyzes and processes the data. The network communication module uploads the processed data to the host computer or cloud server to provide support for subsequent storage, management, and analysis. The software module runs on the hardware and covers functions such as real-time monitoring and data processing, data storage and management, and user interaction interface. Among them, the real-time monitoring module uses sensors and ARM platforms to process the transmitted data and quickly evaluate the power grid status; the data storage and management module is based on cloud servers or local storage devices to ensure the security and integrity of the data; the user interaction interface displays real-time data and analysis results through the host computer, and supports user operations and report generation. The overall system seamlessly connects collection, processing, analysis and display through a complete data link, building a real-time, efficient and stable grid capacity assessment and management platform.

[0094] According to any of the above embodiments, in yet another embodiment:

[0095] The first weight is a subjective weight based on human evaluation, and the second weight is an objective weight based on the power grid parameter.

[0096] In a possible implementation manner of the first aspect, the fusion weight includes a linear part, a nonlinear part, a balance parameter β, and a mixing parameter γ;

[0097] Among them, the linear part is a function associated with the first weight and the second weight; the nonlinear part is a function associated with the first weight and the second weight; the balance parameter β is used to adjust the contribution of the linear part and the nonlinear part to the fusion weight; the mixing parameter γ is used to adjust the contribution of the first weight and the second weight to the nonlinear part.

[0098] According to any of the above embodiments, in yet another embodiment:

[0099] The step of calculating the first weight comprises:

[0100] Based on human evaluation, the judgment matrix A=(a ij ) n×n ; Among them, a ijis the importance of the ith parameter in the power grid parameters relative to the jth parameter, i and j are both positive integers not greater than n, n is the number of the power grid parameters, and for any i and j, the elements of the judgment matrix A simultaneously satisfy the following three formulas:

[0101] a ii =1;

[0102] a ij >0;

[0103]

[0104] Setting an initial weight, wherein the initial weight is associated with: the importance of the power grid parameter based on human evaluation, and the quantitative impact of historical data on the importance of the power grid parameter;

[0105] The first weight is obtained based on the dynamic update of the initial weight; wherein the dynamic update is used to smooth short-term fluctuations.

[0106] In this embodiment, the matrix A functions as follows:

[0107] Constructing the judgment matrix: The elements of the judgment matrix A represent the importance of criterion i relative to criterion j in the subjective evaluation of the decision maker or expert. The construction of this matrix is ​​based on direct pairwise comparison.

[0108] Weight calculation: A common method for calculating weights from the judgment matrix A is to use the eigenvalue method. The specific operation is to calculate the eigenvector corresponding to the maximum eigenvalue of the matrix A, and this eigenvector (after normalization) is used as the weight of each criterion. This step reflects the relative importance of each criterion and integrates the information of all pairwise comparisons.

[0109] In an optional embodiment, the initial weights are used to evaluate the importance of different criteria, which provides a starting point for the model and ensures that decisions can rely on a stable basis of history and expert knowledge in the absence of immediate data updates. 0,j satisfy:

[0110]

[0111] Expert Rating j Experts' rating of the importance of criterion j.

[0112] Historical Impact j Quantitative impact of historical data on the importance of criterion j.

[0113] α: Adjustment coefficient to balance the impact of historical data on the initial weight.

[0114] n: The total number of criteria, ensuring weights are normalized.

[0115] In particular, regarding Expert Rating j 、Historical Impact j These two and a ij The relationship between them is described as follows.

[0116] Expert ratings and historical ratings are usually used for initial weight setting and do not directly affect the construction of the judgment matrix A. The judgment matrix A mainly relies on the subjective judgment of experts on the relative importance of the criteria. In some cases, expert ratings and historical data can be considered for adjusting or verifying the pairwise comparison matrix A, but usually the two are independent when constructing A.

[0117] Furthermore, dynamic weight updates are used to ensure that the model’s output continues to remain sensitive and relevant to the current situation by adjusting the weights. This helps the model adapt to new situations and avoids the problem of being outdated or inaccurate, which may result from relying solely on the initial settings.

[0118] Considering the impact of real-time data on weights, the exponential moving average (EMA) method can be used to update the weights. The exponential moving average can be used to smooth short-term fluctuations and reduce the impact of extreme values ​​on the model.

[0119]

[0120] W j (t): The weight of criterion j at time t.

[0121] W j (t-1): is the weight at the previous time point.

[0122] Real-time Impact t,j : The impact of real-time data on criterion j at time t.

[0123] β: smoothing parameter, higher values ​​enhance the impact of historical weights, lower values ​​enhance the impact of new data, the preferred range is [0.4, 0, 6]

[0124] About Beta:

[0125] Balance between responsiveness and stability: The higher the β value, the more sensitive the model is to new data, but some stability may be sacrificed; a lower β value may make the model slower to adapt to new situations, but provide a smoother output. Dynamicity of data: If the power grid data and its speed of change are very fast, a higher β value may be required to ensure that the model can reflect these changes in a timely manner. On the contrary, if the data does not change much or is relatively stable, a lower β value can be used.

[0126] Therefore, if a certain response speed is required but a certain stability is also required, the β value can be set in the medium range, that is, 0.4 to 0.6. This range provides a balance between the response to new data and the stability of old data.

[0127] According to any of the above embodiments, in yet another embodiment:

[0128] The step of calculating the second weight comprises:

[0129] Standardizing the power grid parameters to obtain standard parameters; the standard parameters are the power grid parameters at the same level after data adjustment;

[0130] Construct the time weight function W(t i ), where W(t i ) is negatively correlated to the time difference Δt=Tt i , T is the preset standard time label;

[0131] According to the standard parameters and the time weight function W(t i ) calculates the second weight; wherein the second weight is positively correlated to the standard parameter and the time weight function W(t i ) value.

[0132] The above series of embodiments provide specific methods for weight calculation. The following will provide an embodiment of weight calculation provided from a more holistic perspective.

[0133] In order to efficiently evaluate the carrying capacity of the power grid, the improved analytic hierarchy process and entropy weight method models are encapsulated in the data processing module in the stm32 embedded system, and the two methods are adaptively modified to simplify the calculation steps to adapt to the processing power and storage limitations of the embedded devices. At the same time, by using modular programming technology, AHP and entropy weight method are encapsulated into independent modules to make their processing effect more efficient.

[0134] Dynamic Adaptive Hierarchy Analysis (AHP) Method to Calculate Subjective Weights

[0135] (1) Constructing a hierarchical model

[0136] First, we need to establish a hierarchical model starting from the top-level goal layer, which represents the overall goal of the problem; the middle criterion layer, which contains multiple decomposition factors of the goal layer; and the bottom indicator layer shows the specific qualitative or quantitative indicators of these factors.

[0137] The structural model is shown in the following table.

[0138]

[0139]

[0140] (2) Construct a judgment matrix for pairwise comparison. Based on the expert's judgment, construct a pairwise comparison judgment matrix A = (a ij ) n×n , where a ij Indicates the importance of criterion i relative to criterion j, usually a ij The following conditions are met:

[0141] a ii =1 (comparison of the criterion with itself)

[0142] a ij >0 (all elements are positive)

[0143] (reciprocals of each other).

[0144] The analytic hierarchy process needs to construct the pairwise judgment matrix A of the criterion layer and the indicator layer. ij ) n×n , the matrix form is as follows:

[0145]

[0146] Calculating Expert Weights from Judgment Matrix Using Geometric Mean Method

[0147] Geometric mean formula

[0148] The geometric mean of each row is:

[0149]

[0150] Where n is the number of criteria, a ij is the element in the judgment matrix

[0151] Normalization formula:

[0152]

[0153] (3) Calculate weight

[0154] 1) Initial weight setting:

[0155]

[0156] Expert Rating j Experts' rating of the importance of criterion j.

[0157] Historical Impact j Quantitative impact of historical data on the importance of criterion j.

[0158] α: Adjustment coefficient to balance the impact of historical data on the initial weight.

[0159] n: The total number of criteria, ensuring weights are normalized.

[0160] 2) Dynamic weight update:

[0161] Considering the impact of real-time data on weights, the weights are updated using the exponential moving average (EMA) method to smooth short-term fluctuations and respond quickly to market changes:

[0162]

[0163] W j (t): The weight of criterion j at time t.

[0164] W j (t-1): is the weight at the previous time point.

[0165] Real-time Impact t,j : The impact of real-time data on criterion j at time t.

[0166] β: smoothing parameter, higher values ​​enhance the impact of historical weights, lower values ​​enhance the impact of new data, value range [0,1].

[0167] 3) Weight normalization

[0168]

[0169] The normalized weight of criterion j at time t.

[0170] 4) Decision matrix update and priority calculation

[0171]

[0172] Criterion Score t,j : The score of the solution on criterion j at time t.

[0173] Calculation of objective weights:

[0174] 1) Data Standardization

[0175] First, the raw data needs to be standardized to ensure that the data is at the same level for easy comparison and calculation:

[0176]

[0177] P ij is the proportion of the standardized data point i on criterion j.

[0178] a ij is the original value of data point i on criterion j.

[0179] 2) Weighted entropy calculation

[0180] After obtaining the standardized ratio and time weight of each data point, the weighted entropy value of criterion j is calculated:

[0181]

[0182] Is a constant that ensures that the entropy value is within a reasonable range.

[0183] E j is the entropy value of criterion j after considering time weighting.

[0184] Among them, the time weight function W(t i ) is the key part, which adjusts the influence of each data point according to the time label ti of the data point. The preferred time weight function is:

[0185]

[0186] t i is the time label of data point i, usually the time interval from the time when data collection started.

[0187] T is the current time stamp or the latest time stamp.

[0188] λ is a parameter that adjusts the speed of time influence. The larger λ is, the faster the influence of time changes.

[0189] The weight of the criterion is calculated using the entropy value. The weight of a criterion is related to the difference in its entropy value, and the higher the weight, the more important the criterion is to the decision.

[0190] The formula for objective weight is:

[0191]

[0192] W j is the objective weight of criterion j.

[0193] E j is the entropy value of criterion j.

[0194] Introducing nonlinear weight fusion model

[0195] In traditional methods, the combination of subjective and objective weights usually adopts fixed linear weighting or product method. Considering that the linear combination may not fully capture the complex interaction effects between the two methods, we can try a nonlinear model to integrate the weights of AHP and entropy weight method.

[0196] Calculate the final nonlinear weight fusion model weights:

[0197]

[0198] W AHP and W Entropy are the weights calculated by AHP and entropy weight method respectively.

[0199] γ is a nonlinear mixing parameter used to adjust the contribution of the two weights.

[0200] β is a balance parameter used to control the influence of the nonlinear and linear combination parts.

[0201] Tanh is the hyperbolic tangent function, which is used to increase the nonlinear characteristics of the model.

[0202] Calculate the total score

[0203] Use the updated weights to calculate the total score of each solution under different criteria

[0204]

[0205] W j : The weight of criterion j after fusion.

[0206] Criterion Score t,j : The score of the solution on criterion j at time t.

[0207] A specific weight parameter operation example is provided below.

[0208] For the parameters: voltage deviation (X1), active power loss (X2), reactive power loss (X3), weight calculation is performed as follows.

[0209] Construct the judgment matrix A through pairwise comparison of experts:

[0210]

[0211] Historical data:

[0212] Assume that the importance of historical data corresponding to the criteria is:

[0213] A=[0.4,0.35,0.25]

[0214] Judgment matrix weight calculation

[0215] Calculating Expert Weights from Judgment Matrix Using Geometric Mean Method

[0216] Geometric mean formula

[0217] The geometric mean of each row is:

[0218]

[0219] Where n is the number of criteria, a ij is the element in the judgment matrix

[0220] Normalization formula:

[0221]

[0222] Calculation results:

[0223] GM1=2

[0224] GM2≈1.1447

[0225] GM3≈0.228

[0226] Normalized weights:

[0227]

[0228] Fusion of historical data:

[0229]

[0230] Let α = 1

[0231] Calculate the subjective weight of each criterion:

[0232]

[0233] Calculate the initial weights:

[0234] Because the calculation of data is complex, simple data is selected for initial weight calculation, and general expert scores are calculated through matrix A to obtain their weights.

[0235] Expert Rating j )

[0236] Voltage deviation (X1): 8

[0237] Active power loss (X2): 6

[0238] Reactive power loss (X3): 4

[0239] Historical Impact j )

[0240] Voltage deviation (X1): 7

[0241] Active power loss (X2): 5

[0242] Reactive power loss (X3): 3

[0243] Adjustment factor:

[0244] α=0.5

[0245] Calculate the initial weights:

[0246]

[0247] Calculation process:

[0248]

[0249]

[0250] Initial weight results:

[0251] W0=[0.4690.3470.224]

[0252] Dynamic weight results:

[0253] (1) Real-time Impact t,j )

[0254] The real-time data when setting time t=1 is as follows:

[0255] Voltage deviation (X1): 10

[0256] Active power loss (X2): 7

[0257] Reactive power loss (X3): 5

[0258] (2) Smoothing parameter (β)

[0259] β = 0.6 makes history weight more proportional

[0260] (3) Weight update formula

[0261]

[0262] (4) Calculation time data normalization (t = 1)

[0263]

[0264] W1(t)=0.6×0.469+0.4×0.455=0.464

[0265] W2(t)=0.6×0.347+0.4×0.318=0.366

[0266] W3(t)=0.6×0.224+0.4×0.227=0.225(6) Dynamically update weight result (t=1)

[0267] W(t=1)=[0.464,0.336,0.225]

[0268] Weight normalization:

[0269]

[0270]

[0271] Final weight result:

[0272] W AHP (t=1)=[0.448,0.328,0.219] Nonlinear weight fusion entropy weight method calculates objective weight

[0273] 1) Data Standardization

[0274]

[0275] Original data matrix:

[0276]

[0277] Calculation results:

[0278]

[0279] 2) Weighted entropy calculation

[0280] formula:

[0281]

[0282] calculate:

[0283] X1:E1≈0.3281

[0284] X2: E2≈0.3305

[0285] X3:E3≈0.3324

[0286] 3) Calculate objective weight

[0287] formula:

[0288]

[0289] Calculate the entropy difference:

[0290] 1-E1=1-0.3281=0.6719

[0291] 1-E2=1-0.3305=0.6695

[0292] 1-E3=1-0.3324=0.6676

[0293]

[0294] Objective weight calculation:

[0295]

[0296] Nonlinear weight fusion model: balance parameter β: 0.7, mixing parameter λ: 0.5 (both weights are equally important) Formula:

[0297]

[0298] β controls the bias of the fusion strategy. The recommended interval is [0.4, 0.7] to balance the contribution of nonlinear and linear mixing. If the weight sources (AHP and entropy weight method) are very different, it is recommended to increase the β value to enhance the contribution of the nonlinear part. Subjective weight:

[0299]

[0300] Objective weight:

[0301]

[0302] Calculate the fusion weights:

[0303] X1: W1(t)=0.2605+0.0575=0.3180

[0304] X2: W2(t)=0.2236+0.0496=0.2732

[0305] X3: W3(t)=0.1882+0.0396=0.2278

[0306] 4) Calculate the total score

[0307] formula:

[0308]

[0309] W j : The weight of criterion j after fusion.

[0310] Criterion Score t,j : The score of the solution on criterion j at time t.

[0311] Assume that the scores under the three criteria are:

[0312] X1:90 points,X2:85 points,X1:80 points

[0313] Calculation: 0.3180×90+0.2732×85+0.2278×80=70.07 points

[0314] It is worth mentioning that the currently preferred FreeRTOS operating system is suitable for the STM32 embedded platform due to its lightweight and simple porting process. However, in scenarios that require higher hardware compatibility or complex function support, the Linux embedded system can also be used as a substitute, although it will take up more resources.

[0315] In addition, the STM32 series processors are the preferred solution due to their high cost-effectiveness and rich interface functions, but they can be replaced with Cortex-A series processors with higher computing power according to performance requirements, or a more cost-effective MCU (such as ESP32) can be selected in cost-sensitive scenarios.

[0316] At the software algorithm level, the analytic hierarchy process (AHP) used in the weight calculation method is preferred because of its clear logic and strong computational interpretability, but the entropy-based weight allocation method can also be selected to reduce subjective intervention, or a dynamic update mechanism can be introduced to adjust the weights through historical data to improve real-time adaptability.

[0317] In addition, the improved entropy weight method also enhances the authenticity of data weights through nonlinear fusion weights, but the fuzzy comprehensive evaluation method has more advantages in dealing with data uncertainty, and the weight learning mechanism combined with machine learning methods such as neural networks can improve adaptability under complex data distribution.

[0318] In the simulation and optimization part, the combination of digital twins and blockchain technology is currently the preferred option, but when the computing and storage pressures are high, traditional distributed databases and mathematical models can also be used as simplified alternatives.

[0319] Furthermore, combined with the weight learning mechanism of neural networks, patterns and weights in data can be automatically learned by training deep neural networks (DNNs) or other machine learning models, leading to better adaptation and decision-making under complex data distributions.

[0320] The following is an illustrative example of neural network weight learning for cases with data uncertainty and complex distributions.

[0321] Example: Multi-criteria decision weight learning based on neural network

[0322] Scenario: In the evaluation of power grid carrying capacity, there are multiple indicators (such as voltage deviation, active power loss, reactive power loss, power factor, etc.), and the selection of weights of these indicators directly affects the evaluation results. In order to automatically learn the optimal weights, a neural network can be used in combination with training data for modeling.

[0323] Neural Network Architecture:

[0324] Assume there are n indicators, and the data sample of each indicator is x i The goal is to automatically learn the weights w through a neural network i And predict the grid carrying capacity, the output is y.

[0325] 1. Input layer:

[0326] Input(X=[x1,x2,…,x n ]), each indicator value is used as an input feature.

[0327] 2. Hidden layer:

[0328] Using a multi-layer perceptron (MLP) structure, the input features are mapped to a high-dimensional space to capture nonlinear relationships.

[0329] h1=ReLU(W1·X+b1)

[0330] h2=ReLU(W2·X+b2)

[0331] Activation function ReLU(x)=max(0,x)

[0332] When the input x>0, the output is x.

[0333] When the input x≤0, the output is 0.

[0334] Function: Enhance nonlinearity: Help the network capture complex nonlinear characteristics. Avoid gradient disappearance: Compared with Sigmoid and Tanh activation functions, ReLU can better avoid the gradient disappearance problem and improve the training efficiency of deep networks.

[0335] Input feature X: Input feature vector, which contains n eigenvalues. For example, in the evaluation of power grid carrying capacity, it may be the value of current, voltage, power factor and other indicators.

[0336] Weight matrices W: W1 and W2 weight matrices represent the connection weights of the first and second hidden layers, respectively.

[0337] Bias vector b: b1 and b2 are bias terms used to adjust the activation value of each neuron, providing additional degrees of freedom.

[0338] 3. Weight generation layer:

[0339] Use a Softmax layer to generate normalized weights w i Make sure the weights satisfy ∑w i =1

[0340] w=Softmax(W1·X+b1)

[0341] w=Softmax(W2·X+b2)

[0342] Where w is the normalized weight or probability distribution, indicating the relative importance of each output.

[0343] 4. Weighted output layer:

[0344] The learned weight w i Applied to input index x i , calculate the final weighted sum output:

[0345]

[0346] 5. Output layer:

[0347] The final output y represents the predicted value of the grid carrying capacity.

[0348] Training process

[0349] 1. Objective function:

[0350] Use real grid capacity data true As an objective, optimize by the mean squared error (MSE) or other loss functions:

[0351]

[0352] 2. Optimizer:

[0353] Use an optimization algorithm (such as Adam or SGD) to train the network parameters, including the hidden layer weights W1, W2, ... and the weight generation layer parameters W3.

[0354] 3. Training Data:

[0355] Provides a historical power grid operation data set, including multiple samples, each sample corresponds to X and y true .

[0356] Practical application examples

[0357] -Input indicators: voltage deviation, active power loss, reactive power loss, power factor, etc.

[0358] -Output target: Maximum carrying capacity of the power grid

[0359] -After the model is trained, the weight w can be automatically predicted through the neural network, and the current carrying capacity of the power grid can be calculated.

[0360] This neural network architecture can be flexibly expanded and used for data fusion and decision optimization in a variety of scenarios. It is particularly suitable for dealing with complex, dynamic, and multi-dimensional data distribution problems.

[0361] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0362] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0363] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0364] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0365] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0366] 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 present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0367] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0368] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. 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 this application.

[0369] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as 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 devices or units, which can be electrical, mechanical or other forms.

[0370] 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 network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0371] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for evaluating power grid carrying capacity, characterized in that: include: Obtaining power grid parameters based on a digital twin platform; wherein the data of the digital twin platform is synchronized through IoT sensors and then distributedly stored and / or encrypted based on a blockchain network; The carrying capacity of the power grid is calculated based on the fusion weight and the power grid parameters; wherein the fusion weight is the weight of each of the power grid parameters obtained by fusing the first weight and the second weight based on a nonlinear model.

2. The method for evaluating the carrying capacity of a power grid according to claim 1, characterized in that: The first weight is a subjective weight based on human evaluation, and the second weight is an objective weight based on the power grid parameter.

3. The method for evaluating the carrying capacity of a power grid according to claim 2, characterized in that: The fusion weight includes a linear part, a nonlinear part, a balance parameter β and a mixing parameter γ; Among them, the linear part is a function associated with the first weight and the second weight; the nonlinear part is a function associated with the first weight and the second weight; the balance parameter β is used to adjust the contribution of the linear part and the nonlinear part to the fusion weight; the mixing parameter γ is used to adjust the contribution of the first weight and the second weight to the nonlinear part.

4. The method for evaluating the carrying capacity of a power grid according to claim 2, wherein: The step of calculating the first weight comprises: Based on human evaluation, the judgment matrix A=(a ij ) n×n ; Among them, a ij is the importance of the ith parameter in the power grid parameters relative to the jth parameter, i and j are both positive integers not greater than n, n is the number of the power grid parameters, and for any i and j, the elements of the judgment matrix A simultaneously satisfy the following three formulas: a ii ＝1； a ij >0； Setting an initial weight, wherein the initial weight is associated with: the importance of the power grid parameter based on human evaluation, and the quantitative impact of historical data on the importance of the power grid parameter; wherein the importance is associated with the judgment matrix A; The first weight is obtained based on the dynamic update of the initial weight; wherein the dynamic update is used to smooth short-term fluctuations.

5. The method for evaluating the carrying capacity of a power grid according to claim 2, wherein: The step of calculating the second weight comprises: Standardizing the power grid parameters to obtain standard parameters; the standard parameters are the power grid parameters at the same level after data adjustment; (t i ), where W(t i ) is negatively correlated to the time difference Δt=Tt i , T is the preset standard time label; construct the time weight function W According to the standard parameters and the time weight function W(t i ) calculates the second weight; wherein the second weight is positively correlated to the standard parameter and the time weight function W(t i ) value.

6. A power grid carrying capacity assessment device, characterized in that: An information processing system is included, wherein the information processing system includes: A parameter module, used to obtain power grid parameters based on a digital twin platform; wherein the data of the digital twin platform is synchronized through IoT sensors and then distributedly stored and / or encrypted based on a blockchain network; The operation module is used to calculate the carrying capacity of the power grid according to the fusion weight and the power grid parameters; wherein the fusion weight is the weight of each of the power grid parameters obtained by fusing the first weight and the second weight based on a nonlinear model.

7. The power grid carrying capacity evaluation device according to claim 6, characterized in that: Also included is a digital twin system, the digital twin system comprising: A twin mapping module for mapping static and dynamic properties of physical entities in the power grid into virtual copies; A model building module, configured to receive real-time data and / or virtual data of the virtual replica, and generate, update and maintain a virtual model corresponding to a physical entity in the power grid generated according to the virtual replica; A data storage module is used to collect, archive and protect the data of the power grid; wherein the operations performed on the data of the power grid are verified and recorded through a blockchain network; the smart contracts of the blockchain network include a power grid maintenance scheduling protocol and a power grid load balancing protocol.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

10. A computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images