Control strategy generation method, system, device and storage medium for power supply equipment

By dividing power-keeping objects and evaluating the performance of power supply equipment, building a weighted directed graph model and optimizing the power supply control strategy, the problem of lack of targetedness and effectiveness of power supply solutions in the existing technology is solved, and the formulation and implementation of power supply solutions are improved. efficiency.

CN118611060BActive Publication Date: 2024-11-29STATE GRID ZHEJIANG ELECTRIC POWER CO MARKETING SERVICE CENT +1
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411081676.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-08
Publication Date
2024-11-29
Estimated Expiration
2044-08-08

AI Technical Summary

Technical Problem

The existing technology lacks scientific regional characteristic analysis and power supply demand assessment methods, resulting in insufficient targeted and effective power supply solutions and low efficiency in information collection and analysis.

Method used

By dividing power-keeping objects, obtaining performance evaluation of power supply equipment, building a weighted directed graph model, using hierarchical analysis method and rule-based inference method, optimizing power supply control strategies, and generating targeted power supply solutions.

Benefits of technology

It improves the efficiency of formulating and execution of power supply plans, ensures the pertinence and effectiveness of the plan, and improves the efficiency of information collection and analysis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118611060B_ABST
    Figure CN118611060B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of electric power supply technology, and discloses a control strategy generation method, system, device and storage medium for power supply equipment, including obtaining power supply equipment on the power supply path of a first power protection object, and performing performance evaluation to obtain equipment performance indicators; constructing a weighted directed graph model of the first power protection object, and using a hierarchical analysis method to perform performance evaluation on the power supply path; optimizing the power supply control strategy of the first power protection object based on a rule-based reasoning method according to the performance evaluation result; obtaining the power consumption information and load distribution information of the second power protection object, performing matching reasoning through a power supply scheme knowledge base, generating a preliminary power supply control strategy, and optimizing the preliminary power supply control strategy according to power supply requirements and scenario constraints. The present invention scientifically analyzes and evaluates the regional characteristics and power supply requirements of the power protection object, accurately describes the regional differences and power supply requirements, and meets the differences and effectiveness of the power supply scheme design.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of electric power supply, and in particular to a control strategy generation method, system, device and storage medium for power supply equipment. Background Art

[0002] At present, when identifying the power supply differences of different types of power protection objects, we are faced with the technical difficulty of how to comprehensively collect and analyze the information of power supply equipment. Due to the highly dispersed and heterogeneous information such as the model, parameters, and operating status of the power supply equipment of each object, and the lack of a unified data format and management platform, the workload of information collection and analysis is huge and inefficient. At the same time, the power supply equipment of different objects is significantly different, lacks comparability and correlation, and it is difficult to carry out common analysis and problem diagnosis. In addition, the identification process is also faced with challenges in data quality and real-time performance. The operating status and parameter information of the power supply equipment change dynamically and need to be collected and updated in real time, but there is currently a lack of effective data collection and transmission mechanisms, resulting in poor timeliness of the acquired data and difficulty in reflecting the true status of the equipment. Quality issues such as missing data, errors, and redundancy also affect the accuracy and reliability of the analysis.

[0003] When carrying out differentiated power supply management, there are also technical bottlenecks in how to customize personalized power supply plans for special areas. The power consumption characteristics, load distribution, and power supply requirements of different regions vary greatly. It is necessary to deeply analyze the regional characteristics and power supply needs, and comprehensively consider factors such as economy, reliability, and operability to formulate a practical power supply plan. However, there is currently a lack of scientific regional characteristics analysis and power supply demand assessment methods, which makes it difficult to accurately characterize regional differences and power supply requirements, resulting in insufficient pertinence and effectiveness of power supply plans. At the same time, in the process of plan formulation, it is also necessary to coordinate the work of multiple departments and multiple professions. There are problems such as high communication costs and complicated processes, which affect the efficiency of plan formulation and implementation. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a control strategy generation method, system, device and storage medium for power supply equipment, so as to solve the current lack of scientific regional characteristics analysis and power supply demand assessment methods, and the difficulty in accurately characterizing regional differences and power supply requirements, resulting in insufficient pertinence and effectiveness of power supply plans, so as to achieve the effect of improving the efficiency of designating and executing power supply plans.

[0005] In a first aspect, the present invention provides a method for generating a control strategy for a power supply device, the method comprising:

[0006] According to the object type of each power protection object, the power protection object is divided into a first power protection object and a second power protection object;

[0007] Acquire power supply equipment on the power supply path of the first power protection object, and perform performance evaluation on each power supply equipment to obtain equipment performance indicators;

[0008] A weighted directed graph model of the first power protection object is constructed based on the shortest path, and a performance evaluation of the power supply path is performed according to the key nodes, key paths and equipment performance indicators in the weighted directed graph model and using a hierarchical analysis method;

[0009] According to the performance evaluation result, the power supply control strategy of the first power protection object is optimized by using a rule-based reasoning method to obtain an optimized power supply control strategy of the first power protection object;

[0010] The power consumption information and load distribution information of the second power protection object are obtained, matching reasoning is performed through the preset power supply scheme knowledge base, a preliminary power supply control strategy is generated, and the preliminary power supply control strategy is optimized according to the power supply demand and scenario constraints of the second power protection object to obtain the optimal power supply control strategy for the second power protection object.

[0011] Furthermore, the step of obtaining power supply equipment on the power supply path of the first power protection object and performing performance evaluation on each power supply equipment to obtain equipment performance indicators includes:

[0012] According to the preset performance evaluation baseline, determine whether the power supply devices on the power supply path have the same performance evaluation baseline, use the power supply devices with the same performance evaluation baseline as the first power supply devices, and use the remaining power supply devices as the second power supply devices;

[0013] According to the rated performance parameters of the first power supply device, a universal parameter model is constructed, and the actual performance parameters of the first power supply device are input into the universal parameter model for performance analysis to obtain device performance indicators of the first power supply device;

[0014] According to the actual performance parameters of the second power supply device, power flow calculation is performed on the second power supply device to obtain a device performance indicator of the second power supply device.

[0015] Furthermore, the step of optimizing the preliminary power supply control strategy according to the power supply demand and scenario constraints of the second power protection object to obtain the optimal power supply control strategy for the second power protection object includes:

[0016] According to the power supply demand and scenario constraints of the second power supply protection object, the network parameters of the power supply network in the preliminary power supply control strategy are globally optimized, and the heuristic algorithm and data planning method are used to coordinately optimize each power supply link to generate multiple alternative power supply control strategies;

[0017] Quantitatively compare and qualitatively analyze multiple power supply alternatives to determine the optimal power supply control strategy.

[0018] Furthermore, the steps of constructing the power supply solution knowledge base include:

[0019] Divide the power usage scenarios of power protection objects according to power usage information and load distribution information;

[0020] According to different power consumption scenarios, a domain-oriented modeling method is used to build a feature vector model based on power supply demand, and a deep learning algorithm is used to build a typical load pattern of the power supply protection object to obtain a power supply demand portrait library;

[0021] According to the power supply demand portrait library and the feature vector model, knowledge graph and reasoning engine technology are used to ontologize and regularize domain knowledge and build a power supply solution knowledge base.

[0022] Furthermore, after the step of obtaining the optimal power supply control strategy, the method further includes:

[0023] Acquire real-time operating parameters of the power supply equipment, perform fault prediction and performance prediction on the power supply equipment according to the real-time operating parameters, and obtain prediction results of the power supply equipment;

[0024] Compare the prediction result of the power supply equipment of the first power protection object with the prediction result of the power supply equipment of the second power protection object, and select a third power supply equipment from the power supply equipment of the first power protection object according to the comparison result;

[0025] Perform a performance analysis on the third power supply device, and generate a maintenance plan for the third power supply device based on the performance analysis result.

[0026] Furthermore, after the step of obtaining the optimization control strategy of the first power protection object, the method further includes:

[0027] According to the emergency event of the first power supply protection object, a corresponding emergency plan is selected from the preset emergency plan model;

[0028] According to the real-time status of the first power protection object, the emergency plan is optimized to obtain the optimal emergency plan.

[0029] Furthermore, the steps of constructing the emergency plan model include:

[0030] Build a resource scheduling model based on the digital management of emergency material resources;

[0031] Intelligently reconstruct the emergency response process and solidify the standard operating procedures into workflow templates;

[0032] Analyze the historical data of power supply objects to generate typical emergency scenario portraits and corresponding emergency plans;

[0033] The resource scheduling model, the workflow template, the typical emergency scenario portrait and the corresponding emergency plan are used as an emergency plan model.

[0034] In a second aspect, the present invention provides a control strategy generation system for a power supply device, the system comprising:

[0035] An object classification module, used for classifying the power protection objects into first power protection objects and second power protection objects according to the object type of each power protection object;

[0036] A first control strategy generation module is used to obtain power supply equipment on the power supply path of the first power protection object, and perform performance evaluation on each power supply equipment to obtain equipment performance indicators;

[0037] A weighted directed graph model of the first power protection object is constructed based on the shortest path, and a performance evaluation of the power supply path is performed according to the key nodes, key paths and equipment performance indicators in the weighted directed graph model and using a hierarchical analysis method;

[0038] According to the performance evaluation result, the power supply control strategy of the first power protection object is optimized by using a rule-based reasoning method to obtain an optimized power supply control strategy of the first power protection object;

[0039] The second control strategy generation module is used to obtain the power consumption information and load distribution information of the second power protection object, perform matching reasoning through a preset power supply scheme knowledge base, generate a preliminary power supply control strategy, and optimize the preliminary power supply control strategy according to the power supply demand and scenario constraints of the second power protection object to obtain the optimal power supply control strategy for the second power protection object.

[0040] In a third aspect, an embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0041] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0042] The present invention provides a control strategy generation method, system, device and storage medium for power supply equipment. Through the method, the regional characteristics and power supply requirements of the power protection object are scientifically analyzed and evaluated, and the regional differences and power supply requirements can be accurately characterized, so as to realize the design of targeted power supply schemes, meet the differences and effectiveness of scheme design, and improve the efficiency of formulating and executing power supply schemes. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is a flow chart of a method for generating a control strategy for a power supply device according to an embodiment of the present invention;

[0044] Figure 2 is a structural schematic diagram of a control strategy generation system for a power supply device in an embodiment of the present invention;

[0045] Figure 3 It is a diagram of the internal structure of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] See also Figure 1 The first embodiment of the present invention provides a method for generating a control strategy for a power supply device, comprising steps S10 to S50:

[0048] Step S10, dividing the power protection objects into first power protection objects and second power protection objects according to the object type of each power protection object;

[0049] Step S20, obtaining power supply equipment on the power supply path of the first power protection object, and performing performance evaluation on each power supply equipment to obtain equipment performance indicators;

[0050] Step S30, constructing a weighted directed graph model of the first power protection object based on the shortest path, and performing a performance evaluation on the power supply path according to the key nodes, key paths and the equipment performance indicators in the weighted directed graph model and using a hierarchical analysis method;

[0051] Step S40, optimizing the power supply control strategy of the first power protection object by using a rule-based reasoning method according to the performance evaluation result, and obtaining an optimized power supply control strategy of the first power protection object;

[0052] Step S50, obtain the power consumption information and load distribution information of the second power protection object, perform matching reasoning through a preset power supply scheme knowledge base, generate a preliminary power supply control strategy, optimize the preliminary power supply control strategy according to the power supply demand and scenario constraints of the second power protection object, and obtain the optimal power supply control strategy for the second power protection object.

[0053] In the power system, power protection means stopping all planned maintenance work and switching operations to achieve a fully wired and fully protected operation state of the power grid. The "One Grid Map" integrates elements such as equipment use, monitoring, operation and maintenance, and production, and is used to support the extensive interconnection between power users, power grid companies, power generation companies, suppliers and their equipment. By connecting the topological structure of each link of the power grid, all relevant data involved in the production management and operation and maintenance of the power grid are integrated together to support the two main business lines of the power grid, the value of data is maximized, and the balance and efficient interconnection of energy flow, information flow, and business flow are achieved. For the power protection objects of the One Grid Map, due to the different types of power protection objects and power supply differences, there will be certain difficulties in collecting and analyzing the power supply equipment information. The power consumption characteristics, load distribution, and power supply requirements of different regions vary greatly. It is necessary to deeply analyze the regional characteristics and power supply needs, and comprehensively consider factors such as economy, reliability, and operability to formulate a practical power supply plan. However, there is currently a lack of scientific regional characteristic analysis and power supply demand assessment methods, which makes it difficult to accurately characterize regional differences and power supply requirements, resulting in insufficient pertinence and effectiveness of power supply plans. Based on this, the present invention provides an information analysis method that combines commonality and individuality to meet the power supply needs of different regions.

[0054] In the present invention, the power protection objects are divided into ordinary power protection objects and special power protection objects according to their types. Specifically, they can be divided according to the areas of the power protection objects, and the power protection objects in ordinary areas such as residents and enterprises are regarded as ordinary power protection objects, that is, the first power protection objects, while the power protection objects in key areas such as hospitals, airports and data centers are regarded as special power protection objects, that is, the second power protection objects. For different types of power protection objects, the analysis of their power supply information and the generation of power supply control schemes are different.

[0055] For the first power protection object, the present invention optimizes the power supply control strategy by evaluating the performance of the power supply equipment and the power supply path. Specifically, the performance of the power supply equipment on the power protection path of the first power protection object is first evaluated, and the evaluation steps include:

[0056] According to the preset performance evaluation baseline, determine whether the power supply devices on the power supply path have the same performance evaluation baseline, use the power supply devices with the same performance evaluation baseline as the first power supply devices, and use the remaining power supply devices as the second power supply devices;

[0057] According to the rated performance parameters of the first power supply device, a universal parameter model is constructed, and the actual performance parameters of the first power supply device are input into the universal parameter model for performance analysis to obtain device performance indicators of the first power supply device;

[0058] According to the actual performance parameters of the second power supply device, power flow calculation is performed on the second power supply device to obtain a device performance indicator of the second power supply device.

[0059] In this embodiment, since the power protection object is a common power protection object, the performance evaluation of the power supply equipment is carried out by common analysis. The premise of common analysis is to establish a performance evaluation baseline of common power supply equipment in advance. The performance evaluation baseline in this embodiment is generated by analyzing the basic information of the power supply equipment of each power protection object. Therefore, it is necessary to first collect the model, parameters and operating status of the power supply equipment of each power protection object, and conduct a preliminary analysis of the equipment specifications and configuration differences through the central processor to obtain the basic information of the power supply equipment, including basic parameters such as rated power, voltage level and frequency range. Specifically, through the intelligent sensors and monitoring devices deployed in each power protection object, key data such as the model, parameters and operating status of the power supply equipment are collected in real time. The Internet of Things technology is used to upload the collected data to the central processing server in real time through a secure and reliable wireless communication network, and a distributed storage and backup mechanism is used to ensure the integrity and accessibility of the data, so as to prepare for subsequent data analysis and mining.

[0060] After receiving the equipment data from each power protection community, the central processing server uses big data processing technologies such as Hadoop and Spark to perform rapid ETL (extraction, transformation, loading) operations on massive amounts of equipment information, and converts heterogeneous data into a unified format through data cleaning and standardization. Then, data mining algorithms are used to automatically extract key attribute fields of the equipment, such as basic parameters such as equipment model, rated power, voltage level, frequency range, as well as important information such as equipment load characteristics, energy consumption level, fault history, and maintenance records.

[0061] For example, intelligent sensors and monitoring devices are deployed in each power supply object, and IoT terminals based on the LoRa communication protocol are used to transmit data in the 915MHz frequency band. The transmission distance can reach 5-10 kilometers, and the maximum number of node connections can reach 1,000. At the same time, the AES-128 encryption algorithm is supported to ensure the security of data transmission. For massive amounts of device data, a Hadoop cluster can be used, with 10 nodes configured, each node equipped with a 32-core CPU, 128GB memory and 10TB storage. Distributed data processing and storage are achieved through MapReduce and HDFS, with a processing capacity of up to 100TB / day.

[0062] Then, the basic information of these power supply devices stored in the server is analyzed for correlation, and common problems and performance bottlenecks between power supply devices are identified, so as to obtain the performance evaluation baseline of power supply devices. Specifically, the extracted device attribute fields are compared and analyzed intelligently, and rule-based pattern recognition technologies such as decision trees and support vector machines are used to automatically discover the differences in power supply equipment specifications, configurations, and performance between different communities. At the same time, machine learning algorithms such as random forests and neural networks are used to establish a correlation model between device attributes and community electricity consumption characteristics. Through model training and optimization, the accuracy and comprehensiveness of device attribute analysis are continuously improved.

[0063] On this basis, knowledge graph technology is used to build a semantic association network between multi-dimensional attributes such as equipment specifications, performance indicators, and the community to which they belong, with the equipment model as the core, to provide data support for subsequent equipment optimization configuration.

[0064] In view of the analyzed equipment specification differences and potential risks, we use equipment performance analysis and fault prediction technology based on big data to establish an equipment health assessment model by mining the correlation of multi-source heterogeneous data such as equipment operating parameters and environmental factors. We use algorithms such as time series analysis and anomaly detection to identify in advance the performance degradation and fault signs that may occur in equipment under different working conditions.

[0065] Based on the common problems and performance bottlenecks of the identified equipment, and taking into account equipment parameters such as basic information, operating data, and fault repair records, differentiated evaluation indicators and weights are set according to different equipment types and application scenarios to build a baseline model for power supply equipment performance evaluation, thereby determining the performance evaluation baseline for each power supply equipment.

[0066] On the basis of the above steps, according to the topological structure and parameter information of the power supply equipment of the power protection object, the depth-first search algorithm is used to traverse the power supply path, obtain all the power supply equipment on the power supply path, and determine whether these power supply equipment have the same performance evaluation baseline. Based on the judgment result, the power supply equipment is divided into power supply equipment with a common baseline as the first power supply equipment, and the remaining power supply equipment is divided into the second power supply equipment. Then the parameters of the first power supply equipment are extracted and normalized to construct a general parameter model. The model contains the key performance parameters of the equipment, such as rated voltage, rated current, impedance parameters, etc.

[0067] For the first power supply equipment, when performing performance analysis, the general parameter model is reused, that is, the actual parameter values ​​of the equipment are substituted into the model for calculation and analysis, and the fuzzy comprehensive evaluation method is used to judge whether the equipment operation status is abnormal by comparing the deviation between the actual operating parameters of the equipment and the rated parameters of the model, thereby obtaining the equipment performance index. For the second power supply equipment, the Newton-Raphson method is used to calculate the power flow based on the actual parameter information of the equipment to obtain the equipment performance index.

[0068] After completing the performance analysis of a single device, the improved Dijkstra algorithm is used to construct a weighted directed graph model of the entire power supply path with the device as the node and the power supply line as the edge. By searching for key nodes and key paths in the graph model, the hierarchical analysis method is used to comprehensively evaluate the performance level and reliability level of the entire power supply path.

[0069] Finally, based on the comprehensive performance evaluation results of the power supply path and combined with the expert experience knowledge base, a rule-based reasoning method is used to generate corresponding optimization control strategies and measures, such as adjusting equipment operating parameters, optimizing the power supply path topology, etc., and the strategies and measures are sent to the control system for execution, so as to achieve continuous optimization of the power supply path performance of the power protection object.

[0070] Exemplarily, the power supply path is traversed by a depth-first search algorithm to obtain a set of power supply devices with a common baseline. For example, a power supply path contains 10 devices, 7 of which have a rated voltage of 10kV, and they can be classified as a set of devices with a common baseline. The parameter information of the device set is extracted and normalized to construct a general parameter model. For example, the short-circuit impedance parameter of the transformer can be normalized to a range of 02~12 as the input of the model. Determine whether the device belongs to a set with a common baseline. If it does, reuse the general parameter model for calculation and analysis; if it does not, use the Newton-Raphson method for power flow calculation. That is, for a transformer with a rated voltage of 10kV, directly substitute it into the general model for calculation; for a transformer with a voltage of 35kV, power flow calculation is required, and convergence is reached after 5 iterations. The fuzzy comprehensive evaluation method is used to determine whether the operating status of the equipment is abnormal. For example, the actual operating voltage of a transformer is 5kV, which has a 5% deviation from the rated voltage of 10kV, and exceeds the preset threshold of 3%, then an alarm message is triggered. The Dijkstra algorithm is used to construct a weighted directed graph model of the power supply path. For example, a graph model is constructed with 10 devices as nodes, 9 power supply lines as edges, and line impedance values ​​as edge weights. Key nodes and key paths are searched in the graph model, and the performance of the power supply path is comprehensively evaluated using the analytic hierarchy process. For example, the diameter of the graph is calculated to be 3, the key path is (transformer A-busbar B-switch C), and the weight of each device is (5, 3, 2). Combined with the device performance indicators, the performance score of the power supply path can be calculated to be 85. Finally, combined with the expert experience knowledge base, the rule-based reasoning method is used to optimize the existing control strategy and generate an optimized power supply control strategy. For example, when the voltage deviation rate of a power supply path exceeds 5%, the reasoning engine generates an optimized control strategy "adjust the transformer tap from the 3rd position to the 4th position" according to the rule "voltage deviation rate>5%->adjust the transformer tap position", and sends it to the control system for execution.

[0071] For the second power protection object, due to its particularity, commonality analysis cannot meet its power supply needs. Therefore, this embodiment adopts a personality analysis method to generate a power supply plan for the second power protection object. Specifically, it is necessary to first establish a power supply plan knowledge base for special power protection objects, and its construction steps include:

[0072] Divide the power usage scenarios of power protection objects according to power usage information and load distribution information;

[0073] According to different power consumption scenarios, a domain-oriented modeling method is used to build a feature vector model based on power supply demand, and a deep learning algorithm is used to build a typical load pattern of the power supply protection object to obtain a power supply demand portrait library;

[0074] According to the power supply demand portrait library and the feature vector model, knowledge graph and reasoning engine technology are used to ontologize and regularize domain knowledge and build a power supply solution knowledge base.

[0075] In this embodiment, the knowledge base is generated based on analysis of relevant information such as power consumption characteristics, load distribution, and power supply demand of special power protection objects. First, the database stores equipment data that cannot be commonly analyzed, including power consumption characteristics and load distribution information in key areas of hospitals, airports, and data centers, while ensuring real-time updating and efficient retrieval of data.

[0076] Specifically, for power supply equipment in key areas such as hospitals, airports, and data centers, real-time operating data is collected, including key indicators such as power load, power quality, and equipment temperature. Through IoT terminals such as smart meters and online monitoring devices, data collection is achieved at a frequency of minutes, while static data such as equipment nameplates, environmental parameters, and geographic locations are integrated, and multi-source heterogeneous data is transmitted back to the cloud in real time using high-speed wireless communication networks such as 5G and NB-IoT.

[0077] A personalized time series database is built on the cloud platform, using professional time series database management systems such as InfluxDB and OpenTSDB. Aiming at the characteristics of high concurrent writing, aggregate query and other loads, all-round optimization is carried out from multiple dimensions such as data storage format, query performance, hardware configuration, etc., to provide millisecond-level data writing and query response capabilities. At the same time, in combination with the different needs of real-time computing and offline processing, a Lambda architecture is built, and message queues such as Kafka are used to realize real-time data stream processing, and big data platforms such as Hadoop and Hive are used to realize offline data batch processing, build a unified data lake, and realize collaborative management of data and full life cycle value mining. Multi-dimensional label management is carried out for power supply operation data, and data is labeled and classified according to dimensions such as equipment type, region, and topological location, to build a flexible label system and indexing mechanism. Distributed search engine technologies such as Elasticsearch and Solr are used to realize rapid retrieval, aggregate computing and correlation analysis of massive time series data, laying a data foundation for subsequent personalized scenario analysis.

[0078] Then, for the input data of the knowledge base, a standardized data interface specification is formulated, using RESTful API and JSON format to define the data type, value range and constraints of key fields such as power consumption characteristics and load distribution, to ensure the accuracy, consistency and interpretability of data during cross-system transmission. The accuracy, timeliness and completeness of the data are evaluated and monitored in real time, and algorithms such as anomaly detection and data completion are used to clean and repair non-compliant data to ensure the high quality of input data.

[0079] Based on the input data, the typical power consumption scenarios of special power protection objects are comprehensively sorted out and classified, and the differentiated needs of the user side and the grid side are considered separately, such as the requirements of important users for power supply reliability and the demands of remote areas for power supply costs. Using a field-oriented modeling method, key elements such as power load curves, power equipment lists, and electricity bill settlement methods are abstracted to construct a feature vector model of personalized power supply demand. Using deep learning algorithms such as convolutional neural networks, the key features of the power load curve are automatically extracted, and clustering algorithms such as K-means and DBSCAN are used to divide the power supply area into several typical load modes to form a standardized power supply demand portrait library as a basic reference for power supply solution design.

[0080] Then, the knowledge graph and reasoning engine technology are introduced to ontologically and rule-basedly represent the knowledge in the fields of user electricity usage habits, power equipment selection, and power supply configuration, and to build a knowledge base system for personalized power supply solution design. In this knowledge base, the graph-based database Neo4j is used to store the knowledge graph, and the SWRL rule language is used to represent the reasoning rules, so that the intelligent matching and reasoning of knowledge can be realized through reasoning engines such as ApacheJena.

[0081] When the task of designing a plan for the second power supply protection object arrives, the preliminary power supply plan framework and key parameters can be quickly generated through knowledge base query and rule matching. Of course, expert review and revision steps can also be added to improve the efficiency and standardization of power supply plan design.

[0082] Due to the particularity of the second power supply object, there are different power supply requirements and scenario constraints. For example, for hospitals, the reliability requirements of their power supply focus on the continuity of power consumption of core loads such as emergency lighting, surgical equipment, and life support systems. For airports, due to the different distribution and change patterns of power loads in different terminals, aprons, runways and other areas at different times, it is necessary to focus on their power load changes. For data centers, due to their high density and high energy consumption, the focus is on energy efficiency optimization. Therefore, it is also necessary to optimize the preliminary plan based on different power supply requirements and scenario constraints. The specific optimization steps include:

[0083] According to the power supply demand and scenario constraints of the second power supply protection object, the network parameters of the power supply network in the preliminary power supply control strategy are globally optimized, and the heuristic algorithm and data planning method are used to coordinately optimize each power supply link to generate multiple alternative power supply control strategies;

[0084] Quantitatively compare and qualitatively analyze multiple power supply alternatives to determine the optimal power supply control strategy.

[0085] In this embodiment, an intelligent power supply scheme optimization algorithm is used to optimize the topology, equipment selection, parameter configuration, etc. of the power supply network in the preliminary power supply scheme in accordance with personalized power supply requirements and scenario constraints, under the premise of satisfying power supply reliability and power quality constraints. Heuristic algorithms such as particle swarm optimization algorithm, non-dominated sorting genetic algorithm, and mathematical programming methods such as mixed integer programming and random optimization are comprehensively applied, considering the coordinated optimization of source, network, load, and storage, exploring the application of new technologies such as flexible AC transmission and solid-state transformers in personalized power supply schemes, and improving the flexibility and adaptability of the power supply system. Thus, a variety of alternative solutions that meet the requirements are generated. Then, the optimal power supply control strategy is determined through quantitative indicator comparison and qualitative analysis.

[0086] In a preferred embodiment, the present invention fully considers the access requirements of new loads and distributed power sources such as new energy, energy storage, and electric vehicles, and incorporates new concepts and models such as ubiquitous power Internet of Things and energy Internet into the design of power supply solutions. In view of the randomness and volatility of distributed power generation, short-term power forecasting, dynamic electricity prices and other technologies are used to achieve the optimal scheduling and economic operation of distributed energy and conventional power grids. For demand response resources such as electric vehicles and energy storage, flexible and friendly power supply access and interaction strategies are formulated, and through demand-side management, virtual power plants and other technologies, coordination and interaction of sources, grids, loads and storage are achieved, thereby improving the social benefits and comprehensive value of the power supply system.

[0087] After the power supply plan is formed, the supporting design reports and drawings are automatically generated. Natural language generation and knowledge reasoning technology are used to intelligently generate text descriptions and instructions based on the design content. Through parametric modeling and template rendering, CAD graphics and 3D models that meet industry standards are automatically generated to improve the standardization and normalization of design results. At the same time, cloud rendering, AR / VR and other visual interaction technologies are fully applied to provide users with immersive power supply plan experience and demonstration, improve the perception and understanding of design plans, and promote multi-party collaboration and decision optimization.

[0088] For example, in the definition of data interface specifications, the OpenAPI specification is adopted, and the input and output parameters, data format, constraints, etc. of the interface are defined through YAML files to achieve self-description and self-documentation of the interface, and the Swagger tool is used to automatically generate interface call code and test cases to improve the usability and maintainability of the interface. For data quality management, data quality assessment indicators can be formulated through data exploration and statistical analysis, such as accuracy>98%, completeness>95%, timeliness<5min, etc., and tools such as PandasProfiling are used to generate data quality reports, and anomaly detection algorithms such as IsolationForest are used to identify and process missing values, outliers and other noise in the data.

[0089] In the personalized electricity demand analysis, the Seq2Seq model is used to model the user's electricity load curve. The encoder extracts the electricity consumption pattern characteristics, the decoder generates a typical load curve, and GMM Gaussian mixture clustering is used to divide users into 20 types of load patterns.

[0090] For the optimization of power supply network, an improved NSGA-III multi-objective genetic algorithm is adopted. The network loss rate, voltage qualification rate and investment cost are taken as optimization targets, and the selection, capacity and distribution of alternative lines and transformers are encoded. The Pareto optimal solution set is iteratively searched through selection, crossover and mutation operations, and the final optimal power supply plan is determined by combining the TOPSIS method.

[0091] In terms of new energy supporting technologies, attention mechanisms such as Transformer are used to predict the ultra-short-term fluctuations of wind and solar power generation, and combined with grid N-1 verification and electricity price response simulation, energy storage configuration and demand response strategy are optimized to increase the proportion of new energy consumption by more than 5%. By building a WebGL visualization platform based on THREE.js and integrating multi-source data such as BIM, GIS, and IOT, users are provided with a 720° panoramic display of construction plans, and the 5G+MEC architecture is used to achieve real-time positioning and digital twins of personnel, equipment, and materials, and realize integrated management of design and construction.

[0092] Through the control strategy generation method provided by the present invention, the regional characteristics and power supply demands of the power protection objects are scientifically analyzed and evaluated, the regional differences and power supply requirements are accurately portrayed, and the power supply scheme is designed in a targeted manner, which meets the diversity and effectiveness of the scheme design and improves the efficiency of formulating and executing the power supply scheme.

[0093] In a preferred embodiment, after the power supply control strategy is formulated, the method further includes:

[0094] Acquire real-time operating parameters of the power supply equipment, perform fault prediction and performance prediction on the power supply equipment according to the real-time operating parameters, and obtain prediction results of the power supply equipment;

[0095] Compare the prediction result of the power supply equipment of the first power protection object with the prediction result of the power supply equipment of the second power protection object, and select a third power supply equipment from the power supply equipment of the first power protection object according to the comparison result;

[0096] Perform a performance analysis on the third power supply device, and generate a maintenance plan for the third power supply device based on the performance analysis result.

[0097] In this embodiment, the execution of the personalized power supply plan is tracked in real time, and the operating status of the power supply equipment is monitored in real time. Then, by comparing the performance of the power supply equipment, it is determined whether the power supply equipment controlled by the common analysis method will have more potential faults or performance degradation than the power supply equipment controlled by the individual analysis method.

[0098] Specifically, firstly, a performance evaluation model of power supply equipment is established. This model includes a fault prediction model and a performance prediction model. For the fault prediction model, it is a data set constructed based on equipment fault data, and is constructed using machine learning algorithms such as XGBoost and LightGBM. Of course, it can also be constructed using a neural network model. For the performance prediction model, firstly, an indicator system is constructed from multiple dimensions such as equipment attributes, operating status, and maintenance records. The weight of each indicator is determined by the hierarchical analysis method. The comprehensive score of equipment performance is obtained by weighted average, and the K-means clustering algorithm is used to divide the equipment into four performance levels: excellent, good, medium, and poor. Then, the long short-term memory neural network (LSTM) is used to model the time series data of the equipment. By introducing the attention mechanism and the autoencoder structure, a multivariate time series anomaly detection framework is constructed to achieve the trend prediction of equipment performance. For the input data of the LSTM model, in addition to the performance level of the equipment and conventional equipment operation data such as temperature and current, it also includes attribute parameters related to the fault frequency. Among them, the attribute parameters related to the fault frequency are obtained based on data statistics, decision tree analysis, and support vector machine classification. The specific acquisition steps include:

[0099] Conduct statistical analysis on the equipment data of power supply equipment to obtain equipment performance guidance parameters;

[0100] Obtain equipment parameters of the power supply equipment, classify the equipment parameters through the decision tree algorithm and equipment performance guidance parameters, and determine key parameters from the equipment parameters;

[0101] Combine key parameters with historical fault data of power supply equipment, use support vector machine algorithm to classify the fault frequency of power supply equipment and determine the frequency of fault occurrence;

[0102] According to the classification results, attribute parameters related to the frequency of fault occurrence are selected from the key parameters.

[0103] In this embodiment, based on the existing power supply equipment data, such as voltage, current, power, temperature and other parameters, the statistical analysis results of various parameters between different devices are obtained. Through these statistical results, a preliminary description of the equipment performance can be obtained, including the average value, standard deviation, maximum value and minimum value of various parameters, etc. These descriptions are helpful for further analyzing the distribution of equipment performance.

[0104] The decision tree algorithm is used to classify the equipment performance by taking the equipment parameter data as input. Through the decision tree classification process, the three levels of equipment performance, high, medium and low, can be determined. The output of this process not only gives the performance level of the equipment, but also reveals which parameters play a decisive role in the classification of equipment performance, such as voltage stability, current peak, etc.

[0105] The key attributes in the decision tree classification results, such as rated voltage and current thresholds, are obtained to further evaluate the failure frequency of the equipment. By combining these key attributes with the historical failure records of the equipment, the support vector machine (SVM) algorithm is used to classify the failure frequency of the equipment to determine whether the frequency of equipment failure is frequent, occasional, or rare. Through the SVM classification results, attributes closely related to the equipment failure frequency, such as heat dissipation and insulation level, are obtained. These attributes will be used to establish a comprehensive performance prediction model. This model not only includes performance levels, but also integrates failure frequency information, which can accurately predict the trend of equipment performance, further providing an important reference for equipment maintenance and operation, and ensuring the stable operation of power supply equipment under various conditions.

[0106] After the performance evaluation model is constructed through the above steps, the performance of each power supply device can be evaluated, including the potential failures and performance trends of the equipment. Then, the evaluation results of the first power supply device are compared with the evaluation results of the second power supply device. If the number of potential failures of a first power supply device is significantly larger than that of the second power supply device, or the performance is significantly reduced compared with the second power supply device, a secondary personalized analysis is performed on these power supply devices to strengthen the maintenance and optimization decision-making of the equipment. Specifically, mathematical modeling methods such as time series analysis and survival analysis are used to predict the dynamic change trend and remaining life distribution of the equipment health status. Through methods such as Monte Carlo simulation, the equipment reliability improvement effect and maintenance cost investment under different maintenance strategies are quantified, and algorithms such as multi-objective optimization and reinforcement learning are used to solve the optimal state maintenance timing, maintenance interval cycle, maintenance intensity and other decision variables from the perspective of the entire life cycle of the equipment, forming a dynamic optimization and closed-loop control equipment intelligent operation and maintenance decision-making system. In addition, for equipment with low scores that need to be optimized and maintained, equipment knowledge graphs, case reasoning and other technologies can also be used to match equipment performance shortcomings and failure mode characteristics, and automatically generate potential equipment failure causes and targeted maintenance and maintenance suggestions.

[0107] Furthermore, in another preferred embodiment, an emergency plan function of the power supply system may be added to the first power protection object, and the specific steps include:

[0108] According to the emergency event of the first power supply protection object, a corresponding emergency plan is selected from the preset emergency plan model;

[0109] According to the real-time status of the first power protection object, the emergency plan is optimized to obtain the optimal emergency plan.

[0110] The emergency plan model in this embodiment includes emergency resource allocation and response processes. The power supply system generates a power supply strategy for dealing with emergencies based on the input data, so that the power supply plan can be adjusted in an emergency to deal with potential power outages. The steps of building the emergency plan model include:

[0111] Build a resource scheduling model based on the digital management of emergency material resources;

[0112] Intelligently reconstruct the emergency response process and solidify the standard operating procedures into workflow templates;

[0113] Analyze the historical data of power supply objects to generate typical emergency scenario portraits and corresponding emergency plans;

[0114] The resource scheduling model, the workflow template, the typical emergency scenario portrait and the corresponding emergency plan are used as an emergency plan model.

[0115] In this embodiment, firstly, based on the Internet of Things technology, emergency materials such as backup power vehicles, generator sets, emergency lighting equipment, etc. are digitally managed. RFID electronic tags, intelligent storage systems, etc. are used to achieve accurate resource positioning, inventory counting, status monitoring, etc., and the spatial distribution and deployment path of emergency resources are displayed in real time through the GIS system to achieve visual management and intelligent scheduling of emergency resources.

[0116] Based on digital management, a multi-objective optimization resource scheduling model is constructed. Combined with factors such as facility site selection, vehicle routing, and scheduling sequence, heuristic algorithms such as ant colony algorithm and genetic algorithm are used to solve the optimal solution for resource allocation and improve the spatiotemporal matching and utilization efficiency of emergency resources.

[0117] Secondly, the emergency response process is reconstructed intelligently, and the standard operating procedures for scenarios such as transmission line fault repair, substation accident handling, and emergency power supply to important users are solidified into workflow templates. The model is used to achieve rapid process loading and semi-automatic collaboration of emergency response. Preferably, blockchain technology can also be used to record the entire emergency response process in a "one-step-one-chain" manner to ensure real-time reliability and traceability of emergency command execution.

[0118] Then, by analyzing historical data, we extract and form typical emergency scene portraits, and automatically generate corresponding emergency plans through intelligent analysis models. For example, we automatically match emergency power supply plans for sudden power outages of important users, and dynamically optimize them in combination with on-site conditions to achieve refined emergency management. Specifically, through causal inference, comparative learning and other technologies, we discover the causes, consequences and evolution laws of emergencies from massive historical events, use knowledge graph technology to build domain knowledge ontology, and use rule reasoning, deep reinforcement learning and other technologies to achieve end-to-end emergency auxiliary decision-making from scene perception to strategy generation, and form an intelligent analysis model from anomaly detection, impact analysis to strategy optimization to achieve self-learning, self-optimization and adaptive generation of emergency plans.

[0119] Furthermore, in order to improve the resource utilization rate of the emergency plan, the present invention also constructs a multi-dimensional simulation space of the power grid, environment, and scenario through digital twin technology, systematically evaluates the impact of various emergencies on the operation of the power grid, and optimizes the emergency response strategy through simulation, providing an immersive emergency drill and auxiliary decision-making environment to achieve the optimization of the emergency plan. At the same time, the microservice architecture and open platform are adopted to achieve data sharing and business collaboration with meteorological, transportation, emergency and other departments, and integrate with internal systems such as distribution automation and distribution and dispatching, and realize overall coordination and integrated linkage through the "1+N" multi-level intelligent emergency command and dispatch system.

[0120] The present embodiment provides a control strategy generation method for power supply equipment. By scientifically analyzing and evaluating the regional characteristics and power supply demands of power protection objects, the method accurately describes the regional differences and power supply requirements, and realizes the targeted design of power supply plans for different power protection objects. It meets the design differences and effectiveness requirements of power supply plans in different regions, and improves the efficiency of formulating and implementing power supply plans.

[0121] See also Figure 2 Based on the same inventive concept, a control strategy generation system for a power supply device proposed in a second embodiment of the present invention includes:

[0122] An object classification module 10 is used to classify the power protection objects into first power protection objects and second power protection objects according to the object type of each power protection object;

[0123] The first control strategy generating module 20 is used to obtain the power supply equipment on the power supply path of the first power protection object, and perform performance evaluation on each power supply equipment to obtain equipment performance indicators;

[0124] A weighted directed graph model of the first power protection object is constructed based on the shortest path, and a performance evaluation of the power supply path is performed according to the key nodes, key paths and equipment performance indicators in the weighted directed graph model and using a hierarchical analysis method;

[0125] According to the performance evaluation result, the power supply control strategy of the first power protection object is optimized by using a rule-based reasoning method to obtain an optimized power supply control strategy of the first power protection object;

[0126] The second control strategy generation module 30 is used to obtain the power consumption information and load distribution information of the second power protection object, perform matching reasoning through a preset power supply scheme knowledge base, generate a preliminary power supply control strategy, and optimize the preliminary power supply control strategy according to the power supply demand and scenario constraints of the second power protection object to obtain the optimal power supply control strategy for the second power protection object.

[0127] The technical features and technical effects of the control strategy generation system for the power supply equipment proposed in the embodiment of the present invention are the same as those of the method proposed in the embodiment of the present invention, and will not be described in detail here. Each module in the control strategy generation system for the above-mentioned power supply equipment can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0128] In addition, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0129] See also Figure 3 , an internal structure diagram of a computer device in an embodiment, the computer device may specifically be a terminal or a server. The computer device includes a processor, a memory, a network interface, a display, a camera and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a control strategy generation method for a power supply device is implemented. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, a trackball or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0130] It can be understood by those skilled in the art that Figure 3The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computing device may include more or fewer components than shown in the figure, or combine certain components, or have the same component arrangement.

[0131] In addition, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0132] In summary, an embodiment of the present invention proposes a control strategy generation method, system, device and storage medium for power supply equipment. The method divides the power protection objects into a first power protection object and a second power protection object according to the object type of each power protection object; obtains the power supply equipment on the power supply path of the first power protection object, and performs performance evaluation on each power supply equipment to obtain equipment performance indicators; constructs a weighted directed graph model of the first power protection object based on the shortest path, and performs performance evaluation on the power supply path according to the key nodes, key paths and equipment performance indicators in the weighted directed graph model and the hierarchical analysis method; optimizes the power supply control strategy of the first power protection object according to the performance evaluation result by using a rule-based reasoning method to obtain the optimized power supply control strategy of the first power protection object; obtains the power consumption information and load distribution information of the second power protection object, performs matching reasoning through a preset power supply scheme knowledge base, generates a preliminary power supply control strategy, and optimizes the preliminary power supply control strategy according to the power supply demand and scenario constraints of the second power protection object to obtain the optimal power supply control strategy for the second power protection object. The present invention scientifically analyzes and evaluates the regional characteristics and power supply needs of the power protection objects, accurately describes the regional differences and power supply requirements, and designs power supply plans in a targeted manner, thereby meeting the diversity and effectiveness of the plan design and improving the efficiency of formulating and implementing the power supply plan.

[0133] Each embodiment in this specification is described in a progressive manner, and the same or similar parts of each embodiment can be directly referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. It should be noted that the technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above-mentioned embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0134] The above-mentioned embodiments only express several preferred implementation modes of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in the technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention, and these improvements and substitutions should also be regarded as the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be based on the protection scope of the claims.

Claims

1. A control strategy generation method for a power supply device, characterized in that: include: According to the object type of each power protection object, the power protection object is divided into a first power protection object and a second power protection object; Acquire power supply equipment on the power supply path of the first power protection object, and perform performance evaluation on each power supply equipment to obtain equipment performance indicators; A weighted directed graph model of the first power protection object is constructed based on the shortest path, and the performance of the power supply path is evaluated according to the key nodes, key paths and equipment performance indicators in the weighted directed graph model and using the analytic hierarchy process; wherein the weighted directed graph model uses the power supply equipment of the first power protection object as a node, the power supply line as an edge, and the impedance value of the power supply line as the weight of the edge; According to the performance evaluation result, the power supply control strategy of the first power protection object is optimized by using a rule-based reasoning method to obtain an optimized power supply control strategy of the first power protection object; Obtain the power consumption information and load distribution information of the second power protection object, perform matching reasoning through a preset power supply scheme knowledge base, generate a preliminary power supply control strategy, optimize the preliminary power supply control strategy according to the power supply demand and scenario constraints of the second power protection object, and obtain the optimal power supply control strategy for the second power protection object; The step of obtaining power supply equipment on the power supply path of the first power protection object and performing performance evaluation on each power supply equipment to obtain equipment performance indicators includes: According to the preset performance evaluation baseline, determine whether the power supply devices on the power supply path have the same performance evaluation baseline, use the power supply devices with the same performance evaluation baseline as the first power supply devices, and use the remaining power supply devices as the second power supply devices; According to the rated performance parameters of the first power supply device, a universal parameter model is constructed, and the actual performance parameters of the first power supply device are input into the universal parameter model for performance analysis to obtain device performance indicators of the first power supply device; According to the actual performance parameters of the second power supply device, power flow calculation is performed on the second power supply device to obtain a device performance indicator of the second power supply device.

2. The control strategy generation method for power supply equipment according to claim 1, characterized in that: The step of optimizing the preliminary power supply control strategy according to the power supply demand and scenario constraints of the second power protection object to obtain the optimal power supply control strategy for the second power protection object includes: According to the power supply demand and scenario constraints of the second power supply protection object, the network parameters of the power supply network in the preliminary power supply control strategy are globally optimized, and the heuristic algorithm and data planning method are used to coordinately optimize each power supply link to generate multiple alternative power supply control strategies; Quantitatively compare and qualitatively analyze multiple power supply alternatives to determine the optimal power supply control strategy.

3. The control strategy generation method for power supply equipment according to claim 1, characterized in that: The steps of constructing the power supply scheme knowledge base include: Divide the power usage scenarios of power protection objects according to power usage information and load distribution information; According to different power consumption scenarios, a domain-oriented modeling method is used to build a feature vector model based on power supply demand, and a deep learning algorithm is used to build a typical load pattern of the power supply protection object to obtain a power supply demand portrait library; According to the power supply demand portrait library and the feature vector model, knowledge graph and reasoning engine technology are used to ontologize and regularize domain knowledge and build a power supply solution knowledge base.

4. The control strategy generation method for power supply equipment according to claim 1, characterized in that: After the step of obtaining the optimal power supply control strategy, the method further includes: Acquire real-time operating parameters of the power supply equipment, perform fault prediction and performance prediction on the power supply equipment according to the real-time operating parameters, and obtain prediction results of the power supply equipment; Compare the prediction result of the power supply equipment of the first power protection object with the prediction result of the power supply equipment of the second power protection object, and select a third power supply equipment from the power supply equipment of the first power protection object according to the comparison result; Perform a performance analysis on the third power supply device, and generate a maintenance plan for the third power supply device based on the performance analysis result.

5. The control strategy generation method for power supply equipment according to claim 1, characterized in that: After the step of obtaining the optimization control strategy for the first power protection object, the method further includes: According to the emergency event of the first power supply protection object, a corresponding emergency plan is selected from the preset emergency plan model; According to the real-time status of the first power protection object, the emergency plan is optimized to obtain the optimal emergency plan.

6. The control strategy generation method for power supply equipment according to claim 5, characterized in that: The steps of constructing the emergency plan model include: Build a resource scheduling model based on the digital management of emergency material resources; Intelligently reconstruct the emergency response process and solidify the standard operating procedures into workflow templates; Analyze the historical data of power supply objects to generate typical emergency scenario portraits and corresponding emergency plans; The resource scheduling model, the workflow template, the typical emergency scenario portrait and the corresponding emergency plan are used as an emergency plan model.

7. A control strategy generation system for power supply equipment, characterized in that: include: An object classification module, used for classifying the power protection objects into first power protection objects and second power protection objects according to the object type of each power protection object; A first control strategy generation module is used to obtain power supply equipment on the power supply path of the first power protection object, and perform performance evaluation on each power supply equipment to obtain equipment performance indicators; A weighted directed graph model of the first power protection object is constructed based on the shortest path, and the performance of the power supply path is evaluated according to the key nodes, key paths and equipment performance indicators in the weighted directed graph model and using the analytic hierarchy process; wherein the weighted directed graph model uses the power supply equipment of the first power protection object as a node, the power supply line as an edge, and the impedance value of the power supply line as the weight of the edge; According to the performance evaluation result, the power supply control strategy of the first power protection object is optimized by using a rule-based reasoning method to obtain an optimized power supply control strategy of the first power protection object; The step of obtaining power supply equipment on the power supply path of the first power protection object and performing performance evaluation on each power supply equipment to obtain equipment performance indicators includes: According to the preset performance evaluation baseline, determine whether the power supply devices on the power supply path have the same performance evaluation baseline, use the power supply devices with the same performance evaluation baseline as the first power supply devices, and use the remaining power supply devices as the second power supply devices; According to the rated performance parameters of the first power supply device, a universal parameter model is constructed, and the actual performance parameters of the first power supply device are input into the universal parameter model for performance analysis to obtain device performance indicators of the first power supply device; According to the actual performance parameters of the second power supply device, power flow calculation is performed on the second power supply device to obtain a device performance index of the second power supply device; The second control strategy generation module is used to obtain the power consumption information and load distribution information of the second power protection object, perform matching reasoning through a preset power supply scheme knowledge base, generate a preliminary power supply control strategy, and optimize the preliminary power supply control strategy according to the power supply demand and scenario constraints of the second power protection object to obtain the optimal power supply control strategy for the second power protection object.

8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. 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 6 are implemented.

Citation Information

Patent Citations

  • Automatic regional power grid voltage reactive power control method based on regional strategy optimization

    CN103475003A

  • Method for determining medium and long term voltage safety and stability preventive control strategy

    CN109638815A