Digital intelligent configuration method of power distribution system, equipment and medium

Abstract

The invention discloses a digital intelligent configuration method and device of a power distribution system and a medium, and relates to the technical field of electrical engineering, and the method comprises the steps: obtaining scene information of the power distribution system through interaction, and the scene information comprises demand and operation information; and based on this, power distribution model optimization is carried out, and an intelligent configuration cloud comprising K equipment models and K gateways is constructed. A power distribution equipment entity is in communication connection with a gateway, the gateway receives and forwards equipment real-time operation information to a cloud end, the cloud end analyzes and generates a parameter adjustment instruction, and the parameter adjustment instruction is transmitted to a power distribution system through the gateway to execute intelligent configuration. The technical problems of low energy utilization efficiency, poor power supply stability and lack of intelligent collaboration and optimization caused by the fact that existing power distribution system configuration cannot accurately adapt to variable power distribution scene requirements and operation conditions in real time are solved, and the purposes of improving the energy utilization efficiency and the power supply stability and reliability, reducing the operation and maintenance cost and improving the power supply efficiency are achieved. And the automation and intelligence level of the system is enhanced.

Description

Technical Field

[0001] The present application relates to the field of electrical engineering technology, and in particular to a digital intelligent configuration method, device and medium for a power distribution system. Background Art

[0002] In the operation scenarios of distribution systems, meeting complex and ever-changing distribution needs and ensuring stable and reliable power supply have become key issues. The contradiction of optimizing the configuration of distribution resources has become increasingly prominent. Achieving efficient and accurate configuration of distribution resources and better adapting to various distribution scenarios have become crucial links in improving the performance of distribution systems. Traditional distribution system configurations are often relatively rigid and fixed, relying only on preset parameters or limited empirical models. They have insufficient grasp of the overall operating conditions of the distribution system, lack of in-depth mining and utilization of real-time operating data, and are difficult to accurately assess distribution needs and potential risks in different scenarios. In terms of resource allocation, there are unscientific situations, resulting in resource shortages in some key areas and excess resources in some areas. The formulation of distribution configuration plans is relatively simple and static, and cannot effectively respond to the ever-changing actual operating conditions of the distribution system.

[0003] At the current stage, relevant technologies have the problem that the distribution system configuration cannot accurately adapt to the changing distribution scenario requirements and operating conditions in real time, resulting in low energy utilization efficiency, poor power supply stability and lack of intelligent coordination and optimization. Summary of the invention

[0004] The present application provides a digital intelligent configuration method, device and medium for a power distribution system, which acquires scene information of the power distribution system, including demand and operation information, through interaction. Based on this, the power distribution model is optimized, and an intelligent configuration cloud containing K types of equipment models and K gateways is constructed. The power distribution equipment entity is connected to the gateway for communication. The gateway receives and forwards the real-time operation information of the equipment to the cloud. The cloud analyzes and generates parameter adjustment instructions, which are transmitted to the distribution system through the gateway to execute intelligent configuration, thereby achieving the technical effect of improving energy utilization efficiency, power supply stability and reliability, reducing operation and maintenance costs, and enhancing the automation and intelligence level of the system.

[0005] The present application provides a digital intelligent configuration method for a power distribution system, comprising:

[0006] Interactively obtain power distribution scenario information of the power distribution system, wherein the power distribution scenario information includes power distribution scenario demand information and power distribution scenario operation information; perform power distribution model optimization analysis based on the power distribution scenario information, and construct an intelligent configuration cloud based on the optimization analysis results, wherein the intelligent configuration cloud includes K groups of target device models of K types of power distribution equipment, and the intelligent configuration cloud is connected to K gateways; according to the K types of power distribution equipment, the power distribution equipment entities in the power distribution system are mapped and communicated to the K gateways; the K gateways receive and forward the real-time operation information of the power distribution equipment entities in the power distribution system to the intelligent configuration cloud; in the intelligent configuration cloud, the real-time operation information is analyzed based on the K groups of target device models to generate device parameter adjustment instructions; after the device parameter adjustment instructions are issued to the K gateways, they are transmitted to the power distribution system via the K gateways to execute the intelligent configuration of the power distribution equipment entities.

[0007] The present application also provides a digital intelligent configuration device for a power distribution system, comprising:

[0008] A power distribution scenario information acquisition module, the power distribution scenario information acquisition module is used to interactively obtain the power distribution scenario information of the power distribution system, wherein the power distribution scenario information includes power distribution scenario demand information and power distribution scenario operation information; an optimization analysis module, the optimization analysis module is used to perform a power distribution model optimization analysis based on the power distribution scenario information, and to construct an intelligent configuration cloud based on the optimization analysis results, wherein the intelligent configuration cloud includes K groups of target device models of K types of power distribution equipment, and the intelligent configuration cloud is connected to K gateways; an entity mapping module, the entity mapping module is used to map the power distribution in the power distribution system according to the K types of power distribution equipment The device entity mapping communication is connected to the K gateways; a configuration cloud module is used for the K gateways to receive and forward the real-time operation information of the distribution device entities in the distribution system to the intelligent configuration cloud; a device parameter adjustment instruction generation module is used in the intelligent configuration cloud to analyze the real-time operation information based on the K groups of target device models to generate device parameter adjustment instructions; an intelligent configuration module is used for transmitting the device parameter adjustment instructions to the distribution system via the K gateways after the device parameter adjustment instructions are sent to the K gateways to execute the intelligent configuration of the distribution device entities.

[0009] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0010] Interactively obtain power distribution scenario information of the power distribution system, wherein the power distribution scenario information includes power distribution scenario demand information and power distribution scenario operation information; perform power distribution model optimization analysis based on the power distribution scenario information, and construct an intelligent configuration cloud based on the optimization analysis results, wherein the intelligent configuration cloud includes K groups of target device models of K types of power distribution equipment, and the intelligent configuration cloud is connected to K gateways; according to the K types of power distribution equipment, the power distribution equipment entities in the power distribution system are mapped and communicated to the K gateways; the K gateways receive and forward the real-time operation information of the power distribution equipment entities in the power distribution system to the intelligent configuration cloud; in the intelligent configuration cloud, the real-time operation information is analyzed based on the K groups of target device models to generate device parameter adjustment instructions; after the device parameter adjustment instructions are issued to the K gateways, they are transmitted to the power distribution system via the K gateways to execute the intelligent configuration of the power distribution equipment entities.

[0011] The digital intelligent configuration method, device and medium of a power distribution system proposed in this application first obtain the scene information of the power distribution system through interaction, including demand and operation information. Based on this, the power distribution model is optimized, and an intelligent configuration cloud containing K types of equipment models and K gateways is constructed. The power distribution equipment entity is connected to the gateway for communication. The gateway receives and forwards the real-time operation information of the equipment to the cloud. The cloud analyzes and generates parameter adjustment instructions, which are transmitted to the distribution system through the gateway to execute intelligent configuration, thereby achieving the technical effect of improving energy utilization efficiency, power supply stability and reliability, reducing operation and maintenance costs, and enhancing the automation and intelligence level of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the device according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed precisely in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0013] Figure 1 A flowchart of a digital intelligent configuration method for a power distribution system provided in an embodiment of the present application;

[0014] Figure 2 A structural schematic diagram of a digital intelligent configuration device for a power distribution system provided in an embodiment of the present application.

[0015] Explanation of the accompanying drawings: power distribution scenario information acquisition module 10, optimization analysis module 20, entity mapping module 30, configuration cloud module 40, equipment parameter adjustment instruction generation module 50, intelligent configuration module 60. DETAILED DESCRIPTION

[0016] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0017] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0018] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, device, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0019] The present application embodiment provides a digital intelligent configuration method for a power distribution system, such as Figure 1 As shown, the method includes:

[0020] Step S100, interactively obtain the distribution scenario information of the distribution system, wherein the distribution scenario information includes the distribution scenario demand information and the distribution scenario operation information. Specifically, the distribution scenario information of the distribution system interactively obtained refers to various related contents covered in the acquisition process. Determine the scope of the distribution system to be studied, prepare the tools and means for information collection, set the parameters for information collection, such as demand type and operation indicators, etc., perform information collection operations, and obtain the distribution scenario demand information record. The distribution scenario demand information record represents the specific requirements of different regions or users in terms of power capacity, power supply reliability, power quality, etc. in the distribution planning stage, and its characteristics are forward-looking and planning-oriented. Continue to perform information collection operations to obtain the distribution scenario operation information record. The distribution scenario operation information record represents the electrical parameters such as current, voltage, power, etc. in the system during the actual distribution operation stage, as well as the working status and maintenance records of the equipment, etc., and its characteristics are real-time and specific.

[0021] Step S200, perform distribution model optimization analysis according to the distribution scenario information, and construct an intelligent configuration cloud according to the optimization analysis results, wherein the intelligent configuration cloud includes K groups of target device models of K types of distribution equipment, and the intelligent configuration cloud is connected to K gateways. Specifically, the distribution model optimization analysis and intelligent configuration cloud construction refer to a series of operations performed when processing distribution scenario information. Clarify the scope of the distribution system to be optimized, prepare the technical tools required for analysis, set the key parameters of the analysis, such as power load prediction accuracy, line loss limit, equipment capacity threshold, power supply reliability index, etc., carry out optimization analysis, and obtain the optimal distribution model result data. The optimal distribution model result data represents the configuration scheme that can enable the distribution system to achieve the best performance and efficiency after comprehensive consideration of various factors, and its characteristics are comprehensiveness and optimization. Continue to build an intelligent configuration cloud based on the analysis results. The intelligent configuration cloud includes K groups of target device models of K types of distribution equipment and is connected to K gateways. The target device model represents the ideal operating parameters and performance indicators carefully designed for each distribution equipment, and its characteristics are accuracy and adaptability.

[0022] In a possible implementation, a distribution model optimization analysis is performed according to the distribution scenario information, and an intelligent configuration cloud is constructed according to the optimization analysis result, wherein the intelligent configuration cloud includes K groups of target device models of K types of distribution equipment, and the intelligent configuration cloud is connected to K gateways, and step S200 further includes step S210, performing a distribution model optimization analysis according to the distribution scenario information to obtain K groups of target device models of the K types of distribution equipment. Specifically, the collected distribution scenario information is deeply studied and analyzed, and simulation technology is used to comprehensively consider various factors, such as changes in electricity demand in different regions, the performance and capacity of existing distribution equipment, and the carrying capacity of lines. Through a large number of calculations and repeated simulations, the optimal K types of distribution equipment are selected from many possible distribution equipment combinations and configuration schemes, and the corresponding K groups of target device models are determined for each device. For example, for a distribution scenario in an industrial park, it is concluded through analysis that K types of equipment such as transformers and switch cabinets of specific models and specifications are required, and each device has a corresponding optimal operating parameter and configuration target model.

[0023] Step S220, constructing an intelligent configuration cloud based on the K groups of target device models. Specifically, using the obtained K groups of target device models, a centralized intelligent configuration cloud platform is built, on which corresponding databases and computing resources are created to store and process the data of these target device models, and efficient servers and network facilities are configured to ensure that the cloud can quickly respond to and process information requests from different devices. For example, a powerful cloud server cluster is built that can simultaneously process the distribution equipment model data of multiple regions to achieve centralized management and optimized configuration.

[0024] Step S230, pre-configure the K gateways for the K types of power distribution equipment, and register and connect the K gateways to the intelligent configuration cloud. Specifically, for the determined K types of power distribution equipment, set up the corresponding K gateways for them in advance. The gateways will be responsible for data transmission and communication between the equipment and the intelligent configuration cloud. After completing the configuration of the gateways, they will be registered in the intelligent configuration cloud to establish a legal connection relationship. Through network settings and security authentication and other steps, ensure that the K gateways can stably and securely interact with the cloud for data. Taking a city's power distribution system as an example, install dedicated gateways for K types of power distribution equipment in different areas, and complete registration and connection in the cloud to achieve unified management across the city.

[0025] Step S240, mapping the K groups of device model metadata extracted based on the K groups of target device models to the K gateways. Specifically, extract key device model metadata from the K groups of target device models, including device model data acquisition attributes (such as the frequency and accuracy of data acquisition), point table template (defining the format and content of device data) and channel information (the path and method of data transmission). Through a secure data transmission channel, these metadata are accurately mapped and sent to the corresponding K gateways. After receiving the metadata, the gateway performs corresponding settings and adjustments based on this information to ensure that the data of the distribution equipment can be accurately collected and transmitted. For example, for a distribution system of a large commercial complex, the extracted device model metadata is sent to each gateway, so that the gateway can collect and transmit the operating data of equipment such as air conditioners and lighting in the shopping mall as required.

[0026] In a possible implementation, a distribution model optimization analysis is performed based on the distribution scenario information to obtain K groups of target device models for the K types of distribution equipment. Step S210 further includes step S211, in which the equipment type is extracted from the distribution scenario operation information to obtain the K types of distribution equipment. Specifically, the collected distribution scenario operation information is deeply analyzed and data mined. The operation information contains a lot of detailed data about the running distribution equipment. This information is screened and classified using specific algorithms and data analysis tools, with a focus on the type characteristics of the equipment. After processing and identification, K different types of distribution equipment are finally accurately extracted. For example, in a complex industrial distribution scenario, K key types of distribution equipment such as transformers, switch cabinets, and distribution cabinets are extracted from a large amount of operation data.

[0027] Step 212, pre-construct a distribution equipment model library, use the K types of distribution equipment to traverse the distribution equipment model library, and screen to obtain a spare distribution equipment model set. Specifically, collect, organize and establish a rich and comprehensive distribution equipment model library, which covers distribution equipment models of various types and specifications. Use the extracted K types of distribution equipment to search and compare them one by one in the model library. According to specific screening conditions and matching rules, select a series of spare distribution equipment models that match the K types of equipment from the model library to form a spare distribution equipment model set. For example, for a new commercial complex distribution project, the pre-constructed model library contains various common commercial distribution equipment models, and a set of spare models such as transformers and circuit breakers suitable for the project are screened out through traversal.

[0028] Step S213, using the power distribution scenario demand information as a constraint, the backup power distribution equipment model set is optimized and analyzed to locate K equipment models to be called. Specifically, the demand information of the power distribution scenario is studied and analyzed in detail, including but not limited to the peak and valley values ​​of the power load, the requirements for power supply stability, the expectations for equipment reliability, etc. The demand information is used as a strict constraint condition, and advanced optimization algorithms and analysis methods are applied to perform in-depth optimization calculations and evaluations on the backup power distribution equipment model set. Through calculation and comparison, K equipment models to be called that best meet the requirements and have the best performance are accurately located from the backup model set. Taking the transformation of a hospital's power distribution system as an example, according to the hospital's high reliability and stability requirements for power supply, the backup model set is optimized and analyzed to determine the most suitable K models to be called, such as uninterruptible power supplies and intelligent monitoring equipment.

[0029] Step S214, extract the equipment quantity of the power distribution scenario operation information based on the K types of power distribution equipment to obtain K equipment quantity information. Specifically, based on the previously determined K types of power distribution equipment, re-examine the operation information of the power distribution scenario, use data analysis technology and statistical methods to accurately extract the quantity-related data of each type of power distribution equipment from the operation information, and finally obtain K accurate equipment quantity information about each of the K types of power distribution equipment after processing and sorting. For example, in a residential area's power distribution system, extract the specific quantity of K types of equipment such as distribution boxes and electric meters from the operation information.

[0030] Step S215, based on the K device quantity information, the K target device models are replicated. Specifically, based on the K pieces of information about the number of devices obtained, the K previously located device models to be called are replicated accordingly to ensure that the number of replicates fully matches the number of devices actually required, thereby forming the final K target device models. The target device models will provide precise guidance and basis for the subsequent power distribution system configuration and optimization. For example, in a school's power distribution system upgrade project, the K selected device models to be called are replicated based on the determined number of devices to obtain K target device models that meet the school's power demand.

[0031] In a possible implementation, a distribution equipment model library is pre-constructed, and the K types of distribution equipment are used to traverse the distribution equipment model library to screen and obtain a spare distribution equipment model set. Step S212 further includes step S2121, interactively obtaining multiple sample distribution model sets and multiple sample model performance sets of multiple distribution equipment. Specifically, by actively interacting with relevant data sources, databases or expert systems, the data sources may include power equipment manufacturers, power research institutions, actual distribution systems, etc., and a large number of sample distribution model sets for multiple different types of distribution equipment are obtained from the source. These model sets contain detailed design and parameter information of various equipment, and the corresponding multiple sample model performance sets are obtained, which cover the performance data of the equipment under different operating conditions, such as efficiency, reliability, stability and other indicators. For example, cooperate with a number of well-known power equipment manufacturers to obtain sample distribution models and performance data of their latest products to establish a rich basic database.

[0032] Step S2122, based on the knowledge graph, multiple sample power distribution model sets of the multiple power distribution equipment are stored in association to obtain the power distribution equipment model library. Specifically, the multiple sample power distribution model sets of the multiple power distribution equipment obtained are sorted and organized using advanced knowledge graph technology. The knowledge graph can clearly show the association between different models, such as the compatibility and similarity between different types of equipment. The sorted model sets are stored according to a specific structure and classification method, so as to build a comprehensive and orderly power distribution equipment model library. For example, a knowledge graph with equipment type, performance indicator, applicable scenario, etc. as nodes and relationships is constructed, and the sample model sets are stored therein to form a model library that is easy to query and use.

[0033] Step S2123, interacting with the power distribution scenario operation information to obtain the power distribution equipment composition information of the power distribution system, wherein the power distribution equipment composition information includes multiple power distribution equipment entities. Specifically, real-time information interaction is performed with the running power distribution system to collect detailed data about its operating status and configuration, and from the information, the specific power distribution equipment composition information contained in the power distribution system is extracted. The composition information is specifically manifested as multiple power distribution equipment entities, such as specific models of transformers, switch cabinets, distribution boxes, etc. Taking the power distribution system of a large factory as an example, by interacting with the system's monitoring system, the detailed composition information of various electrical equipment in operation is obtained.

[0034] Step S2124, extracting the equipment types of the multiple power distribution equipment entities to obtain the K types of power distribution equipment. Specifically, the relevant data of the multiple power distribution equipment entities obtained are analyzed, and they are classified into different equipment types according to the functions, characteristics, working principles and other factors of the equipment. After screening and sorting, K representative types of power distribution equipment are finally determined. For example, when analyzing the power distribution system of a commercial building, K common equipment types such as high-voltage switchgear, transformer, low-voltage distribution cabinet, etc. are extracted from many equipment entities.

[0035] Step S2125, using the K types of power distribution equipment to traverse the power distribution equipment model library, and screen to obtain the backup power distribution equipment model set, wherein the backup power distribution equipment model set includes K backup power distribution equipment model subsets of the K types of power distribution equipment. Specifically, based on the determined K types of power distribution equipment, a comprehensive search and comparison is performed in the constructed power distribution equipment model library, and a series of backup power distribution equipment models that conform to the K types of equipment are selected from the model library according to preset screening conditions and matching rules. The backup models are organized into a set, wherein each of the K types of power distribution equipment has a corresponding K subsets of backup power distribution equipment models. For example, when designing a power distribution system for a new residential area, the determined K types of equipment are used to screen out a suitable set of backup models in the model library, providing a basis for subsequent optimization selection.

[0036] In one possible implementation, multiple sample power distribution model sets and multiple sample model performance sets of multiple power distribution equipment are interactively obtained, and step S2121 further includes step S21211, and the composition information of each sample model performance in the multiple sample model performance sets specifically includes storage resource consumption, computing resource consumption, data processing speed and response time interval. Specifically, for each of the multiple sample models, it is necessary to clarify the storage resources occupied by the model during operation, including the storage space occupied by various types of data such as the model's own code, parameters, training data, intermediate results, and final output. Use storage monitoring tools to accurately measure the storage usage of the model at different operation stages. For example, when training the model, monitor the changes in storage space caused by the writing and updating of data; when the model is predicting, pay attention to the storage occupancy of the output results, record the results of each measurement in detail, and form a detailed data set on storage resource consumption for subsequent analysis and comparison. For each sample model, determine its utilization of computing resources when executing computing tasks, covering the CPU usage time, usage rate, GPU memory usage, number of computing cores used, etc. With the help of system performance monitoring tools and related computing resource management software, track the dynamic changes of computing resources during model operation in real time. For example, by viewing the CPU task manager, obtain the CPU resource usage of the model process; use GPU monitoring tools , understand the usage of video memory and the working status of the computing core, organize and record the collected computing resource consumption data to provide a basis for evaluating the computing efficiency of the model. To measure the data processing speed of each sample model, it is first necessary to define a clear test data set and processing tasks. The data set has a certain scale and complexity and can reflect the typical situation in actual applications. Start the sample model to process the test data set, and use high-precision timing tools to record the time interval from the start of data processing to the completion of processing and output of results. Repeat the test many times to obtain more accurate average processing speed data to ensure that the measurement results of data processing speed are reliable and representative. For each sample model, simulate the input request scenario in actual applications, send input data or operation instructions to the model, and use time measurement tools to accurately record the time difference from the moment the model receives the input request to the moment it returns the response result. Perform multiple tests on input requests of different types and complexities to obtain comprehensive response time interval data to evaluate the real-time response capability of the model under different situations.

[0037] In one possible implementation, the backup power distribution equipment model set is optimized and analyzed with the power distribution scenario demand information as a constraint to locate K equipment models to be called, and step S213 further includes step S2131, combining and enumerating the K backup power distribution equipment model subsets to obtain multiple equipment model combinations, wherein each equipment model combination includes K backup power distribution equipment models corresponding to the K types of power distribution equipment. Specifically, the K backup power distribution equipment model subsets are used as basic elements, and the K subsets are fully arranged or combined according to specific rules through a systematic enumeration method to ensure that each generated equipment model combination contains K backup power distribution equipment models corresponding to the K types of power distribution equipment, that is, each combination is a complete power distribution equipment configuration solution. For example, if there are 3 types of power distribution equipment, each type of equipment has 2 subsets, then 8 different equipment model combinations may be obtained through enumeration.

[0038] Step S2132, performing sum calculation of storage resource consumption and computing resource consumption for the multiple device model combinations to obtain multiple comprehensive storage consumptions and multiple comprehensive computing consumptions. Specifically, for each generated device model combination, respectively calculate the storage resource consumption and computing resource consumption of each standby power distribution device model, add up the storage resource consumption of all devices belonging to the same combination to obtain the comprehensive storage consumption of the combination, add up the computing resource consumption to obtain the comprehensive computing consumption, and after calculation, obtain clear comprehensive storage consumption and comprehensive computing consumption values ​​for each device model combination.

[0039] Step S2133, traverse the multiple comprehensive storage consumptions and multiple comprehensive computing consumptions of the multiple device model combinations according to the storage resource constraints and computing resource constraints of the power distribution scenario demand information, so as to eliminate the multiple device model combinations that are not compatible with computing resources, and obtain multiple adaptive model combinations. Specifically, carefully analyze the power distribution scenario demand information, clarify the specific constraints on storage resources and computing resources, and check in turn whether the comprehensive storage consumption and comprehensive computing consumption of each device model combination meet these constraints. If the comprehensive storage consumption or comprehensive computing consumption of a combination exceeds the constraint limit, it will be removed from the candidate list. After a round of traversal and screening, what remains are multiple adaptive model combinations that meet the resource constraints.

[0040] Step S2134, introduce a model fitness evaluation function, and use the model fitness evaluation function to evaluate the fitness of the multiple adaptation model combinations to obtain multiple combination fitness coefficients. Specifically, a specially designed model fitness evaluation function is introduced, which comprehensively considers multiple factors related to fitness, inputs the relevant parameters of each adaptation model combination into the evaluation function, and after calculation, the function outputs a specific combination fitness coefficient for each adaptation model combination, which reflects the degree of fitness of the combination in multiple aspects.

[0041] Step S2135, serialize the multiple combination matching coefficients, and call the device model combination corresponding to the extreme value based on the serialization result to obtain the K device models to be called. Specifically, the obtained multiple combination matching coefficients are arranged in order from small to large or from large to small to achieve serialization, and according to the serialization result, the device model combination corresponding to the extreme value (maximum value or minimum value, depending on the specific evaluation criteria) is found, and finally the device model combination corresponding to the extreme value is determined and called, and it is used as the K device models to be called for the subsequent distribution system configuration.

[0042] In a possible implementation, a model fitness evaluation function is introduced, and the model fitness evaluation function is used to evaluate the fitness of the plurality of adaptation model combinations to obtain a plurality of combination fitness coefficients. Step S2134 further includes step S21341, and the model fitness evaluation function is as follows:

[0043] Among them, M is the model fitness, U1 is the comprehensive storage consumption, C1 is the storage resource constraint, U2 is the comprehensive computing consumption, C2 is the computing resource constraint, CI1 is the data processing consistency coefficient, S i is the data processing speed of the ith standby power distribution equipment model, CI2 is the response time consistency coefficient, T i is the response time interval of the ith standby power distribution equipment model, n is the total number of standby power distribution equipment models in the adaptive model combination, w1, w2 and w3 are the computing resource weight, data processing weight and model response weight respectively. Specifically, in the function, CI1 represents the data processing consistency coefficient. The calculation process is as follows: for each standby power distribution equipment model (a total of n) in the adaptive model combination, first calculate the data processing speed S of the ith model i Average data processing speed of all models The difference is squared and summed, then divided by n-1, then squared and divided by the average of all model data processing speeds. CI2 represents the response time consistency coefficient. It is calculated in a similar way, for each model’s response time interval T iFirst, calculate the response time interval of the i-th model and the average response time interval of all models. The difference is squared and summed, then divided by n-1, then squared and divided by the average of all model response time intervals Calculate the model fitness M, which consists of three parts: the first part is Among them, U1 is the comprehensive storage consumption, C1 is the storage resource constraint, U2 is the comprehensive computing consumption, and C2 is the computing resource constraint. This part mainly considers the relationship between the consumption and constraints of storage and computing resources, and adjusts it through the weight w_1. The second part is w2CI1, where w2 is the data processing weight, and CI1 is the data processing consistency coefficient calculated previously. This part reflects the impact of the consistency of data processing speed on the model fitness. The third part is w3CI2, where w3 is the model response weight, and CI2 is the response time consistency coefficient. This part reflects the effect of response time consistency on model fitness. In practical applications, first determine the data processing speed S of each standby power distribution equipment model. i , response time interval T i , as well as the comprehensive storage consumption U1, the comprehensive computing consumption U2, the storage resource constraint C1, and the computing resource constraint C2. Then, according to the total number n of standby power distribution equipment models in the model combination, CI1 and CI2 are calculated. Next, the computing resource weight w1, the data processing weight w2, and the model response weight w3 are set. Finally, the values ​​calculated above and the set weights are substituted into the formula to calculate the value of the model fitness M, thereby evaluating the fitness of the model combination.

[0044] Step S300, mapping the distribution equipment entities in the distribution system to the K gateways according to the K types of distribution equipment. Specifically, the operation of mapping the distribution equipment entities to the gateways refers to a key step performed in the distribution system. Clarify the categories and characteristics of the K types of distribution equipment that have been determined, such as the capacity specifications of the transformer, the control mode of the switch cabinet, etc. A comprehensive inventory of the actual distribution equipment entities in the distribution system is carried out, and the entities corresponding to the K types of distribution equipment are accurately identified based on the exact information such as the equipment identification, model and installation location. Select K corresponding gateways for each type of distribution equipment. The selection of gateways needs to consider factors such as its communication performance, data processing rate and stability to meet the requirements of data transmission and control. Use physical line connections (such as network cables, optical fibers, etc.) or wireless communication technologies (such as Bluetooth, Wi-Fi, etc.) to build a direct communication link between each distribution equipment entity and the corresponding gateway. For physical connections, cable laying, interface connection and fixing operations are implemented to ensure the stability of the connection. For wireless connections, pairing, frequency band setting, signal strength optimization and other tasks are carried out to ensure the reliability of communication. After the connection is established, the communication protocol is configured and debugged. The distribution equipment entity is enabled to transmit data to the gateway according to the predetermined format and rules, and the gateway can also accurately understand and process the information from the equipment entity and forward it to the corresponding place. For example, in the power distribution system of a factory, K types of key distribution equipment are identified, such as transformers of specific capacity and switch cabinets of specific models. Then, find out the actual installed equipment in the factory and equip each equipment with a dedicated gateway. Connect the transformer to the corresponding gateway by laying the network cable, and set the wireless communication between the switch cabinet and the gateway. Complete the configuration of the communication protocol so that the data can be smoothly exchanged between the equipment and the gateway to achieve the purpose of real-time monitoring and control.

[0045] In step S400, the K gateways receive and forward the real-time operation information of the power distribution equipment entity in the power distribution system to the intelligent configuration cloud. Specifically, the process of the K gateways receiving and forwarding the real-time operation information of the power distribution equipment entity in the power distribution system is as follows. First, the K gateways are in a standby state and have a specific receiving mechanism and protocol to accurately obtain data from the power distribution equipment entity. When the power distribution equipment entity is running, it follows the pre-set communication link to transmit the real-time generated operation information, such as voltage value, current size, power level, equipment temperature and operation status, to the corresponding gateway in a predetermined format and frequency. After receiving this information, the gateway immediately carries out preliminary processing and verification. Check the integrity and accuracy of the data. If the data is missing or abnormal, it may request the power distribution equipment entity to resend or take error correction measures. After the data is processed and verified, the gateway quickly forwards it to the intelligent configuration cloud in accordance with the preset routing rules and communication protocols. During the forwarding process, the gateway fully guarantees the security and stability of the data to prevent data loss or tampering. In order to improve the efficiency and reliability of data transmission, the gateway may use technologies such as data compression and encryption. At the same time, the data transmission process is monitored in real time. Once a network failure or delay is detected, the retransmission mechanism is automatically started or the backup communication line is switched. For example, in the power distribution system of a large industrial park, the distribution boxes, transformers and other distribution equipment entities scattered in various factories and areas will transmit real-time operation information to the corresponding gateway. After receiving this data, the gateway will process and verify it, and quickly transfer the data to the intelligent configuration cloud through the high-speed network, so that the cloud can timely analyze and optimize the operation status of the entire distribution system.

[0046] Step S500, in the intelligent configuration cloud, the real-time operation information is analyzed based on the K groups of target device models to generate device parameter adjustment instructions. Specifically, the process of generating device parameter adjustment instructions based on the K groups of target device models in the intelligent configuration cloud is as follows. First, the intelligent configuration cloud receives the real-time operation information of the power distribution equipment entity forwarded by K gateways. This information is quickly imported into a powerful data processing and analysis system. The cloud calls the pre-built K groups of target device models, and each group of target device models covers various parameters and performance indicators of this type of equipment under ideal operating conditions. Then, the real-time operation information is carefully compared and analyzed with the parameters in the target device model. This involves a one-by-one comparison of many key parameters such as voltage, current, power, and device temperature. Through complex algorithms and model operations, the difference between the real-time operating state and the ideal target state is found. For example, if the actual current exceeds the safety threshold in the target model, or the device temperature is higher than the normal range, it will be identified as an abnormal condition that needs to be adjusted. Based on these differences and analysis results, the intelligent system in the cloud generates corresponding device parameter adjustment instructions. These instructions accurately indicate the equipment parameters that need to be adjusted, as well as the magnitude and direction of the adjustment. For example, if the output voltage of a transformer is found to be lower than the target value, the generated parameter adjustment instruction may be to increase its output voltage by a certain number of volts; if the current of a switch cabinet is overloaded, the instruction may be to reduce the current passing through the switch cabinet. The entire process of analyzing and generating parameter adjustment instructions is fast and accurate, ensuring that the operation of the distribution equipment can be optimized and adjusted in a timely manner. For example, in the power distribution system of a large hospital, the intelligent configuration cloud obtains real-time operating information of each distribution box and emergency power supply equipment. After comparative analysis with the target equipment model, it is found that the voltage fluctuations of some distribution boxes exceed the normal range, and the corresponding parameter adjustment instructions are immediately generated, requiring stable voltage to ensure the reliable operation of the hospital's power system and the normal use of medical equipment.

[0047] Step S600, after the device parameter adjustment instruction is sent to the K gateways, it is transmitted to the power distribution system via the K gateways to execute the intelligent configuration of the power distribution device entity. Specifically, after the device parameter adjustment instruction is sent to the K gateways, it is transmitted to the power distribution system via the K gateways to execute the intelligent configuration of the power distribution device entity as follows. When the device parameter adjustment instruction is generated in the intelligent configuration cloud, it is immediately sent to the K gateways in a specific data format and communication protocol. During the transmission process, these instructions are ensured to arrive at each gateway accurately and without errors. After receiving the parameter adjustment instruction, the K gateways immediately parse and confirm the instruction. Check the integrity and accuracy of the instruction to ensure that there is no data missing or error. After confirmation, the gateway transmits the parameter adjustment instruction quickly and stably based on the previously established communication link with the power distribution device entity in the power distribution system. During the transmission process, the gateway monitors the transmission status of the instruction in real time and handles possible network delays, interference and other problems. If a transmission failure or interruption occurs, the gateway will automatically start the retransmission mechanism to ensure that the instruction can be successfully delivered. After receiving the parameter adjustment instruction, the distribution equipment entity compares and converts the parameters in the instruction with its current operating parameters. Then, according to the requirements of the instruction, the relevant parameters of the equipment are adjusted through the internal control system and actuator, such as changing the voltage output, adjusting the current limit, changing the operating mode of the equipment, etc. During the adjustment process, the equipment monitors the effect of the adjustment in real time, and feeds back the new operating status to the gateway and the intelligent configuration cloud for subsequent monitoring and optimization. For example, in the power distribution system of an intelligent storage center, the parameter adjustment instruction for a certain distribution cabinet generated by the cloud is sent to the corresponding gateway, and the gateway quickly passes the instruction to the distribution cabinet. The distribution cabinet adjusts the internal parameters according to the instruction, and feeds back the adjusted operating data and status to the gateway and the cloud, achieving intelligent configuration and optimization.

[0048] The embodiment of the present application adopts the method of acquiring the scenario information of the power distribution system through interaction, including demand and operation information. Based on this, the power distribution model is optimized, and an intelligent configuration cloud containing K types of equipment models and K gateways is constructed. The power distribution equipment entity is connected to the gateway for communication. The gateway receives and forwards the real-time operation information of the equipment to the cloud. The cloud analyzes and generates parameter adjustment instructions, which are transmitted to the power distribution system through the gateway to execute intelligent configuration, thereby achieving the technical effect of improving energy utilization efficiency, power supply stability and reliability, reducing operation and maintenance costs, and enhancing the automation and intelligence level of the system.

[0049] In the above, refer to Figure 1 A digital intelligent configuration method for a power distribution system according to an embodiment of the present invention is described in detail. Figure 2 A digital intelligent configuration device for a power distribution system according to an embodiment of the present invention is described.

[0050] A digital intelligent configuration device for a power distribution system according to an embodiment of the present invention is used to solve the technical problem that the existing power distribution system configuration cannot accurately adapt to the changing power distribution scene requirements and operating conditions in real time, resulting in low energy utilization efficiency, poor power supply stability and lack of intelligent coordination and optimization, so as to achieve the technical effect of improving energy utilization efficiency, power supply stability and reliability, reducing operation and maintenance costs, and enhancing the automation and intelligence level of the system. A digital intelligent configuration device for a power distribution system includes: a power distribution scene information acquisition module 10, an optimization analysis module 20, an entity mapping module 30, a configuration cloud module 40, a device parameter adjustment instruction generation module 50, and an intelligent configuration module 60.

[0051] The power distribution scenario information acquisition module 10 is used to interactively obtain power distribution scenario information of a power distribution system, wherein the power distribution scenario information includes power distribution scenario demand information and power distribution scenario operation information.

[0052] The optimization analysis module 20 is used to perform optimization analysis on the power distribution model according to the power distribution scenario information, and to construct an intelligent configuration cloud according to the optimization analysis results, wherein the intelligent configuration cloud includes K groups of target device models of K types of power distribution equipment, and the intelligent configuration cloud is connected to K gateways.

[0053] The entity mapping module 30 is used to physically map and communicate the power distribution devices in the power distribution system to the K gateways according to the K types of power distribution devices.

[0054] The configuration cloud module 40 is used for the K gateways to receive and forward the real-time operation information of the power distribution equipment entities in the power distribution system to the intelligent configuration cloud.

[0055] The device parameter adjustment instruction generation module 50 is used to generate device parameter adjustment instructions based on the K groups of target device models by analyzing the real-time operation information in the intelligent configuration cloud.

[0056] The intelligent configuration module 60 is used to transmit the device parameter adjustment instruction to the K gateways through the K gateways to the power distribution system to execute the intelligent configuration of the power distribution equipment entity.

[0057] The optimization analysis module 20 will be described in detail below. As described above, the optimization analysis module is used to perform optimization analysis on the distribution model according to the distribution scenario information, and to construct and obtain an intelligent configuration cloud according to the optimization analysis results, wherein the intelligent configuration cloud includes K groups of target device models of K types of distribution equipment, and the intelligent configuration cloud is connected to K gateways, and the optimization analysis module 20 may further include a target device model acquisition unit for performing optimization analysis on the distribution model according to the distribution scenario information, and obtaining K groups of target device models of the K types of distribution equipment; an intelligent configuration cloud acquisition unit for constructing an intelligent configuration cloud based on the K groups of target device models; a gateway registration unit for pre-configuring the K gateways for the K types of distribution equipment, and registering and connecting the K gateways to the intelligent configuration cloud; a mapping and sending unit for mapping and sending the K groups of device model metadata extracted based on the K groups of target device models to the K gateways.

[0058] Among them, a distribution model optimization analysis is performed according to the distribution scenario information to obtain K groups of target device models for the K types of distribution equipment. The target device model acquisition unit may further include an equipment type extraction subunit for extracting the equipment type from the distribution scenario operation information to obtain the K types of distribution equipment; a distribution equipment model library pre-construction subunit is used to pre-construct the distribution equipment model library, and the K types of distribution equipment are used to traverse the distribution equipment model library to screen and obtain a set of standby distribution equipment models; a to-be-called equipment model positioning subunit is used to perform optimization analysis on the standby distribution equipment model set with the distribution scenario demand information as a constraint to locate K to-be-called equipment models; an equipment quantity information acquisition subunit is used to extract the equipment quantity from the distribution scenario operation information based on the K types of distribution equipment to obtain K equipment quantity information; a model replication subunit is used to perform model replication on the K to-be-called equipment models according to the K equipment quantity information, the K groups of target device models.

[0059] Among them, a distribution equipment model library is pre-constructed, and the K types of distribution equipment are used to traverse the distribution equipment model library to screen and obtain a spare distribution equipment model set. The distribution equipment model library pre-construction sub-unit may further include: an interactive micro-unit for interactively obtaining multiple sample distribution model sets and multiple sample model performance sets of multiple distribution equipment; a distribution equipment model library acquisition micro-unit is used to associate and store multiple sample distribution model sets of the multiple distribution equipment based on the knowledge graph to obtain the distribution equipment model library; a distribution equipment composition information acquisition micro-unit is used to interact with the distribution scenario operation information to obtain the distribution equipment composition information of the distribution system, wherein the distribution equipment composition information includes multiple distribution equipment entities; an equipment type extraction micro-unit is used to extract equipment types from the multiple distribution equipment entities to obtain the K types of distribution equipment; a screening micro-unit is used to traverse the distribution equipment model library using the K types of distribution equipment to screen and obtain the spare distribution equipment model set, wherein the spare distribution equipment model set includes K spare distribution equipment model subsets of the K types of distribution equipment.

[0060] Among them, multiple sample power distribution model sets and multiple sample model performance sets of multiple power distribution equipment are interactively obtained, and the interactive micro-unit may further include: a sample model performance composition nano-unit is used for the composition information of each sample model performance in the multiple sample model performance sets, specifically including storage resource consumption, computing resource consumption, data processing speed and response time interval.

[0061] Among them, the backup power distribution equipment model set is optimized and analyzed with the power distribution scenario demand information as a constraint to locate K device models to be called, and the device model locating subunit to be called may further include: a combination enumeration microunit is used to combine and enumerate the K backup power distribution equipment model subsets to obtain multiple device model combinations, wherein each device model combination includes K backup power distribution equipment models corresponding to the K types of power distribution equipment; a sum calculation microunit is used to sum the storage resource consumption and computing resource consumption of the multiple device model combinations to obtain multiple comprehensive storage consumptions and multiple comprehensive computing consumptions; an adaptation model combination acquisition microunit is used to According to the storage resource constraints and computing resource constraints of the power distribution scenario demand information, the multiple comprehensive storage consumptions and the multiple comprehensive computing consumptions of the multiple device model combinations are traversed to eliminate the incompatible combinations of computing resources for the multiple device model combinations to obtain multiple adapted model combinations; the function introduction micro-unit is used to introduce a model fitness evaluation function, and the model fitness evaluation function is used to evaluate the adaptability of the multiple adapted model combinations to obtain multiple combination fitness coefficients; the serialization micro-unit is used to serialize the multiple combination fitness coefficients, and based on the serialization result, the device model combination corresponding to the extreme value is called to obtain the K device models to be called.

[0062] Among them, a model fitness evaluation function is introduced, and the model fitness evaluation function is used to evaluate the fitness of the plurality of adaptation model combinations to obtain a plurality of combination fitness coefficients. The function introduction micro-unit may further include: a fitness evaluation function unit, and the fitness evaluation function unit is used for the model fitness evaluation function as follows: Among them, M is the model fitness, U1 is the comprehensive storage consumption, C1 is the storage resource constraint, U2 is the comprehensive computing consumption, C2 is the computing resource constraint, CI1 is the data processing consistency coefficient, S i is the data processing speed of the ith standby power distribution equipment model, CI2 is the response time consistency coefficient, T i is the response time interval of the i-th backup power distribution equipment model, n is the total number of backup power distribution equipment models in the adaptation model combination, w1, w2 and w3 are the computing resource weight, data processing weight and model response weight respectively.

[0063] A digital intelligent configuration device for a power distribution system provided in an embodiment of the present invention can execute a digital intelligent configuration method for a power distribution system provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0064] In one embodiment, a computer device is provided, comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: interactively obtaining distribution scenario information of a distribution system, wherein the distribution scenario information includes distribution scenario demand information and distribution scenario operation information; performing distribution model optimization analysis according to the distribution scenario information, and constructing an intelligent configuration cloud according to the optimization analysis result, wherein the intelligent configuration cloud includes K groups of target device models of K types of distribution equipment, and the intelligent configuration cloud is connected to K gateways; mapping distribution equipment entities in the distribution system to the K gateways according to the K types of distribution equipment; the K gateways receive and forward real-time operation information of distribution equipment entities in the distribution system to the intelligent configuration cloud; in the intelligent configuration cloud, analyzing the real-time operation information based on the K groups of target device models to generate device parameter adjustment instructions; after the device parameter adjustment instructions are issued to the K gateways, they are transmitted to the distribution system via the K gateways to execute intelligent configuration of distribution equipment entities.

[0065] Although the present application makes various references to certain modules in the devices according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be implemented; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0066] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A digital intelligent configuration method for a power distribution system, characterized in that: The method comprises: Interactively obtaining power distribution scenario information of the power distribution system, wherein the power distribution scenario information includes power distribution scenario demand information and power distribution scenario operation information; Performing an optimization analysis of the power distribution model according to the power distribution scenario information, and constructing an intelligent configuration cloud according to the optimization analysis result, wherein the intelligent configuration cloud includes K groups of target device models of K types of power distribution devices, and the intelligent configuration cloud is connected to K gateways; According to the K types of power distribution equipment, mapping the power distribution equipment entities in the power distribution system to be communicatively connected to the K gateways; The K gateways receive and forward real-time operation information of the power distribution equipment entities in the power distribution system to the intelligent configuration cloud; In the intelligent configuration cloud, the real-time operation information is analyzed based on the K groups of target device models to generate device parameter adjustment instructions; After the device parameter adjustment instruction is sent to the K gateways, it is transmitted to the power distribution system via the K gateways to execute the intelligent configuration of the power distribution equipment entity.

2. A digital intelligent configuration method for a power distribution system as claimed in claim 1, characterized in that: Performing an optimization analysis of the power distribution model according to the power distribution scenario information, and constructing an intelligent configuration cloud according to the optimization analysis result, wherein the intelligent configuration cloud includes K groups of target device models, and the intelligent configuration cloud is connected to K gateways, and the method further includes: Performing power distribution model optimization analysis according to the power distribution scenario information to obtain K groups of target device models for the K types of power distribution devices; Based on the K groups of target device models, an intelligent configuration cloud is obtained; Pre-configuring the K gateways for the K types of power distribution equipment, and registering and connecting the K gateways to the intelligent configuration cloud; The K groups of device model metadata mappings extracted based on the K groups of target device models are sent to the K gateways.

3. A digital intelligent configuration method for a power distribution system as claimed in claim 2, characterized in that: Performing power distribution model optimization analysis according to the power distribution scenario information to obtain K groups of target device models of the K types of power distribution devices, the method further includes: Extracting the equipment type from the power distribution scenario operation information to obtain the K types of power distribution equipment; Pre-constructing a power distribution equipment model library, using the K types of power distribution equipment to traverse the power distribution equipment model library, and screening to obtain a spare power distribution equipment model set; Taking the power distribution scenario demand information as a constraint, an optimization analysis is performed on the backup power distribution equipment model set to locate K equipment models to be called; Extracting the number of devices from the power distribution scenario operation information based on the K types of power distribution devices to obtain K pieces of equipment quantity information; Model replication is performed on the K to-be-called device models according to the K device quantity information, the K groups of target device models.

4. A digital intelligent configuration method for a power distribution system as claimed in claim 3, characterized in that: The method further comprises: Interactively obtain multiple sample power distribution model sets and multiple sample model performance sets for multiple power distribution devices; Based on the knowledge graph, multiple sample power distribution model sets of the multiple power distribution equipment are stored in association to obtain the power distribution equipment model library; Interacting the power distribution scenario operation information to obtain the power distribution equipment composition information of the power distribution system, wherein the power distribution equipment composition information includes a plurality of power distribution equipment entities; Extracting equipment types from the multiple power distribution equipment entities to obtain the K types of power distribution equipment; The K types of power distribution equipment are used to traverse the power distribution equipment model library, and the backup power distribution equipment model set is screened to obtain the backup power distribution equipment model set, wherein the backup power distribution equipment model set includes K backup power distribution equipment model subsets of the K types of power distribution equipment.

5. A digital intelligent configuration method for a power distribution system as claimed in claim 4, characterized in that: The composition information of each sample model performance in the plurality of sample model performance sets specifically includes storage resource consumption, computing resource consumption, data processing speed and response time interval.

6. A digital intelligent configuration method for a power distribution system as claimed in claim 5, characterized in that: Taking the power distribution scenario demand information as a constraint, an optimization analysis is performed on the backup power distribution equipment model set to locate K equipment models to be called. The method further includes: Combining and enumerating the K standby power distribution equipment model subsets to obtain a plurality of equipment model combinations, wherein each equipment model combination includes K standby power distribution equipment models corresponding to the K types of power distribution equipment; Performing sum calculation of storage resource consumption and computing resource consumption on the plurality of device model combinations to obtain a plurality of comprehensive storage consumptions and a plurality of comprehensive computing consumptions; According to the storage resource constraint and the computing resource constraint of the power distribution scenario demand information, the multiple comprehensive storage consumptions and the multiple comprehensive computing consumptions of the multiple device model combinations are traversed to eliminate the multiple device model combinations that are not compatible with computing resources, and obtain multiple compatible model combinations; Introducing a model fitness evaluation function, and using the model fitness evaluation function to evaluate the fitness of the plurality of fitness model combinations, to obtain a plurality of combination fitness coefficients; The multiple combination matching coefficients are serialized, and based on the serialization result, the device model combination corresponding to the extreme value is called to obtain the K device models to be called.

7. A digital intelligent configuration method for a power distribution system as claimed in claim 6, characterized in that: The model fitness evaluation function is as follows: Among them, M is the model fitness, U1 is the comprehensive storage consumption, C1 is the storage resource constraint, U2 is the comprehensive computing consumption, C2 is the computing resource constraint, CI1 is the data processing consistency coefficient, S i is the data processing speed of the ith standby power distribution equipment model, CI2 is the response time consistency coefficient, T i is the response time interval of the i-th backup power distribution equipment model, n is the total number of backup power distribution equipment models in the adaptation model combination, w1, w2 and w3 are the computing resource weight, data processing weight and model response weight respectively.

8. A digital intelligent configuration device for a power distribution system, characterized in that: The device is used to implement a digital intelligent configuration method for a power distribution system according to any one of claims 1 to 7, and the device comprises: A power distribution scenario information acquisition module, the power distribution scenario information acquisition module is used to interactively obtain power distribution scenario information of the power distribution system, wherein the power distribution scenario information includes power distribution scenario demand information and power distribution scenario operation information; An optimization analysis module, the optimization analysis module is used to perform an optimization analysis of the power distribution model according to the power distribution scenario information, and construct an intelligent configuration cloud according to the optimization analysis result, wherein the intelligent configuration cloud includes K groups of target device models of K types of power distribution devices, and the intelligent configuration cloud is connected to K gateways; A physical mapping module, the physical mapping module is used to physically map the power distribution devices in the power distribution system and connect them to the K gateways according to the K types of power distribution devices; A configuration cloud module, wherein the configuration cloud module is used for the K gateways to receive and forward real-time operation information of the power distribution equipment entities in the power distribution system to the intelligent configuration cloud; A device parameter adjustment instruction generation module, wherein the device parameter adjustment instruction generation module is used to generate a device parameter adjustment instruction based on the K groups of target device models in the intelligent configuration cloud; An intelligent configuration module, wherein the intelligent configuration module is used to transmit the device parameter adjustment instruction to the K gateways via the K gateways to the power distribution system to execute the intelligent configuration of the power distribution equipment entity.

9. A digital intelligent configuration device for a power distribution system as claimed in claim 8, characterized in that: The optimization analysis module includes: A target device model acquisition unit, the target device model acquisition unit is used to perform power distribution model optimization analysis according to the power distribution scenario information to obtain K groups of target device models of the K types of power distribution devices; An intelligent configuration cloud acquisition unit, the intelligent configuration cloud acquisition unit is used to obtain an intelligent configuration cloud based on the K groups of target device models; A gateway registration unit, the gateway registration unit is used to pre-configure the K gateways for the K types of power distribution equipment, and register and connect the K gateways to the intelligent configuration cloud; A mapping sending unit, wherein the mapping sending unit is used to map and send K groups of device model metadata extracted based on the K groups of target device models to the K gateways.

10. A digital intelligent configuration device for a power distribution system as claimed in claim 9, characterized in that: The target device model acquisition unit includes: A device type extraction subunit, the device type extraction subunit is used to extract the device type from the power distribution scenario operation information to obtain the K types of power distribution devices; A power distribution equipment model library pre-construction subunit, the power distribution equipment model library pre-construction subunit is used to pre-construct a power distribution equipment model library, use the K types of power distribution equipment to traverse the power distribution equipment model library, and screen and obtain a spare power distribution equipment model set; A device model positioning subunit to be called, the device model positioning subunit to be called is used to perform optimization analysis on the backup power distribution device model set based on the power distribution scenario demand information as a constraint, and locate K device models to be called; A device quantity information acquisition subunit, the device quantity information acquisition subunit is used to extract the device quantity of the power distribution scenario operation information based on the K types of power distribution devices, and obtain K pieces of device quantity information; A model replication subunit is used to perform model replication on the K to-be-called device models according to the K device quantity information, the K groups of target device models.

11. A digital intelligent configuration device for a power distribution system as claimed in claim 10, characterized in that: The power distribution equipment model library pre-construction subunit includes: An interactive micro-unit, the interactive micro-unit being used to interactively obtain a plurality of sample power distribution model sets and a plurality of sample model performance sets for a plurality of power distribution devices; A power distribution equipment model library acquisition micro-unit, wherein the power distribution equipment model library acquisition micro-unit is used to associate and store a plurality of sample power distribution model sets of the plurality of power distribution equipment based on a knowledge graph to obtain the power distribution equipment model library; A power distribution equipment composition information acquisition micro unit, the power distribution equipment composition information acquisition micro unit is used to exchange the power distribution scenario operation information to obtain the power distribution equipment composition information of the power distribution system, wherein the power distribution equipment composition information includes a plurality of power distribution equipment entities; A device type extraction micro-unit, wherein the device type extraction micro-unit is used to extract device types from the multiple power distribution device entities to obtain the K types of power distribution devices; A screening micro-unit is used to traverse the power distribution equipment model library using the K types of power distribution equipment to screen and obtain the backup power distribution equipment model set, wherein the backup power distribution equipment model set includes K backup power distribution equipment model subsets of the K types of power distribution equipment.

12. A digital intelligent configuration device for a power distribution system as claimed in claim 11, characterized in that: The composition information of each sample model performance in the plurality of sample model performance sets specifically includes storage resource consumption, computing resource consumption, data processing speed and response time interval.

13. A digital intelligent configuration device for a power distribution system as claimed in claim 12, characterized in that: The device model positioning subunit to be called includes: A combination enumeration micro-unit, the combination enumeration micro-unit is used to perform combination enumeration on the K standby power distribution equipment model subsets to obtain a plurality of equipment model combinations, wherein each equipment model combination includes K standby power distribution equipment models corresponding to the K types of power distribution equipment; A summing calculation micro-unit, the summing calculation micro-unit is used to perform summing calculations on the storage resource consumption and the computing resource consumption of the plurality of device model combinations to obtain a plurality of comprehensive storage consumptions and a plurality of comprehensive computing consumptions; An adaptation model combination acquisition micro-unit is used to traverse the multiple comprehensive storage consumptions and multiple comprehensive computing consumptions of the multiple device model combinations according to the storage resource constraints and computing resource constraints of the power distribution scenario demand information, so as to eliminate the multiple device model combinations that are not compatible with computing resources, and obtain multiple adaptation model combinations; A function introduces a micro-unit, wherein the function introduces a micro-unit for introducing a model fitness evaluation function, and uses the model fitness evaluation function to evaluate the fitness of the plurality of fitness model combinations to obtain a plurality of combination fitness coefficients; A serialization micro-unit is used to serialize the plurality of combination matching coefficients, and based on the serialization result, a combination of device models corresponding to the extreme values ​​is called to obtain the K device models to be called.

14. A digital intelligent configuration device for a power distribution system as claimed in claim 13, characterized in that: The function introduced into the micro-unit includes: The fitness evaluation function unit is used for the model fitness evaluation function as follows: Among them, M is the model fitness, U1 is the comprehensive storage consumption, C1 is the storage resource constraint, U2 is the comprehensive computing consumption, C2 is the computing resource constraint, CI1 is the data processing consistency coefficient, S i is the data processing speed of the ith standby power distribution equipment model, CI2 is the response time consistency coefficient, T i is the response time interval of the i-th backup power distribution equipment model, n is the total number of backup power distribution equipment models in the adaptation model combination, w1, w2 and w3 are the computing resource weight, data processing weight and model response weight respectively.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images