Method for establishing, deriving and remodeling a phantom fidelity model of a power grid digital twin model

Abstract

This disclosure provides a method for establishing, evolving, and reshaping a biomimetic model of a power grid digital twin model. The method includes: establishing a biomimetic model based on polyvariable functions, high-fidelity functions, and adaptive change functions; processing operation and maintenance models and process data from different original scenarios to evolve the biomimetic model; and collecting operation and maintenance data from the target scenario to reshape the biomimetic model. This approach utilizes biological mimicry to establish a biomimetic model based on the digital twin model, allowing the complete digital twin model to be analogized to a basic biomimetic system. This generates a highly realistic information copy to create a mirrored virtual model for observation, prediction, and control of managed objects. Applying this model to the power grid security control system improves the responsiveness of the power grid's digital twin model and promotes the digitalization and intelligentization of the power grid.

Description

Technical Field

[0001] This disclosure relates to the field of model evolution technology for digital twin models of power grids, and in particular to a method for establishing, evolving, and reshaping a biomimetic model of a digital twin model of a power grid. Background Technology

[0002] In the context of the digital and information age, promoting comprehensive perception of power grid status, end-to-end online business operations, and comprehensive connectivity of operational data have become effective ways to achieve stable power grid operation, improve enterprise mechanisms, and build highly digitalized and intelligent energy internet enterprises. Digital twins, as an emerging and rapidly developing digital and information technology, provide a new approach to promoting comprehensive perception, networked connectivity, and stable operation of power grids. Power grid digital twins use digitalization as a carrier, establishing a mapping from real space to virtual space to achieve real-time perception of the status of equipment or systems in the real space, and feeding back data carrying instructions to guide their actions. Through the construction of a digital twin power grid system, power grid operation, management, and services move from the real to the virtual. Through modeling, simulation, interpretation, and manipulation in virtual space, the power grid can control the real, strengthening its self-perception, self-decision-making, and self-evolution capabilities. This supports the digital operation of various power grid businesses, revolutionizing traditional operating models and opening up new construction and management models for digital smart grids. It promotes the digital and intelligent transformation of power grids and is an inevitable stage and necessary path for building energy internet enterprises.

[0003] However, with the integration of digital twin technology into the power grid, it has been gradually discovered that the established power grid digital twin model has poor adaptability, rigid evolution mechanism, and outdated reshaping and evaluation methods. Therefore, there is a huge challenge in establishing a power grid digital twin evolution fidelity model. Summary of the Invention

[0004] This disclosure provides a method for establishing, evolving, and reshaping a biomimetic model of a power grid digital twin model. By utilizing the biomimetic phenomenon, a biomimetic model is established for application in the power grid security control system. This model is used for the observation, prediction, and control of controlled objects, thereby improving the responsiveness of the power grid's digital twin model and promoting the digitalization and intelligentization of the power grid.

[0005] According to a first aspect of this disclosure, a method for establishing, evolving, and reshaping a biomimetic model of a power grid digital twin is provided, comprising:

[0006] A digital twin model is established based on multivariable functions, high-fidelity functions, and adaptive change functions; information data is obtained from morphology, physics, and time to generate corresponding information models, and the corresponding information models are integrated into the digital twin model to construct a biomimetic fidelity model;

[0007] Process the operation and maintenance models and process data of different original scenarios to build dynamic multi-views; through virtual-real fusion and real-time tracking, update the operation and maintenance system or equipment information and derive a mimicry and fidelity model;

[0008] Collect operation and maintenance data of the target scene and extract feature data; calculate the distribution distance of feature data between the target scene and the original scene to obtain the feature dataset with the smallest distribution distance; analyze the feature dataset to obtain the change type of the target scene, and select a reconstruction strategy to reshape the mimicry model.

[0009] According to a second aspect of this disclosure, a device for mimicking a digital twin model of a power grid is provided, comprising:

[0010] The model building module establishes a digital twin model based on polymorphic functions, high-fidelity functions, and adaptive change functions; it acquires information data from morphology, physics, and time to generate corresponding information models, and integrates the corresponding information models into the digital twin model to construct a biomimetic fidelity model.

[0011] The model evolution module is used to process operation and maintenance models and process data from different original scenarios, build dynamic multi-views, update operation and maintenance system or equipment information through virtual-real fusion and real-time tracking, and evolve a realistic model.

[0012] The model reshaping module is used to collect operation and maintenance data of the target scene, extract feature data, calculate the distribution distance of feature data between the target scene and the original scene, and obtain the feature dataset with the smallest distribution distance; analyze the feature dataset to obtain the change type of the target scene, and select a reconstruction strategy to reshape the mimicry model.

[0013] According to a third aspect of this disclosure, an electronic device is provided. The electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the program to implement the method described above.

[0014] According to a fourth aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the methods as described in the first and / or second aspects of this disclosure.

[0015] The present invention employs a biomimetic model that utilizes biological biomimicry to establish a biomimetic model based on a digital twin model. The complete digital twin model can be analogized to a basic biomimetic system, generating a highly realistic information copy to establish a mirror virtual model for observation, prediction, and control of controlled objects. This model is then applied to the power grid security control system to improve the responsiveness of the power grid's digital twin model and promote the digitalization and intelligentization of the power grid.

[0016] It should be understood that the description in the Summary of the Invention is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0017] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. The drawings are provided for a better understanding of the invention and are not intended to limit the scope of this disclosure. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0018] Figure 1 A flowchart illustrating the establishment, evolution, and reshaping of the mimicry model according to an embodiment of this disclosure is shown;

[0019] Figure 2 A flowchart illustrating the geometric information model construction process of the biomimetic model according to an embodiment of this disclosure is shown.

[0020] Figure 3 A flowchart illustrating the physical information model construction process of the biomimetic fidelity model according to an embodiment of this disclosure is shown.

[0021] Figure 4 A flowchart illustrating the process information model construction of the mimicry-fidelity model according to an embodiment of this disclosure is shown.

[0022] Figure 5 A diagram illustrating a data integration method for a mimicry-fidelity model according to an embodiment of this disclosure is shown.

[0023] Figure 6 A diagram illustrating the evolution method of the mimicry-fidelity model according to an embodiment of this disclosure is shown;

[0024] Figure 7 A diagram illustrating a method for reshaping a biomimetic model according to an embodiment of this disclosure is shown.

[0025] Figure 8 A block diagram of a mimicry device according to an embodiment of the present disclosure is shown;

[0026] Figure 9 A block diagram of an exemplary electronic device capable of implementing the mimicry-fidelity model of the present disclosure is shown. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0028] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0029] This disclosure proposes the establishment, evolution, and reshaping of a mimicry-fidelity model for a digital twin model of a power grid. It is based on the integration of historical and updated data and the principle that the dead leaf butterfly can improve its survival chances by changing the color of its wings to match the environment.

[0030] Since mimicry is a biological process of seeking as much similarity as possible for personal gain—that is, after a mimic successfully imitates another organism, it pursues a function that can be defensive or offensive—this is similar to the concept of a digital twin model, which generates a highly realistic copy of information to create a mirrored virtual model for observation, prediction, and control of controlled objects. Therefore, inspired by the mimicry behavior of the dead leaf butterfly, a complete digital twin model can be likened to a basic mimicry system. The digital twin model can be likened to a mimic, the power grid object to the object to be simulated, and "defense and predation" to the system functions of the digital twin model. Therefore, when a digital twin model operates, it acquires relevant information and functions, striving for maximum similarity in geometric, physical, and scene information, while automatically adapting to changes based on processing conditions, ultimately engaging in "defense or predation."

[0031] The first aspect of this invention provides a method for establishing, evolving, and reshaping a biomimetic model of a power grid digital twin model, comprising the following steps:

[0032] A digital twin model is established based on multivariable functions, high-fidelity functions, and adaptive change functions; information data is obtained from morphology, physics, and time to generate corresponding information models, and the corresponding information models are integrated into the digital twin model to construct a biomimetic fidelity model;

[0033] Process the operation and maintenance models and process data of different original scenarios to build dynamic multi-views; through virtual-real fusion and real-time tracking, update the operation and maintenance system or equipment information and derive a mimicry and fidelity model;

[0034] Collect operation and maintenance data of the target scene and extract feature data; calculate the distribution distance of feature data between the target scene and the original scene to obtain the feature dataset with the smallest distribution distance; analyze the feature dataset to obtain the change type of the target scene, and select a reconstruction strategy to reshape the mimicry model.

[0035] The aforementioned mimicry-fidelity model is applied to the power grid security control system to observe, predict, and control the power grid security situation, thereby improving the system's intelligence and digitalization. Figure 1 As shown, it specifically includes the following steps:

[0036] S1: Establish a mimicry-fidelity model:

[0037] When establishing a mimicry-fidelity model, based on the mimicry phenomenon of the dead leaf butterfly, it is necessary to establish corresponding functional relationships that satisfy the variability of the object environment, the high fidelity of the object, and its sensitive adaptability. These are the object environment variability function, the high fidelity function, and the adaptive change function, respectively. Specifically,

[0038] 1) Establish the variable function of the object environment of the model:

[0039] The variability function ensures that the environmental information in the established power grid security control system model is almost completely similar to the surrounding environment and can change with changes in the surrounding environment, achieving a high degree of "fidelity" and "reproducibility." This requires comprehensive information acquisition and timely updates to information changes. Similar to the characteristic of the dead leaf butterfly adapting its morphology to different environmental changes, the high-fidelity evolutionary model of digital twins needs to address various application scenarios. Therefore, the model needs to be able to analyze the application scenarios implemented by the system. The key lies in the data component of the high-fidelity evolutionary model system having analysis and update functions. The following formula can be used:

[0040]

[0041] in: Represents an adaptive function for the environment. This represents the variation factor for different scenarios.

[0042] 2) Establish the high-fidelity function for the derived high-fidelity model:

[0043] A high-fidelity function ensures that the established digital twin model and the power grid security control system have a high degree of similarity in their reconstruction, and that the virtual entity closely mirrors the physical entity; the size ratio can be freely switched to ensure convenient simulation, but its morphological details cannot be changed to prevent distortion; similar to the high similarity characteristic of a mimic, the digital twin model should be as similar as possible to the physical entity, thus, the amount of information contained in the physical entity and the virtual entity should be as similar as possible. This can be achieved using the following formula:

[0044]

[0045]

[0046]

[0047] in: This represents the changes in the geometric shape of physical objects in the power grid. This represents the change in the physical state of physical objects in the power grid. This represents a geometrically adaptive change function that responds to geometric changes in an object. This represents a physical adaptive change function that responds to physical changes in the object.

[0048] 3) Establish an adaptive change function with decision-making capabilities for the derived high-fidelity model:

[0049] The adaptive change function possesses all the functionalities of a real-world object, especially the ability to adapt to environmental changes. This embodies the evolutionary function, which is the core of model evolution and updating. Evolving a high-fidelity model system requires specific analysis and updating capabilities to adapt to changes in different power grid scenarios and physical entities, thus adaptively altering its functionality. This can be achieved using the following formula:

[0050]

[0051] in, Indicates the scene change factor. This represents the functional change factor. This represents the algorithm's adaptive update function, used to update the algorithm.

[0052] A digital twin model is established based on the above functional relationships. The digital twin model acquires information data from the three dimensions of the power grid security control system: morphology, physicality, and time, generating corresponding geometric information models, physical information models, and process information models respectively. These information models are then integrated into the digital twin model to construct a biomimetic model.

[0053] Geometric information models are geometric information models of equipment in power grid scenarios, including static measurement models and static ideal models. For details, please refer to... Figure 2As shown, the geometric information model of the equipment consists of multiple basic equipment models, such as basic equipment model 1, 2...n. Each basic equipment model has a corresponding static measurement model and a static ideal model. The geometric information model is composed of the equation Geom = {Am, Dm}, where Pm represents the static ideal model, which is the ideal model of the power grid equipment when the equipment is not in operation; Dm represents the static measurement model, which is the measurement model of the power grid equipment when it is stationary. Combined feature data, independent feature data, and complex feature data are extracted from the static measurement model and the static ideal model, respectively. Based on the extracted complex feature data, combined feature data and feature data are extracted to establish a corresponding feature dataset.

[0054] Physical information models are used to reflect the physical characteristics of electrical equipment; see details below. Figure 3 As shown: The physical information model is composed of multiple physical models of devices, such as physical model 1, 2...n, including the functional parameters of many power devices. The composition information of physical information is as follows: PHYM={Mat,Str,Disa...}, where Mat represents the material information of the power grid equipment, such as material, grade, description and other information data; Str represents the structure and its principle, such as measurement, control, protection and other information data; Disa represents the defects of the power grid equipment, such as discoloration, cracks, heat generation and other information data.

[0055] The operational process information model primarily involves collecting operational information from various power grid devices during their use, as expressed in the formula Conm = Dis∪Tran∪Other, where Dis represents the collection of information during distribution network operation and maintenance, Tran represents the collection of information during transmission network operation and maintenance, and Other represents the collection of information during other operation and maintenance processes. (Refer to...) Figure 4 As shown, the operation and maintenance process of power distribution and transmission includes, in sequence: information collection, information dissemination, information replacement, information processing, information updating, and formation selection.

[0056] After constructing the geometric, physical, and process information models using the methods described above, the acquired information is integrated into the constructed data models using XML (Extensible Markup Language) data integration methods and stored in the digital twin storage system of the power grid security control system for future information processing. At this point, the simulated fidelity model of the power grid security control system is complete. The specific data integration steps are as follows: Figure 5 As shown:

[0057] Determine if the current data is the root node: If the node is not the root node, traverse upwards until the root node of the current data (the first row node); if the node is the root node, obtain the content data of the root node as the current data.

[0058] Determine if the current data exists: If it does not exist, obtain the current data and identify the corresponding data; if it exists, identify whether the current data is a device geometric information model, physical characteristic information model, or operation and maintenance process information model, obtain the current data type, and find and output the current data location.

[0059] Continuously analyze and process the relevant data of the current data, find the association table of the relevant data, and gradually store it in the digital twin mimicry model data of XML to complete the establishment of the digital twin mimicry fidelity model of the power grid security control system.

[0060] S2: Evolved Mimicry Fidelity Model

[0061] Reference Figure 6 The evolution process of the mimicry model shown is as follows: In the power grid security control system, the mimicry model is used to screen, preprocess, format, and analyze the operation and maintenance models and process data of different original scenarios, generate corresponding decision result data, such as data, icons, text, symbols, etc., combine and recombine the main elements and auxiliary elements, and recommend matching corresponding view objects, such as ARVO1, ARVO2, ... ARVOn, etc. for operators to choose from. Finally, a sufficient number of views are combined to construct a dynamic multi-view.

[0062] The system identifies the power grid operation and maintenance system or equipment information of the target scene through a camera or augmented reality (AR) glasses. After coordinate transformation, the physical entity data of the power grid equipment operation is obtained. The corresponding virtual entity data is obtained through a mimicry model. The corresponding dynamic multi-view is registered and displayed through gradient direction and attitude description. The process information of the power grid operation and maintenance system or equipment object in the target scene is updated and fused in real time through a multi-directional information tracking algorithm.

[0063] Leveraging the prediction module of the digital twin operation and maintenance system, real-time operation and maintenance status data is obtained based on historical operation and maintenance data. This data, combined with real-time data from multi-sensor devices and measurement equipment, outputs decision-making information including model and data change considerations, and recommends operation and maintenance strategies for the current fusion model and data model. Throughout the process, an update interval is set, and the data in the view is automatically updated based on the collected real-time data and personnel operation instructions. This automatically updates the process information of the power grid operation and maintenance system or equipment objects, displaying a view containing operation and maintenance change models and data, thus completing the evolution of the biomimetic model.

[0064] S3: Reconstructing a Faithful Model:

[0065] When the working scenario of the power grid security control system changes from the original scenario to the target scenario, a mimicry-fidelity model is reshaped, such as... Figure 7As shown, a small amount of operation and maintenance data of the target scenario is collected, preprocessed, and the operation and maintenance dataset of the target scenario is obtained.

[0066] Based on the operation and maintenance dataset of the target scenario, after fine-tuning and updating the mimicry model, the main features of the original operation and maintenance data of the original scenario are extracted to obtain the feature data Fa of the target scenario, which is then stored in the feature database of the model.

[0067] Based on the feature data Fa, the original algorithm model OM is matched from the algorithm model library. The distribution distance of the feature data between the target scene and the original scene is calculated to obtain the feature dataset with the smallest distribution distance. The data feature set is indexed in the algorithm model library and scene database in the mimicry model to obtain the original model and related scene operation and maintenance dataset in the algorithm model library.

[0068] Specifically, to address the problem of finding the most similar feature data Fa distributions between the new target scene and the original scene, the original algorithm model OM is matched from the algorithm model library. The maximum mean difference (MMD) metric is used to calculate the similarity of data distributions between the algorithm models of the target scene and the original scene, as shown in the formula:

[0069]

[0070] In the formula: z represents the function set, and x and y represent the feature datasets of the target scene and the original scene, respectively. This represents a mapping function used to map feature data to a high-dimensional space; it is calculated... The average of the two types of feature data is then calculated and differencing is performed to obtain... The average value on; then Maximizing the mean difference yields the maximum mean difference (MMD). The original algorithm model OM is derived from... The corresponding algorithm model is indexed from the library of scenario conditions.

[0071] When the original model is not fully applicable to the target scenario, it is necessary to analyze the type of change of the operation and maintenance data relative to the target scenario, select an appropriate reconstruction strategy from the algorithm model library to reconstruct the original algorithm model, obtain the algorithm model for the target scenario, and store the algorithm model in the algorithm model library; in addition, generate and store the algorithm model and operation and maintenance data in the operation and maintenance information dataset under the target scenario, and reshape the mimicry and fidelity model.

[0072] According to the embodiments of this disclosure, the following technical effects are achieved:

[0073] By utilizing the biomimicry phenomenon, a biomimicry-fidelity model is established based on the digital twin model. The complete digital twin model can be likened to a basic biomimicry system, which generates a highly realistic information copy to create a mirror virtual model for observation, prediction, and control of the controlled objects. This model is then applied to the power grid security control system to improve the responsiveness of the power grid's digital twin model and promote the digitalization and intelligentization of the power grid.

[0074] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this disclosure is not limited to the described order of actions, because according to this disclosure, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this disclosure.

[0075] The above is an introduction to the method embodiments. The following describes the solution described in this disclosure further through device embodiments.

[0076] Figure 8 A block diagram of a mimicry device 800 according to an embodiment of the present disclosure is shown. Figure 8 As shown, the mimicry device 800 includes:

[0077] The model building module 810 establishes a digital twin model based on multivariable functions, high-fidelity functions, and adaptive change functions; it acquires information data from morphology, physics, and time, generates corresponding information models, and integrates the corresponding information models into the digital twin model to construct a mimicry-fidelity model.

[0078] The model evolution module 820 is used to process operation and maintenance models and process data of different original scenarios, build dynamic multi-views, update operation and maintenance system or equipment information through virtual-real fusion and real-time tracking, and evolve a realistic model.

[0079] The model reshaping module 830 is used to collect operation and maintenance data of the target scene, extract feature data, calculate the distribution distance of feature data between the target scene and the original scene, and obtain the feature dataset with the smallest distribution distance; analyze the feature dataset to obtain the change type of the target scene, and select a reconstruction strategy to reshape the mimicry model.

[0080] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the described module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0081] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0082] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0083] Figure 9 A schematic block diagram of an electronic device 900 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0084] Electronic device 900 includes a computing unit 901, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 902 or a computer program loaded into random access memory (RAM) 903 from storage unit 908. The RAM 903 may also store various programs and data required for the operation of electronic device 900. The computing unit 901, ROM 902, and RAM 903 are interconnected via bus 904. An input / output (I / O) interface 905 is also connected to bus 904.

[0085] Multiple components in electronic device 900 are connected to I / O interface 905, including: input unit 906, such as keyboard, mouse, etc.; output unit 907, such as various types of displays, speakers, etc.; storage unit 908, such as disk, optical disk, etc.; and communication unit 909, such as network card, modem, wireless transceiver, etc. Communication unit 909 allows electronic device 900 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0086] The computing unit 901 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 901 performs the various methods and processes described above, such as the mimicry model building, evolution, and reshaping methods. For example, in some embodiments, the mimicry model building, evolution, and reshaping methods can be implemented as computer software programs tangibly contained in a machine-readable medium, such as storage unit 908. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 900 via ROM 902 and / or communication unit 909. When the computer program is loaded into RAM 903 and executed by the computing unit 901, one or more steps of the mimicry model building, evolution, and reshaping methods described above can be performed. Alternatively, in other embodiments, the computing unit 901 may be configured by any other suitable means (e.g., by means of firmware) to perform methods for establishing, evolving, and reshaping the biomimetic model.

[0087] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0088] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0089] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0090] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0091] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0092] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0093] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0094] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for establishing, evolving, and reshaping a biomimetic model of a power grid digital twin, characterized in that it includes: A digital twin model is established based on multivariable functions, high-fidelity functions, and adaptive change functions; among them, The following formula is used to establish the variability function of the object environment of the model: wherein: an adaptive function representing the environment, representing different scene variation factors; The high-fidelity function of the derived high-fidelity model is established using the following formula: wherein: represents a change in geometry of a grid physical object, represents a change in physical state of a grid physical object, represents a geometric adaptive change function to react to a change in geometry of an object, represents a physical adaptive change function to react to a change in physical state of an object; The following formula is used to establish the adaptive change function with decision-making capabilities for the derived high-fidelity model: in, Indicates the scene change factor. Indicates the functional change factor. This represents the algorithm's adaptive update function, used to update the algorithm. A digital twin model is established based on the above functional relationship; information data is obtained from morphology, physics and time to generate corresponding information models, and the corresponding information models are integrated into the digital twin model to construct a mimicry-fidelity model; Process the operation and maintenance models and process data of different original scenarios to build dynamic multi-views; through virtual-real fusion and real-time tracking, update the operation and maintenance system or equipment information and derive a mimicry and fidelity model; Collect operation and maintenance data of the target scene and extract feature data; calculate the distribution distance of feature data between the target scene and the original scene to obtain the feature dataset with the smallest distribution distance; analyze the feature dataset to obtain the change type of the target scene, and select a reconstruction strategy to reshape the mimicry model.

2. The method according to claim 1, characterized in that, The process of acquiring information data from morphology, physics, and time to generate a corresponding information model includes: Information data is acquired from the morphological dimension to generate a geometric information model; the geometric information model is divided into a static measurement model and a static ideal model; the static measurement model is the measurement model of the power grid equipment in a static process; the static ideal model is the rational model of the power grid equipment in a non-operating state; Information data is acquired from the physical dimension to generate a physical information model; the physical information model reflects the physical characteristics of power grid equipment. Information data is acquired from the time dimension to generate a process information model; the process information model is the collection of operational information during the use of power grid equipment.

3. The method according to claim 2, characterized in that, The step of integrating the corresponding information model into the digital twin model to construct a mimicry-fidelity model includes: Based on the data integration method, the geometric information model, the physical information model, and the process information model are integrated into the storage system of the digital twin model to construct a mimicry model.

4. The method according to claim 1, characterized in that, The construction of dynamic multi-view includes: By using a mimicry-fidelity model, we process and analyze the operation and maintenance models and process data of different original scenarios, generate corresponding decision data, match the corresponding views, and combine the multiple views to construct a dynamic multi-view.

5. The method according to claim 1, characterized in that, The process of updating operation and maintenance system or equipment information through virtual-real fusion and real-time tracking includes: Collect information on the power grid operation and maintenance system or equipment in the target scenario, obtain the corresponding mimicry model, register the mimicry model of the target scenario, and display the corresponding dynamic multi-view. Through tracking algorithms, update and merge the process information of the power grid operation and maintenance system or equipment in the target scenario in real time. The system outputs decision data through a biomimetic model, recommends current operational strategies, and automatically updates the view.

6. The method according to claim 1, characterized in that, The collection of operation and maintenance data for the target scenario, and the extraction of feature data, include: When transforming the original scenario into the target scenario, the operation and maintenance data of the target scenario is collected, preprocessed, and the operation and maintenance dataset of the target scenario is obtained. Based on the operation and maintenance dataset, after fine-tuning and updating the mimicry model, the main features of the original operation and maintenance data of the original scenario are extracted to obtain the feature data of the target scenario.

7. The method according to claim 6, characterized in that, The calculation of the distribution distance of feature data between the target scene and the original scene yields the feature dataset with the smallest distribution distance, including: Based on the feature data, the original algorithm model is matched from the algorithm model library. The distribution distance of the feature data between the target scene and the original scene is calculated to obtain the feature dataset with the smallest distribution distance. The data feature set is then indexed in the algorithm model library and scene database of the mimicry model to obtain the original model and related scene operation and maintenance dataset in the algorithm model library.

8. The method according to claim 7, characterized in that, The analysis of the feature dataset yields the change types of the target scene, and a reconstruction strategy is selected to reshape the mimicry-fidelity model, including: When the original model is not fully applicable to the target scenario, it is necessary to analyze the types of changes in the operation and maintenance data relative to the target scenario, select an appropriate reconstruction strategy to reconstruct the original algorithm model, obtain the algorithm model for the target scenario, and store the algorithm model in the algorithm model library; at the same time, store the algorithm model and operation and maintenance data in the operation and maintenance dataset.

9. A device for mimicking a digital twin model of a power grid, comprising: The model building module establishes digital twin models based on polyvariable functions, high-fidelity functions, and adaptive change functions; among them, The following formula is used to establish the variability function of the object environment of the model: in: Represents an adaptive function for the environment. Indicates the factors that change in different scenarios; The high-fidelity function of the derived high-fidelity model is established using the following formula: in: This represents the changes in the geometric shape of physical objects in the power grid. This represents the change in the physical state of physical objects in the power grid. This represents a geometrically adaptive change function that responds to geometric changes in an object. This represents a physical adaptive change function that reflects the physical changes of the object. The following formula is used to establish the adaptive change function with decision-making capabilities for the derived high-fidelity model: in, Indicates the scene change factor. Indicates the functional change factor. This represents the algorithm's adaptive update function, used to update the algorithm. A digital twin model is established based on the above functional relationship; information data is obtained from morphology, physics and time to generate corresponding information models, and the corresponding information models are integrated into the digital twin model to construct a mimicry-fidelity model; The model evolution module is used to process operation and maintenance models and process data from different original scenarios, build dynamic multi-views, update operation and maintenance system or equipment information through virtual-real fusion and real-time tracking, and evolve a realistic model. The model reshaping module is used to collect operation and maintenance data of the target scene, extract feature data, calculate the distribution distance of feature data between the target scene and the original scene, and obtain the feature dataset with the smallest distribution distance; analyze the feature dataset to obtain the change type of the target scene, and select a reconstruction strategy to reshape the mimicry model.

10. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

Images