Electric power design enterprise intelligent auxiliary system based on knowledge base big data

Abstract

The invention relates to the field of electric power design, and provides an electric power design enterprise intelligent auxiliary system based on knowledge base big data, and the system comprises the steps: receiving an electric power design scheme of a user side, and determining an electric power dispatching state and an electric power design demand; the design function component representing the power dispatching state and a user triggering operation pre-configured from a user side serve as calling requests of the design function component, and a request calling library of the design function component is built based on preset knowledge base big data; an auxiliary sandbox is configured between the request calling library and the user side, and user triggering operation corresponding to the calling request is converted into an execution script of the user side through the auxiliary sandbox; according to the execution script, generating a first simulation model of the current power design scheme in a power design program of the user side; and generating an electric power design evaluation matrix, judging whether design defects exist or not through the electric power design evaluation matrix, and generating a target simulation model and electric power design data corresponding to the target simulation model.

Description

Technical Field

[0001] The present invention relates to the field of power design, and particularly to a smart auxiliary system for power design enterprises based on knowledge base big data. Background Art

[0002] At present, as an important part of the country's infrastructure, power grid projects involve a large amount of data exchange and information sharing in the process of design, construction, and operation and maintenance, and are facing the need for digital transformation; digitalization can not only improve the efficiency of design and construction, but also enhance the intelligent management level of the power grid, and improve the safety and reliability of power grid operation. The application of BIM (Building Information Modeling) in the field of power grid engineering design has gradually matured. It realizes the informatization management of the entire life cycle of design, construction, and management by creating a digital model containing physical and functional information; applying BIM to the field of power grid engineering design helps to improve design quality, optimize the construction process, and reduce operation and maintenance costs. At present, some enterprises have developed power grid engineering design platforms. Such platforms integrate geographic information technology, three-dimensional modeling technology, and digital collaborative design technology, and can meet the visualization and intelligent construction needs in stages such as power grid planning and design. Achieve the development goals of full-process three-dimensional visualization, integrated work platform, modular equipment and facilities, and mechanized on-site installation; will be deeply integrated with new technologies such as big data, cloud computing, Internet of Things, and artificial intelligence to promote the digital and intelligent transformation of the power grid.

[0003] Although the power design and construction in our country have achieved certain development and made substantial breakthroughs, in the actual development process, there are still many problems to be solved in our country's power design, specifically as follows:

[0004] In the prior art, power design often relies on the manual operation and experience of designers, which may lead to a slow design process and often insufficient design risk assessment, resulting in problems in the construction and operation stages.

[0005] In traditional design, due to the lack of a standardized design process, it may lead to inconsistent design results, and it is difficult to effectively inherit and share the knowledge and experience of senior designers. Summary of the Invention

[0006] The present invention proposes a smart auxiliary system for power design enterprises based on knowledge base big data, which is used to solve the problems in the prior art that power design often relies on the manual operation and experience of designers, which may lead to a slow design process and often insufficient design risk assessment, resulting in problems in the construction and operation stages; in traditional design, due to the lack of a standardized design process, it may lead to inconsistent design results, and it is difficult to effectively inherit and share the knowledge and experience of senior designers.

[0007] The present invention proposes a smart auxiliary system for power design enterprises based on big data in a knowledge base, including:

[0008] A design analysis module: used to receive a power design scheme from a user terminal and determine the power dispatching status and power design requirements;

[0009] A design request module: used to take the design function components representing the power dispatching status and the user trigger operations pre-configured from the user terminal as call requests for the design function components, and build a request call library for the design function components based on the preset big data in the knowledge base;

[0010] A sandbox processing module: used to configure an auxiliary sandbox between the request call library and the user terminal, and convert the user trigger operation corresponding to the call request into an execution script for the user terminal through the auxiliary sandbox;

[0011] A power simulation module: used to generate a first simulation model of the current power design scheme in the power design program of the user terminal according to the execution script;

[0012] A simulation evaluation module: used to generate a power design evaluation matrix according to the first simulation model and the power design requirements, and determine whether there are design defects through the power design evaluation matrix, and generate a target simulation model and power design data corresponding to the target simulation model based on the design defects.

[0013] Furthermore, it is characterized in that when receiving the power design scheme of the user terminal, an auxiliary analysis network is configured based on the preset first design path and second design path respectively;

[0014] Among them, the auxiliary analysis network includes a node graph calculation platform docked with the first design path and a load forecasting network docked with the second design path;

[0015] Each graph node in the node graph calculation platform corresponds to a power dispatching node;

[0016] The load forecasting network is used to estimate the load interval of each power dispatching node and determine the corresponding power item data.

[0017] Furthermore, the trigger operations include voice trigger operations and data call trigger operations;

[0018] Among them, when the trigger operation is a voice trigger operation, the user voice is responded to, and based on the preset voice Q&A model, multiple Q&A candidate entity information corresponding to different call requests is generated, and the Q&A candidate entity information is generated in real time through the preset question answering model from the power design data in the knowledge base big data;

[0019] When the trigger operation is a data call trigger operation, determine the data path complexity of the power design data called by the user, generate a power design tool function entity corresponding to the call request based on the data path complexity, and determine the target power design function component through the data path complexity.

[0020] Furthermore, the knowledge base big data further includes a power design analysis network and a power design database;

[0021] Among them, the power design analysis network is used to analyze the call request through the power design database and generate a call function through the established request call library;

[0022] The power design database includes: a power demand analysis index database, a power system composition database, a power network architecture database, a power index constraint analysis database, a power design database, and a power fault analysis database.

[0023] Furthermore, the request call library for building the design function component based on the preset knowledge base big data includes:

[0024] Build function frameworks for different power design scenarios and match power layout parameters with power design attributes to different power design scenarios with power dispatch nodes;

[0025] Determine different design function components according to the power layout parameters;

[0026] Match the design function components with the function functions of the function frameworks in different power design scenarios and perform granularity slicing of different power dispatch nodes on the matched function frameworks;

[0027] Obtain the function databases of different power design scenarios after granularity slicing, and perform spatial aggregation on the design function components corresponding to the function databases to generate a request call library after spatial aggregation.

[0028] Furthermore, the auxiliary sandbox is used to determine the corresponding call data in the request call library according to the call request of the user side and convert it into an execution script for the user side;

[0029] Among them, the auxiliary sandbox includes: a function sandbox and a display sandbox.

[0030] Furthermore, the conversion into an execution script for the user side includes:

[0031] Obtain the power design requirements of the call data on the user side and determine the execution method of the call data;

[0032] According to the execution method, send a conversion request for the power design requirement data to the corresponding auxiliary sandbox;

[0033] Based on the conversion request by the auxiliary sandbox, convert the call data into an application instance of the execution script through a preset conversion tool;

[0034] Among them, the conversion tool is called through the conversion tool library in the knowledge base big data;

[0035] Generate a target execution script according to the application instance.

[0036] Furthermore, generating a first simulation model of the current power design scheme in the power design program on the user side includes:

[0037] Input the power design scheme into a preset power design program to generate an initial power visual model and an initial power dispatching state display model;

[0038] Based on the initial power visual model and the initial power dispatching state display model, construct a power operation state simulation model, and use the power operation state simulation model to determine the node parameters of different power dispatching nodes;

[0039] According to the node parameters, determine the power simulation model corresponding to the power design scheme.

[0040] Furthermore, the method for generating a power design evaluation matrix according to the first simulation model and power design requirements includes:

[0041] Obtain the associated nodes between the first simulation model and the power design requirements, where the associated nodes are based on the power simulation design requirements and the corresponding design nodes in the power simulation model;

[0042] Based on the associated nodes, establish a design layout network for power design;

[0043] Based on the user relationship network, calculate the demand matching values of each dispatching node for power design;

[0044] Based on the demand matching values, generate the evaluation parameters of the power design scheme at each dispatching node;

[0045] Generate a power design evaluation matrix according to the evaluation parameters.

[0046] Furthermore, the method for determining whether there are design defects includes:

[0047] According to the power design evaluation matrix, obtain the evaluation values of each dispatching node and locate the deviation index of each dispatching node;

[0048] According to the deviation index, predict the operation state tendency information of each dispatching node under each power design requirement condition, and identify the load factor of the corresponding dispatching node;

[0049] Under the preset power supply, judge the fluctuation compensation coefficient of each dispatching node according to the load factor and deviation index;

[0050] Judge whether the fluctuation compensation coefficient exceeds the preset defect threshold according to the fluctuation compensation coefficient;

[0051] When it does not exceed the defect threshold, determine the corresponding target simulation parameters.

[0052] The beneficial effects of the present invention are as follows:

[0053] By automatically calling the design function components and execution scripts, the system can greatly improve the efficiency of power design, reduce manual operations and repetitive work. Using the knowledge base big data and simulation models, the system can help designers discover and correct design defects, thereby improving the quality and reliability of the design. Through simulation and evaluation, the system can predict the performance of the design before actual construction, reducing construction risks and operation risks caused by improper design.

[0054] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in the written specification and the drawings.

[0055] The technical solutions of the present invention will be further described in detail below through the drawings and embodiments. Description of the Drawings

[0056] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0057] Figure 1 is the system composition diagram of a power design enterprise intelligent assistance system based on knowledge base big data in an embodiment of the present invention;

[0058] Figure 2 is the positioning flowchart of the power design scheme in an embodiment of the present invention;

[0059] Figure 3 is the entity generation flowchart of the power design tool function in an embodiment of the present invention; Detailed Embodiments

[0060] The following describes the preferred embodiments of the present invention with reference to the drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0061] As Figure 1As shown in the figure, the present invention proposes an intelligent assistance system for power design enterprises based on big data in a knowledge base, specifically including:

[0062] The design analysis module receives the power design scheme from the user side and conducts in-depth analysis on it. Specifically, it needs to identify the key technical points involved in these design schemes, understand the requirements therein, and at the same time take into account the actual application scenarios and conditions. In this way, we can obtain a comprehensive understanding of the technical details and implementation conditions of the design scheme, providing a basis for subsequent work.

[0063] The design request module converts the requirements of the design scheme we just analyzed into a form that users can understand and use through a pre-configured method. We will place various functional modules required by the design scheme, such as power dispatching status monitoring, user-triggered operations, etc., in a special database in the form of a request call. In this way, when users need to call these functions, they only need to directly call the corresponding database to quickly and accurately obtain the required information.

[0064] The sandbox processing module functions to set up an auxiliary sandbox environment between the request call library and the user side. In this environment, we convert various operations of the user into instructions that the system can understand, and then pass these instructions to the power design program on the user side. This can ensure the security and consistency of the user's operations.

[0065] The power simulation module generates the first simulation model in the power design program on the user side according to the execution script generated by the power simulation module. The execution script contains all the operation steps and conditions on the user side. The power simulation module generates a simulated result, that is, the first simulation model of the current power design scheme, by simulating these steps and conditions.

[0066] The simulation evaluation module generates a power design evaluation matrix based on the simulation model generated by the power simulation module and in combination with our analysis of the power design requirements. Through this matrix, we can see whether the current power design scheme meets our requirements and whether there are areas that need to be improved or optimized. If so, we will generate a new simulation model and optimize it to meet our requirements.

[0067] The beneficial effects of the above technical solutions are as follows:

[0068] By automatically invoking design function components and executing scripts, the system can significantly improve the efficiency of power design, reducing manual operations and repetitive work. Utilizing the big data in the knowledge base and simulation models, the system can assist designers in discovering and correcting design flaws, thereby enhancing the quality and reliability of the design. Through simulation and evaluation, the system can predict the performance of the design before actual construction, reducing construction risks and operation risks caused by improper design.

[0069] As an embodiment of the present invention, as Figure 2 shown, first, the system receives the power design scheme submitted by the user, which may include a series of operation steps and requirements. The system will analyze this scheme, identify the key points and potential problems therein, and provide them for the user's reference.

[0070] Secondly, the system will recommend possible operation paths for the user according to the preset first design path and second design path. These two paths may provide different results and suggestions. For example, the first path may lead to system stability problems, while the second path may bring higher efficiency but may sacrifice a certain degree of stability. The choice is up to the user.

[0071] Then, the system will connect the user's operation selection to the node graph calculation platform docked with the first design path, and conduct detailed analysis and calculation through this platform. Each node corresponds to a power dispatching node. That is to say, if the user selects the first path, the operating conditions of the corresponding power dispatching node will be displayed on the node graph calculation platform.

[0072] Finally, the system will connect the user's operation selection to the load forecasting network docked with the second design path. This network will estimate the load intervals of each power dispatching node according to the user's operation selection, and determine the corresponding power item data based on these load intervals. In this way, the user can formulate the final power design scheme based on these data.

[0073] As an embodiment of the present invention, as Figure 3 shown, in such a system, when the user issues a voice request, the system should be able to understand the user's language and make appropriate responses. This may require the system to use natural language processing technology to identify and understand the user's voice, and convert it into text format for further processing. Then, the system can use the preset voice Q&A model to generate multiple candidate answers, which should vary according to different user requests. These candidate answers can be generated in real time through the preset question answering model trained with power design data from the knowledge base big data.

[0074] When a user issues a data call request, the system needs to determine the source and path of the data. This may require the system to use a data path complexity model to determine the specific source and path of the data, and generate a power design tool function entity corresponding to the data call request based on this path. This function entity should be able to call specific power design function components to help users complete their tasks.

[0075] As an embodiment of the present invention, the call request submitted by the user is analyzed, and a corresponding call function is generated according to the content of the request. This call function can be called by the power design application on the user side to complete the tasks required by the user.

[0076] The power design database is a very important component, which contains all the data and information required in the power design process. It includes multiple sub-databases such as the power demand analysis index database, the power system composition database, the power network architecture database, the power index constraint analysis database, the power design specification database, and the power fault analysis database. These sub-databases are all essential parts of the power design process and can provide users with rich data and information support.

[0077] As an embodiment of the present invention, this method of building a request call library for design function components based on a preset knowledge base big data first builds function frameworks for different power design scenarios and matches power layout parameters with power design attributes to these scenarios. Then, according to the power layout parameters, different design function components are determined and matched with the function functions of the function framework. After the matching is completed, the matched function framework is sliced at different power scheduling node granularities. Finally, the function databases of different power design scenarios after granularity slicing are obtained, and the corresponding design function components are spatially aggregated to finally generate a spatially aggregated request call library.

[0078] As an embodiment of the present invention, this application is divided into two subsystems: a function sandbox and a display sandbox.

[0079] The function sandbox is mainly responsible for processing various power design requests from users. It will query the corresponding data according to the call requests submitted by users in the request call library and convert them into execution scripts on the user side. In this way, users can directly run these scripts in their own power design programs without modifying the existing code.

[0080] The display sandbox is mainly used to display and explain the execution scripts generated by the function sandbox. It can present the key data and results during the execution process to users in real time, allowing users to intuitively understand the operation of the power design and facilitating users to adjust and optimize their design schemes.

[0081] These two sandboxes can not only work independently, but also cooperate with each other to jointly complete the power design tasks on the user side.

[0082] As an embodiment of the present invention, obtain the power design requirements of the call data on the user side and determine the execution mode of the call data; according to the execution mode, send a conversion request for the power design requirement data to the corresponding auxiliary sandbox;

[0083] Through the auxiliary sandbox, according to the conversion request, convert the call data into an application instance of the execution script through a preset conversion tool; wherein, the conversion tool is called through the conversion tool library in the knowledge base big data;

[0084] Generate a target execution script according to the application instance.

[0085] The "call data" here not only includes the power design requirements on the user side, but also includes other relevant information that the user side may need, such as equipment parameters, operating conditions, etc. These data will be converted into an application instance of the execution script after being processed by the auxiliary sandbox. This application instance is the final target execution script we require.

[0086] The key to this process is to find the corresponding execution mode according to the user's requirements, and then use the preset conversion tool to convert this execution mode into a specific application instance. Finally, we obtain this application instance, which is the target execution script we require.

[0087] In this process, I used the knowledge base big data and helped us complete this conversion process by calling the conversion tool library inside the knowledge base.

[0088] As an embodiment of the present invention, first, we need to input the power design scheme into a preset power design program, and automatically generate an initial power visual model and a power dispatch status display model through the program. These two can help us better understand and present the design scheme, and also provide a basis for subsequent simulation work.

[0089] Secondly, based on the initial power visual model and the power dispatch status display model, we need to construct a simulation model of the power operation state. This process can be achieved by modeling and connecting various parts of the power system (such as generators, transformers, lines, etc.), and then using mathematical models to describe the dynamic behavior of each part.

[0090] Then, we need to use the generated simulation model of the power operation state to determine the node parameters of different power dispatch nodes. These parameters determine the behavior of each part in the system and are important factors determining the power operation state.

[0091] Finally, according to the determined node parameters, we can determine the power simulation model corresponding to the power design scheme.

[0092] As an embodiment of the present invention, first, the system obtains the associated nodes between the first simulation model and the power design requirements. These nodes are based on the power design requirements and the corresponding design nodes in the power simulation model. The main purpose of this step is to find the connection between the two, so as to better evaluate in the follow-up.

[0093] Secondly, the system establishes the design layout network of the power design based on the associated nodes. This network can be used to display the structure and composition of the power design, which helps users understand the design scheme more intuitively.

[0094] Then, the system calculates the demand matching values of each scheduling node of the power design according to the user relationship network. This matching value can reflect the advantages and disadvantages of each scheduling node in meeting the power design requirements, and can provide valuable information for users.

[0095] Next, the system generates the evaluation parameters of the power design scheme at each scheduling node according to the demand matching values. These evaluation parameters are the criteria for evaluating the performance of the design scheme at different scheduling nodes, which can help users understand the importance of each scheduling node.

[0096] Finally, the system generates a power design evaluation matrix according to the evaluation parameters. This matrix is a structured and quantitative tool, which can help users intuitively compare and select different design schemes, so as to make the best decision.

[0097] As an embodiment of the present invention, the system obtains the evaluation values of each scheduling node according to the power design evaluation matrix, and calculates the deviation index of each scheduling node. This evaluation value reflects the gap between the actual state and the ideal state of the scheduling node, while the deviation index reflects the size of this gap.

[0098] Then, the system uses the deviation index to predict the operation state tendency information of each scheduling node under various power design requirement conditions. Through this prediction, we can understand the load situation of each scheduling node, and then identify the corresponding load coefficient.

[0099] Next, the system determines the fluctuation compensation coefficient of each scheduling node according to the load coefficient and the deviation index. This fluctuation compensation coefficient reflects the degree of change in the power demand of the scheduling node. For scheduling nodes with larger loads, this coefficient may be higher.

[0100] Next, the system will use the fluctuation compensation coefficient to determine whether the fluctuation compensation of each scheduling node exceeds the preset defect threshold. If it exceeds, it indicates that there is a design defect.

[0101] Finally, when a design defect is found, the system will make corrections according to the preset target simulation parameters to generate a new simulation model.

[0102] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these changes and modifications therein.

Claims

1. A smart auxiliary system for electric power design enterprises based on knowledge base big data, characterized in that: include: Design analysis module: used to receive the power design plan from the user side and determine the power dispatching status and power design requirements; Design request module: used to use the design function component representing the power dispatching state and the user trigger operation pre-configured from the user end as the call request of the design function component, and build a request call library of the design function component based on the preset knowledge base big data; Sandbox processing module: used to configure an auxiliary sandbox between the request call library and the user end, and convert the user-triggered operation corresponding to the call request into an execution script on the user end through the auxiliary sandbox; Power simulation module: used to generate a first simulation model of the current power design scheme in the power design program at the user end according to the execution script; Simulation evaluation module: used to generate an electric power design evaluation matrix according to the first simulation model and the electric power design requirements, and to determine whether there are design defects through the electric power design evaluation matrix, and based on the design defects, to generate a target simulation model and electric power design data corresponding to the target simulation model.

2. The intelligent auxiliary system for electric power design enterprises based on knowledge base big data according to claim 1, characterized in that: When receiving the power design scheme of the user end, configuring the auxiliary analysis network based on the preset first design path and the second design path respectively; The auxiliary analysis network includes a node graph computing platform connected to the first design path and a load forecasting network connected to the second design path; Each graph node in the node graph computing platform corresponds to a power dispatching node; The load forecasting network is used to estimate the load range of each power dispatching node and determine the corresponding power item data.

3. The intelligent auxiliary system for electric power design enterprises based on knowledge base big data as claimed in claim 1, characterized in that: The trigger operation includes a voice trigger operation and a data call trigger operation; When the trigger operation is a voice trigger operation, the system responds to the user's voice and generates multiple question-answer candidate entity information corresponding to different call requests based on a preset voice question-answer model. The question-answer candidate entity information is generated in real time from the power design data training in the knowledge base big data through the preset question answer model. When the trigger operation is a data call trigger operation, the data path complexity of the power design data called by the user is determined, and based on the data path complexity, a power design tool function entity corresponding to the call request of the data call trigger is generated, and the target power design functional component is determined through the data path complexity.

4. The intelligent auxiliary system for electric power design enterprises based on knowledge base big data according to claim 1, characterized in that: The knowledge base big data also includes a power design analysis network and a power design database; The power design analysis network is used to analyze the call request through the power design database, and generate a call function through the established request call library; The power design database includes: power demand analysis index database, power system composition database, power network architecture database, power index constraint analysis database, power design database, and power fault analysis database.

5. The intelligent auxiliary system for electric power design enterprises based on knowledge base big data as claimed in claim 4, characterized in that: The request call library for designing functional components based on the preset knowledge base big data includes: Build a function framework for different power design scenarios, and match power layout parameters with power design attributes to different power design scenarios with power dispatch nodes; Determine different design functional components based on power layout parameters; Match the design functional components with the functional functions of the function framework in different power design scenarios, and divide the matched function framework into granularities of different power dispatch nodes; A function database of different power design scenarios after granular segmentation is obtained, and the design function components corresponding to the function database are spatially aggregated to generate a spatially aggregated request call library.

6. The intelligent auxiliary system for electric power design enterprises based on knowledge base big data according to claim 1, characterized in that: The auxiliary sandbox is used to determine corresponding call data in the request call library according to the call request of the user end, and convert it into an execution script of the user end; Among them, auxiliary sandboxes include: functional sandbox and display sandbox.

7. The intelligent auxiliary system for electric power design enterprises based on knowledge base big data as claimed in claim 6, characterized in that: The conversion into a user-side execution script includes: Obtain the power design requirements of the calling data at the user end and determine the execution method of the calling data; According to the execution mode, a conversion request of the power design requirement data is sent to the corresponding auxiliary sandbox; According to the conversion request, the calling data is converted into the application instance of the execution script by a preset conversion tool through the auxiliary sandbox; Among them, the conversion tool is called through the conversion tool library in the knowledge base big data; According to the application example, a target execution script is generated.

8. The intelligent auxiliary system for electric power design enterprises based on knowledge base big data as claimed in claim 1, characterized in that: The generating of the first simulation model of the current power design scheme in the power design program at the user end includes: Input the power design scheme into the preset power design program to generate an initial power visual model and an initial power dispatch status display model; Based on the initial power visual model and the initial power dispatching state display model, a power operation state simulation model is constructed, and the node parameters of different power dispatching nodes are determined by using the power operation state simulation model; According to the node parameters, the power simulation model corresponding to the power design scheme is determined.

9. The intelligent auxiliary system for electric power design enterprises based on knowledge base big data according to claim 1, characterized in that: The method for generating a power design evaluation matrix according to the first simulation model and the power design requirement includes: Acquire an association node between the first simulation model and the power design requirement, wherein the association node is based on the power simulation design requirement and a corresponding design node in the power simulation model; Based on the associated nodes, establishing a design layout network for power design; Based on the user relationship network, calculating the demand matching value of each dispatching node of the power design; Based on the demand matching value, generating evaluation parameters of the power design scheme at each scheduling node; An electric power design evaluation matrix is ​​generated according to the evaluation parameters.

10. The intelligent auxiliary system for electric power design enterprises based on knowledge base big data according to claim 1, characterized in that: The determination of whether there is a design defect includes: According to the power design evaluation matrix, an evaluation value of each scheduling node is obtained, and a deviation index of each scheduling node is located; According to the deviation index, the operating status tendency information of each dispatching node under each power design demand condition is predicted, and the load factor of the corresponding dispatching node is identified; According to the load factor and deviation index, under the preset power supply, the fluctuation compensation coefficient of each dispatching node is determined; According to the fluctuation compensation coefficient, determining whether the fluctuation compensation coefficient exceeds a preset defect threshold; When the defect threshold is not exceeded, corresponding target simulation parameters are determined.

Images