Power distribution network symbiosis simulation system and method based on digital twinning

Abstract

The invention provides a power distribution network symbiotic simulation system and method based on digital twinning. The system comprises a power distribution network digital twinning simulation platform, a cloud edge hierarchical deployment collaborative architecture and a power distribution network terminal. The digital twinborn simulation platform for the power distribution network comprises a data layer, a model layer, a service layer and an application layer which are covered in sequence by taking a cloud platform as a bottom, and the cloud edge hierarchical deployment collaborative architecture performs hierarchical deployment according to different service functions of the power distribution network. According to the invention, through the constructed full-attribute isomorphic power distribution network digital twinborn simulation platform and the cloud edge hierarchical deployment collaborative architecture, the fusion demand of multi-scene multi-service flow is fully considered, through the symbiotic simulation technology, dynamic feedback and collaboration between the simulation system and a real system are realized, and the highly integrated and collaborative simulation system has the advantages of high simulation efficiency and high reliability. Various changes in the power distribution network can be quickly responded, and a solid guarantee is provided for safe and efficient operation of the power distribution network.

Description

Technical Field

[0001] The present invention relates to the technical field of digital twins for distribution networks, and in particular to a distribution network symbiosis simulation system and method based on digital twins. Background Art

[0002] The digital twin simulation platform for distribution networks is an effective tool for realizing the demonstration and application of digital twin technology for distribution networks. It can digitize all elements of the physical world of distribution networks, build a digital world with full attribute isomorphism, and realize real-time synchronization and virtual-real interaction between the physical world and the digital world of distribution networks. Symbiotic simulation essentially refers to a symbiotic dynamic feedback control system that cooperates with each other between the simulation system and the real system. At present, there are certain studies on the combination of digital twin technology and distribution network systems at home and abroad, but the construction and application of digital twin platforms based on symbiotic simulation in distribution networks are still insufficient.

[0003] Existing research on scenarios such as distribution network fault diagnosis and power supply restoration based on digital twin platforms mainly analyzes from the perspectives of energy flow, information flow, and control flow. There is a lack of analysis and verification of the integration of multiple scenarios and multiple business flows, and the requirements for real-time and concurrency of digital twin responses in different scenarios are not considered. The existing distribution network simulation auxiliary platform is difficult to meet the requirements of rapid virtual interaction of distribution network digital twins. In addition, although symbiotic simulation technology has been applied in many fields and has achieved certain development, there are few related applications in the distribution field. Summary of the invention

[0004] In order to solve the problems that the prior art lacks analysis and verification for the integration of multiple scenarios and multiple business flows, does not consider the requirements of different scenarios for the real-time and concurrency of digital twin responses, and is difficult to meet the requirements of the rapidity of virtual interaction of distribution network digital twins, the present invention proposes a distribution network digital twin simulation platform, which is connected to the cloud-edge hierarchical deployment collaborative architecture, including:

[0005] The data layer is used to receive real-time data sent by the cloud-edge hierarchical deployment collaborative architecture and analyze and process the real-time data;

[0006] The model layer is used to build a three-dimensional simulation model with electrical properties based on the real-time data analyzed and processed by the data layer and combined with the business rules of the distribution network to perform synchronous simulation of the distribution network;

[0007] The service layer is used to generate optimization strategies and analysis results by simulating different distribution network scenarios and various computing services based on the real-time data and three-dimensional simulation models of the data layer and model layer;

[0008] The application layer is used to control the distribution network based on the optimization strategies and analysis results obtained by the service layer through the resource management module, analysis and evaluation module, business control module and decision-making command module.

[0009] Preferably, the data layer includes:

[0010] A data storage module, used to store the real-time data sent by the cloud-edge hierarchical deployment collaborative architecture according to different data types;

[0011] Data sharing module, used to share the required data of each level synchronously or asynchronously;

[0012] Data analysis module, which is used to analyze real-time data using the Apache Flink stream processing framework and offline data using the computing engine Apache Spark;

[0013] The data processing module is used to process the real-time data sent by the received cloud-edge hierarchical deployment collaborative architecture by using data deduplication, missing value processing, outlier processing and data standardization.

[0014] Preferably, the model layer includes:

[0015] Physical model module, used to build the physical structure model of the distribution network and surrounding buildings;

[0016] Data model module, used to build entity location, connection relationship and equipment parameter model;

[0017] The knowledge model module is used to set various rules, specifications, processes and strategies in the distribution network business;

[0018] Virtual Model module, used to build three-dimensional simulation models with electrical properties.

[0019] Preferably, the service layer includes:

[0020] The power flow calculation module is used to determine the voltage and current of each node in the distribution network, as well as the distribution of active power, reactive power and voltage in the power grid;

[0021] Line loss calculation module, used to calculate the distribution law of power loss in the distribution network;

[0022] Fault calculation module, used to calculate and analyze distribution network equipment faults;

[0023] The reliability calculation module is used to quantitatively analyze and evaluate distribution network equipment failures and improve the reliability of the distribution network.

[0024] Preferably, the service layer also includes: an auxiliary support module; the auxiliary support module is used for interaction between the model layer and the application layer, and combines the flow calculation module, the line loss calculation module, the fault calculation module and the reliability calculation module to generate optimization strategies and preventive measures.

[0025] Preferably, the auxiliary support module includes:

[0026] Active and reactive power regulation unit, used to generate and optimize distributed power inverter control strategy and reactive voltage control strategy according to different working conditions of the distribution network;

[0027] Fault diagnosis unit, used to timely and accurately locate the feeder fault point, analyze the fault cause and fault impact range, and provide suggestions for fault prediction and prevention;

[0028] The power supply restoration unit is used to generate the optimal power supply restoration strategy based on the fault information through real-time adjustment and feedback mechanism after a fault occurs in the distribution network;

[0029] The risk prevention unit is used to quantitatively analyze various risk factors based on various risk scenarios in the operation process of the simulated distribution network feeder and the real-time data of the distribution network feeder, and to take timely preventive measures.

[0030] Preferably, the application layer includes:

[0031] Resource management module, which is used to optimize resource usage and visualize equipment management based on the physical entities and resources of the distribution network through asset management and the geographic spatial representation of the distribution network provided by the Geographic Information System (GIS);

[0032] Analysis and evaluation module, used to analyze and evaluate the operation status of the distribution network;

[0033] Business control module, used to provide support for the operation and management of the distribution network based on distribution network business;

[0034] The decision-making and command module is used to formulate optimization strategies based on the analysis and evaluation results of the distribution network operation status, simulate and predict the distribution network entities based on the digital twin technology, and analyze and evaluate the effects and risks of different decision-making plans.

[0035] Preferably, the simulation platform is based on a cloud platform.

[0036] The cloud platform is used to create network resources and environment, decompose the distribution network into multiple different service functions based on microservices combined with distributed computing, manage cluster services according to function types, manage gateways and call microservices through gateway cluster services, use remote call application program interface HTTP API to communicate between services, use relational database Mysql and remote dictionary service Redis to store main business data and cache data, use analysis and visualization platform Kibana and data collection engine Logstash to collect and analyze logs, and use message agent RabbitMQ to provide asynchronous communication and decoupling between multiple services.

[0037] Preferably, it also includes: a display layer;

[0038] The display layer is used to visualize, access and interact with the real-time status of the distribution network on a mobile terminal through a browser or micro-application based on a three-dimensional simulation model.

[0039] Based on the same inventive concept, the present invention also proposes a control method for a distribution network digital twin simulation platform, comprising:

[0040] Receive real-time data sent by the cloud-edge hierarchical deployment collaborative architecture, and analyze and process the real-time data;

[0041] Based on the analyzed and processed real-time data and combined with the business rules of the distribution network, a three-dimensional simulation model with electrical properties is constructed to perform synchronous simulation of the distribution network;

[0042] Based on real-time data and three-dimensional simulation models, by simulating different distribution network scenarios and various computing services, optimization strategies and analysis results for various distribution network businesses are generated, and the distribution network is controlled through resource management modules, analysis and evaluation modules, business control modules and decision-making and command modules.

[0043] Preferably, the receiving of real-time data sent by the cloud-edge hierarchical deployment collaborative architecture and analyzing and processing the real-time data includes:

[0044] Based on receiving real-time data sent by the cloud-edge hierarchical deployment collaborative architecture, the data is stored according to different data types and shared synchronously or asynchronously.

[0045] The real-time data sent by the received cloud-edge hierarchical deployment collaborative architecture is processed by using data deduplication, missing value processing, outlier processing and data standardization.

[0046] Preferably, the construction of a three-dimensional simulation model with electrical properties based on the analyzed and processed real-time data and in combination with the business rules of the distribution network includes:

[0047] Build a physical model based on the physical structure of the distribution network and surrounding buildings;

[0048] Build a data model based on the location, connection relationship and equipment parameters of the distribution network and surrounding buildings;

[0049] Based on the physical model and data model, combined with various pre-set rules, specifications, processes and strategies in the distribution network business, a three-dimensional simulation model with electrical properties is constructed.

[0050] Preferably, the multiple computing services include:

[0051] Power flow calculation, determining the voltage and current of each node in the distribution network, as well as the distribution of active power, reactive power and voltage in the power grid;

[0052] Line loss calculation, calculate the distribution law of power loss in the distribution network;

[0053] Fault calculation: calculate and analyze distribution network equipment faults;

[0054] Reliability calculation, quantitative analysis and evaluation of distribution network equipment failures to improve the reliability of the distribution network.

[0055] Preferably, the optimization strategies and analysis results for generating multiple services of the distribution network include:

[0056] Active and reactive power regulation: Generate and optimize distributed power inverter control strategy and reactive voltage control strategy according to different working conditions of the distribution network;

[0057] Fault diagnosis: timely and accurate location of feeder fault points, analysis of fault causes and fault impact range, and provision of fault prediction and prevention suggestions;

[0058] Power restoration: after a distribution network failure occurs, the optimal power restoration strategy is generated based on the fault information through real-time adjustment and feedback mechanism;

[0059] Risk prevention: Based on various risk scenarios during the operation of the simulated distribution network feeder, various risk factors are quantitatively analyzed in combination with the real-time data of the distribution network feeder, and preventive measures are taken in a timely manner.

[0060] Preferably, the automatic and intelligent control of the distribution network through the resource management module, the analysis and evaluation module, the business management and control module and the decision-making and command module includes:

[0061] Based on the physical entities and resources of the distribution network, through asset management and the geographic spatial representation of the distribution network provided by the Geographic Information System (GIS), we can optimize resource utilization and visualize equipment management, and provide support for the operation and management of the distribution network by the distribution network business;

[0062] Analyze and evaluate the operating status of the distribution network, provide optimization strategies based on the analysis and evaluation results, simulate and predict the distribution network entities based on digital twin technology, and analyze and evaluate the effects and risks of different decision-making plans.

[0063] Preferably, it also includes:

[0064] Use the cloud platform to create network resources and environment, and decompose the distribution network into multiple different service functions based on microservices combined with distributed computing. Perform cluster service management according to function type, manage gateways and call microservices through gateway cluster services, use remote call application interface HTTP API for communication between services, use relational database Mysql and remote dictionary service Redis to store main business data and cache data, use analysis and visualization platform Kibana and data collection engine Logstash to collect and analyze logs, and use message broker RabbitMQ to provide asynchronous communication and decoupling between multiple services.

[0065] Preferably, it also includes:

[0066] Based on the three-dimensional simulation model, the real-time status of the distribution network can be visualized, accessed and interacted on mobile terminals through browsers or micro-applications.

[0067] Based on the same inventive concept, the present invention also proposes a cloud-edge hierarchical deployment collaborative architecture, wherein the cloud-edge hierarchical deployment collaborative architecture is respectively communicated with the distribution network digital twin simulation platform and the distribution network terminal as described above, including:

[0068] Edge computing nodes are used to obtain real-time data collected by acquisition devices and send them to the edge;

[0069] Image repository, used to store different versions of applications on the edge or in the cloud.

[0070] The hierarchical collaborative module is used to obtain real-time data based on edge computing nodes, transmit it according to the needs of the distribution network digital twin simulation platform, and receive data feedback from the distribution network digital twin simulation platform; the different service functions of the distribution network are hierarchically deployed on the edge and cloud, the edge processes the data, the cloud analyzes and centrally controls the edge.

[0071] Preferably, the hierarchical collaboration includes:

[0072] The data hierarchical collaboration unit is used to persistently store and preprocess the real-time data obtained by the edge computing node based on the edge, and send the preprocessed real-time data to the distribution network digital twin simulation platform; the cloud receives the data fed back by the distribution network digital twin simulation platform, and backs up, aggregates and analyzes the data fed back by the distribution network digital twin simulation platform, and sends the aggregation and analysis results to the distribution network digital twin simulation platform;

[0073] The model analysis collaboration unit is used to build a physical model and a data model based on the edge aggregation and analysis results, and upload the physical model and the data model to the cloud in the form of data; the cloud builds a three-dimensional simulation model with electrical properties based on the physical model and the data model, combined with the business rules of the distribution network;

[0074] A service hierarchical coordination unit is used to upload service calls or service requests to the cloud based on the service registration information received by the edge and the service calls or service requests of the registered service users; the cloud authorizes, monitors and coordinates according to the received service calls or service requests;

[0075] The application hierarchical collaboration unit is used to pre-set alarm thresholds and message standards based on the edge and perform intelligent processing of application operations; the cloud performs hierarchical and classified management based on the different permissions and types of applications.

[0076] Based on the same inventive concept, the present invention also proposes a deployment method of a cloud-edge hierarchical deployment collaborative architecture, using the cloud-edge hierarchical deployment collaborative architecture as described above, the method comprising:

[0077] Obtain real-time data collected by the collection device and send it to the edge;

[0078] Mirror different versions of applications stored in the image repository to the edge or cloud.

[0079] Based on the real-time data obtained by the edge computing nodes, it is transmitted according to the needs of the distribution network digital twin simulation platform, and the data feedback from the distribution network digital twin simulation platform is received; the different service functions of the distribution network are hierarchically deployed on the edge and the cloud, the edge processes the data, and the cloud analyzes and centrally controls the edge.

[0080] Preferably, based on the real-time data obtained by the edge computing node, the data fed back by the distribution network digital twin simulation platform is transmitted according to the needs of the distribution network digital twin simulation platform; different service functions of the distribution network are hierarchically deployed on the edge and the cloud, the edge processes the data, the cloud analyzes and centrally controls the edge, including:

[0081] The real-time data obtained by the edge computing node is persistently stored and preprocessed based on the edge, and the preprocessed real-time data is sent to the distribution network digital twin simulation platform; the cloud receives the data fed back by the distribution network digital twin simulation platform, and backs up, aggregates and analyzes the data fed back by the distribution network digital twin simulation platform, and sends the aggregation and analysis results to the distribution network digital twin simulation platform;

[0082] The physical model and data model are built based on the edge aggregation and analysis results, and uploaded to the cloud in the form of data. The cloud builds a three-dimensional simulation model with electrical properties based on the physical model and data model and the business rules of the distribution network.

[0083] Based on the service registration information received by the edge and the service call or service request of the registered service user, the service call or service request is uploaded to the cloud; the cloud authorizes, monitors and coordinates according to the received service call or service request;

[0084] Alarm thresholds and message standards are pre-set on the edge, and application operations are processed intelligently; the cloud performs hierarchical and categorized management based on the different permissions and types of applications.

[0085] Based on the same inventive concept, the present invention also proposes a distribution network symbiosis simulation system based on digital twins, including a distribution network digital twin simulation platform, a cloud-edge hierarchical deployment collaborative architecture, and a distribution network terminal;

[0086] The cloud-edge hierarchical deployment collaborative architecture is respectively communicated with the distribution network digital twin simulation platform and the distribution network terminal;

[0087] The distribution network digital twin simulation platform adopts the distribution network digital twin simulation platform as described above;

[0088] The cloud-edge hierarchical deployment collaborative architecture adopts the cloud-edge hierarchical deployment collaborative architecture as described above.

[0089] Preferably, the system further comprises: an offline-online integrated distributed architecture;

[0090] The offline-online integrated distributed architecture is used to distribute the real-time data obtained by the cloud-edge hierarchical deployment collaborative architecture according to different data types, and classify and manage the data according to data characteristics.

[0091] Based on the same inventive concept, the present invention also proposes a distribution network symbiosis simulation method based on digital twins, which adopts the distribution network symbiosis simulation system based on digital twins as described above, including:

[0092] Based on the acquired real-time data, the processed real-time data is processed and combined with the business rules of the distribution network to build a three-dimensional simulation model with electrical properties;

[0093] Based on real-time data and three-dimensional simulation models, by simulating different distribution network scenarios and various computing services, optimization strategies and analysis results for various distribution network businesses are generated, and the distribution network is controlled through resource management modules, analysis and evaluation modules, business management and control modules, and decision-making and command modules.

[0094] Preferably, the processing based on the acquired real-time data includes:

[0095] The real-time data acquired by the edge in the cloud-edge hierarchical deployment collaborative architecture is persisted and preprocessed, and the preprocessed real-time data is sent to the data layer in the distribution network digital twin simulation platform;

[0096] The data layer stores the preprocessed real-time data according to different data types, shares the data required at each level in the distribution network digital twin simulation platform in a synchronous or asynchronous manner, and uses data deduplication, missing value processing, outlier processing and data standardization to process the stored data and send it to the cloud in the cloud-edge hierarchical deployment collaborative architecture.

[0097] Preferably, the processing of the real-time data in combination with the business rules of the power distribution network to construct a three-dimensional simulation model with electrical properties includes:

[0098] Based on the cloud-edge hierarchical deployment collaborative architecture, the processed real-time data received from the cloud is backed up, aggregated and analyzed through data synchronization;

[0099] Send the aggregation and analysis results to the model layer in the distribution network digital twin simulation platform to build physical models and data models;

[0100] Based on the physical model and data model, combined with various rules, specifications, processes and strategies in the pre-set distribution network business, a three-dimensional simulation model with electrical properties is constructed;

[0101] The physical model includes: the physical structure of the distribution network and surrounding buildings;

[0102] The data model includes: the location, connection relationship and equipment parameters of the distribution network and surrounding buildings.

[0103] Preferably, the physical model and the data model are deployed at the edge in the cloud-edge hierarchical deployment collaborative architecture; the edge in the cloud-edge hierarchical deployment collaborative architecture is responsible for various rules, specifications, processes and policies in the pre-set distribution network business, and constructs a three-dimensional simulation model with electrical properties;

[0104] Preferably, the generation of optimization strategies and analysis results of various services of the distribution network based on real-time data and a three-dimensional simulation model by simulating different distribution network scenarios and various computing services includes:

[0105] Based on the three-dimensional simulation model, the power flow calculation, line loss calculation, fault calculation and reliability calculation provided by the service layer in the distribution network digital twin simulation platform are adopted. Combined with the real-time data of the distribution network and simulation of different distribution network scenarios, optimization strategies and preventive measures for various distribution network businesses are generated.

[0106] Preferably, the optimization strategy and preventive measures for generating multiple services of the distribution network include:

[0107] Active and reactive power regulation: Generate and optimize distributed power inverter control strategy and reactive voltage control strategy according to different working conditions of the distribution network;

[0108] Fault diagnosis: timely and accurate location of feeder fault points, analysis of fault causes and fault impact range, and provision of fault prediction and prevention suggestions;

[0109] Power restoration: after a distribution network failure occurs, the optimal power restoration strategy is generated based on the fault information through real-time adjustment and feedback mechanism;

[0110] Risk prevention: Based on various risk scenarios during the operation of the simulated distribution network feeder, various risk factors are quantitatively analyzed in combination with the real-time data of the distribution network feeder, and preventive measures are taken in a timely manner.

[0111] Preferably, the automation and intelligent control of the distribution network through resource management, analysis and evaluation, business management and control, and decision-making and command includes:

[0112] Based on the physical entities and resources of the distribution network, through asset management and the geographic spatial representation of the distribution network provided by the Geographic Information System (GIS), we can optimize resource utilization and visualize equipment management, and provide support for the operation and management of the distribution network by the distribution network business;

[0113] Analyze and evaluate the operating status of the distribution network, provide optimization strategies based on the analysis and evaluation results, simulate and predict the distribution network entities based on digital twin technology, and analyze and evaluate the effects and risks of different decision-making plans.

[0114] Preferably, it also includes:

[0115] Based on the three-dimensional simulation model, the real-time status of the distribution network can be visualized, accessed and interacted on mobile terminals through browsers or micro-applications.

[0116] Preferably, it also includes:

[0117] Based on the edge in the cloud-edge hierarchical deployment collaborative architecture, the service registration information and service calls or service requests of registered service users are received, and the service calls or service requests are uploaded to the cloud. The cloud authorizes, monitors and coordinates based on the received service calls or service requests.

[0118] Preferably, it also includes:

[0119] Based on the edge in the cloud-edge hierarchical deployment collaborative architecture, alarm thresholds and message standards are pre-set, and application operations are processed intelligently. The cloud performs hierarchical and classified management based on the different permissions and types of applications.

[0120] Based on the same inventive concept, the present invention also proposes a computer device, comprising: at least one processor and a memory;

[0121] The memory is used to store one or more programs;

[0122] When the one or more programs are executed by the at least one processor, the control method of the distribution network digital twin simulation platform, the deployment method of the cloud-edge hierarchical deployment collaborative architecture, or the distribution network symbiosis simulation method based on digital twins as described above are implemented.

[0123] Based on the same inventive concept, the present invention also proposes a computer-readable storage medium on which a computer program is stored. When the computer program is executed, it implements the control method of the distribution network digital twin simulation platform, the deployment method of the cloud-edge hierarchical deployment collaborative architecture, or the distribution network symbiosis simulation method based on digital twins as described above.

[0124] Compared with the prior art, the present invention has the following beneficial effects:

[0125] The present invention proposes a distribution network digital twin simulation platform, which is connected to a cloud-edge hierarchical deployment collaborative architecture, including: a data layer, which is used to receive real-time data sent by the cloud-edge hierarchical deployment collaborative architecture, and analyze and process the real-time data; a model layer, which is used to build a three-dimensional simulation model with electrical properties based on the real-time data analyzed and processed by the data layer, combined with the business rules of the distribution network, and synchronously simulate the distribution network; a service layer, which is used to generate optimization strategies and analysis results by simulating different distribution network scenarios and multiple computing services according to the real-time data and three-dimensional simulation models of the data layer and the model layer; an application layer, which is used to control the distribution network through a resource management module, an analysis and evaluation module, a business control module, and a decision-making command module based on the optimization strategies and analysis results obtained by the service layer. The present invention realizes the real-time synchronization and virtual-real interaction between the physical world and the digital world through digital twin technology, and improves the comprehensive intelligent management level of the distribution network through the generated optimization strategies and analysis results, so as to meet the high performance and high concurrency requirements of the distribution network scenario.

[0126] The present invention proposes a cloud-edge hierarchical deployment collaborative architecture, which is respectively connected to the distribution network digital twin simulation platform and the distribution network terminal in communication, including: edge computing nodes, used to obtain real-time data collected by the acquisition equipment and send it to the edge; image warehouse, used to mirror the stored different versions of the application to the edge or cloud; hierarchical collaboration, used to receive data fed back by the distribution network digital twin simulation platform based on the real-time data obtained by the edge computing node and transmit it according to the needs of the distribution network digital twin simulation platform; hierarchical deployment of different service functions of the distribution network on the edge and cloud, the edge processes data, and the cloud analyzes and centrally controls the edge. The present invention achieves the best operating effect through hierarchical collaborative scheduling, unified deployment and management of various resources, and realizes elastic expansion and high-availability architecture, meeting the requirements of rapid interaction between the distribution network and the simulation model.

[0127] The present invention proposes a distribution network symbiotic simulation method and system based on digital twins, including a distribution network digital twin simulation platform, a cloud-edge hierarchical deployment collaborative architecture, and a distribution network terminal; based on the acquired real-time data, the real-time data is processed, and the processed real-time data is combined with the business rules of the distribution network to construct a three-dimensional simulation model with electrical properties; based on the real-time data and the three-dimensional simulation model, different distribution network scenarios and multiple computing services are simulated to generate optimization strategies and analysis results for multiple businesses of the distribution network, and the distribution network is controlled through a resource management module, an analysis and evaluation module, a business management module, and a decision-making command module. The present invention fully considers the integration requirements of multiple scenarios and multiple business flows through the constructed full-attribute isomorphic distribution network digital twin simulation platform and cloud-edge hierarchical deployment collaborative architecture, and realizes dynamic feedback and collaboration between the simulation system and the real system through symbiotic simulation technology. This highly integrated and collaborative simulation system can quickly respond to various changes in the distribution network, providing a solid guarantee for the safe and efficient operation of the distribution network.

[0128] The present invention also breaks through the limitations of traditional distribution network simulation auxiliary platforms, and builds a twin high-performance and high-concurrency cloud platform structure based on Spring Cloud (an ordered collection of a series of frameworks). Through the integration of multiple scenarios and multiple business flows, the distribution network can be analyzed and verified more accurately and efficiently in complex scenarios, meeting the real-time response requirements of digital twins in different scenarios, and providing new ideas and methods for the intelligent management of distribution networks. BRIEF DESCRIPTION OF THE DRAWINGS

[0129] Figure 1 A schematic diagram of the structure of the digital twin simulation platform for the distribution network provided by the present invention;

[0130] Figure 2 A schematic diagram of the architecture of the cloud platform of the distribution network digital twin simulation platform provided by the present invention;

[0131] Figure 3 A schematic diagram of the cloud-edge hierarchical deployment collaborative architecture provided by the present invention;

[0132] Figure 4 A schematic diagram of the structure of the distribution network symbiosis simulation system based on digital twin provided by the present invention.

[0133] Figure 5 A schematic diagram of an offline-online integrated distributed architecture of a digital twin-based distribution network symbiosis simulation system provided by the present invention;

[0134] Figure 6 Schematic diagram of electronic equipment for the distribution network symbiosis simulation method based on digital twin provided by the present invention. DETAILED DESCRIPTION

[0135] The specific embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings.

[0136] Embodiment 1:

[0137] like Figure 1 As shown, the present invention proposes a distribution network digital twin simulation platform, which is connected to a cloud-edge hierarchical deployment collaborative architecture and includes: a data layer, a model layer, a service layer, and an application layer;

[0138] The data layer is used to receive real-time data sent by the cloud-edge hierarchical deployment collaborative architecture, and analyze and process the real-time data;

[0139] The model layer is used to construct a three-dimensional simulation model with electrical properties based on the real-time data analyzed and processed by the data layer and combined with the business rules of the distribution network to perform synchronous simulation of the distribution network;

[0140] The service layer is used to generate optimization strategies and analysis results by simulating different distribution network scenarios and multiple computing services based on the real-time data of the data layer and the model layer and the three-dimensional simulation model;

[0141] The application layer is used to perform automated and intelligent control of the distribution network based on the optimization strategies and analysis results obtained by the service layer through the resource management module, the analysis and evaluation module, the business management and control module, and the decision-making and command module.

[0142] The data layer includes:

[0143] A data storage module, used to store the real-time data sent by the cloud-edge hierarchical deployment collaborative architecture according to different data types;

[0144] Data sharing module, used to share the required data of each level synchronously or asynchronously;

[0145] Data analysis module, which is used to analyze real-time data using the Apache Flink stream processing framework and offline data using the computing engine Apache Spark;

[0146] The data processing module is used to process the real-time data sent by the received cloud-edge hierarchical deployment collaborative architecture by using data deduplication, missing value processing, outlier processing and data standardization.

[0147] Specifically, the data layer realizes data sharing, data processing, data storage and data analysis of the distribution network digital twin based on network protocols such as Hypertext Transfer Protocol HTTP and Transmission Control Protocol TCP. Data can be transmitted to different application modules in real time or in batches, supporting functions such as power flow calculation, line loss calculation, fault calculation, reliability calculation and application chart display.

[0148] In the data processing stage, methods such as data deduplication, missing value processing, outlier processing and data standardization are applied. Data deduplication uses Bloom filters to ensure data uniqueness; missing value processing uses linear interpolation to complete data; outlier processing uses the Isolation Forest algorithm to identify and process abnormal data; data standardization normalizes the data to a range of 0 to 1. After these processes, the original data is converted into a format suitable for distribution network digital twin applications to ensure data accuracy, completeness and consistency.

[0149] Data storage mainly uses relational database Mysql as the main data storage, uses distributed document storage database MongoDB to store semi-structured and unstructured data, and uses time series database InfluxDB to store time series data. Data partitioning is done by time dimension, and B-tree index is established to optimize query performance. Through the open source data warehouse Apache Hive to store and manage historical data and large-scale data, efficient OLAP online analytical processing query and big data analysis capabilities are provided.

[0150] In the data analysis phase, real-time data analysis uses the Apache Flink open source stream processing framework to perform real-time power flow calculations, line loss calculations, fault calculations, and reliability calculations, and generate real-time reports and warnings. Offline data analysis uses the computing engine Apache Spark for batch processing, supporting in-depth analysis such as trend analysis, predictive analysis, and pattern recognition. The data analysis results are displayed through the open source data visualization tool Grafana, which generates custom reports to provide intuitive support for decision-making. The entire data processing, storage, and analysis process is seamlessly connected to ensure efficient and reliable data flow in the distribution network digital twin application.

[0151] The model layer includes:

[0152] Physical model module, used to build the physical structure model of the distribution network and surrounding buildings;

[0153] Data model module, used to build entity location, connection relationship and equipment parameter model;

[0154] The knowledge model module is used to set various rules, specifications, processes and strategies in the distribution network business;

[0155] Virtual Model module, used to build three-dimensional simulation models with electrical properties.

[0156] Specifically, the model layer includes physical models, data models, knowledge models and virtual models. Physical models and data models include entities such as equipment, lines, bridges, buildings, and their locations, connections, power consumption, load operation and other parameter information; knowledge models refer to various information and rules in the power distribution business, including equipment maintenance specifications, fault diagnosis rules, operating procedures, and optimization strategies. In addition, it also includes expert systems and rule-based systems for intelligent analysis and fault prevention of distribution network scenarios; virtual models refer to the three-dimensional digital representation and simulation model of the distribution network, including static structures (such as the geometry of lines and equipment) and dynamic behaviors (such as time-varying parameters such as current, voltage, and temperature). These models can simulate and predict the operating status of the distribution network, and perform flow analysis, load forecasting, fault simulation, etc.

[0157] The service layer includes:

[0158] The power flow calculation module is used to determine the voltage and current of each node in the distribution network, as well as the distribution of active power, reactive power and voltage in the power grid;

[0159] Line loss calculation module, used to calculate the distribution law of power loss in the distribution network;

[0160] Fault calculation module, used to calculate and analyze distribution network equipment faults;

[0161] The reliability calculation module is used to quantitatively analyze and evaluate distribution network equipment failures and improve the reliability of the distribution network.

[0162] The service layer receives data and information from the data layer and the model layer, performs real-time prediction calculations, and provides various algorithm services including power flow calculations, line loss calculations, fault calculations, and reliability calculations. It determines the operating status of the entire system based on the specific distribution network structure and operating conditions, including the voltage (amplitude and phase angle) of each node, power distribution in the network, and power loss data.

[0163] The service layer also includes: an auxiliary support module; the auxiliary support module is used for interaction between the model layer and the application layer, and combines the power flow calculation module, the line loss calculation module, the fault calculation module and the reliability calculation module to generate optimization strategies and preventive measures.

[0164] The auxiliary support module includes:

[0165] Active and reactive power regulation unit, used to generate and optimize distributed power inverter control strategy and reactive voltage control strategy according to different working conditions of the distribution network;

[0166] Fault diagnosis unit, used to timely and accurately locate the feeder fault point, analyze the fault cause and fault impact range, and provide suggestions for fault prediction and prevention;

[0167] The power supply restoration unit is used to generate the optimal power supply restoration strategy based on the fault information through real-time adjustment and feedback mechanism after a fault occurs in the distribution network;

[0168] The risk prevention unit is used to quantitatively analyze various risk factors based on various risk scenarios in the operation process of the simulated distribution network feeder and the real-time data of the distribution network feeder, and to take timely preventive measures.

[0169] Specifically, the active and reactive power regulation unit includes distributed power inverter control and reactive voltage control. Distributed power inverter control refers to the real-time generation of distributed power inverter control strategies for different working conditions and requirements, including voltage, frequency, power and other aspects of control, to ensure that the inverter can operate stably under various conditions, by setting upper and lower limit adjustment parameters, recalculating the distribution network flow, outputting to the digital twin platform, and displaying it in the three-dimensional simulation model; reactive voltage control refers to the use of different reactive voltage control strategies, including capacitors, reactors, static reactive compensators, etc., to evaluate the impact of each control strategy on the grid voltage stability, and find the optimal control scheme, and output the real-time voltage control results to the digital twin platform and three-dimensional model for display. For distributed power inverter control, the system generates optimized control strategies in real time according to different working conditions and requirements, including precise regulation of voltage, frequency and power. By setting upper and lower limit adjustment parameters and combining with recalculating the distribution network flow, the optimized control results are output to the digital twin platform and three-dimensional simulation model to achieve a comprehensive display and intelligent management of the distribution network operation status. In terms of reactive voltage control, the system adopts a variety of advanced reactive voltage control strategies, such as capacitors, reactors and static VAR compensators. By evaluating the impact of each strategy on the voltage stability of the distribution network and using the optimization algorithm to find the optimal control solution, the system can adjust the control parameters in real time, according to the adjusted load value PQ, input it into the target feeder at the same time, call the active and reactive adjustment algorithm, recalculate the PQIV value of each node, and also output the real-time voltage control results to the digital twin platform and three-dimensional model in the form of XML as the adjusted output strategy, fully displaying the dynamic changes in the operation status of the distribution network.

[0170] The fault diagnosis unit is used to locate the feeder fault point in a timely and accurate manner, analyze the possible causes of the fault and the scope of influence, and provide suggestions for fault prediction and prevention. Through the interaction of two-dimensional topology and three-dimensional scenes, different fault scenarios are simulated, covering various situations such as line short circuit, equipment damage, load abnormality, etc., and single-phase grounding, double-phase grounding, three-phase circuit breaker, phase-to-phase short circuit and other problems are quickly identified. On this basis, the fault repair scenario is simulated, and a large amount of simulation data, including historical data and fault experience, is generated through the digital twin platform. The recommended measures for fault prevention are provided to the operation and maintenance personnel through analysis algorithm prediction. The power flow calculation is the basis of fault diagnosis. By equivalentizing the power supply, switchgear, line, terminal load and other nodes in the distribution network feeder, the input is detected to be correct and the current input is ensured for each branch line; each device is classified and calculated uniformly, and the voltage, current, active power, reactive power and load status of the head and end of each phase of each device are output; the PQIV of the main load equipment is analyzed to determine whether it is reasonable, and the calculation is iterated until the voltage function of each node of the target feeder converges. The overall input and output uses XML as the interactive format, which corresponds the connection relationship in the actual distribution network one by one, and maps the output results to the digital twin platform and three-dimensional simulation model.

[0171] The power supply recovery unit is used to promptly re-establish power supply after a distribution network failure occurs to meet the power demand of users. According to the real-time fault information, the corresponding main line and branch line circuit breakers are found to isolate the fault, the number of power-off devices and loads caused by the fault is calculated, and the branch line that can restore power supply is found to generate a power transfer plan, which is output to the digital twin platform and three-dimensional simulation model. Current, voltage, frequency and other data are collected in real time from the sensors and monitoring equipment of the distribution network, and pre-processed and fault feature extracted. With these data, the system can quickly detect and locate faults and accurately identify the fault locations of the main line and branch line. Subsequently, the system evaluates the impact of the fault on the distribution network, simulates the number and location of power-off devices and loads using the power flow calculation algorithm, and establishes a list of power-off devices to provide a basis for the subsequent power supply recovery strategy generation; the system generates a variety of alternative power supply recovery paths, and applies a multi-objective optimization algorithm to consider factors such as the fault impact range, power supply capacity, and load balance, so as to select the optimal recovery strategy. The optimal recovery plan is dynamically optimized through real-time adjustment and feedback mechanisms to ensure that the normal power consumption of other loads is not affected during the power supply process. Finally, the system outputs the optimized restoration plan, including detailed information such as restoration path, power supply equipment, and power flow calculation results. These data are not only used to support operators’ decision-making, but also integrated into the digital twin platform and 3D simulation model to achieve real-time monitoring and visualization of the entire power restoration process.

[0172] The risk prevention unit is used to help operation and maintenance personnel to timely discover potential risks in the distribution network. By combining simulation and real-time data analysis, it quantitatively analyzes different risk factors, including weather changes, equipment failures, human operating errors and other factors, evaluates their possible impact on the operation of the distribution network, and evaluates their severity and possible scope of impact, providing timely warning information for operation and maintenance personnel, and specifically displays it in the three-dimensional simulation model. Specifically, the risk prevention module simulates various risk scenarios in the operation of the distribution network feeder, including weather changes, equipment failures, human operating errors and other factors, supports manual input and real-time detection, quantitatively analyzes risk factors, combines the real-time flow data of the distribution network feeder, generates the overload and overvoltage conditions of each device, and updates them to the three-dimensional simulation model, and clearly displays the risks in the distribution network scenario in 3D visualization, so that operation and maintenance personnel can take preventive measures in time.

[0173] The application layer includes:

[0174] Resource management module, which is used to optimize resource usage and visualize equipment management based on the physical entities and resources of the distribution network through asset management and the geographic spatial representation of the distribution network provided by the Geographic Information System (GIS);

[0175] Analysis and evaluation module, used to analyze and evaluate the operation status of the distribution network;

[0176] Business control module, used to provide support for the operation and management of the distribution network based on distribution network business;

[0177] The decision-making and command module is used to formulate optimization strategies based on the analysis and evaluation results of the distribution network operation status, simulate and predict the distribution network entities based on the digital twin technology, and analyze and evaluate the effects and risks of different decision-making plans.

[0178] Specifically, the application layer includes controlling load, regulating voltage, optimizing operation mode, etc., to realize automation and intelligence of the distribution network.

[0179] The resource management module is responsible for the comprehensive management of all physical entities and resources in the distribution network. This includes detailed recording and tracking of equipment, lines, bridges, and buildings, and managing their status, location, connection relationships, and performance parameters. This module also covers asset management, which optimizes resource usage by maintaining asset ledgers and implementing asset lifecycle management (such as procurement, maintenance, and scrapping). In addition, the geographic information system (GIS) provides a geospatial representation of the distribution network to help visualize management and equipment positioning, and improve the efficiency and accuracy of asset management.

[0180] The analysis and evaluation module is used to systematically analyze and evaluate the operating status of the distribution network. This module includes load analysis to understand and predict load demand; power quality monitoring to evaluate parameters such as voltage, current and frequency to ensure power quality; fault analysis to identify fault modes through historical data and provide diagnostic and prediction functions; and energy efficiency evaluation to help identify and optimize energy use.

[0181] The business control module provides operation and management support for the distribution network to ensure its safe and stable operation. This module includes intelligent dispatching management to optimize the allocation of power resources; real-time monitoring to promptly detect and handle operational anomalies; equipment maintenance to develop preventive maintenance plans and monitor equipment health; and emergency management to develop and implement emergency plans to improve the ability to respond to emergencies.

[0182] The decision-making and command module provides a powerful decision-making support and command platform for senior management. This module integrates operation data and analysis results to help formulate optimization strategies; provides unified command and dispatch to support rapid response; reports and visualization tools generate detailed operation reports and charts to provide management with intuitive operation status and trend display; prediction and simulation functions use digital twin technology to simulate and predict the distribution network and evaluate the effects and risks of different decision-making plans.

[0183] The present application proposes a distribution network digital twin simulation platform, which is based on a cloud platform;

[0184] The cloud platform is used to create network resources and environment, decompose the distribution network into multiple different service functions based on microservices combined with distributed computing, manage cluster services according to function types, manage gateways and call microservices through gateway cluster services, use remote call application program interface HTTP API to communicate between services, use relational database Mysql and remote dictionary service Redis to store main business data and cache data, use analysis and visualization platform Kibana and data collection engine Logstash to collect and analyze logs, and use message agent RabbitMQ to provide asynchronous communication and decoupling between multiple services.

[0185] Specifically, Figure 2As shown, the cloud platform selects AWS Amazon as the cloud service provider, builds EC2 Amazon Elastic Compute Cloud instances as the backend servers, configures VPC virtual private cloud networks, creates network resources such as subnets and routing tables, and configures security groups. It uses the managed relational database Amazon RDS service to create relational database Mysql and time series database InfluxDB to store the core data of the distribution network twin system. Based on the cloud platform, the efficiency of distributed computing is utilized, and the microservice architecture is used to decompose the distribution network service into multiple small applications, including distribution network twin services, graph model integration services, and risk prevention services. Nacos (Dynamic Naming and Configuration Service, dynamic service discovery, configuration management and service management platform) is used as the registration center middleware to realize service discovery and configuration management. The Feign declarative service remotely calls the application program interface HTTP API for communication between services. The Gateway gateway manages and calls microservices, and the relational database Mysql and the remote dictionary service Redis are used to store data. The main service data is managed by the relational database Mysql cluster, and the remote dictionary service Redis is used as a cache database to store frequently accessed data to achieve unified microservice data management.

[0186] Based on the cloud platform, a micro-application functional system for distribution network business is also built, using digital twin technology to create accurate, dynamic and interactive virtual models for key equipment in the distribution network (such as transformers, switches, protection devices, etc.). Through the real-time data interface, the virtual model is ensured to be synchronized with the operating status, parameters and performance data of the actual equipment. Furthermore, the micro-application obtains the equipment status data from the three-dimensional simulation model in real time, including key parameters such as current, voltage, temperature, and power. Provide an intuitive and user-friendly monitoring interface to display equipment status, performance indicators and operating trends, and support remote real-time monitoring and operation. Through the micro-application interface, remote equipment control and operation, such as switch control, parameter adjustment and fault recovery instructions, are realized. Based on the SpringCloud framework microservice construction method, data communication and transaction rollback between gateways, registration centers and services are realized, including risk prevention, fault diagnosis, power supply recovery, voltage control and other service modules, to realize the edge micro-application expansion of the distribution network twin platform.

[0187] like Figure 1 As shown, a distribution network digital twin simulation platform proposed in the present application also includes: a display layer;

[0188] The display layer is used to visualize, access and interact with the real-time status of the distribution network on a mobile terminal through a browser or micro-application based on a three-dimensional simulation model.

[0189] Specifically, a display layer is built based on the browser / server architecture B / S (Browser / Server), and the front-end page browser display and mobile software APP micro-application display are used. The back-end is built with a Java microservice framework to provide various digital twin services. The three-dimensional simulation model is packaged into WebGL (Web Graphics Library, a 3D drawing protocol) format and embedded in the front-end page, and displayed on the large screen through the browser. Through the digital twin technology, the actual feeders and environment of the distribution network are fully presented in the digital virtual world, and accessed and interacted through the Internet or other terminal devices; the digital model of the distribution network is combined with the mobile phone application, and the three-dimensional scene, equipment information, operation status and other data of the distribution network are displayed on the mobile phone, so that users can clearly see the real-time status of the distribution network through the mobile phone screen, and understand the operation status and related data of the equipment.

[0190] The digital twin simulation platform for distribution network proposed in the present invention adopts computer technologies such as cloud computing, distributed computing, and microservice architecture. With cloud platform as the base, it proposes a high-performance and high-concurrency technical architecture based on cloud, microservice, and Internet, and builds an open and scalable digital twin simulation platform architecture for distribution network, covering data layer, model layer, service layer, application layer, and display layer. Under the high-performance architecture of cloud platform, each layer is connected from bottom to top, and data is passed from the underlying infrastructure through data analysis and processing, data sharing interface, model construction, algorithm calculation and other processes to the top application layer. It proposes a high-performance and high-concurrency technical architecture, a method for rapid implementation of digital twin virtual interaction, and an agile construction method for microservices and micro-applications, and on this basis, focuses on supporting scenarios for typical comprehensive auxiliary decision-making such as distribution network fault analysis and power supply restoration.

[0191] Embodiment 2:

[0192] Based on the same inventive concept, the present application also proposes a control method for a distribution network digital twin simulation platform, including:

[0193] Receive real-time data sent by the cloud-edge hierarchical deployment collaborative architecture, and analyze and process the real-time data;

[0194] Based on the analyzed and processed real-time data and combined with the business rules of the distribution network, a three-dimensional simulation model with electrical properties is constructed to perform synchronous simulation of the distribution network;

[0195] Based on real-time data and three-dimensional simulation models, by simulating different distribution network scenarios and various computing services, optimization strategies and analysis results for various distribution network businesses are generated, and the distribution network is controlled through resource management modules, analysis and evaluation modules, business control modules and decision-making and command modules.

[0196] The receiving real-time data sent by the cloud-edge hierarchical deployment collaborative architecture and analyzing and processing the real-time data includes:

[0197] Based on receiving real-time data sent by the cloud-edge hierarchical deployment collaborative architecture, the data is stored according to different data types and shared synchronously or asynchronously.

[0198] The real-time data sent by the received cloud-edge hierarchical deployment collaborative architecture is processed by using data deduplication, missing value processing, outlier processing and data standardization.

[0199] The three-dimensional simulation model with electrical properties is constructed based on the analyzed and processed real-time data and combined with the business rules of the distribution network, including:

[0200] Build a physical model based on the physical structure of the distribution network and surrounding buildings;

[0201] Build a data model based on the location, connection relationship and equipment parameters of the distribution network and surrounding buildings;

[0202] Based on the physical model and data model, combined with various pre-set rules, specifications, processes and strategies in the distribution network business, a three-dimensional simulation model with electrical properties is constructed.

[0203] The various computing services include:

[0204] Power flow calculation, determining the voltage and current of each node in the distribution network, as well as the distribution of active power, reactive power and voltage in the power grid;

[0205] Line loss calculation, calculate the distribution law of power loss in the distribution network;

[0206] Fault calculation: calculate and analyze distribution network equipment faults;

[0207] Reliability calculation, quantitative analysis and evaluation of distribution network equipment failures to improve the reliability of the distribution network.

[0208] The optimization strategy and analysis results for generating multiple services of the distribution network include:

[0209] Active and reactive power regulation: Generate and optimize distributed power inverter control strategy and reactive voltage control strategy according to different working conditions of the distribution network;

[0210] Fault diagnosis: timely and accurate location of feeder fault points, analysis of fault causes and fault impact range, and provision of fault prediction and prevention suggestions;

[0211] Power restoration: after a distribution network failure occurs, the optimal power restoration strategy is generated based on the fault information through real-time adjustment and feedback mechanism;

[0212] Risk prevention: Based on various risk scenarios during the operation of the simulated distribution network feeder, various risk factors are quantitatively analyzed in combination with the real-time data of the distribution network feeder, and preventive measures are taken in a timely manner.

[0213] The control of the distribution network through the resource management module, the analysis and evaluation module, the business management and control module and the decision-making and command module includes:

[0214] Based on the physical entities and resources of the distribution network, through asset management and the geographic spatial representation of the distribution network provided by the Geographic Information System (GIS), we can optimize resource utilization and visualize equipment management, and provide support for the operation and management of the distribution network by the distribution network business;

[0215] Analyze and evaluate the operating status of the distribution network, provide optimization strategies based on the analysis and evaluation results, simulate and predict the distribution network entities based on digital twin technology, and analyze and evaluate the effects and risks of different decision-making plans.

[0216] The control method further comprises:

[0217] Use the cloud platform to create network resources and environment, and decompose the distribution network into multiple different service functions based on microservices combined with distributed computing. Perform cluster service management according to function type, manage gateways and call microservices through gateway cluster services, use remote call application interface HTTP API for communication between services, use relational database Mysql and remote dictionary service Redis to store main business data and cache data, use analysis and visualization platform Kibana and data collection engine Logstash to collect and analyze logs, and use message broker RabbitMQ to provide asynchronous communication and decoupling between multiple services.

[0218] The control method further comprises:

[0219] Based on the three-dimensional simulation model, the real-time status of the distribution network can be visualized, accessed and interacted on mobile terminals through browsers or micro-applications.

[0220] Embodiment 3:

[0221] like Figure 3 As shown, the present application proposes a cloud-edge hierarchical deployment collaborative architecture, which is respectively communicated with the distribution network digital twin simulation platform and the distribution network terminal as described above, including:

[0222] Edge computing nodes are used to obtain real-time data collected by acquisition devices and send them to the edge;

[0223] Image repository, used to store different versions of applications on the edge or in the cloud.

[0224] The hierarchical collaborative module is used to obtain real-time data based on edge computing nodes, transmit it according to the needs of the distribution network digital twin simulation platform, and receive data feedback from the distribution network digital twin simulation platform; the different service functions of the distribution network are hierarchically deployed on the edge and cloud, the edge processes the data, the cloud analyzes and centrally controls the edge.

[0225] Specifically, the cloud-edge hierarchical deployment collaborative architecture is to coordinate the distribution network data, models, services, and applications, uniformly allocate various resources to achieve the best operating effect, deploy multiple identical instances at the cloud edge to achieve elastic expansion and high-availability architecture, and uniformly manage edge computing node servers, including cloud-edge data hierarchical collaboration, model hierarchical collaboration, service hierarchical collaboration, and application hierarchical collaboration, to achieve centralized control of the cloud over the edge. The image warehouse is a central location for storing and managing various software images and container images. It is responsible for securely storing different versions of software, conveniently distributing images to various edge computing nodes or cloud servers, supporting rapid deployment and updating of applications and services, and ensuring that only authorized users or systems can access and manage images, thereby ensuring the security of the system.

[0226] The hierarchical collaboration module includes:

[0227] The data hierarchical collaboration unit is used to persistently store and preprocess the real-time data obtained by the edge computing node based on the edge, and send the preprocessed real-time data to the distribution network digital twin simulation platform; the cloud receives the data fed back by the distribution network digital twin simulation platform, and backs up, aggregates and analyzes the data fed back by the distribution network digital twin simulation platform, and sends the aggregation and analysis results to the distribution network digital twin simulation platform;

[0228] Specifically, the data hierarchical coordination unit is edge processing and cloud analysis. The distribution network operation data is preprocessed and simply analyzed according to the model, and then the results and related data are uploaded to the cloud; the cloud stores and analyzes the data; the edge device data is collected by the terminal device and uploaded to the edge computing node. The edge computing node preprocesses the data at the edge to filter out a large amount of redundant or invalid data, and selects key data related to the distribution network, including real-time voltage, current, active power, reactive power, and uploads it to the cloud on demand, and jointly maintains device data, edge node configuration, application configuration and other data, including data storage, synchronization and aggregation.

[0229] The model analysis collaboration unit is used to build a physical model and a data model based on the edge aggregation and analysis results, and upload the physical model and the data model to the cloud in the form of data; the cloud builds a three-dimensional simulation model with electrical properties based on the physical model and the data model, combined with the business rules of the distribution network;

[0230] Specifically, the edge is connected to the cloud through the network, and the operating status of the equipment in the display scene is transmitted to the cloud through data, so that the model operating status can be displayed in the cloud, thereby realizing the collaboration between the model and the real object; the edge node can provide computing, storage, network and other infrastructure resources, and can independently schedule and manage local resources, or collaborate with the cloud to accept and execute the resource scheduling management strategy issued by the cloud. The digital twin system can use model data to control the system to better adjust the production process. The model can also communicate with various applications through API application program interfaces or Web services to use digital twin data.

[0231] A service hierarchical coordination unit is used to upload service calls or service requests to the cloud based on the service registration information received by the edge and the service calls or service requests of the registered service users; the cloud authorizes, monitors and coordinates according to the received service calls or service requests;

[0232] Specifically, the edge of cloud-edge service hierarchical collaboration includes service registration, service call and service request. Each service request includes service name, service description, service parameters, etc., and sends a service call request to the cloud through a network interface or a data interface. The cloud authorizes, monitors and coordinates it, and records the execution time, execution results and error information of the service for subsequent monitoring and management.

[0233] The application classification and coordination unit is used to pre-set alarm thresholds and message standards based on the edge and perform intelligent processing on application operations; the cloud performs classification and classification management based on the different permissions and types of applications;

[0234] Specifically, the hierarchical collaboration of cloud-edge applications realizes effective collaboration and resource optimization between the edge and the cloud. The alarm threshold setting and intelligent processing of the operation application on the edge ensure the consistency and operability of the data through message standardization. The cloud is responsible for hierarchical management of permissions to ensure that users or systems at different levels can collaborate safely and efficiently. In addition, classified management and optimized configuration are carried out for different types of applications to achieve the optimal allocation and collaborative operation of system resources, thereby improving the stability and responsiveness of the overall system.

[0235] Embodiment 4:

[0236] Based on the same inventive concept, the present application also proposes a deployment method of a cloud-edge hierarchical deployment collaborative architecture, which adopts the cloud-edge hierarchical deployment collaborative architecture as described above. The method includes:

[0237] Obtain real-time data collected by the collection device and send it to the edge;

[0238] Mirror different versions of applications stored in the image repository to the edge or cloud.

[0239] Based on the real-time data obtained by the edge computing nodes, it is transmitted according to the needs of the distribution network digital twin simulation platform, and the data feedback from the distribution network digital twin simulation platform is received; the different service functions of the distribution network are hierarchically deployed on the edge and the cloud, the edge processes the data, and the cloud analyzes and centrally controls the edge.

[0240] Based on the real-time data obtained by the edge computing nodes, the data is transmitted according to the needs of the distribution network digital twin simulation platform, and the data fed back by the distribution network digital twin simulation platform is received; different service functions of the distribution network are hierarchically deployed on the edge and cloud, the edge processes the data, the cloud analyzes and centrally controls the edge, including:

[0241] The real-time data obtained by the edge computing node is persistently stored and preprocessed based on the edge, and the preprocessed real-time data is sent to the distribution network digital twin simulation platform; the cloud receives the data fed back by the distribution network digital twin simulation platform, and backs up, aggregates and analyzes the data fed back by the distribution network digital twin simulation platform, and sends the aggregation and analysis results to the distribution network digital twin simulation platform;

[0242] The physical model and data model are built based on the edge aggregation and analysis results, and uploaded to the cloud in the form of data. The cloud builds a three-dimensional simulation model with electrical properties based on the physical model and data model and the business rules of the distribution network.

[0243] Based on the service registration information received by the edge and the service call or service request of the registered service user, the service call or service request is uploaded to the cloud; the cloud authorizes, monitors and coordinates according to the received service call or service request;

[0244] Alarm thresholds and message standards are pre-set on the edge, and application operations are processed intelligently; the cloud performs hierarchical and categorized management based on the different permissions and types of applications.

[0245] Embodiment 5:

[0246] like Figure 4 As shown, the present invention proposes a distribution network symbiosis simulation system based on digital twins, including a distribution network digital twin simulation platform, a cloud-edge hierarchical deployment collaborative architecture, and a distribution network terminal;

[0247] The cloud-edge hierarchical deployment collaborative architecture is respectively communicated with the distribution network digital twin simulation platform and the distribution network terminal;

[0248] The distribution network digital twin simulation platform adopts the distribution network digital twin simulation platform as described above;

[0249] The cloud-edge hierarchical deployment collaborative architecture adopts the cloud-edge hierarchical deployment collaborative architecture described above.

[0250] like Figure 5 As shown, the system also includes: an offline-online integrated distributed architecture;

[0251] The offline-online integrated distributed architecture is used to distribute the real-time data obtained by the cloud-edge hierarchical deployment collaborative architecture according to different data types, and classify and manage the data according to data characteristics.

[0252] Specifically, in view of the complexity of distribution network data, an offline-online integrated architecture is adopted to distribute and store different types of data, and classify and manage the data according to its characteristics. The offline layer is used to store some online data, planning data, and management data, etc. The online layer is used for real-time data processing and interaction and pushes the twin model to realize dynamic updates, providing comprehensive and accurate data visualization and analysis.

[0253] Furthermore, the online layer mainly processes the equipment status, authority information, and flow data. Real-time data is collected from various sensors, equipment, or distribution network master stations, including voltage, current, power, and other information of the feeder, and processed, analyzed, or aggregated to generate useful real-time status information. The user's identity information, authority settings, and some hot data are stored in a non-relational database; hot data such as electrical equipment current, voltage, active power, and reactive power are used as cache for easy query and display.

[0254] Furthermore, the offline layer mainly processes ledger data, historical data, and simulation data. The ledger data of the distribution network feeder, such as equipment parameters, configuration, maintenance history, ownership, and other related static and dynamic information, are stored in the relational database Mysql; the historical status data generated by the equipment during operation, including the daily operation status of the equipment, fault records, maintenance records, grid structure, offline flow, offline faults and other data as well as simulation prediction results, are stored in the relational database Mysql.

[0255] Embodiment 6:

[0256] Based on the same inventive concept, the present application also proposes a distribution network symbiosis simulation method based on digital twins, which adopts the distribution network symbiosis simulation system based on digital twins as described above, including:

[0257] Based on the acquired real-time data, the processed real-time data is processed and combined with the business rules of the distribution network to build a three-dimensional simulation model with electrical properties;

[0258] Based on real-time data and three-dimensional simulation models, by simulating different distribution network scenarios and various computing services, optimization strategies and analysis results for various distribution network businesses are generated, and the distribution network is controlled through resource management modules, analysis and evaluation modules, business management and control modules, and decision-making and command modules.

[0259] The processing based on the acquired real-time data includes:

[0260] The real-time data acquired by the edge in the cloud-edge hierarchical deployment collaborative architecture is persisted and preprocessed, and the preprocessed real-time data is sent to the data layer in the distribution network digital twin simulation platform;

[0261] The data layer stores the preprocessed real-time data according to different data types, shares the data required at each level in the distribution network digital twin simulation platform in a synchronous or asynchronous manner, and uses data deduplication, missing value processing, outlier processing and data standardization to process the stored data and send it to the cloud in the cloud-edge hierarchical deployment collaborative architecture.

[0262] The process of combining the processed real-time data with the business rules of the distribution network to construct a three-dimensional simulation model with electrical properties includes:

[0263] Based on the cloud-edge hierarchical deployment collaborative architecture, the processed real-time data received from the cloud is backed up, aggregated and analyzed through data synchronization;

[0264] Send the aggregation and analysis results to the model layer in the distribution network digital twin simulation platform to build physical models and data models;

[0265] Based on the physical model and data model, combined with various rules, specifications, processes and strategies in the pre-set distribution network business, a three-dimensional simulation model with electrical properties is constructed;

[0266] The physical model includes: the physical structure of the distribution network and surrounding buildings;

[0267] The data model includes: the location, connection relationship and equipment parameters of the distribution network and surrounding buildings.

[0268] The physical model and the data model are deployed at the edge in the cloud-edge hierarchical deployment collaborative architecture; the edge in the cloud-edge hierarchical deployment collaborative architecture is responsible for various pre-set rules, specifications, processes and policies in the distribution network business, and constructs a three-dimensional simulation model with electrical properties;

[0269] The optimization strategies and analysis results of various distribution network services are generated based on real-time data and three-dimensional simulation models by simulating different distribution network scenarios and various computing services, including:

[0270] Based on the three-dimensional simulation model, the power flow calculation, line loss calculation, fault calculation and reliability calculation provided by the service layer in the distribution network digital twin simulation platform are adopted. Combined with the real-time data of the distribution network and simulation of different distribution network scenarios, optimization strategies and preventive measures for various distribution network businesses are generated.

[0271] The optimization strategy and preventive measures for generating multiple services of the distribution network include:

[0272] Active and reactive power regulation: Generate and optimize distributed power inverter control strategy and reactive voltage control strategy according to different working conditions of the distribution network;

[0273] Fault diagnosis: timely and accurate location of feeder fault points, analysis of fault causes and fault impact range, and provision of fault prediction and prevention suggestions;

[0274] Power restoration: after a distribution network failure occurs, the optimal power restoration strategy is generated based on the fault information through real-time adjustment and feedback mechanism;

[0275] Risk prevention: Based on various risk scenarios during the operation of the simulated distribution network feeder, various risk factors are quantitatively analyzed in combination with the real-time data of the distribution network feeder, and preventive measures are taken in a timely manner.

[0276] The automation and intelligent control of distribution network through resource management, analysis and evaluation, business management and control, and decision-making and command includes:

[0277] Based on the physical entities and resources of the distribution network, through asset management and the geographic spatial representation of the distribution network provided by the Geographic Information System (GIS), we can optimize resource utilization and visualize equipment management, and provide support for the operation and management of the distribution network by the distribution network business;

[0278] Analyze and evaluate the operating status of the distribution network, provide optimization strategies based on the analysis and evaluation results, simulate and predict the distribution network entities based on digital twin technology, and analyze and evaluate the effects and risks of different decision-making plans.

[0279] Also includes:

[0280] Based on the three-dimensional simulation model, the real-time status of the distribution network can be visualized, accessed and interacted on mobile terminals through browsers or micro-applications.

[0281] Also includes:

[0282] Based on the edge in the cloud-edge hierarchical deployment collaborative architecture, the service registration information and service calls or service requests of registered service users are received, and the service calls or service requests are uploaded to the cloud. The cloud authorizes, monitors and coordinates based on the received service calls or service requests.

[0283] Also includes:

[0284] Based on the edge in the cloud-edge hierarchical deployment collaborative architecture, alarm thresholds and message standards are pre-set, and application operations are processed intelligently. The cloud performs hierarchical and classified management based on the different permissions and types of applications.

[0285] Specifically, for data collection, real-time data or historical data are collected from different sources such as sensors, instruments, and equipment, including information on each key point of the distribution network. The collected data is preprocessed, including data cleaning, denoising, and format conversion. Based on the physical characteristics, operating parameters, and connection relationships of the distribution equipment, simulation results are generated through calculation and simulation. The drone oblique photography technology is used for aerial photography, mainly shooting the main line of the actual scene distribution network and the characteristic areas from the branch line to the power-consuming villages and rooftop photovoltaics. The drone is equipped with high-resolution camera equipment to take aerial photos at different angles and heights in the air to obtain high-resolution aerial images, thereby building the scene generation capability of the system. Extract distribution network equipment and environmental information, including identifying distribution equipment such as poles, wires, transformers, and surrounding environmental features such as buildings and roads, and train and predict these feature information. Use 3D modeling software such as 3ds Max to perform fine manual modeling of the distribution network environment, and use 3D mapping of houses, ground, people, and other environments that are blurred in the shooting according to key parameters such as actual size, shape, and position to ensure the accuracy and realism of the model. On this basis, the generated scenes and models are dynamically rendered through the unity cross-platform development engine, and human-computer interaction of distribution network dynamics is realized through script mounting.

[0286] Embodiment 7:

[0287] like Figure 6As shown, based on the same inventive concept, the present invention also provides a computer device, which includes a processor and a memory, the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function, so as to realize the control method of a distribution network digital twin simulation platform in the above embodiment, the deployment method of the cloud-edge hierarchical deployment collaborative architecture, or the steps of a distribution network symbiosis simulation method based on digital twins.

[0288] Embodiment 8:

[0289] Based on the same inventive concept, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in a computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space that stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by a processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement a control method of a distribution network digital twin simulation platform, a deployment method of a cloud-edge hierarchical deployment collaborative architecture, or a step of a distribution network symbiosis simulation method based on digital twins in the above-mentioned embodiment.

[0290] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0291] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0292] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0293] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0294] The above are merely embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are included in the scope of the claims of the present invention to be approved.

Claims

1. A distribution network digital twin simulation platform, characterized in that: The distribution network digital twin simulation platform is connected with the cloud-edge hierarchical deployment collaborative architecture, including: The data layer is used to receive real-time data sent by the cloud-edge hierarchical deployment collaborative architecture and analyze and process the real-time data; The model layer is used to build a three-dimensional simulation model with electrical properties based on the real-time data analyzed and processed by the data layer and combined with the business rules of the distribution network to perform synchronous simulation of the distribution network; The service layer is used to generate optimization strategies and analysis results for various services of the distribution network by simulating different distribution network scenarios and various computing services based on the real-time data of the data layer and model layer and the three-dimensional simulation model; The application layer is used to control the distribution network based on the optimization strategies and analysis results obtained by the service layer through the resource management module, analysis and evaluation module, business control module and decision-making command module.

2. The simulation platform according to claim 1, characterized in that: The data layer includes: A data storage module, used to store the real-time data sent by the cloud-edge hierarchical deployment collaborative architecture according to different data types; Data sharing module, used to share the required data of each level synchronously or asynchronously; Data analysis module, which is used to analyze real-time data using the Apache Flink stream processing framework and offline data using the computing engine Apache Spark; The data processing module is used to process the real-time data sent by the received cloud-edge hierarchical deployment collaborative architecture by using data deduplication, missing value processing, outlier processing and data standardization.

3. The simulation platform according to claim 1, characterized in that: The model layer includes: Physical model module, used to build the physical structure model of the distribution network and surrounding buildings; Data model module, used to build entity location, connection relationship and equipment parameter model; The knowledge model module is used to set various rules, specifications, processes and strategies in the distribution network business; Virtual Model module, used to build three-dimensional simulation models with electrical properties.

4. The simulation platform according to claim 1, characterized in that: The service layer includes: The power flow calculation module is used to determine the voltage and current of each node in the distribution network, as well as the distribution of active power, reactive power and voltage in the power grid; Line loss calculation module, used to calculate the distribution law of power loss in the distribution network; Fault calculation module, used to calculate and analyze distribution network equipment faults; The reliability calculation module is used to quantitatively analyze and evaluate distribution network equipment failures and improve the reliability of the distribution network.

5. The simulation platform according to claim 4, characterized in that: The service layer also includes: an auxiliary support module; the auxiliary support module is used for interaction between the model layer and the application layer, and combines the power flow calculation module, the line loss calculation module, the fault calculation module and the reliability calculation module to generate optimization strategies and preventive measures.

6. The simulation platform according to claim 5, characterized in that: The auxiliary support module includes: Active and reactive power regulation unit, used to generate and optimize distributed power inverter control strategy and reactive voltage control strategy according to different working conditions of the distribution network; Fault diagnosis unit, used to timely and accurately locate the feeder fault point, analyze the fault cause and fault impact range, and provide suggestions for fault prediction and prevention; The power supply restoration unit is used to generate the optimal power supply restoration strategy based on the fault information through real-time adjustment and feedback mechanism after a fault occurs in the distribution network; The risk prevention unit is used to quantitatively analyze various risk factors based on various risk scenarios in the operation process of the simulated distribution network feeder and the real-time data of the distribution network feeder, and to take timely preventive measures.

7. The simulation platform according to claim 1, characterized in that: The application layer includes: Resource management module, which is used to optimize resource usage and visualize equipment management based on the physical entities and resources of the distribution network through asset management and the geographic spatial representation of the distribution network provided by the Geographic Information System (GIS); Analysis and evaluation module, used to analyze and evaluate the operation status of the distribution network; Business control module, used to provide support for the operation and management of the distribution network based on distribution network business; The decision-making and command module is used to formulate optimization strategies based on the analysis and evaluation results of the distribution network operation status, simulate and predict the distribution network entities based on the digital twin technology, and analyze and evaluate the effects and risks of different decision-making plans.

8. The simulation platform according to claim 1, characterized in that: The simulation platform is based on the cloud platform. The cloud platform is used to create network resources and environment, decompose the distribution network into multiple different service functions based on microservices combined with distributed computing, manage cluster services according to function types, manage gateways and call microservices through gateway cluster services, use remote call application program interface HTTP API to communicate between services, use relational database Mysql and remote dictionary service Redis to store main business data and cache data, use analysis and visualization platform Kibana and data collection engine Logstash to collect and analyze logs, and use message agent RabbitMQ to provide asynchronous communication and decoupling between multiple services.

9. The platform according to claim 1, characterized in that Also includes: Presentation layer; The display layer is used to visualize, access and interact with the real-time status of the distribution network on a mobile terminal through a browser or micro-application based on a three-dimensional simulation model.

10. A control method for a distribution network digital twin simulation platform, characterized in that: include: Receive real-time data sent by the cloud-edge hierarchical deployment collaborative architecture, and analyze and process the real-time data; Based on the analyzed and processed real-time data and combined with the business rules of the distribution network, a three-dimensional simulation model with electrical properties is constructed to perform synchronous simulation of the distribution network; Based on real-time data and three-dimensional simulation models, by simulating different distribution network scenarios and various computing services, optimization strategies and analysis results for various distribution network businesses are generated, and the distribution network is controlled through resource management modules, analysis and evaluation modules, business control modules and decision-making and command modules.

11. The method according to claim 10, characterized in that The receiving real-time data sent by the cloud-edge hierarchical deployment collaborative architecture and analyzing and processing the real-time data includes: Based on receiving real-time data sent by the cloud-edge hierarchical deployment collaborative architecture, the data is stored according to different data types and shared synchronously or asynchronously. The real-time data sent by the received cloud-edge hierarchical deployment collaborative architecture is processed by using data deduplication, missing value processing, outlier processing and data standardization.

12. The method according to claim 10, characterized in that The three-dimensional simulation model with electrical properties is constructed based on the analyzed and processed real-time data and combined with the business rules of the distribution network, including: Build a physical model based on the physical structure of the distribution network and surrounding buildings; Build a data model based on the location, connection relationship and equipment parameters of the distribution network and surrounding buildings; Based on the physical model and data model, combined with various pre-set rules, specifications, processes and strategies in the distribution network business, a three-dimensional simulation model with electrical properties is constructed.

13. The method according to claim 10, characterized in that The various computing services include: Power flow calculation, determining the voltage and current of each node in the distribution network, as well as the distribution of active power, reactive power and voltage in the power grid; Line loss calculation, calculate the distribution law of power loss in the distribution network; Fault calculation: calculate and analyze distribution network equipment faults; Reliability calculation, quantitative analysis and evaluation of distribution network equipment failures to improve the reliability of the distribution network.

14. The method according to claim 13, characterized in that The optimization strategy and analysis results for generating multiple services of the distribution network include: Active and reactive power regulation: Generate and optimize distributed power inverter control strategy and reactive voltage control strategy according to different working conditions of the distribution network; Fault diagnosis: timely and accurate location of feeder fault points, analysis of fault causes and fault impact range, and provision of fault prediction and prevention suggestions; Power restoration: after a distribution network failure occurs, the optimal power restoration strategy is generated based on the fault information through real-time adjustment and feedback mechanism; Risk prevention: Based on various risk scenarios during the operation of the simulated distribution network feeder, various risk factors are quantitatively analyzed in combination with the real-time data of the distribution network feeder, and preventive measures are taken in a timely manner.

15. The method according to claim 10, characterized in that The control of the distribution network through the resource management module, the analysis and evaluation module, the business management and control module and the decision-making and command module includes: Based on the physical entities and resources of the distribution network, through asset management and the geographic spatial representation of the distribution network provided by the Geographic Information System (GIS), we can optimize resource utilization and visualize equipment management, and provide support for the operation and management of the distribution network by the distribution network business; Analyze and evaluate the operating status of the distribution network, provide optimization strategies based on the analysis and evaluation results, simulate and predict the distribution network entities based on digital twin technology, and analyze and evaluate the effects and risks of different decision-making plans.

16. The method according to claim 10, characterized in that Also includes: Use the cloud platform to create network resources and environment, and decompose the distribution network into multiple different service functions based on microservices combined with distributed computing. Perform cluster service management according to function type, manage gateways and call microservices through gateway cluster services, use remote call application interface HTTP API for communication between services, use relational database Mysql and remote dictionary service Redis to store main business data and cache data, use analysis and visualization platform Kibana and data collection engine Logstash to collect and analyze logs, and use message broker RabbitMQ to provide asynchronous communication and decoupling between multiple services.

17. The method according to claim 10, characterized in that Also includes: Based on the three-dimensional simulation model, the real-time status of the distribution network can be visualized, accessed and interacted on mobile terminals through browsers or micro-applications.

18. A cloud-edge hierarchical deployment collaborative architecture, characterized in that: The cloud-edge hierarchical deployment collaborative architecture is respectively connected to the distribution network digital twin simulation platform and the distribution network terminal according to any one of claims 1 to 9, including: Edge computing nodes are used to obtain real-time data collected by acquisition devices and send them to the edge; Image repository, used to store different versions of applications on the edge or in the cloud. The hierarchical collaborative module is used to obtain real-time data based on edge computing nodes, transmit it according to the needs of the distribution network digital twin simulation platform, and receive data feedback from the distribution network digital twin simulation platform; the different service functions of the distribution network are hierarchically deployed on the edge and cloud, the edge processes the data, the cloud analyzes and centrally controls the edge.

19. The architecture according to claim 18, characterized in that The hierarchical collaboration module includes: The data hierarchical collaboration unit is used to persistently store and preprocess the real-time data obtained by the edge computing node based on the edge, and send the preprocessed real-time data to the distribution network digital twin simulation platform; the cloud receives the data fed back by the distribution network digital twin simulation platform, and backs up, aggregates and analyzes the data fed back by the distribution network digital twin simulation platform, and sends the aggregation and analysis results to the distribution network digital twin simulation platform; The model analysis collaboration unit is used to build a physical model and a data model based on the edge aggregation and analysis results, and upload the physical model and the data model to the cloud in the form of data; the cloud builds a three-dimensional simulation model with electrical properties based on the physical model and the data model, combined with the business rules of the distribution network; A service hierarchical coordination unit is used to upload service calls or service requests to the cloud based on the service registration information received by the edge and the service calls or service requests of the registered service users; the cloud authorizes, monitors and coordinates according to the received service calls or service requests; The application hierarchical collaboration unit is used to pre-set alarm thresholds and message standards based on the edge and perform intelligent processing of application operations; the cloud performs hierarchical and classified management based on the different permissions and types of applications.

20. A method for deploying a cloud-edge hierarchical deployment collaborative architecture, using the cloud-edge hierarchical deployment collaborative architecture as claimed in claim 18, characterized in that: The method comprises: Obtain real-time data collected by the collection device and send it to the edge; Mirror different versions of applications stored in the image repository to the edge or cloud. Based on the real-time data obtained by the edge computing nodes, it is transmitted according to the needs of the distribution network digital twin simulation platform, and the data feedback from the distribution network digital twin simulation platform is received; the different service functions of the distribution network are hierarchically deployed on the edge and the cloud, the edge processes the data, and the cloud analyzes and centrally controls the edge.

21. The deployment method according to claim 20, characterized in that: Based on the real-time data obtained by the edge computing nodes, it is transmitted according to the needs of the distribution network digital twin simulation platform, and the data fed back by the distribution network digital twin simulation platform is received; Different service functions of the distribution network are hierarchically deployed on the edge and cloud. The edge processes data, and the cloud analyzes and centrally controls the edge, including: The real-time data obtained by the edge computing node is persistently stored and preprocessed based on the edge, and the preprocessed real-time data is sent to the distribution network digital twin simulation platform; the cloud receives the data fed back by the distribution network digital twin simulation platform, and backs up, aggregates and analyzes the data fed back by the distribution network digital twin simulation platform, and sends the aggregation and analysis results to the distribution network digital twin simulation platform; The physical model and data model are built based on the edge aggregation and analysis results, and uploaded to the cloud in the form of data. The cloud builds a three-dimensional simulation model with electrical properties based on the physical model and data model and the business rules of the distribution network. Based on the service registration information received by the edge and the service call or service request of the registered service user, the service call or service request is uploaded to the cloud; the cloud authorizes, monitors and coordinates according to the received service call or service request; Alarm thresholds and message standards are pre-set on the edge, and application operations are processed intelligently; the cloud performs hierarchical and categorized management based on the different permissions and types of applications.

22. A distribution network symbiosis simulation system based on digital twins, characterized in that: Including distribution network digital twin simulation platform, cloud-edge hierarchical deployment collaborative architecture and distribution network terminals; The cloud-edge hierarchical deployment collaborative architecture is respectively communicated with the distribution network digital twin simulation platform and the distribution network terminal; The distribution network digital twin simulation platform adopts the distribution network digital twin simulation platform as described in any one of claims 1 to 9; The cloud-edge hierarchical deployment collaborative architecture adopts the cloud-edge hierarchical deployment collaborative architecture as described in any one of claims 18-19.

23. The system according to claim 22, characterized in that The system also includes: an offline-online integrated distributed architecture; The offline-online integrated distributed architecture is used to distribute the real-time data obtained by the cloud-edge hierarchical deployment collaborative architecture according to different data types, and classify and manage the data according to data characteristics.

24. A distribution network symbiosis simulation method based on digital twin, characterized in that: A distribution network symbiosis simulation system based on digital twin as claimed in any one of claims 22 to 23 is adopted, comprising: Based on the acquired real-time data, the processed real-time data is processed and combined with the business rules of the distribution network to build a three-dimensional simulation model with electrical properties; Based on real-time data and three-dimensional simulation models, by simulating different distribution network scenarios and various computing services, optimization strategies and analysis results for various distribution network businesses are generated, and the distribution network is controlled through resource management modules, analysis and evaluation modules, business management and control modules, and decision-making and command modules.

25. The method according to claim 24, characterized in that The processing based on the acquired real-time data includes: The real-time data acquired by the edge in the cloud-edge hierarchical deployment collaborative architecture is persisted and preprocessed, and the preprocessed real-time data is sent to the data layer in the distribution network digital twin simulation platform; The data layer stores the preprocessed real-time data according to different data types, shares the data required at each level in the distribution network digital twin simulation platform in a synchronous or asynchronous manner, and uses data deduplication, missing value processing, outlier processing and data standardization to process the stored data and send it to the cloud in the cloud-edge hierarchical deployment collaborative architecture.

26. The method according to claim 24, characterized in that The process of combining the processed real-time data with the business rules of the distribution network to construct a three-dimensional simulation model with electrical properties includes: Based on the cloud-edge hierarchical deployment collaborative architecture, the processed real-time data received from the cloud is backed up, aggregated and analyzed through data synchronization; Send the aggregation and analysis results to the model layer in the distribution network digital twin simulation platform to build physical models and data models; Based on the physical model and data model, combined with various rules, specifications, processes and strategies in the pre-set distribution network business, a three-dimensional simulation model with electrical properties is constructed; The physical model includes: the physical structure of the distribution network and surrounding buildings; The data model includes: the location, connection relationship and equipment parameters of the distribution network and surrounding buildings.

27. The method according to claim 26, characterized in that The physical model and data model are deployed at the edge in the cloud-edge hierarchical deployment collaborative architecture; the edge in the cloud-edge hierarchical deployment collaborative architecture is responsible for various pre-set rules, specifications, processes and strategies in the distribution network business, and builds a three-dimensional simulation model with electrical properties.

28. The method according to claim 24, characterized in that The optimization strategies and analysis results of various distribution network services are generated based on real-time data and three-dimensional simulation models by simulating different distribution network scenarios and various computing services, including: Based on the three-dimensional simulation model, the power flow calculation, line loss calculation, fault calculation and reliability calculation provided by the service layer in the distribution network digital twin simulation platform are adopted. Combined with the real-time data of the distribution network and simulation of different distribution network scenarios, optimization strategies and preventive measures for various distribution network businesses are generated.

29. The method according to claim 28, characterized in that The optimization strategy and preventive measures for generating multiple services of the distribution network include: Active and reactive power regulation: Generate and optimize distributed power inverter control strategy and reactive voltage control strategy according to different working conditions of the distribution network; Fault diagnosis: timely and accurate location of feeder fault points, analysis of fault causes and fault impact range, and provision of fault prediction and prevention suggestions; Power restoration: after a distribution network failure occurs, the optimal power restoration strategy is generated based on the fault information through real-time adjustment and feedback mechanism; Risk prevention: Based on various risk scenarios during the operation of the simulated distribution network feeder, various risk factors are quantitatively analyzed in combination with the real-time data of the distribution network feeder, and preventive measures are taken in a timely manner.

30. The method according to claim 24, characterized in that The automation and intelligent control of distribution network through resource management, analysis and evaluation, business management and control, and decision-making and command includes: Based on the physical entities and resources of the distribution network, through asset management and the geographic spatial representation of the distribution network provided by the Geographic Information System (GIS), we can optimize resource utilization and visualize equipment management, and provide support for the operation and management of the distribution network by the distribution network business; Analyze and evaluate the operating status of the distribution network, provide optimization strategies based on the analysis and evaluation results, simulate and predict the distribution network entities based on digital twin technology, and analyze and evaluate the effects and risks of different decision-making plans.

31. The method according to claim 24, characterized in that Also includes: Based on the three-dimensional simulation model, the real-time status of the distribution network can be visualized, accessed and interacted on mobile terminals through browsers or micro-applications.

32. The method according to claim 24, characterized in that Also includes: Based on the edge in the cloud-edge hierarchical deployment collaborative architecture, the service registration information and service calls or service requests of registered service users are received, and the service calls or service requests are uploaded to the cloud. The cloud authorizes, monitors and coordinates based on the received service calls or service requests.

33. The method according to claim 24, characterized in that Also includes: Based on the edge in the cloud-edge hierarchical deployment collaborative architecture, alarm thresholds and message standards are pre-set, and application operations are processed intelligently. The cloud performs hierarchical and classified management based on the different permissions and types of applications.

34. A computer device, characterized in that: include: at least one processor and memory; The memory is used to store one or more programs; When the one or more programs are executed by the at least one processor, the control method of the distribution network digital twin simulation platform as described in any one of claims 10-17, the deployment method of the cloud-edge hierarchical deployment collaborative architecture as described in any one of claims 20-21, or the distribution network symbiosis simulation method based on digital twin as described in any one of claims 24-33 is implemented.

35. A computer-readable storage medium, characterized in that: A computer program is stored thereon, which, when executed, implements the control method of the distribution network digital twin simulation platform as described in any one of claims 10-17, the deployment method of the cloud-edge hierarchical deployment collaborative architecture as described in any one of claims 20-21, or the distribution network symbiosis simulation method based on digital twin as described in any one of claims 24-33.

Images