New energy AGC active control joint simulation test method and device and electronic equipment

Abstract

The embodiment of the invention discloses a new energy AGC active control joint simulation test method and device and electronic equipment, and relates to the technical field of power system tests.The method comprises the steps that a simulation model is constructed, a multi-agent modeling method is adopted for the simulation model, different fault factors are regarded as independent agents respectively, and the independent agents are used as independent agents; each agent has a self-sensing capability, an information interaction capability and a decision-making capability; setting a power grid fault scene, and performing fault simulation; collecting monitoring data in the simulation process; comparing and verifying a simulation result with actual power grid monitoring data or a theoretical analysis result; if the deviation exists, calibrating the simulation model and the algorithm; according to the invention, an actual power grid operation scene and various fault working conditions can be simulated, and active control of new energy AGC in different modes is accurately tested and deeply analyzed, so that the accuracy and efficiency of the test are improved, and the correctness and effectiveness of a control strategy are effectively verified.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power system testing, and particularly relates to a new energy AGC active control joint simulation test method, device and electronic equipment. BACKGROUND

[0002] With the growing global demand for clean energy, the proportion of new energy in the power system is increasing. As a key technology to ensure the reliable access of new energy to the power grid and maintain the stable operation of the power system, new energy automatic generation control (AGC) plays an increasingly important role. In practical applications, new energy AGC has been widely used in various new energy stations, such as wind power plants and photovoltaic power stations. Through the AGC system, new energy stations can adjust the power generation power in real time according to the demand of the power grid to maintain the power balance and frequency stability of the power system.

[0003] However, the existing new energy AGC test method has the following limitations: Limitations of field testing. Although traditional field testing can be carried out in a real environment, it has many limitations. On the one hand, field testing is costly and requires a large amount of human, material and time resources. For example, when testing at a new energy station, the operation of some power generation equipment needs to be suspended, which not only affects the normal power generation income of the station, but also may have some impact on the stability of power supply. On the other hand, field testing faces the complexity and uncertainty of actual power grid operation, making it difficult to fully simulate various possible faults and working conditions.

[0004] Deficiencies of existing simulation testing. Although the existing simulation testing method can simulate some common faults and working conditions, it may be difficult to accurately and comprehensively simulate the mutual influence mechanism between faults and working conditions when facing extremely complex and strongly coupled power grid fault scenarios, such as multiple new energy power generation equipment being subjected to severe natural condition changes. Due to the complex interaction between factors in these complex fault scenarios, the existing simulation method may not accurately reflect the active control response characteristics of new energy AGC under such extreme conditions, resulting in deviations in the evaluation of its control effect, and thus affecting the verification and optimization of the control strategy.

[0005] Lack of systematic testing method. The current testing methods mainly focus on the simulation of single faults or simple working conditions, and lack a method that can comprehensively and systematically test the active control performance of new energy AGC under multiple complex working conditions and fault scenarios. This makes it difficult to fully verify the performance and reliability of new energy AGC systems in actual applications, increasing the risk of power grid operation.

[0006] Therefore, there is an urgent need for a systematic method that can accurately simulate complex fault scenarios and comprehensively test the active control performance of new energy AGC. SUMMARY

[0007] The main purpose of the present application is to provide a new energy AGC active control joint simulation test method, device and electronic equipment, which can more accurately and comprehensively simulate actual power grid operation scenarios and various fault conditions, accurately test and deeply analyze the active control of new energy AGC in different modes, and improve the accuracy and efficiency of the test.

[0008] To achieve the above purpose, the first aspect of the present application provides a new energy AGC active control joint simulation test method, which comprises: A simulation model is constructed, which adopts a multi-agent modeling method, different fault factors are regarded as independent agents respectively, each agent has self-perception ability, information interaction ability and decision-making ability; the fault factors include transmission section overrun, new energy power generation equipment affected by natural condition changes and new energy AGC system; A power grid fault scene is set, and fault simulation is performed; Monitoring data in the simulation process is collected; The simulation results are compared and verified with actual power grid monitoring data or theoretical analysis results; if there is a deviation, the simulation model and algorithm are calibrated.

[0009] The second aspect of the present application provides a new energy AGC active control joint simulation test device, which comprises: A simulation model construction module is configured to construct a simulation model, which adopts a multi-agent modeling method, different fault factors are regarded as independent agents respectively, each agent has self-perception ability, information interaction ability and decision-making ability; the fault factors include transmission section overrun, new energy power generation equipment affected by natural condition changes and new energy AGC system; A fault simulation module is configured to set a power grid fault scene and perform fault simulation; A data collection module is configured to collect monitoring data in the simulation process; A verification and calibration module is configured to compare and verify the simulation results with actual power grid monitoring data or theoretical analysis results; if there is a deviation, the simulation model and algorithm are calibrated.

[0010] The third aspect of the present application provides an electronic device comprising a memory and a processor, the memory stores a computer program, and the computer program is executed by the processor to make the processor execute the steps of the first aspect and any possible implementation manner thereof.

[0011] The application provides a new energy AGC active control joint simulation test method, device and electronic equipment, a simulation model is constructed, the simulation model adopts a multi-agent modeling method, different fault factors are regarded as independent agents respectively, each agent has self-perception ability, information interaction ability and decision-making ability; the fault factors include transmission section overrun, new energy power generation equipment affected by natural condition changes and new energy AGC system; a power grid fault scene is set, fault simulation is carried out; monitoring data in the simulation process is collected; the simulation result is compared and verified with actual power grid monitoring data or theoretical analysis result; if there is deviation, the simulation model and algorithm are calibrated; the actual power grid operation scene and various fault conditions can be simulated, the active control of new energy AGC in different modes is accurately tested and deeply analyzed, so that the accuracy and efficiency of the test are improved, and the correctness and effectiveness of the control strategy are effectively verified. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0013] Among them: Figure 1 A flowchart of a new energy AGC active control joint simulation test method provided by the embodiments of the present application; Figure 2 A fault scene simulation flowchart provided by the embodiments of the present application; Figure 3 A simulation result verification and calibration flowchart provided by the embodiments of the present application; Figure 4 A structure diagram of a new energy AGC active control joint simulation test device provided by the embodiments of the present application; Figure 5 A structure diagram of an electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0014] In order to make the person skilled in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0015] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0016] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0017] The following explains some of the terms, concepts, or related background information used in the embodiments of this application: Automatic Generation Control (AGC): Within a defined area, when the power system frequency or tie-line power changes, the active power of generator sets is automatically adjusted through a control program to maintain the system frequency or ensure predetermined power exchange between areas. Its technical equipment system mainly includes grid operation control systems of dispatching agencies at all levels, remote transmission channels, remote terminal equipment or computer monitoring systems at power plants, generator set coordination control systems, generator sets and their active power regulation devices, and application software to implement AGC functions. For regulation and control involving renewable energy AGC, under normal circumstances, renewable energy power plants generate electricity at maximum capacity. When the grid experiences issues such as exceeding capacity limits, difficulties in peak shaving, insufficient reserves, or frequency fluctuations, the renewable energy AGC automatically adjusts the output power of renewable energy power generation equipment (such as photovoltaic inverters) to meet the needs of grid safety and stability.

[0018] Power Regulator (PLC): Following instructions from the AGC system, the PLC precisely controls the output power of the renewable energy power generation equipment. It calculates the difference between the total generated power and the sum of the current generated power of each device as the power to be regulated. Then, it prioritizes each device based on its adjustable power ratio and allocates the regulated power to each device. This process ensures that the renewable energy power generation equipment operates efficiently and stably while meeting grid demands. In the renewable energy AGC system, the PLC can also integrate optimization algorithms and strategies, such as proportional allocation and priority ranking methods, to achieve more precise and efficient power regulation. These algorithms and strategies fully consider the characteristics of the renewable energy power generation equipment and grid demands, ensuring stable system operation even under complex and changing conditions.

[0019] The principle of PLC equivalence for regional dispatch centers: Provincial-level coordinated control should support equivalence of a single regional dispatch center into multiple virtual machines based on group objects, grid topology nodes, and cross-sectional partitions, so as to achieve refined control of photovoltaic / wind power plants and related cross-sections at the central dispatch center. The principles for PLC equivalence of regional dispatch centers' new energy power plants at the central dispatch center's main station are as follows: 1) Geological survey stations whose output affects the same provincial-level coordination section can be considered as one PLC; other new energy stations not affected by the provincial-level coordination section can be considered as one PLC. 2) New energy power stations connected to the same 220kV node can be equivalent to one PLC; 3) Each prefecture-level new energy power station is connected to only one PLC.

[0020] 4. Provincial-Local Coordination: An effective coordination mechanism is established between provincial and prefecture-level power grid dispatching. Generally, the provincial dispatching center formulates overall control strategies and objectives based on the overall power supply and demand situation and the forecast results of renewable energy generation, and then issues them to the prefecture-level dispatching centers. The prefecture-level dispatching centers, in turn, formulate specific control plans based on the provincial dispatching center's control strategies and objectives, combined with the local renewable energy generation situation and power grid structure. This provincial-local coordinated control strategy optimizes the dispatching and control of renewable energy generation. This not only improves the safety and stability of the power grid but also enhances the utilization rate and power generation efficiency of renewable energy.

[0021] The embodiments of this application mentioned below are described in conjunction with the accompanying drawings.

[0022] Figure 1 A flowchart illustrating a joint simulation test method for active power control of new energy AGC provided in this application embodiment is shown below. Figure 1 As shown, the method includes: 101. Construct a simulation model. The simulation model adopts a multi-agent modeling method, treating different fault factors as independent agents. Each agent has self-perception ability, information interaction ability, and decision-making ability. The fault factors include transmission section exceeding limits, new energy power generation equipment being affected by changes in natural conditions, and new energy AGC system.

[0023] The method in this application embodiment can be implemented by a new energy AGC active power control joint simulation test device, which can be implemented on an electronic device in practical applications.

[0024] Specifically, simulation models can be built using pre-existing tools such as power system simulation software, like PSCAD or MATLAB's power system toolbox. In this model, a multi-agent system (MAS) modeling approach is adopted, treating different fault factors—such as transmission line overruns, the impact of natural conditions on renewable energy generation equipment (extreme wind speed changes in wind farms, sudden strong shading in photovoltaic power stations, etc.)—and the renewable energy AGC system as independent agents.

[0025] Accordingly, the intelligent agents in this simulation system mainly include the following three categories: New energy power generation intelligent agent: This intelligent agent is used to simulate the operating characteristics of new energy power plants such as wind farms and photovoltaic power plants, taking into account the impact of natural conditions such as wind speed and light intensity on the output of new energy, and has the ability to adjust power autonomously.

[0026] Transmission section intelligent agent: This intelligent agent is used to monitor the power flow of transmission lines and simulate power flow constraints caused by load changes or equipment failures.

[0027] AGC Unit Intelligent Agent: This intelligent agent is mainly used to simulate the power regulation characteristics of AGC units, and adjust the active power in real time according to the grid dispatch signal and frequency fluctuations to maintain system power balance and stability.

[0028] Within the MAS-based modeling framework, each agent possesses self-awareness, information interaction, and decision-making capabilities. Self-awareness enables agents to acquire real-time state data, such as the power output of renewable energy generation equipment, power flow changes at transmission cross-sections, and the power generation of AGC units. Information interaction ensures that agents can transmit necessary information through established communication mechanisms, such as real-time power output data of renewable energy generation and power flow limits at transmission cross-sections. Decision-making capabilities enable agents to take appropriate regulatory measures based on perceived information and predetermined control strategies, such as renewable energy power plants adjusting output according to changes in sunlight or wind speed, and AGC units adjusting power based on grid frequency deviations.

[0029] In one alternative implementation, the above-described construction of the simulation model includes: When building the model, electrical parameters, control parameters, and initial conditions for system operation are set for each power system component module according to actual power grid data, and each agent is given a clear function, initial state, and decision-making rules.

[0030] In the simulation environment, a multi-agent modeling method is adopted, which treats key power system components as independent agents with autonomous perception, communication and decision-making capabilities, and defines them, their initial states and decision rules to ensure the rationality and accuracy of the simulation results.

[0031] Specifically, when constructing the model, electrical parameters (rated power, conversion efficiency, and power factor of new energy power generation equipment, speed regulation system parameters, excitation system parameters, etc. of conventional AGC units, etc.) and control parameters (regulation rate, regulation dead zone, control cycle, etc. of AGC units, etc.) can be set according to actual grid data. Simultaneously, safety margins and limits for transmission sections, as well as initial operating conditions (initial power distribution, initial frequency set to the grid's rated frequency) are set. Each agent is assigned a clear function, initial state, and decision-making rules. Based on its own state and information transmitted from other agents, each agent possesses the ability to make real-time decisions and adjust its behavior, thereby simulating the dynamic interaction of various factors in complex scenarios.

[0032] To ensure the accuracy of the simulation results, reasonable electrical parameters, control parameters, and operating conditions need to be set for the new energy power generation intelligent agent, the transmission section intelligent agent, and the AGC unit intelligent agent when constructing the simulation model. In one optional implementation, the parameters can be set as follows: (1) New energy power generation intelligent agent. The new energy power generation intelligent agent is used to simulate wind power generation and photovoltaic power generation systems. Its main parameters include: Rated power (MW): In some scenarios, the rated capacity of wind turbine units is 2MW, and the total capacity is 150MW; the total capacity of photovoltaic module array is 100MW.

[0033] Power output model:

[0034]

[0035] in, p air density (kg / m³). A The swept area of ​​the wind turbine (m²) Cp The wind energy utilization coefficient, v Wind speed (m / s) ηFor wind turbine efficiency, S Light intensity (W / m²) A PV This represents the total area of ​​the photovoltaic panels (m²). η PV The conversion efficiency of photovoltaic modules.

[0036] P wind : refers to the active power output value of a wind power plant (unit: MW, megawatt), used to simulate the dynamic impact of wind speed changes on wind power output, and is the core output parameter of the wind power generation module in the new energy power generation intelligent body.

[0037] P pv : refers to the active power output value of a photovoltaic power station (unit: MW, megawatt), used to simulate the dynamic impact of natural conditions such as light intensity and shading on photovoltaic output, and is the core output parameter of the photovoltaic power generation module in the intelligent body of new energy power generation.

[0038] (2) Transmission section intelligent agent: The transmission section intelligent agent is used to monitor the power flow of transmission lines and simulate transmission capacity constraints. Its main parameters include: Line impedance (Ω) determines the active power flow P and reactive power flow Q of the line.

[0039] R The resistance of the circuit (unit: Ω, ohm). X The reactance of the line (unit: Ω, ohm).

[0040] The master equation of its power flow calculation model is:

[0041] in, V i ,V j The voltage across the two busbars is (kV). The voltage phase angle (degrees) Transmission section i - j The active current (MW).

[0042] (3) AGC unit intelligent agent: The AGC unit intelligent agent is used to simulate the regulation characteristics of conventional generator sets. Its main parameters include: unit inertia constant. H(s) This determines the unit's response speed to frequency changes.

[0043] The speed regulation system model of this intelligent agent is as follows:

[0044] in,R The governor dead zone (Hz / MW) The power grid frequency deviation (Hz) is the power grid frequency deviation. This refers to the power adjustment (MW) controlled by the AGC unit. △ P m This represents the change in the mechanical power of the prime mover. In a power system, the output mechanical power of the prime mover of a synchronous generator set (such as a steam turbine or water turbine) is adjusted according to factors such as changes in grid frequency and automatic generation control. When a deviation occurs in the grid frequency (such as a frequency decrease), the speed control system will change the mechanical power of the prime mover, Δ. P m This adjustment is used to adapt the electromagnetic power output of the generator unit to the grid demand and maintain grid frequency stability.

[0045] Further optional, the aforementioned power system component modules include new energy power plants, conventional AGC units, and power grid transmission sections; The aforementioned electrical parameters include, but are not limited to: the rated power, conversion efficiency, and power factor of the new energy power generation equipment, as well as the speed control system parameters and excitation system parameters of the aforementioned conventional AGC units.

[0046] Furthermore, the modeling method based on multi-agent systems assigns specific functions to different agents, enabling them to make real-time decisions and adjust their behavior based on their own state and information transmitted from other agents, thereby simulating the dynamic interactions of various factors in complex power grid scenarios. Specific settings can be as follows: For the intelligent agent of the new energy power station, its function is to simulate the active power output characteristics of wind farms and photovoltaic power stations, and dynamically adjust the output according to changes in natural conditions (wind speed, solar intensity). The initial rated power is set as the rated operating condition, the wind turbine speed and power curves conform to the wind energy conversion characteristics, and photovoltaic power generation follows the solar-current relationship curve. Its main decision-making rules are: when wind speed or solar intensity changes, the new energy intelligent agent calculates and adjusts the output according to the equipment power conversion model; if the new energy output decreases, the intelligent agent sends a power compensation demand signal to the AGC unit; if the power flow exceeds the limit at the transmission section, the new energy intelligent agent adjusts the power factor to improve reactive power support capability.

[0047] For conventional AGC (Automatic Generation Control) generator units, their function is to respond to fluctuations in renewable energy output and grid frequency deviations, maintaining system stability by adjusting active power. The initial rated power of the AGC unit is set according to actual grid data, and speed control and excitation system parameters are preset. The main decision-making rules it relies on are: calculating the unit's output adjustment based on grid frequency deviations; alleviating line overload problems by coordinating AGC unit power adjustments when power flow exceeds transmission line limits; and optimizing power adjustment within the control dead zone by combining the demand signals from renewable energy generators, avoiding equipment fatigue caused by frequent adjustments.

[0048] For the intelligent agent at the transmission section, its function is to monitor and evaluate the grid's transmission capacity, identify power flow exceeding limits, and interact with AGC units and renewable energy power plants. Initially, line parameters are set according to the grid topology, including rated voltage, line impedance, safety margin, and thermal stability limits. Its main decision-making rules are: when the power flow approaches the limits, it sends adjustment requests to the AGC units to optimize the grid power flow distribution; and based on changes in renewable energy generation power, it adjusts the system's reactive power support strategy to improve grid stability.

[0049] In multi-agent modeling methods, each agent's decision-making rules need to be adaptive to cope with the uncertainties of complex grid faults and fluctuations in renewable energy output. Therefore, machine learning algorithms can be used to optimize and train the agents, enabling them to learn optimal decision-making strategies based on historical grid fault data and renewable energy AGC control data. The training objective is to enable the agents to dynamically adjust their strategies based on existing experience and real-time data when facing different fault conditions, thereby improving the response speed, regulation accuracy, and grid stability of the renewable energy AGC system.

[0050] The optimization training of the agent includes data collection and model training, which will be explained later.

[0051] 102. Set up power grid fault scenarios and conduct fault simulation.

[0052] Specifically, in this application embodiment, an extremely complex and highly coupled power grid fault scenario can be set, involving multiple transmission section overruns, various new energy power generation devices simultaneously experiencing severe changes in natural conditions, and large fluctuations in grid frequency and voltage. Based on the simulation model constructed above, corresponding fault triggering and simulation can be set as needed during the simulation process.

[0053] In one optional implementation, the above-mentioned fault simulation includes: When simulating multiple transmission sections exceeding their limits, the industrial load is increased or the power output is reduced at one end of each transmission section according to a preset ratio. When a simulated wind farm encounters extreme wind speed changes, the power output characteristics of the wind power generation equipment are modified according to the actual wind speed change pattern. When a simulated photovoltaic power station encounters a sudden severe shading, the power output of the photovoltaic power generation equipment is adjusted according to the degree of shading. Record the time of the fault, the type of fault, and the duration of the fault.

[0054] Specifically, during the simulation, corresponding faults can be triggered by increasing or decreasing the load at one end of the transmission section, or by altering the power output of new energy power generation equipment to simulate changes in natural conditions. When simulating multiple transmission sections exceeding their limits, industrial loads are simultaneously increased or power output is decreased at one end of different transmission sections according to a preset ratio. For wind farms encountering extreme wind speed changes, the power output characteristics of wind power generation equipment can be rapidly altered based on the actual wind speed variation patterns. For photovoltaic power stations encountering sudden severe shading, the power output of photovoltaic power generation equipment is adjusted according to the degree of shading. During the fault injection process, the fault occurrence time (accurate to the second), fault type (such as specific transmission section exceeding limits, changes in natural conditions, frequency and voltage fluctuation values, etc.), and fault duration are recorded in detail.

[0055] Figure 2 This is a schematic diagram illustrating a fault scenario simulation process provided in an embodiment of this application. Figure 2 As shown, setting up fault scenarios can include three types; fault simulation methods can include: Based on the contents of the disclosure document and the provided fault scenario simulation flowchart, the process can be described as follows: 0. First, define the grid fault scenarios to be simulated. These scenarios may include transmission line overruns, the impact of natural conditions on renewable energy generation equipment (such as extreme wind speed changes at wind farms, sudden strong shading at photovoltaic power stations, etc.), and large fluctuations in grid frequency and voltage. Specific simulation scenarios may include: 1. Simulate a power transmission section fault: At one end of the power transmission section, the over-limit fault of the section is simulated by increasing or decreasing the load or adjusting the power output.

[0056] Monitor the status of power transmission sections to ensure that situations where sections exceed limits can be detected in real time.

[0057] 2. Simulate new energy power generation equipment failure: For wind farms, extreme wind speed changes are simulated to rapidly alter the power output characteristics of wind power generation equipment.

[0058] For photovoltaic power plants, simulate sudden strong shading situations and adjust the power output of photovoltaic power generation equipment.

[0059] 3. Grid frequency and voltage regulation: The power grid frequency changes are simulated based on the imbalance of active power.

[0060] The voltage changes in the power grid are simulated by adjusting the reactive power.

[0061] 4. Record fault information: During the fault injection process, the time, type, duration of the fault, and changes in key parameters in the system are recorded in detail.

[0062] In setting and simulating complex fault scenarios, it is necessary to consider various power grid devices and their interactions, including different factors such as transmission lines, wind farms, and photovoltaic power stations, while also introducing extreme natural condition changes and drastic fluctuations in grid frequency and voltage. Simulation enables dynamic simulation of these fault scenarios and allows for fault injection and scheduling decision optimization. When setting specific fault scenarios, the situation of transmission line overruns must first be considered. To simulate this fault, load fluctuations in the system are simulated by increasing or decreasing the load or adjusting the power output at one end of the transmission line, thereby triggering the phenomenon of transmission line overruns. In this case, the specific methods of increasing or decreasing the load can be defined using the following algorithm:

[0063] in, This represents the load change. It is the load adjustment factor, which represents the proportion by which the load increases or decreases. This represents the load during normal operation. This adjustment simulates different load fluctuations and, by adjusting power output, simulates power overload or shortage fault scenarios. This process requires real-time monitoring of the status of each transmission section of the power grid and uses an intelligent agent model to decide on the range of load changes to ensure the system's dynamic response and stability.

[0064] Specifically, for new energy power generation equipment, wind farms may encounter extreme wind speed changes, leading to fluctuations in power output. To simulate the impact of wind speed changes on wind power generation, the simulation can be based on actual wind speed variation patterns. During the simulation, extreme wind speed changes will directly affect the power output of wind power generation. For example, extremely high wind speeds will increase the output power of wind power generation equipment, while extremely low wind speeds or no wind will lead to a sharp decrease in power generation. Using the formula of the aforementioned wind power output model, the power output of wind power generation equipment can be quickly adjusted to simulate the impact of natural wind speed changes on the power grid.

[0065] For photovoltaic (PV) power plants, sudden and severe shading can cause significant fluctuations in power output. In such cases, the power output of the PV equipment needs to be adjusted based on the degree and duration of the shading. Using the formula from the aforementioned PV power output model, the dynamic response of PV power generation can be accurately simulated, ensuring timely adjustments to the control strategy when shading occurs.

[0066] Optionally, during fault injection, in addition to simulating the output changes of the aforementioned equipment, drastic fluctuations in grid frequency and voltage must also be considered. Grid frequency changes are related to active power imbalances, while voltage changes are closely related to reactive power adjustments. During simulation, the time, type, duration, and changes in key parameters of the system for each fault are recorded. By recording this information, the system response and agent decision-making can be further optimized, enabling the system to respond more quickly and accurately when encountering similar faults.

[0067] Ultimately, by simulating these fault scenarios, we can gain a detailed understanding of the dynamic interactions of various factors under complex power grid faults. This helps optimize the control strategy of new energy AGC systems in actual operation, improving the robustness and stability of the power grid. This highly coupled and complex simulation is not just a simple simulation of a single fault, but can simulate multiple faults occurring simultaneously, thereby evaluating the overall performance of the system under multiple disturbances.

[0068] 103. Collect monitoring data during the simulation process.

[0069] Specifically, data monitoring points can be deployed at locations such as the outlets of the new energy power plants, transmission sections, and conventional AGC units in the aforementioned simulation model. The data acquisition module acquires key data in real time during the model simulation process, including the output power, current, and voltage of new energy power generation; the active power flow, reactive power flow, and voltage phase angle difference of the transmission section; and electrical quantities such as the power generation, speed, and frequency of the conventional AGC units.

[0070] 104. Compare and verify the simulation results with actual power grid monitoring data or theoretical analysis results; if there are deviations, calibrate the above simulation model and algorithm.

[0071] Specifically, after simulating complex fault scenarios, the simulation results of the model can be compared and verified with monitoring data of similar faults in the actual power grid or authoritative theoretical analysis results. Parameters can be corrected accordingly, and the simulation model and algorithm can be calibrated.

[0072] Figure 3 This is a schematic diagram illustrating a simulation result verification and calibration process provided in an embodiment of this application. Figure 3 As shown, the specific steps are as follows: 1. Obtain simulation results: After completing the simulation test of the new energy AGC system, the first step is to obtain the result data generated during the simulation process.

[0073] 2. Comparison with actual or theoretical data: The simulation results are compared with actual power grid monitoring data or authoritative theoretical analysis results. This step is to verify the accuracy and reliability of the simulation model.

[0074] 3. Determine if there is a significant deviation: By comparing and analyzing the results, we can determine whether there is a significant deviation between the simulation results and the actual data.

[0075] 4. Adjust model and algorithm parameters: If a significant deviation is identified, adjustments to the parameters of the simulation model and algorithm are necessary. This may include changing the interaction coefficients of the factors in the model or correcting the parameters of the simulation algorithm, which will not be elaborated further here.

[0076] 5. Use sensitivity analysis to identify key factors: Sensitivity analysis can identify the factors and parameters that have a significant impact on simulation results. This helps to pinpoint which parameters have the most significant effect on the model's output, allowing for priority adjustment and calibration of these key factors and parameters, thus improving calibration efficiency.

[0077] 6. Prioritize calibration of key factors and parameters: Based on the results of sensitivity analysis, key factors and parameters are calibrated first. This improves calibration efficiency and allows simulation results to more quickly approximate reality.

[0078] Optionally, after adjusting and calibrating the parameters, the simulation test can be performed again, and the above steps can be repeated until the deviation between the simulation results and the actual data is within an acceptable range or the predetermined accuracy requirements are met.

[0079] Optionally, the content of the above comparative verification includes, but is not limited to, any one or more of the following: The active power control response characteristics of new energy AGC, its regulation effect on grid frequency and voltage, and its control of power flow at transmission sections.

[0080] Specifically, the comparison can include the active power control response characteristics of new energy AGC, such as the timeliness and stability of power regulation, the effect on grid frequency and voltage regulation, and the control of power flow at transmission sections. If the simulation results deviate significantly from reality or theory, the simulation model and algorithm should be calibrated. This can be achieved by adjusting the interaction coefficients of various factors in the model, such as changing the influence weights between different fault agents and new energy AGC agents; and by correcting the parameters of the simulation algorithm, such as adjusting the threshold and step size in the agent's decision rules, to make the simulation results closer to reality, thereby improving the accuracy of evaluating the control effect of new energy AGC in complex fault scenarios.

[0081] In this embodiment, a data acquisition step is used to compare the simulation results with actual power grid monitoring data or theoretical analysis results to evaluate the control effect of the new energy AGC system under complex fault scenarios. Comparative analysis reveals the differences between the simulation model and the actual system, providing a basis for subsequent model adjustments and algorithm optimization. The main comparisons include the active power control response characteristics of the new energy AGC system, the regulation effect of power grid frequency and voltage, and the control of power flow at transmission sections. Verification of these factors ensures the accuracy of the simulation model and allows for adjustments when necessary to improve its consistency with actual power grid operation. Specifically, the comparative analysis may include: First, the active power control response characteristics of the new energy AGC need to be verified by comparing simulation results with actual or theoretical data. The new energy AGC system is primarily responsible for regulating power generation to ensure the stability of the grid frequency and voltage. When complex faults occur, the regulation characteristics of the new energy AGC are affected by grid frequency fluctuations and power changes; therefore, its regulation rate and stability are crucial. The regulation rate of the new energy AGC system... Describe it using the following formula:

[0082] in, For power adjustment amount, Δt The time required for adjustment is crucial. If the power adjustment is too slow or too fast within the period following a fault, significant fluctuations in system frequency and voltage will occur, affecting grid stability. Therefore, it is necessary to verify the timeliness and accuracy of the power regulation response of renewable energy generation by comparing simulation results with actual monitoring data.

[0083] The effectiveness of grid frequency and voltage regulation is another important indicator for evaluating the performance of AGC control for new energy sources. During simulation, the grid frequency deviation Δf and voltage deviation ΔV are affected by fluctuations in the power generation of new energy sources. The frequency deviation is calculated using the following formula:

[0084] in, The actual frequency of the power grid. This is the rated frequency of the power grid. The effect of frequency regulation can be verified by comparing the changes in frequency deviation during simulation with the frequency fluctuations in the actual system. The voltage deviation ΔV can be calculated using the following formula:

[0085] in, The actual voltage of the power grid. This is the rated voltage of the power grid. By monitoring changes in frequency and voltage deviation, the ability of new energy AGC to regulate grid stability can be assessed.

[0086] When comparing simulation results with actual or theoretical analysis data, model calibration is necessary. The goal of model calibration is to make the simulation results more closely reflect reality, thereby improving the accuracy of evaluating the control effect of new energy AGC. During calibration, the interaction coefficients of various factors in the model can be adjusted, such as changing the influence weights between different faulty agents and the new energy AGC agent. By adjusting these weights, the interaction between agents can be altered, thus optimizing the accuracy of the simulation results. For example, if extreme wind speed changes at wind farms have a significant impact on grid frequency, the adjustment of the weights on the response of the new energy AGC system to wind speed changes can optimize the regulation effect.

[0087] Furthermore, parameters in the simulation algorithm can be modified, such as adjusting thresholds and step sizes in the agent's decision-making rules. These parameters determine the agent's decision sensitivity and adjustment speed during the simulation process. For example, if the power regulation dead zone set in the agent's regulation rules is too large, the new energy AGC system may not respond sensitively enough to grid frequency fluctuations. In this case, the sensitivity to frequency fluctuations can be enhanced by reducing the dead zone range, thereby improving control accuracy.

[0088] These adjustments effectively reduce the discrepancy between simulation results and actual power grid operation data, improving model accuracy. For example, during simulation, if the power regulation of the new energy AGC system is not timely enough under extreme wind speed conditions, adjusting the step size and regulation rate in the agent's decision-making rules can make the regulation faster, avoiding excessive fluctuations in grid frequency. This approach not only improves control performance but also provides more accurate decision support for fault response in actual system operation. Ultimately, the calibrated simulation model can better simulate the power grid's response under complex fault scenarios, thereby optimizing the performance of the new energy AGC system and ensuring stable power grid operation.

[0089] In this embodiment of the application, the decision rules of each agent in the multi-agent modeling method can be optimized and trained through machine learning algorithms. By utilizing historical power grid fault data and new energy AGC control data, the agents can make more realistic decisions when facing different situations. The training method of the decision rule model is described below.

[0090] In one implementation, the method further includes training a decision rule model for the agent, including: Collect historical power grid fault data, new energy AGC control data, and simulation test data; After preprocessing the collected data, a supervised learning method is used to optimize and train the decision rule model of the agent. In this process, a deep neural network is used to predict the optimal AGC unit power adjustment amount, and the mean square error is used as the loss function for model optimization.

[0091] Specifically, the optimization training of intelligent agents includes data acquisition and model training.

[0092] The training data acquired primarily includes historical power grid fault data, new energy AGC control data, and simulation test data. Among these: Historical power grid fault data mainly includes power flow exceeding limits at transmission sections (fault time, section number, active power flow, reactive power flow, and exceeding limit amplitude), power grid frequency deviation (frequency changes before and after the fault), and voltage fluctuation (voltage changes at key nodes). New energy AGC control data mainly includes wind power and photovoltaic output data (real-time power, wind speed, and solar intensity), AGC unit response data (adjustment rate, adjustment range, and control delay), and load change data (system load forecast and actual load data). The simulation data mainly includes data related to the interactive behavior of new energy intelligent agents, AGC unit intelligent agents, and power transmission section intelligent agents under different fault scenarios.

[0093] After data collection, preprocessing is performed. Data preprocessing may include normalization, outlier removal, and time series resampling.

[0094] The main normalization method can be the Min-Max normalization method:

[0095] in: X This is the original data; , These are the minimum and maximum values ​​of the data, respectively. X′ This is the normalized data.

[0096] For certain tasks of AGC control in new energy sources (such as power adjustment decisions for AGC units), supervised learning methods are used to train the system to learn appropriate power adjustment strategies under different fault conditions. In this embodiment, a deep neural network (DNN) can be used, with the goal of predicting the optimal power adjustment amount for the AGC unit.

[0097] Where: Input X includes the power grid frequency deviation Changes in new energy output Trend exceeding limits etc.; output This refers to the power adjustment amount of the AGC unit.

[0098] The loss function for neural networks uses mean squared error (MSE):

[0099] in: The target output is the result of the training data; Adjusted power for model prediction; N The total number of samples.

[0100] When dealing with complex environments such as fluctuations in new energy sources and sudden failures, intelligent agents need to possess adaptive decision-making capabilities. Reinforcement learning can be used for optimization, enabling the agent to learn the optimal decision-making strategy through continuous trial and error. The core of reinforcement learning is that the agent performs actions in the environment and adjusts its strategy based on reward feedback. The states, actions, and rewards are set as follows: State space S:

[0101] in, For power grid frequency deviation, For excess power, Changes in renewable energy power refer to changes in the power generation capacity of renewable energy sources such as wind and solar energy. V bus This refers to the voltage at critical nodes.

[0102] Action Space A:

[0103] in, This refers to the active power regulation of the AGC unit. This is the reactive power regulation quantity.

[0104] Reward function R:

[0105] in: a, b, g These are the weighting coefficients; This is the rated voltage.

[0106] Deep Q-learning (DQN) can be used to train the agent, allowing it to iteratively optimize its decision-making strategy through Q-value optimization.

[0107] in: m The learning rate; q Discount factor; Q ( s, a ) represents the Q-value of the current state-action pair; Q t+1 ( s , a The new Q value is the result of the iteration. r For instant rewards.

[0108] In the above formula s The "state space" representing the state of the intelligent agent, in the power grid simulation scenario of this application, refers to this space. s May include grid frequency deviation f Power flow exceeding limits at transmission sections P Changes in new energy output P N Critical node voltage V bus These are key pieces of information that comprehensively reflect the current operating status of the power grid; a The "action space" represents the actions that an intelligent agent can perform. In the context of a power grid scenario, this corresponds to... a This may include the active power regulation of the AGC unit. P adjust Reactive power regulation Q adjust This refers to the specific actions that an intelligent agent can take in response to the current state.

[0109] Q ( s , a () is the "state-action value function", which represents the agent's state in the current state. s Next, execute the action. a Then, the expected long-term cumulative rewards that can be obtained. Q ( s , a The higher the value, the more likely the action will be taken under the current power grid conditions. a This is more beneficial for maintaining grid stability and optimizing AGC control performance.

[0110] Q ( s' , a' ) indicates when the agent enters a new state s'Then, for all possible actions a' Value prediction. For example, when the power grid state changes due to frequency deviation or cross-sectional power flow. s' Then, the agent determines and performs an action. a' This refers to the benefits that can be obtained after AGC adjusts its power.

[0111] Q ( s' , a' States and actions are "potential". s' It is to perform an action a The state that will appear later a' Is s 'All possible actions that can be selected in this state.' max Q ( s' , a' ) is in state s' The maximum value of Q among all possible actions.

[0112] During the training process of deep Q-learning, the agent continuously interacts with the simulation environment and updates its algorithm using the formula described above. Q ( s , a The value of ), where r It is to perform an action a Immediate rewards after the action, such as a decrease in frequency deviation, will result in a positive reward; if the cross-sectional exceedance worsens, a negative reward will be given. s' It is to perform an action a The new state that is entered later, max Q ( s' , a' ) is in the new state s' The maximum value of Q among all possible actions. m It is the learning rate (which controls the magnitude of each update). q It's a discount factor (balancing the importance of immediate rewards and future rewards). Through such iterative updates, Q ( s , a It can gradually approach the optimal value, allowing the intelligent agent to continuously learn the optimal decision-making strategy in complex power grid fault scenarios. For example, when multiple faults overlap, it can accurately select the adjustment amount of the AGC unit to achieve stable control of the power grid.

[0113] The reference values ​​for each weight in the reward function R above can be determined by following a process of theoretical derivation, testing and verification, and continuous iteration. Specifically: 1. Theoretical Derivation (1) Determine the "weight of influence" of each indicator on the power grid Based on the power grid's goals of "stabilizing frequency, controlling power flow, and ensuring voltage," key indicators can be initially prioritized. For example, frequency collapse directly leads to widespread power outages and requires priority control, thus warranting a higher weight. Power flow exceeding limits may cause equipment overload and line tripping, therefore it should be set as a secondary priority. Based on the deviation limits of each indicator, the theoretical weight can be initially set as follows: α : β : g =0.5:0.2:0.1=5:2:1.

[0114] (2) Correction based on "control sensitivity" Using small-disturbance stability analysis, calculate the adjustment sensitivity of AGC control to various indicators, such as the adjustment sensitivity of AGC to frequency. S f =0.8Hz / MW means that for every 1MW increase in output, the frequency rises by 0.8Hz. The adjustment sensitivity of each indicator is calculated and tested. Higher sensitivity indicates that the AGC can more easily control that indicator, allowing for a more appropriate reduction in its weight. The weights are then adjusted accordingly.

[0115] 2. Testing and Verification After obtaining the theoretically calculated weights, different weight combinations can be set in simulation tests to observe the control effect of AGC, thereby judging the error in the weight setting and adjusting it in a timely manner. If the weights... α If the value is too small, the frequency exceeding the limit cannot be suppressed in time during the simulation, resulting in significant fault losses. Therefore, the corresponding weight should be increased appropriately.

[0116] Through multi-scenario testing and algorithmic optimization of weights, the expected failure loss is minimized, ultimately determining the project's usability. α , β , g .

[0117] 3. Continuous iteration The system should be recalibrated periodically as the grid topology and the proportion of new energy sources connected change. This could include annual updates or re-optimization when large-scale new energy power plants are added.

[0118] The method in this embodiment has the advantages of improving testing accuracy and efficiency, and is implemented using a multi-agent modeling approach. Transmission section overruns, the impact of natural conditions on new energy power generation equipment, and the new energy AGC system are each treated as an independent agent. Each agent is given a clear function, initial state, and decision-making rules, enabling it to make real-time decisions and adjust its behavior based on its own state and information from other agents. This accurately simulates the dynamic interactions of various factors in complex scenarios, thereby improving testing accuracy. Simultaneously, machine learning algorithms are used to optimize the agent's decision-making rules, and historical data is used to train the agents, enabling them to make more realistic decisions in different situations, further improving testing accuracy and efficiency.

[0119] The method in this embodiment has the advantage of more accurately simulating complex fault scenarios. It achieves this by setting up an extremely complex and highly coupled power grid fault scenario, involving multiple transmission line sections exceeding their limits simultaneously, various new energy power generation devices experiencing severe changes in natural conditions simultaneously, and large fluctuations in grid frequency and voltage simultaneously. During the simulation, corresponding faults are triggered by increasing or decreasing the load at one end of the transmission line section and changing the power output of the new energy power generation devices. The occurrence time, type, and duration of each fault are recorded in detail, comprehensively simulating complex fault situations that may occur in actual power grid operation. This provides a more realistic scenario for testing the active power control response of new energy AGC under extreme conditions.

[0120] The method in this application embodiment has the advantage of improving the accuracy of simulation results, which is achieved by using simulation result verification and calibration, as well as sensitivity analysis methods. After simulating complex fault scenarios, the simulation results are compared and verified with monitoring data of similar faults in the actual power grid or authoritative theoretical analysis results. If there is a large deviation, the interaction coefficients of various factors in the model and the parameters of the simulation algorithm are adjusted to make the simulation results closer to the actual situation. At the same time, sensitivity analysis methods are used to identify the factors and parameters that have a significant impact on the simulation results, and these key factors and parameters are adjusted and calibrated first to improve calibration efficiency, thereby improving the accuracy of the evaluation of the control effect of new energy AGC under complex fault scenarios.

[0121] New energy AGC (Automatic Generation Control) has been widely applied in various new energy power plants, such as wind farms and photovoltaic power stations. Through the AGC system, new energy power plants can adjust their power generation in real time according to the grid's needs to maintain power balance and frequency stability in the power system. Currently, different AGC control modes have been developed to adapt to the complex and ever-changing grid operating environment and the characteristics of new energy power generation. For example, the coordination mode in the regional control mode enables close cooperation between the new energy power plant and the grid dispatch center, uniformly calculating regional control deviations and adjustment needs, effectively improving the stability and reliability of the regional grid; in the conventional mode, the new energy AGC master station calculates frequency regulation commands independently, suitable for scenarios with high requirements for real-time performance and independence; the full absorption mode aims to fully utilize new energy power generation, reduce wind and solar curtailment, and improve energy efficiency. In the power plant PLC control mode, different strategies such as BASEO, SCHEO, SCHER, AUTOR, SCHEA, and MAXG are used for different operating conditions and control objectives. For example, the planned mode (BASEO) can control power according to a preset power generation plan, while the planned frequency regulation mode (SCHEO) takes into account frequency regulation functions on the basis of planned power generation.

[0122] Currently, testing of active power control under different AGC modes in new energy sources mainly employs traditional field testing methods and some simple simulation tests. While traditional field testing can be conducted in real-world environments, it has several limitations. Firstly, field testing is costly, requiring significant investment of manpower, resources, and time. For example, testing at new energy power plants necessitates suspending the operation of some power generation equipment, which not only affects the plant's normal power generation revenue but may also impact the stability of the power grid. Secondly, field testing faces the complexity and uncertainty of actual power grid operation, making it difficult to comprehensively simulate all possible faults and operating conditions.

[0123] Existing simulation testing methods generally begin with scenario building and parameter setting. Power system simulation software is used to construct models including renewable energy power plants, conventional AGC units, and power grid transmission sections. Modular modeling breaks down each part into independent modules, connects them using standardized interfaces, and sets various parameters and initial conditions based on actual needs and operational data. Then, fault injection and operating condition simulation are performed. Based on the established model, grid faults such as section over-limit faults are simulated, and changes in system electrical quantities are monitored and recorded in real time. Simultaneously, different operating conditions are simulated under various AGC control modes, including constant power control, tracking the planned curve control, and participation in primary frequency regulation control of the power grid. Finally, the system operating status, control command execution, and related electrical quantity change trends are recorded, providing a data foundation for subsequent testing and analysis.

[0124] In the process of fault injection and operating condition simulation, traditional simulation methods may struggle to accurately and comprehensively simulate the interaction mechanisms between various faults and operating conditions for some extremely complex and highly coupled power grid fault scenarios. Due to the intricate interactions between factors in these complex fault scenarios, existing simulation methods may fail to accurately reflect the active power control response characteristics of new energy AGC under such extreme conditions, leading to biases in the evaluation of its control effectiveness and consequently affecting the verification and optimization of control strategies.

[0125] The method in this embodiment employs a multi-agent modeling approach, treating different fault factors and the new energy AGC system as independent agents. Each agent makes real-time decisions and adjusts its behavior based on its own state and information from other agents, thus more realistically simulating actual conditions in complex scenarios. This approach accurately reflects the active power control actions and response characteristics of the new energy AGC under extremely complex fault scenarios. Furthermore, it can more realistically simulate complex scenarios, accurately reflecting the active power control actions and response characteristics of the new energy AGC when facing extreme and complex fault scenarios such as multiple transmission line over-limits, various new energy power generation devices being affected by changes in natural conditions, and large fluctuations in grid frequency and voltage. For example, during the simulation, the new energy power generation agent can adjust its output in real time based on changes in wind speed and light intensity; the transmission line agent monitors power flow and requests adjustments when approaching limits; and the AGC unit agent adjusts its power based on grid frequency deviations and signals from other agents. The collaborative work of these agents clearly presents the control process of the new energy AGC, providing accurate data for performance evaluation.

[0126] Based on the description of the foregoing method embodiments, this application also provides a new energy AGC active power control joint simulation test device.

[0127] Figure 4 This is a schematic diagram of a new energy AGC active power control co-simulation test device provided in an embodiment of this application. Figure 4 As shown, the new energy AGC active power control joint simulation test device 400 includes: The simulation model construction module 410 is used to construct the simulation model. The simulation model adopts a multi-agent modeling method, which treats different fault factors as independent agents. Each agent has self-perception ability, information interaction ability, and decision-making ability. The fault factors include transmission section exceeding the limit, new energy power generation equipment being affected by changes in natural conditions, and new energy AGC system. The fault simulation module 420 is used to set up power grid fault scenarios and perform fault simulation. The data acquisition module 430 is used to collect monitoring data during the simulation process; The verification and calibration module 440 is used to compare and verify the simulation results with actual power grid monitoring data or theoretical analysis results; if there is a deviation, the above simulation model and algorithm are calibrated.

[0128] Optionally, the simulation model construction module 410 mentioned above is specifically used for: When building the model, electrical parameters, control parameters, and initial conditions for system operation are set for each power system component module according to actual power grid data, and each agent is given a clear function, initial state, and decision-making rules.

[0129] Optionally, the aforementioned power system component modules include new energy power plants, conventional AGC units, and power grid transmission sections; The aforementioned electrical parameters include, but are not limited to: the rated power, conversion efficiency, and power factor of the new energy power generation equipment, as well as the speed control system parameters and excitation system parameters of the aforementioned conventional AGC units.

[0130] Optionally, the above monitoring data includes: The output power, current, and voltage of the aforementioned new energy power generation equipment; the active power flow, reactive power flow, and voltage phase angle difference of the aforementioned power grid transmission sections; and the power generation, speed, and frequency of the aforementioned conventional AGC units.

[0131] Optionally, the aforementioned fault simulation module 420 is specifically used for: When simulating multiple transmission sections exceeding their limits, the industrial load is increased or the power output is reduced at one end of each transmission section according to a preset ratio. When a simulated wind farm encounters extreme wind speed changes, the power output characteristics of the wind power generation equipment are modified according to the actual wind speed change pattern. When a simulated photovoltaic power station encounters a sudden severe shading, the power output of the photovoltaic power generation equipment is adjusted according to the degree of shading. Record the time of the fault, the type of fault, and the duration of the fault.

[0132] Optionally, the content of the above comparative verification includes, but is not limited to, any one or more of the following: The active power control response characteristics of new energy AGC, its regulation effect on grid frequency and voltage, and its control of power flow at transmission sections.

[0133] Optionally, the simulation model building module 410 described above is also used to train the decision rule model of the intelligent agent; specifically, the simulation model building module is used for: Collect historical power grid fault data, new energy AGC control data, and simulation test data; After preprocessing the collected data, a supervised learning method is used to optimize and train the decision rule model of the agent. In this process, a deep neural network is used to predict the optimal AGC unit power adjustment amount, and the mean square error is used as the loss function for model optimization.

[0134] Optionally, the simulation model construction module 410 is also used to further optimize the agent's adaptive decision-making ability using reinforcement learning, wherein by setting the state space, action space and reward function, the agent uses a deep Q-learning algorithm to iteratively optimize the decision-making strategy through Q-value.

[0135] Understandably, this involves Figure 4 The relevant content of each module in the above method embodiments has been described in detail, and you can refer to the content of the method embodiments for details; that is... Figure 4 The provided new energy AGC active power control joint simulation test device 400 can perform, for example... Figure 1 , Figure 2 or Figure 3 Any steps in the illustrated embodiments will not be described in detail here.

[0136] In one embodiment of this application, an electronic device is also provided. See also... Figure 5 , Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 5 As shown, the electronic device 500 includes a processor 501 and a memory 502. The memory 502 stores a computer program, which, when executed by the processor 501, will perform actions such as... Figure 1 , Figure 2 or Figure 3 Any step in the method embodiment shown. The electronic device 500 may also include input / output devices, etc. In a specific embodiment, the electronic device may be a terminal device, etc.

[0137] In one embodiment, a computer-readable storage medium is also provided, which stores a computer program that, when executed by a processor 501, causes the processor 501 to perform any of the steps in the above method embodiments.

[0138] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0139] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0140] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A joint simulation test method for active power control of new energy AGC, characterized in that, The method includes: A simulation model is constructed, which adopts a multi-agent modeling method, treating different fault factors as independent agents. Each agent has self-perception, information interaction, and decision-making capabilities. The fault factors include transmission section exceeding limits, new energy power generation equipment being affected by changes in natural conditions, and new energy AGC systems. Set up power grid fault scenarios and conduct fault simulation; Collect monitoring data during the simulation process; The simulation results are compared and verified with actual power grid monitoring data or theoretical analysis results; if there are deviations, the simulation model and algorithm are calibrated.

2. The new energy AGC active power control joint simulation test method according to claim 1, characterized in that, The construction of the simulation model includes: When building the model, electrical parameters, control parameters, and initial conditions for system operation are set for each power system component module according to actual power grid data, and each agent is given a clear function, initial state, and decision-making rules.

3. The new energy AGC active power control joint simulation test method according to claim 2, characterized in that, The power system component modules include new energy power plants, conventional AGC units, and power grid transmission sections; The electrical parameters include: the rated power, conversion efficiency, and power factor of the new energy power generation equipment, and the speed regulation system parameters and excitation system parameters of the conventional AGC unit.

4. The new energy AGC active power control joint simulation test method according to claim 3, characterized in that, The monitoring data includes: The output power, current, and voltage of the new energy power generation equipment; the active power flow, reactive power flow, and voltage phase angle difference of the power grid transmission section; and the power generation power, speed, and frequency of the conventional AGC unit.

5. The new energy AGC active power control joint simulation test method according to claim 4, characterized in that, The fault simulation includes: When simulating multiple transmission sections exceeding their limits, the industrial load is increased or the power output is reduced at one end of each transmission section according to a preset ratio. When a simulated wind farm encounters extreme wind speed changes, the power output characteristics of the wind power generation equipment are modified according to the actual wind speed change pattern. When a simulated photovoltaic power station encounters a sudden severe shading, the power output of the photovoltaic power generation equipment is adjusted according to the degree of shading. Record the time of the fault, the type of fault, and the duration of the fault.

6. The new energy AGC active power control joint simulation test method according to claim 1, characterized in that, The comparative verification includes: The active power control response characteristics of new energy AGC, its regulation effect on grid frequency and voltage, and its control of power flow at transmission sections.

7. The new energy AGC active power control joint simulation test method according to claim 4, characterized in that, The method further includes training a decision rule model for the agent, specifically including: Collect historical power grid fault data, new energy AGC control data, and simulation test data; After preprocessing the collected data, a supervised learning method is used to optimize and train the decision rule model of the agent. In this process, a deep neural network is used to predict the optimal AGC unit power adjustment amount, and the mean square error is used as the loss function for model optimization.

8. The new energy AGC active power control joint simulation test method according to claim 7, characterized in that, The method further includes: Reinforcement learning is employed to further optimize the agent's adaptive decision-making ability. Specifically, by setting a state space, action space, and reward function, a deep Q-learning algorithm is used to enable the agent to iteratively optimize the decision-making strategy through Q-value optimization.

9. A joint simulation test device for active power control of new energy AGC, characterized in that, include: The simulation model construction module is used to construct the simulation model. The simulation model adopts a multi-agent modeling method, which treats different fault factors as independent agents. Each agent has self-perception ability, information interaction ability, and decision-making ability. The fault factors include transmission section exceeding the limit, the impact of natural conditions on new energy power generation equipment, and new energy AGC system. The fault simulation module is used to set up power grid fault scenarios and perform fault simulation. The data acquisition module is used to collect monitoring data during the simulation process; The verification and calibration module is used to compare and verify the simulation results with actual power grid monitoring data or theoretical analysis results; if there is a deviation, the simulation model and algorithm are calibrated.

10. An electronic device, characterized in that, It includes a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method as described in any one of claims 1-8.

Images