Parallel simulation processing method and device for multiple agents, terminal equipment and storage medium

Abstract

The invention discloses a parallel simulation processing method and device for multiple agents, terminal equipment and a storage medium, and belongs to the field of power simulation systems.The method comprises the steps that basic parameters of power equipment in a power system, topological structures among the power equipment and interaction relations among the power equipment are obtained; based on the simulation model modeling parameters, a simulation model agent corresponding to each power device is constructed; determining a plurality of target agents in the plurality of simulation model agents according to a simulation scene selected by a user, and determining operation scene data of each target agent based on the simulation scene; inputting each piece of operation scene data into each corresponding target agent to obtain operation simulation data corresponding to each target agent; and receiving operation simulation data generated by all the target agents, and obtaining a simulation report. According to the invention, the simulation efficiency of multi-device simulation of the power system can be improved.

Description

Technical Field

[0001] The present invention relates to the field of electric power simulation systems, and in particular to a parallel simulation processing method, apparatus, terminal equipment and storage medium for multiple intelligent agents. Background Art

[0002] In modern power systems, with the continuous expansion of the scale and increasing complexity of power system simulation training, higher requirements are placed on the systematicity, uniformity, accuracy, efficiency and real-time performance of the simulation system. It is necessary to realize not only device-level simulation but also grid-level simulation of multiple devices connected to the grid.

[0003] However, existing simulation models are developed independently for single metering devices or local systems, lacking unified standards and frameworks. This makes it difficult to build a unified, network-wide power metering simulation model encompassing various power devices and complex grid structures, and unable to simulate metering system operation in large-scale grid environments. Consequently, existing power simulation technologies suffer from low efficiency when simulating multiple devices in a power system. Summary of the Invention

[0004] The present invention provides a parallel simulation processing method, apparatus, terminal device and storage medium for multiple intelligent agents, which can solve the problem of low simulation efficiency in existing power simulation technology when simulating multiple devices in a power system.

[0005] The present invention provides a multi-agent parallel simulation processing method, comprising:

[0006] Obtain the basic parameters of each power device in the power system, the topological structure between each power device, and the interaction relationship between each power device;

[0007] Based on the basic parameters of each power device, the topological structure between the power devices, the interaction relationship between the power devices and the simulation model parameters, a simulation model agent corresponding to each power device is constructed;

[0008] According to the simulation scenario selected by the user, a plurality of target agents are determined from the plurality of simulation model agents, and operation scenario data of each target agent is determined based on the simulation scenario;

[0009] Input each operation scenario data into each corresponding target intelligent agent respectively, so that each target intelligent agent performs simulation operation based on the corresponding operation adjustment data, and obtains operation simulation data corresponding to each target intelligent agent;

[0010] Receive the running simulation data generated by all the target intelligent agents and obtain a simulation report.

[0011] Furthermore, the simulation model modeling parameters include: modeling language, equipment operation rules, and operation state change rules between power system equipment; the simulation model agent corresponding to each power equipment is constructed based on the basic parameters of each power equipment, the topological structure between each power equipment, the interaction relationship between each power equipment, and the simulation model modeling parameters, including:

[0012] Construct a simulation model for each power device based on the modeling language, equipment operation rules, and basic parameters of each power device;

[0013] Determine the data transmission relationship between each simulation model according to the operating state change rules between the power system devices, the topological structure between the power of each device, and the interaction relationship between the power devices;

[0014] Based on each of the simulation models and the data transmission relationship between each of the simulation models, a simulation model agent corresponding to each power device is constructed.

[0015] Furthermore, the simulation model intelligent agent includes: receiving real-time operation data of the power equipment collected by the power metering device, so that the simulation model intelligent agent converts the simulation data based on the real-time operation data to obtain equipment simulation data; wherein, the power metering device is arranged inside the power equipment.

[0016] Furthermore, after obtaining the simulation report, the method further includes:

[0017] Matching the running simulation data with the preset fault event data;

[0018] If the match is successful, a control strategy corresponding to the fault event data is generated, and an update operation instruction is generated according to the control strategy; each target agent is adjusted based on the update operation instruction, and after each adjusted target agent is simulated and run, the operation update data of each target agent is obtained;

[0019] If the match fails, no action is taken.

[0020] Furthermore, after constructing the simulation model agent corresponding to each power device, the method further includes:

[0021] Obtaining a training scenario input by a user, determining a plurality of training agents from the plurality of simulation model agents, and determining running training data for each training agent based on the training scenario;

[0022] Input each running training data into each corresponding training agent, so that each training agent performs simulation operation based on the corresponding running training data and receives training operation instructions from the user;

[0023] The training agents are adjusted based on the training operation instructions, and after each adjusted training agent performs simulation operation, the adjusted operation data of each training agent is obtained.

[0024] Furthermore, after obtaining the adjusted operation data of each training agent, the method further includes:

[0025] The training operation instructions and the adjustment operation data are analyzed to obtain operation scores and operation adjustment suggestions.

[0026] Furthermore, the power metering equipment includes: a simulated electric energy meter, a simulated transformer, a simulated mutual inductor, and a simulated switch cabinet.

[0027] Another embodiment of the present invention further provides a parallel simulation processing device for multiple agents, comprising: a data acquisition module, a model construction module, a simulation scenario module, a simulation operation module, and a result generation module;

[0028] The data acquisition module is used to obtain basic parameters of each power device in the power system, the topological structure between each power device, and the interaction relationship between each power device;

[0029] The model building module is used to build a simulation model agent corresponding to each power device based on the basic parameters of each power device, the topological structure between the power devices, the interaction relationship between the power devices and the simulation model modeling parameters;

[0030] The simulation scenario module is used to determine a plurality of target agents from the plurality of simulation model agents according to the simulation scenario selected by the user, and determine the operation scenario data of each target agent based on the simulation scenario;

[0031] The simulation operation module is used to input each operation scenario data into each corresponding target intelligent agent, so that each target intelligent agent performs simulation operation based on the corresponding operation adjustment data, and obtains operation simulation data corresponding to each target intelligent agent;

[0032] The result generation module is used to receive the operation simulation data generated by all the target intelligent agents and obtain a simulation report.

[0033] Another embodiment of the present invention also provides a terminal device, comprising: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the steps of the parallel simulation processing method for multiple agents provided by the present invention.

[0034] Another embodiment of the present invention also provides a computer-readable storage medium item, including: a stored computer program, which controls the device where the computer-readable storage medium is located to execute the steps of the parallel simulation processing method for multiple agents provided by the present invention when the computer program is running.

[0035] The following beneficial effects are achieved by implementing the present invention:

[0036] The present invention discloses a parallel simulation processing method for multiple intelligent agents. The method comprises the following steps: obtaining basic parameters of each power device in a power system, topological structures between each power device, and interactive relationships between each power device; constructing a simulation model intelligent agent corresponding to each power device based on the basic parameters of each power device, the topological structures between each power device, the interactive relationships between each power device, and simulation model modeling parameters; determining multiple target intelligent agents from the multiple simulation model intelligent agents according to a simulation scenario selected by a user, and determining operation scenario data for each target intelligent agent based on the simulation scenario; inputting each operation scenario data into each corresponding target intelligent agent, so that each target intelligent agent performs simulation operation based on corresponding operation adjustment data, and obtains operation simulation data corresponding to each target intelligent agent; receiving operation simulation data generated by all the target intelligent agents, and obtaining a simulation report. The present invention models multiple power devices and establishes relationships between multiple intelligent agents based on the topological structures and interactive relationships between the multiple power devices, thereby enabling data transmission between the multiple intelligent agents, allowing the user to perform simulation operation of the simulation scenario based on the multiple intelligent agents, obtain operation simulation data, and realize unified simulation of multiple power devices. Compared with the prior art which can only simulate a single electric power device, the present invention improves the simulation efficiency by performing unified simulation on multiple electric power devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for use in the implementation. Obviously, the drawings described below are only some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0038] Figure 1 1 is a flow chart of a parallel simulation processing method for multiple agents provided by one embodiment of the present invention;

[0039] Figure 2 1 is a schematic structural diagram of a parallel simulation processing device for multiple agents provided by one embodiment of the present invention;

[0040] Figure 3 1 is a schematic diagram of the architecture of a multi-agent parallel simulation system provided by one embodiment of the present invention;

[0041] Figure 4 1 is a schematic structural diagram of a simulation model agent provided by an embodiment of the present invention;

[0042] Figure 5 It is a schematic diagram of the simulation modeling process provided by one embodiment of the present invention;

[0043] Figure 6 This is a schematic diagram of the framework of the power marketing intelligent simulation training system provided by one embodiment of the present invention;

[0044] Figure 7 is a schematic diagram of a parallel computing process provided by an embodiment of the present invention;

[0045] Figure 8 This is a schematic diagram of a simulation process based on scenario control provided by an embodiment of the present invention;

[0046] Figure 9 is a schematic diagram of a simulation process based on scenario control provided by another embodiment of the present invention;

[0047] Figure 10 This is a flow chart of information interaction for simulation training provided by one embodiment of the present invention;

[0048] Figure 11 This is a control flow diagram of the power marketing intelligent simulation training system provided by one embodiment of the present invention;

[0049] Figure 12 It is a flowchart of a parallel simulation processing method for multiple agents provided by another embodiment of the present invention. DETAILED DESCRIPTION

[0050] To make the objectives, technical solutions, and advantages of this application more clear, the technical solutions in this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this application.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0052] In the description of the embodiments of this application, the technical terms "first" and "second" are used only to distinguish different objects and should not be understood to indicate or imply relative importance or implicitly specify the quantity, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, the meaning of "plurality" is more than two, unless otherwise clearly and specifically defined.

[0053] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0054] In the description of the embodiments of this application, the term "and / or" is simply a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0055] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0056] In the description of the embodiments of the present application, unless otherwise expressly specified or limited, technical terms such as "installed," "connected," "connected," and "fixed" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integration; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; internal connections between two components or interactions between two components. Those skilled in the art can understand the specific meanings of the above terms in the embodiments of the present application based on specific circumstances.

[0057] See also Figure 1 To address the problem of low simulation efficiency in existing power simulation technologies when simulating multiple devices in a power system, an embodiment of the present invention provides a parallel simulation processing method for multiple agents, comprising:

[0058] 101. Obtain the basic parameters of each power device in the power system, the topological structure between each power device, and the interaction relationship between each power device.

[0059] 102. Based on the basic parameters of each power device, the topological structure between the power devices, the interaction relationship between the power devices, and the simulation model parameters, construct a simulation model agent corresponding to each power device.

[0060] In this embodiment, the simulation model modeling parameters include: modeling language, equipment operation rules, and operation state change rules between power system equipment; the construction of a simulation model agent corresponding to each power equipment based on the basic parameters of each power equipment, the topological structure between each power equipment, the interaction relationship between each power equipment, and the simulation model modeling parameters includes:

[0061] Construct a simulation model for each power device based on the modeling language, equipment operation rules, and basic parameters of each power device;

[0062] Determine the data transmission relationship between each simulation model according to the operating state change rules between the power system devices, the topological structure between the power of each device, and the interaction relationship between the power devices;

[0063] Based on each of the simulation models and the data transmission relationship between each of the simulation models, a simulation model agent corresponding to each power device is constructed.

[0064] In this embodiment, the simulation model agent includes: receiving real-time operating data of the power equipment collected by the power metering device, so that the simulation model agent converts the simulation data based on the real-time operating data to obtain device simulation data; wherein, the power metering device is arranged inside the power equipment.

[0065] In this embodiment, the power metering equipment includes: a simulated electric energy meter, a simulated transformer, a simulated mutual inductor, and a simulated switch cabinet.

[0066] In this embodiment, after constructing the simulation model agent corresponding to each power device, the method further includes:

[0067] Obtaining a training scenario input by a user, determining a plurality of training agents from the plurality of simulation model agents, and determining running training data for each training agent based on the training scenario;

[0068] Input each running training data into each corresponding training agent, so that each training agent performs simulation operation based on the corresponding running training data and receives training operation instructions from the user;

[0069] The training agents are adjusted based on the training operation instructions, and after each adjusted training agent performs simulation operation, the adjusted operation data of each training agent is obtained.

[0070] In this embodiment, after obtaining the adjusted operation data of each training agent, the method further includes:

[0071] The training operation instructions and the adjustment operation data are analyzed to obtain operation scores and operation adjustment suggestions.

[0072] In a specific embodiment, this embodiment uses a multi-agent parallel simulation system as the execution subject of the multi-agent parallel simulation processing method. The multi-agent parallel simulation system includes: a device layer 1, a platform layer 2, a simulation support layer 3, a simulation application layer 4 and a simulation interaction layer 5. Figure 3 The power marketing intelligent simulation training system consists of a simulation support layer 3, a simulation application layer 4, and a simulation interaction layer 5.

[0073] Preferably, the device layer 1 is composed of multiple simulation model agents interconnected by Ethernet. The simulation model agent is a device combination of the minimum application scenario. Each simulation model agent includes a coordinator 11, a central console 12, and a simulation power device 13 (i.e., the power metering device described in the present invention). Figure 4 shown.

[0074] The coordinator 11 has uplink and downlink communication functions and protocol conversion functions, and is used to connect the training system software with simulation model intelligent bodies of different manufacturers and different versions to achieve protocol compatibility and collaborative work between intelligent bodies.

[0075] The central console 12 comprises a movable platform 121 with universal wheels and a large-screen integrated computer 122 embedded in the platform. Its primary function is to receive device model configuration parameters, training data, simulation data, and training tasks forwarded by the coordinator 11, and to upload data and status information received from the simulated power equipment 13 to the training system software via the coordinator.

[0076] The simulated power equipment 13, such as simulated electric energy meters, simulated transformers, simulated mutual inductors, simulated switch cabinets, etc., are connected to the central console via communication methods such as LORA, WIFI, RS485, etc., and receive commands from the central console.

[0077] Preferably, the platform layer 2 is based on the architecture system of the Southern Power Grid cloud platform, unifies the simulation power grid model, data model and data service model, adopts the "first-level management, multi-node deployment" approach, fully integrates cloud computing, big data analysis, artificial intelligence and other advanced technologies, and builds an overall infrastructure that integrates cloud, data and intelligence, realizing digital intelligent simulation training of "full perception of power grid status, full online management and training, full control of simulation data, new customer service experience, and win-win cooperation in energy development".

[0078] 103. According to the simulation scenario selected by the user, a plurality of target agents are determined from the plurality of simulation model agents, and operation scenario data of each target agent is determined based on the simulation scenario.

[0079] 104. Input each operation scenario data into each corresponding target intelligent agent respectively, so that each target intelligent agent performs simulation operation based on the corresponding operation adjustment data, and obtains operation simulation data corresponding to each target intelligent agent.

[0080] In a specific embodiment, the platform layer 2 is based on simulation modeling of a unified model of the entire network, and includes a student model 21, a teacher model 22, a teaching model 23, a graphics library 24, parameters 25, a rule library 26, an examination model 27, a fault model 28, a system model 29, a knowledge base 2A, a case library 2B and an exercise library 2C that are unified across the entire network.

[0081] The simulation support layer 3 includes integrated simulation modeling 31, component-based rapid modeling 32, parallel computing-based simulation 33, and scenario-controlled simulation processes 34. The simulation support layer 3 accesses various resources provided by the cloud platform via Ethernet, provides a comprehensive management module for resources and data, and effectively manages and maintains the system's various model data, rule base, and other aspects, ensuring efficient operation of the simulation system.

[0082] The integrated simulation modeling 31 utilizes the unified modeling language (UML, i.e. the modeling language described in the present invention) in combination with the electric power industry standards to establish a unified model of the entire network covering various types of electric power metering training scenarios (plant simulation training scenarios, special transformer metering simulation training scenarios, public transformer simulation training scenarios, i.e. the simulation scenarios described in the present invention), various types of electric power metering equipment (electric meters, mutual inductors, acquisition terminals, etc.), power grid topology, power transmission characteristics and metering business processes. The data involved in the construction of the simulation model intelligent body include but are not limited to: basic parameters (such as rated parameters, accuracy levels), equipment operation rules (such as metering algorithms, data transmission mechanisms), topological structures between various electric power equipment, interactive relationships between various electric power equipment, and operating status change rules between power system equipment. Through standardized data structures and storage methods, the model data is stored in a relational database or distributed file system to ensure data consistency and accessibility. Its simulation modeling process is as follows: Figure 5 shown.

[0083] The componentized rapid modeling 32 componentizes the commonly used equipment units in the power marketing metering simulation scenario, encapsulates the parameters and functions in the simulation model intelligent body as the unit, realizes reuse, improves the efficiency of simulation scenario equipment modeling, and provides an interface to help system administrators participate in simulation training or anti-accident drills.

[0084] The parallel computing-based simulation 33 includes a multi-agent-based parallel simulation framework 331 and a multi-agent-based parallel simulation calculation process 332.

[0085] The multi-agent-based parallel simulation framework 331 designs the plant, test stand transformer, distribution room, box-type transformer, etc. into simulation model agents. Each simulation model agent includes simulated power equipment (meters, terminals, transformers, mutual inductors, etc.) and a central control console. Multiple simulation model agents are networked through a coordinator and a simulation system master station, and joint simulation is achieved through communication between simulation model agents. A separate simulation model agent can be used to control or simulate its own behavior, adjust its own state, and achieve autonomous control of a test stand transformer, a distribution room, or a box-type transformer. The simulation model agents of multiple test stand transformers, box-type transformers, and distribution rooms can communicate with each other, cooperate, and complete large-scale power grid simulation plans in parallel, thereby achieving more realistic and more refined simulations. See the simulation framework of the multi-agent-based power marketing intelligent simulation training system. Figure 6 .like Figure 6 As shown, the simulation model agent includes: power marketing simulation training system software, intelligent coordinator, internal network, plant simulation training scenario (composed of plant training agent), special transformer simulation training simulation scenario (composed of bench transformer agent, distribution room agent, box transformer agent) and public transformer simulation training simulation scenario (composed of distribution room agent, European box transformer agent, bench transformer agent); each training scenario can be regarded as an independent training system and a separate simulation model agent.

[0086] Based on the parallel simulation calculation process 332 of multiple agents, the power marketing simulation training system software issues training tasks to each simulation model agent in the simulation scene. Each simulation model agent uses distributed parallel computing to uniformly call the student model, teacher model, teaching model, graphic library, parameter library and marketing professional business model of the platform layer. According to the task requirements, a unified fault model, system model, examination model, case library and exercise library are generated on demand. Accurately simulate the various operating states of the power system and provide accurate simulation models and real-time information for the power marketing simulation training system. Its parallel computing process is as follows: Figure 7 shown.

[0087] The simulation process 34 based on scenario control is mainly used for power marketing simulation training and fault inspection exercises. The scenario control teacher defines the scale of training or exercises through training scenarios, defines hypothetical faults through fault types, and defines the exercise objects that need to be automatically managed through user models. During training and exercises, the changes in accidents and new power grid states are constantly perceived based on the actions of the trainees, and relevant strategies are formulated for the next action response. As training and exercises continue to advance, scenario control can track and calculate the operating status of each step of the power grid throughout the process, and make decision adjustments based on it. The power marketing simulation training / fault inspection exercise process based on scenario control, such as Figure 8 shown.

[0088] The simulation application layer 4 includes grid level simulation 41, device level simulation 42, monitoring simulation 43 and teacher control 44. The training technology framework is as follows Figure 9 shown.

[0089] The grid-level simulation 41 adopts unified modeling technology based on full-network data and multi-agent high-performance parallel computing technology, which can realize 10kV power system simulation, line loss calculation simulation and electricity consumption information data collection simulation of integrated multi-agent networking.

[0090] Device-level simulation 42 uses the simulation model agents in the simulation training system as units. This can decompose the entire power grid simulation training system into multiple scenarios, each with its own agent, for parallel simulation. This allows for full-process simulation of device operation information, anomaly information, and fault information, meeting the monitoring simulation's requirements for telemetry, telesignaling, and remote control information from the agents. Device simulation primarily simulates equipment failures, abnormal operation, normal load, light load, and heavy load.

[0091] The monitoring simulation 43 simulates multiple dimensions, including grid operation, monitoring, operation, and safety. It implements multi-level co-simulation of intelligent entities in simulation models, including power plants, American-style box-type transformers, distribution rooms, and test bench transformers. This supports daily monitoring, normal operation, and incident handling training for trainees in various power marketing departments. The monitoring simulation primarily implements real-time grid operation monitoring simulation, centralized real-time equipment monitoring, comprehensive intelligent alarm simulation, and scenario-based training strategy control simulation.

[0092] To better illustrate the monitoring simulation, assume that a 10kV line loss needs to be simulated. Due to the existence of electricity thieves, the 10kV line loss is as high as 11%. Set the dedicated transformer rack to the electricity thief, and set the power curve of each metering point.

[0093] The specific simulation process is as follows:

[0094] Step 1: Design a 2-hour load curve on the power station metering panel as the total output power curve of the 10kV simulation line;

[0095] Step 2: The power marketing simulation training system software calls the entire 10kV line grid model and equipment parameters. Based on the line loss rate and the total line load power curve, as well as the power theft power curve, it simulates and calculates the power curves of the remaining metering points, and outputs the voltage, current, and power curves of each metering point in the corresponding time period.

[0096] Step 3: The power marketing simulation training system software sends the corresponding voltage, current, and power curve data to the central console of each intelligent entity through Ethernet and the coordinator;

[0097] Step 4: After receiving the voltage, current, and power curves forwarded by the power marketing simulation training system software through the coordinator, each central console works in parallel and controls the virtual power supply to output the voltage, current, power and other data of the corresponding metering point at the corresponding time point;

[0098] Step 5: The data acquisition module of the power marketing simulation training system software collects data from meters at each metering point in real time. The line loss calculation module calculates the line loss rate and electricity thieves based on the real-time data collected, and displays the suspected electricity thieves and suspicious power curves through the interface for students to learn.

[0099] The teacher control 44, the simulation training system supports switching between teacher mode and student mode. The teacher control selects the accident simulation model and issues instructions based on the full network model and training exercise requirements. In teacher mode, the development of the accident and the entire handling process of students at all levels are viewed, and real-time communication is carried out with students at all levels. In student mode, relevant accident handling operations are performed on the visual operating console. The simulation training system software can issue instructions to the central control consoles of the subordinate intelligent bodies. Each operation action can be reflected in real time on the full network simulation visualization platform and displayed to all training participants through the cloud platform. Teacher control mainly realizes the functions of lesson plan production, training control, training evaluation and joint anti-accident exercise support. Its information interaction process is as follows: Figure 10 shown.

[0100] The simulation interaction layer 5 realizes dual control and dual use of power marketing simulation, including: intelligent agent control 51, training and evaluation process monitoring 52, teacher use 53 and student use 54.

[0101] The intelligent agent control 51 includes simulation panoramic display 511 and simulation task issuance 512.

[0102] The simulation panoramic display 511 is characterized in that it can display the basic usage of the power marketing simulation training site, and can access power grid topology data, power grid graphic data, simulation data (power consumption information data, distribution information data, etc.), model data (equipment model, fault model, etc.), resource management data (student information, material information, site information, examination information, etc.), video information, etc.

[0103] The simulation task is sent 512, and various on-site training tasks can be sent to the intelligent agent through the simulation interaction layer interface, so as to achieve unified and remote sending.

[0104] The training and assessment process monitoring 52 can realize the monitoring of trainee registration status, real-time progress monitoring of training and assessment, remote monitoring of training and assessment, etc. through the simulation interaction layer interface.

[0105] The teacher can use 53 to generate training plans and examination plans through the simulation interaction layer interface, and can publish training notices and training plans in the system; can realize online teaching, can complete the students' practical training and registration of examination results, can realize machine evaluation and scoring; can establish a shared knowledge base, teachers can upload courseware, and students can share learning notes.

[0106] The student user 54 can automatically create a student file after the student reports through the simulation interaction layer interface; the student's training tasks or examination tasks can be issued on the system; the student can scan the code to sign in, and the student's performance record during the training process and the examination record can be intelligently analyzed to form a radar chart of the student's skills and business capabilities.

[0107] To better illustrate, a simulation case: 10kV power system fault response training drill:

[0108] Step 1: Set up the training scenario: 1) Input data: Set the initial state of the power system (such as grid topology, equipment parameters, load distribution, etc.). 2) Processing: Initialize the simulation environment and set the simulation start time and conditions. 3) Output data: The state of the power system after initialization.

[0109] Step 2: Start training / exercise: 1) Input data: Initialized power system status obtained from the previous step. 2) Processing: Start the simulation engine and simulate the power system operation. 3) Output data: Real-time power system operation status.

[0110] Step 3: Establish / Update Grid Status: 1) Input Data: Real-time power system operating status. 2) Processing: Update the grid model based on the current status, taking into account various possible events (such as faults, load changes, etc.). 3) Output Data: Updated grid status.

[0111] Step 4: Simulation calculation:

[0112] 1) Input data: Updated grid status. 2) Processing: Perform power system simulation calculations, including power flow analysis and stability analysis. 3) Output data: Simulation results (such as voltage, current, and power distribution).

[0113] Step 5: Derivation: 1) Input data: Simulation results. 2) Processing: Derivation of possible control strategies or countermeasures based on the simulation results. 3) Output data: Derived control strategies or countermeasures.

[0114] Step 6: Matching: 1) Input: The derived control strategy or countermeasure. 2) Processing: Match the derived strategy with the existing knowledge in the knowledge base. 3) Output: Matching results and determine the optimal strategy.

[0115] Step 7: Update the knowledge base: 1) Input data: Matching results. 2) Processing: Store and update the knowledge base, recording the new knowledge gained during this simulation. 3) Output data: Updated knowledge base.

[0116] Step 8: Update the rule base: 1) Input data: Updated knowledge base. 2) Processing: Update the rule base based on the information in the knowledge base. 3) Output data: Updated rule base.

[0117] Step 9: Evaluation / Assessment: 1) Input Data: All data from the entire simulation process (including simulation results, derivation strategies, matching results, etc.). 2) Processing: Evaluate and assess the entire simulation process, analyzing the simulation results and any existing problems. 3) Output Data: Evaluation report and improvement suggestions.

[0118] Step 10: Responding to Grid Events: 1) Input Data: Real-time grid events (such as fault alarms, load changes, etc.). 2) Processing: Invoke the corresponding processing flow based on the event type. 3) Output Data: Event processing results.

[0119] Step 11: Students interact with the system to complete the training: 1) Input data: Operational instructions from online and offline students. 2) Processing: Receive student operation instructions and convert them into input signals that the simulation system can recognize. 3) Output data: The converted operation instructions.

[0120] Step 12: Completion: 1) Input Data: All data from the entire simulation process. 2) Processing: End the simulation process and save all relevant data. 3) Output Data: The complete simulation record and final results.

[0121] It is understandable that the multi-agent parallel simulation system involved in this embodiment has the following beneficial effects:

[0122] 1) Improve simulation efficiency: The multi-agent parallel simulation framework can decompose power marketing simulation tasks into multiple agents for parallel processing. The use of a unified model for the entire network avoids problems such as duplicate modeling and data inconsistency, greatly shortening simulation time and improving training efficiency, allowing trainees to complete more practical training tasks in a shorter time.

[0123] 2) Enhanced Simulation Accuracy: The unified network model provides accurate and consistent basic data and model architecture for simulations. This allows multiple agents to more precisely model and simulate the complex behaviors and interactions in power marketing. For example, when simulating user electricity usage, the collaborative working of agents can more accurately reflect actual conditions, thereby improving simulation accuracy and allowing students to experience power marketing scenarios that are closer to reality.

[0124] 3) Improving students' practical skills: This framework can simulate various complex real-world scenarios and emergencies in power marketing, such as 10kV line loss simulation and equipment failure. Training in this simulated environment can hone students' ability to cope with complex problems, improve their practical skills and decision-making abilities, and enable them to more quickly adapt to real-world jobs after graduation.

[0125] 105. Receive the operation simulation data generated by all the target intelligent agents and obtain a simulation report.

[0126] In this embodiment, after obtaining the simulation report, the method further includes:

[0127] Matching the running simulation data with the preset fault event data;

[0128] If the match is successful, a control strategy corresponding to the fault event data is generated, and an update operation instruction is generated according to the control strategy; each target agent is adjusted based on the update operation instruction, and after each adjusted target agent is simulated and run, the operation update data of each target agent is obtained;

[0129] If the match fails, no action is taken.

[0130] To better illustrate, the following case is given: The implementation method of the multi-agent parallel simulation framework based on the unified model of the whole network, its specific application diagram is as follows Figure 11 As shown in the simulation training flow chart, Figure 12 shown.

[0131] The specific implementation method and process of the multi-agent parallel simulation processing method are as follows:

[0132] First, log in to the system as a teacher and establish a unified student model, examination model, fault model, equipment model, training model, knowledge base, process library, etc. for the entire network.

[0133] Secondly, students log in to the system, enter their user ID and password, and perform permission authentication.

[0134] Furthermore, after the student successfully logs in and authenticates, he or she enters the student information, creates a student file, and displays the student history record.

[0135] Furthermore, select the training mode (learning mode, practice mode and assessment mode), retrieve the student model, teaching model (examination plan), training process, etc.

[0136] Further, it is determined whether it is a learning mode. If it is a learning mode, the multimedia intelligent guidance information is loaded. If it is other modes, the multimedia intelligent guidance information is not loaded.

[0137] Furthermore, in learning and practice mode, the system outputs training tasks to the agents according to the training process and predetermined plan. Multiple agents perform parallel simulations, output system models and fault models, and initiate device or system simulations. In assessment mode, the system retrieves exam models, test questions, and scoring criteria, and distributes them to the agents. Multiple agents perform parallel simulations, output system models and fault models, and initiate device or system simulations.

[0138] Furthermore, in learning and practice mode, students conduct practical learning and practice on the intelligent simulation equipment, such as meter installation and wiring, power consumption inspection, meter reading and collection, terminal operation and maintenance, and anti-theft inspection. In assessment mode, students answer questions on the simulation equipment, such as fault detection and business operations.

[0139] Furthermore, in learning and practice mode, the system automatically tracks the training process and collects students' learning process and operation results in real time. It also automatically scores students and makes real-time model corrections, records learning time, and decrements the total learning time. In assessment mode, the system tracks the exam process and automatically analyzes and determines operation results, scores students, and decrements exam time.

[0140] Furthermore, in learning and practice mode, the system determines whether the student's training has been completed and whether the decrement time has reached zero. If so, the system exits the simulation state and turns off the voltage and current outputs. Otherwise, the system continues to the next training exercise. In assessment mode, the system determines whether the student has completed the exam and whether the decrement time has reached zero. If not, the system continues to the next exam.

[0141] Furthermore, in learning and practice mode, if the training is completed and no next round of training is conducted, the system will upload the learning results and record them in the database. In assessment mode, if the exam is completed, the system will output the exam results to the marketing center for display and record the assessment results.

[0142] Further, the training or assessment is completed.

[0143] like Figure 2 As shown, based on the above method embodiment, a corresponding device embodiment is provided;

[0144] An embodiment of the present invention provides a parallel simulation processing device for multiple agents, comprising: a data acquisition module 201, a model construction module 202, a simulation scenario module 203, a simulation operation module 204, and a result generation module 205;

[0145] The data acquisition module is used to obtain basic parameters of each power device in the power system, the topological structure between each power device, and the interaction relationship between each power device;

[0146] The model building module is used to build a simulation model agent corresponding to each power device based on the basic parameters of each power device, the topological structure between the power devices, the interaction relationship between the power devices and the simulation model modeling parameters;

[0147] The simulation scenario module is used to determine a plurality of target agents from the plurality of simulation model agents according to the simulation scenario selected by the user, and determine the operation scenario data of each target agent based on the simulation scenario;

[0148] The simulation operation module is used to input each operation scenario data into each corresponding target intelligent agent, so that each target intelligent agent performs simulation operation based on the corresponding operation adjustment data, and obtains operation simulation data corresponding to each target intelligent agent;

[0149] The result generation module is used to receive the operation simulation data generated by all the target intelligent agents and obtain a simulation report.

[0150] It can be understood that the above-mentioned device embodiment corresponds to the method embodiment of the present invention, which can implement any of the above-mentioned method embodiments of the present invention to provide a parallel simulation processing method for multiple agents.

[0151] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. Furthermore, in the drawings of the device embodiments provided by the present invention, the connection relationship between modules indicates that they have a communication connection, which may be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement the present invention without inventive effort.

[0152] Based on the above-mentioned embodiment of the parallel simulation processing method for multiple agents, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the parallel simulation processing method for multiple agents of any embodiment of the present invention.

[0153] For example, in this embodiment, the computer program may be divided into one or more modules, which are stored in the memory and executed by the processor to implement the present invention. The one or more module elements may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device.

[0154] The terminal device may be a computing device such as a desktop computer, a notebook computer, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0155] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, connecting various parts of the entire terminal device using various interfaces and lines.

[0156] Based on the above-mentioned method embodiments, another embodiment of the present invention provides a computer-readable storage medium, including a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the parallel simulation processing method for multiple agents described in any one of the above-mentioned method embodiments of the present invention.

[0157] Wherein, the module / unit integrated in the device / terminal equipment, if implemented in the form of a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0158] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A parallel simulation processing method for multiple agents, characterized in that: include: Obtain the basic parameters of each power device in the power system, the topological structure between each power device, and the interaction relationship between each power device; Based on the basic parameters of each power device, the topological structure between the power devices, the interaction relationship between the power devices and the simulation model parameters, a simulation model agent corresponding to each power device is constructed; According to the simulation scenario selected by the user, a plurality of target agents are determined from the plurality of simulation model agents, and operation scenario data of each target agent is determined based on the simulation scenario; Input each operation scenario data into each corresponding target intelligent agent respectively, so that each target intelligent agent performs simulation operation based on the corresponding operation adjustment data, and obtains operation simulation data corresponding to each target intelligent agent; Receive the running simulation data generated by all the target intelligent agents and obtain a simulation report.

2. The parallel simulation processing method for multiple agents according to claim 1, wherein: The simulation model modeling parameters include: modeling language, equipment operation rules, and operation status change rules between power system equipment; the simulation model agent corresponding to each power equipment is constructed based on the basic parameters of each power equipment, the topological structure between each power equipment, the interaction relationship between each power equipment, and the simulation model modeling parameters, including: Construct a simulation model for each power device based on the modeling language, equipment operation rules, and basic parameters of each power device; Determine the data transmission relationship between each simulation model according to the operating state change rules between the power system devices, the topological structure between the power of each device, and the interaction relationship between the power devices; Based on each of the simulation models and the data transmission relationship between each of the simulation models, a simulation model agent corresponding to each power device is constructed.

3. The parallel simulation processing method for multiple agents according to claim 2, wherein: The simulation model agent includes: receiving real-time operating data of the power equipment collected by the power metering device, so that the simulation model agent converts simulation data based on the real-time operating data to obtain device simulation data; wherein, the power metering device is set inside the power equipment.

4. The parallel simulation processing method for multiple agents according to claim 3, wherein: After obtaining the simulation report, the method further includes: Matching the running simulation data with the preset fault event data; If the match is successful, a control strategy corresponding to the fault event data is generated, and an update operation instruction is generated according to the control strategy; each target agent is adjusted based on the update operation instruction, and after each adjusted target agent is simulated and run, the operation update data of each target agent is obtained; If the match fails, no action is taken.

5. The parallel simulation processing method for multiple agents according to claim 4, characterized in that: After constructing the simulation model agent corresponding to each power device, the method further includes: Obtaining a training scenario input by a user, determining a plurality of training agents from the plurality of simulation model agents, and determining running training data for each training agent based on the training scenario; Input each running training data into each corresponding training agent, so that each training agent performs simulation operation based on the corresponding running training data and receives training operation instructions from the user; The training agents are adjusted based on the training operation instructions, and after each adjusted training agent performs simulation operation, the adjusted operation data of each training agent is obtained.

6. The parallel simulation processing method for multiple agents according to claim 5, wherein: After obtaining the adjusted running data of each training agent, the method further includes: The training operation instructions and the adjustment operation data are analyzed to obtain operation scores and operation adjustment suggestions.

7. The parallel simulation processing method for multiple agents according to claim 6, wherein: The electric power metering equipment includes: a simulated electric energy meter, a simulated transformer, a simulated mutual inductor, and a simulated switch cabinet.

8. A parallel simulation processing device for multiple agents, characterized in that: include: Data acquisition module, model building module, simulation scenario module, simulation operation module and result generation module; The data acquisition module is used to obtain basic parameters of each power device in the power system, the topological structure between each power device, and the interaction relationship between each power device; The model building module is used to build a simulation model agent corresponding to each power device based on the basic parameters of each power device, the topological structure between the power devices, the interaction relationship between the power devices and the simulation model modeling parameters; The simulation scenario module is used to determine a plurality of target agents from the plurality of simulation model agents according to the simulation scenario selected by the user, and determine the operation scenario data of each target agent based on the simulation scenario; The simulation operation module is used to input each operation scenario data into each corresponding target intelligent agent, so that each target intelligent agent performs simulation operation based on the corresponding operation adjustment data, and obtains operation simulation data corresponding to each target intelligent agent; The result generation module is used to receive the operation simulation data generated by all the target intelligent agents and obtain a simulation report.

9. A terminal device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the method implements the parallel simulation processing method for multiple agents as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that include: A stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the parallel simulation processing method for multiple agents as described in any one of claims 1 to 7.

Images