A data-driven based multi-vsg inertia and damping adaptive adjustment method and system

Abstract

The application discloses a kind of based on data driving's multiple VSG inertia and damping self-adapting adjustment method and system. Among them, method includes for each VSG node in multiple VSG grid-connected system, the optimal rotational inertia and optimal damping coefficient of each VSG node at current time are obtained using agent;The agent is used to select action quantity according to current state quantity at each time step, and the effect of action quantity is evaluated by reward function and feedback, through multiple iteration feedback, the rotational inertia and damping coefficient of each VSG node are automatically adjusted;According to the optimal rotational inertia and the optimal damping coefficient, the inverter is controlled by VSG control algorithm.The scheme provided by the application considers frequency deviation and frequency change rate on the basis of ensuring the transient stability of multiple VSG, realizes the comprehensive optimization of multiple VSG transient performance.

Description

Technical Field

[0001] This invention relates to the field of virtual synchronous machine control technology, and in particular to a data-driven method and system for adaptive adjustment of multiple VSG inertia and damping. Background Technology

[0002] With the steady increase in installed capacity of new energy sources, the degree of power electronics integration in power systems is also gradually deepening. In traditional power systems, the main power generation unit is a synchronous generator (SG) driven by non-renewable energy sources such as coal. These traditional synchronous generators can store mechanical energy through their rotor shafts, thus possessing significant inertia. This effectively maintains the generator's rotational speed when faced with disturbances, ensuring stable generator output. In contrast, power electronic devices lack the rotor shaft of traditional synchronous generators, resulting in a lack of overall inertia in the new power system. When faced with disturbances such as voltage and frequency drops, this can lead to significant rates of change of frequency (RoCoF), which in severe cases can even jeopardize the safe and stable operation of the power system.

[0003] It is worth emphasizing that the inertia and damping of a new energy power grid-connected system mainly depend on the control strategy of the grid-connected inverter. Therefore, scholars both domestically and internationally have proposed a series of control schemes to enhance the system's inertia and damping. Among them, Virtual Synchronous Generator (VSG) control, by simulating the rotor swing equation of a traditional synchronous generator to add virtual "moment of inertia" and "damping" to the inverter, is considered one of the most effective control schemes for enhancing power system inertia and improving voltage and frequency response under the new power grid architecture. While inheriting the external characteristics of traditional SG, VSG control technology also exhibits different features. On the one hand, the moment of inertia and damping coefficient of a traditional SG are fixed, their values ​​determined by the physical entity, while the moment of inertia and damping coefficient of a VSG are virtualized through the control strategy and can be flexibly adjusted within the allowable capacity range. On the other hand, the damping braking effect of the damping winding of a traditional SG is very small, and its damping coefficient is almost negligible, while the damping dissipation term of a VSG has a relatively large impact on transient performance and cannot be ignored like in a SG. Therefore, when the grid voltage drops or a short-circuit fault occurs in the transmission line, the transient stability problem of VSG is more complex than that of SG. If the traditional transient analysis methods for SG are directly applied to VSG, it may lead to bias or overly conservative tendencies in the transient stability assessment results of VSG, which will ultimately affect the correctness of VSG parameter adjustment and worsen the transient response of VSG.

[0004] In summary, overcoming the conservatism of existing VSG transient stability analysis methods, adaptively reshaping the inertia and damping of the VSG system, improving the system's transient stability, and optimizing the transient performance of the VSG system are of great significance for the stable operation of new power systems. Summary of the Invention

[0005] To address the aforementioned technical problems, embodiments of the present invention provide a data-driven adaptive adjustment method and system for multiple VSG inertia and damping.

[0006] The technical solution of this invention is implemented as follows:

[0007] This invention provides a data-driven adaptive adjustment method for the inertia and damping of multiple VSGs, the method comprising:

[0008] For each VSG node in a multi-VSG grid-connected system, an agent is used to obtain the optimal moment of inertia and optimal damping coefficient of each VSG node at the current moment. The agent selects an action quantity based on the current state quantity at each time step and evaluates the effect of the action quantity through a reward function for feedback. Through multiple iterations of feedback, the moment of inertia and damping coefficient of each VSG node are automatically adjusted. The state quantity characterizes the operating state of the multi-VSG grid-connected system; the action quantity characterizes the control action taken by the multi-VSG grid-connected system at each time step; and the reward function is used to evaluate the performance of the multi-VSG grid-connected system.

[0009] The inverter is controlled by the VSG control algorithm based on the optimal moment of inertia and the optimal damping coefficient.

[0010] In one embodiment, the state variables are the angular frequency and angular frequency change rate of the current VSG node and its neighboring VSG nodes, and the calculation expression for the state variables is:

[0011]

[0012] Among them, s ti Represents the state variable, ω i This represents the frequency of the i-th VSG. ω represents the rate of change of the frequency of the i-th VSG. j This represents the frequency of the j-th VSG. Let Ω represent the frequency change rate of the j-th VSG, and let Ω be the set of adjacent VSG nodes of the i-th VSG node.

[0013] In one embodiment, the motion quantity is the moment of inertia and damping coefficient of this VSG node, and the calculation expression for the motion quantity is:

[0014] a ti ={Ji D i}

[0015] Among them, a ti J represents the amount of motion. i D represents the moment of inertia of the i-th VSG node. i This represents the damping coefficient of the i-th VSG node.

[0016] In one embodiment, the calculation expression for the reward function is:

[0017]

[0018] Where, r 1i This represents the penalty term r for VSG related to frequency deviation. 2i The term r represents the penalty term for the VSG related to the rate of change of frequency. 3i The term r represents the penalty for frequency deviation between neighboring VSGs. ti Represents the reward function, ρ ω ρ ω0 ρ dω ρ dω0 ρ m All are penalty coefficients, Δω i This represents the frequency deviation of the i-th VSG. ω represents the rate of change of the frequency of the i-th VSG. i ω represents the frequency of the i-th VSG. j Let Ω represent the frequency of the j-th VSG, and let Ω be the set of adjacent VSG nodes of the i-th VSG node.

[0019] In one embodiment, the inverter is controlled by a VSG control algorithm based on the optimal moment of inertia and the optimal damping coefficient, including:

[0020] Measure the output current and output voltage of the inverter, and calculate the output power based on the output current and output voltage;

[0021] Based on the optimal moment of inertia and the optimal damping coefficient, the voltage amplitude reference value and frequency are obtained through the VSG control algorithm;

[0022] Based on the voltage amplitude reference value and the frequency, an output reference voltage is synthesized; after the output reference voltage passes through a voltage and current dual closed loop, the inverter is controlled by a pulse width modulation unit using a modulation signal.

[0023] In one embodiment, calculating the output power based on the output current and the output voltage includes:

[0024]

[0025] Among them, P i Let Q be the output active power of the i-th VSG. i V is the output reactive power of the i-th VSG. d V represents the d-axis component of the inverter's output voltage in the dq coordinate system. q Let I be the q-axis component of the inverter's output voltage in the dq coordinate system. d Let I be the d-axis component of the inverter's output current in the dq coordinate system. q Let q be the q-axis component of the inverter's output current in the dq coordinate system.

[0026] In one embodiment, based on the optimal moment of inertia and the optimal damping coefficient, the voltage amplitude reference value and frequency are obtained through the VSG control algorithm, including:

[0027]

[0028] E = K(Q) ref -Q i )+E ref

[0029] Among them, J i D is the virtual rotational inertia of the i-th VSG node; i It is the virtual damping coefficient of the i-th VSG node; and P i ω represents the reference value of active power and the actual output active power of the i-th VSG node, respectively; i ω is the actual operating frequency of the i-th VSG node. j ω is the actual operating frequency of the j-th VSG node. ref This is the rated frequency value; D k For frequency-modulated mutual damping, δ is the phase difference between the common coupling point voltage Vpcc and the grid voltage Vg, defined as the power angle; E is the voltage amplitude reference value of the voltage-current dual closed loop; E ref It is the rated voltage amplitude; K is the reactive power-voltage droop coefficient; Q ref and Q i These are the reactive power reference value and the actual reactive power output of the VSG, respectively. The derivative of the VSG output frequency.

[0030] This invention also provides a data-driven multi-VSG inertia and damping adaptive adjustment system, comprising: a processor and a memory for storing a computer program that can run on the processor; wherein, when the processor runs the computer program, it executes the steps of the method described above.

[0031] This invention also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the method described above.

[0032] The method in this embodiment has the following beneficial effects:

[0033] This embodiment addresses the comprehensive optimization problem of transient frequency deviation, frequency change rate, and frequency coupling oscillation in multi-machine VSG grid-connected systems. It adaptively adjusts and optimizes the rotational inertia and damping coefficient of multiple VSGs in the distributed network based on deep reinforcement learning. This overcomes the reliability and security issues caused by the high dependence of centralized reinforcement learning on communication. While ensuring the transient stability of VSGs, it also takes into account frequency deviation and frequency change rate, achieving comprehensive optimization of VSG transient performance. Attached Figure Description

[0034] Figure 1 This is a flowchart illustrating the data-driven adaptive adjustment method for multiple VSG inertia and damping according to an embodiment of the present invention.

[0035] Figure 2 This is a schematic diagram of the intelligent agent optimization process in an embodiment of the present invention;

[0036] Figure 3 This is a schematic diagram of a distributed optimization scheme for a multi-VSG grid-connected system according to an embodiment of the present invention;

[0037] Figure 4 This is a schematic diagram of the control scheme according to an embodiment of the present invention;

[0038] Figure 5 This is an internal structural diagram of a computer device according to an embodiment of the present invention. Detailed Implementation

[0039] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments.

[0040] This invention provides a data-driven adaptive adjustment method for the inertia and damping of multiple VSGs, such as... Figure 1 As shown, the method includes:

[0041] Step 101: For each VSG node in the multi-VSG grid-connected system, an agent is used to obtain the optimal moment of inertia and optimal damping coefficient of each VSG node at the current moment. The agent is used to select an action quantity based on the current state quantity at each time step, and evaluates the effect of the action quantity through a reward function for feedback. Through multiple iterations of feedback, the moment of inertia and damping coefficient of each VSG node are automatically adjusted. The state quantity is used to characterize the operating state of the multi-VSG grid-connected system. The action quantity is used to characterize the control action taken by the multi-VSG grid-connected system at each time step. The reward function is used to evaluate the performance of the multi-VSG grid-connected system.

[0042] Step 102: Based on the optimal moment of inertia and the optimal damping coefficient, control the inverter using the VSG control algorithm.

[0043] This embodiment addresses the comprehensive optimization problem of transient frequency deviation, frequency change rate, and frequency coupling oscillation in multi-machine VSG grid-connected systems. It adaptively adjusts and optimizes the rotational inertia and damping coefficient of multiple VSGs in the distributed network based on deep reinforcement learning. This overcomes the reliability and security issues caused by the high dependence of centralized reinforcement learning on communication. While ensuring the transient stability of VSGs, it also takes into account frequency deviation and frequency change rate, achieving comprehensive optimization of VSG transient performance.

[0044] The method in this embodiment first constructs a mathematical model and second-order transfer function of a virtual synchronous generator (VSG); secondly, it establishes the transient space and action space of a multi-VSG grid-connected system and evaluates the system state through a reward function mechanism; thirdly, it proposes a control scheme and trains a neural network using a deep reinforcement learning algorithm; finally, it adjusts the moment of inertia J and damping coefficient D of the multi-VSG grid-connected system based on the trained neural network. Simulation experiments verify the effectiveness and operability of the method.

[0045] Specifically, the solution in this embodiment includes the following:

[0046] 1. Using the rotor motion equations of a synchronous generator as a prototype, derive the mathematical model of a virtual synchronous generator:

[0047] Active power control simulates the primary frequency regulation function of a synchronous generator governor:

[0048]

[0049] J is the virtual moment of inertia; D is the virtual damping coefficient; P ref P and ω represent the active power reference value and the actual active power output of the VSG, respectively; ω and ω ref These are the actual operating frequency and rated frequency of the VSG; δ is the phase difference between the common coupling point voltage vpcc and the grid voltage vg, which is defined as the power angle.

[0050] Simulating the excitation regulation function of a traditional synchronous generator, reactive power control uses droop control to achieve voltage regulation:

[0051] E = K(Q) ref -Q)+E ref

[0052] Where E is the voltage amplitude reference value of the voltage-current dual closed loop; E ref It is the rated voltage amplitude; K is the reactive power-voltage droop coefficient; Q ref Q and Q represent the reactive power reference value and the actual reactive power output of VSG, respectively.

[0053] Under high-voltage power grids, the line impedance is negligible in resistance and is approximately purely inductive.

[0054] The second-order transfer function model of the VSG system is:

[0055]

[0056] Where, ω n U is the natural frequency and ζ is the damping ratio. grid X is the grid voltage, and X is the line impedance.

[0057] The moment of inertia J is a parameter that simulates the rotor inertia of a synchronous generator in a VSG system. It reflects the system's inertia in response to frequency changes: a larger J can smooth frequency fluctuations and improve the system's frequency stability, while a smaller J can improve the system's dynamic response speed, but may lead to more severe frequency fluctuations.

[0058] The damping coefficient D is a parameter in the VSG system that simulates the damping characteristics of a synchronous generator. It reflects the system's ability to suppress oscillations: a larger D can effectively suppress system oscillations and improve system stability, while a smaller D can improve the system's dynamic response speed but may lead to system oscillations.

[0059] J and D together determine the dynamic response characteristics of the VSG system. In practical applications, the values ​​of J and D need to be optimized according to system requirements and operating conditions in order to achieve good dynamic performance and stability.

[0060] 2. Establish the transient space and action space of the multi-VSG grid-connected system, and evaluate the system state through a reward function mechanism.

[0061] In this embodiment, the optimization process is implemented using a deep reinforcement learning algorithm. Specifically, the system constructs the reinforcement learning environment and policy using the state variables, action variables, nonlinear state-space equations, and reward functions defined above, thereby achieving adaptive adjustment of the rotational inertia (J) and damping coefficient (D) of the multi-VSG system.

[0062] For a deep reinforcement learning task, the most important thing is to define the three elements: state space, action space, and reward function.

[0063] See Figure 2 After an action set is output to the environment, the environment generates a new set of state variables based on the action parameters. This set of state variables serves as the agent's input. Through the constructed reward function and the current input state, the agent determines the current state, then assesses the optimization of the previous set of action variables, and adjusts the output of the next set of actions. The goal is to maximize the cumulative reward, thereby achieving optimal action. Here, the agent refers to the entity that learns and takes actions through interaction with the environment.

[0064] State variables: State variables are the current state information of the system, used to describe the dynamic behavior of the system. In this embodiment, the frequency value ω and the angular frequency change rate RoCoF, which can characterize the frequency characteristics of the VSG, are selected as state variables. Each VSG node cooperates with its neighbors based on local information and communication. In this embodiment, the state variables obtained by each VSG node are the angular frequency and angular frequency change rate of its local VSG and two neighboring VSGs:

[0065]

[0066] Where Ω is the set of adjacent VSGs of the target VSG unit.

[0067] Each agent acquires state variables through local information and neighbor communication collaboration. The selection of state variables can characterize the frequency characteristics of the VSG and help the agent understand the current operating state of the system.

[0068] Action quantity: Action quantity refers to the control action that the system can take at each time step. In this invention, the moment of inertia and damping coefficient are defined as action quantities.

[0069] a ti ={J i D i}

[0070] State quantity s ti The control strategy u(.) is mapped to the action quantity a. ti The functional relationship of the mapping can be expressed as:

[0071] a ti =u(s ti )

[0072] Where, x tiThis represents all state variables in the entire system, including the VSG's output current if, output voltage vo, angular frequency ω, output power P, etc.; d ti This represents uncertain disturbances or variables, such as changes in the active power reference value, sudden increases or decreases in load, and voltage drops in the power grid.

[0073] The agent selects appropriate actions based on the current state variables and optimizes the dynamic response of the system by adjusting these parameters.

[0074] Agent: An agent is a subject that learns and takes action by interacting with its environment. In this invention, the agent is each VSG node, which selects actions based on the current state and evaluates the effectiveness of the actions through a reward function. The agent's goal is to find the optimal moment of inertia and damping coefficient through continuous learning and adjustment to optimize the system's transient performance.

[0075] Reward Function: The reward function is used to evaluate the system's performance and guide the optimization direction of the reinforcement learning algorithm. In this invention, considering the training objective's requirements for frequency bias and rate of change, the reward function is designed as follows:

[0076]

[0077] Where, r 1i This represents the penalty term related to the frequency deviation of the VSG. Since the training objective of deep reinforcement learning in this embodiment is to reduce the frequency deviation of the VSG to no more than 0.5 Hz, a smaller penalty coefficient ρ is chosen when the frequency deviation is less than 0.5 Hz. ω The penalty term is calculated by multiplying the frequency deviation by the value of the penalty term. When the frequency deviation exceeds 0.5 Hz, a relatively large penalty coefficient ρ is chosen. ω0 The hope is to prevent this from happening through training.

[0078] r 2i This represents the penalty term for the VSG's frequency change rate. Since another training objective of deep reinforcement learning in this embodiment is to reduce the VSG's frequency change rate to no more than 2 Hz / s, a smaller penalty coefficient ρ is chosen when the frequency change rate is less than 2 Hz / s. dω The product of the absolute value of the rate of change of frequency and the frequency is used as a penalty term. When the rate of change of frequency exceeds 2 Hz / s, a relatively large penalty coefficient ρ is chosen. dω0 The hope is to prevent this from happening through training.

[0079] r 3i The penalty term represents the frequency deviation between neighboring VSGs, with a penalty coefficient ρ. m .

[0080] The above three penalties, when normalized, yield the reward function for the deep reinforcement learning algorithm in this section, denoted as r. ti .

[0081] Through the reward function, the agent can evaluate the effect of the current action and adjust its strategy to maximize the cumulative reward.

[0082] Environment: The environment is the object of interaction between the agent and the system. It generates new state variables based on the agent's actions and returns rewards. In this embodiment, the environment is a multi-VSG grid system. The agent influences the system's frequency response by adjusting the moment of inertia and damping coefficient. The environment then generates new frequencies and rates of change of frequency based on these adjustments and returns corresponding rewards.

[0083] Based on the above definition, reinforcement learning algorithms can, at each time step, adjust the current state variable (s) according to the current state variable (s). ti Select the amount of motion (a) ti The reward function is used to evaluate the effect of the action and feeds back to the algorithm to adjust the strategy. Through continuous iteration and optimization, the optimal value of the reward function that maximizes the accumulated reward is found. The reinforcement learning algorithm eventually finds the optimal moment of inertia (J) and damping coefficient (D), thereby achieving comprehensive optimization of frequency deviation and frequency change rate in a multi-VSG grid system and improving the transient stability of the system.

[0084] See the schematic diagram of the distributed optimization scheme for a multi-VSG grid-connected system. Figure 3 As shown.

[0085] In summary, this embodiment achieves the optimal parameters as follows:

[0086] State observation: The agent first observes the current state variables (frequency and rate of change of frequency) to understand the current operating state of the system.

[0087] Action selection: The agent selects action quantities (moment of inertia and damping coefficient) based on the current state quantities, and maps them to specific parameter adjustments through the control strategy.

[0088] Environmental feedback: The environment generates new state variables based on the agent's actions, calculates the reward function, and evaluates the effect of the current action.

[0089] Policy optimization: The agent adjusts its policy based on feedback from the reward function, aiming to maximize cumulative reward. Through continuous iteration and optimization, the agent gradually finds the optimal moment of inertia and damping coefficient.

[0090] Optimal parameters: After multiple iterations and optimizations, the agent finally finds the optimal moment of inertia and damping coefficient, which comprehensively optimizes the system's frequency deviation and rate of change, thereby improving the system's transient stability.

[0091] 3. Propose a control plan

[0092] See the schematic diagram of the control scheme. Figure 4 As shown.

[0093] The following are the calculation steps for the control scheme:

[0094] Step 1) Measure the inverter's output current and voltage and calculate the corresponding output power P. i Q i ;

[0095] Output power P i Q i The calculation is as follows:

[0096]

[0097] In the formula, V d V represents the d-axis component of the inverter's output voltage in the dq coordinate system. q Let I be the q-axis component of the inverter's output voltage in the dq coordinate system. d Let I be the d-axis component of the inverter's output current in the dq coordinate system. q Let q be the q-axis component of the inverter's output current in the dq coordinate system.

[0098] Step 2) Control algorithm via VSG:

[0099]

[0100] J i D is the virtual rotational inertia of the i-th VSG; i It is the virtual damping coefficient of the i-th VSG; and P i ω represents the active power reference value and the actual output active power of the i-th VSG, respectively; i ω j and ω ref These are the actual operating frequency and rated frequency values ​​of the i-th and j-th VSGs; D k For frequency-mutated damping, δ is the phase difference between the common coupling point voltage vpcc and the grid voltage vg, and is defined as the power angle.

[0101] E = K(Q) ref -Q)+E ref

[0102] Where E is the voltage amplitude reference value of the voltage-current dual closed loop; E ref It is the rated voltage amplitude; K is the reactive power-voltage droop coefficient; Q ref Q and Q represent the reactive power reference value and the actual reactive power output of VSG, respectively.

[0103] It is particularly noteworthy that J here i With D i This is given by the intelligent agent mentioned earlier.

[0104] Step 3) The reference voltage amplitude and frequency obtained in the previous step are combined into an output reference voltage, which is then passed through a voltage and current double closed loop. The inverter is controlled by the pulse width modulation (PWM) unit using the modulation signal.

[0105] This embodiment proposes a data-driven adaptive online learning and adjustment method for multiple VSG inertia and damping. This method can overcome the reliability and security problems caused by the high dependence of centralized reinforcement learning on communication, and solve the drawback of traditional adaptive VSG control that cannot take into account both frequency deviation and frequency change rate. It takes into account both frequency deviation and frequency change rate while ensuring the transient stability of VSG, and realizes the comprehensive optimization of VSG transient performance.

[0106] To implement the method of the embodiments of the present invention, the embodiments of the present invention also provide a data-driven multi-VSG inertia and damping adaptive adjustment system, including: a processor and a memory for storing a computer program that can run on the processor; wherein, when the processor runs the computer program, it executes the steps of the method described above.

[0107] The system provided in this embodiment and the method embodiment described above belong to the same concept. For details of its implementation process, please refer to the method embodiment, which will not be repeated here.

[0108] To implement the method of the embodiments of the present invention, the present invention also provides a computer program product, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps of the above-described method.

[0109] Based on the hardware implementation of the above-described program modules, and in order to implement the method of this embodiment of the invention, this embodiment also provides an electronic device (computer device). Specifically, in one embodiment, the computer device may be a terminal, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor A01, a network interface A02, a display screen A04, an input device A05, and a memory (not shown) connected via a system bus. The processor A01 provides computing and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A06. The non-volatile storage medium A06 stores an operating system B01 and a computer program B02. The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 stored in the non-volatile storage medium A06. The network interface A02 is used for communication with external terminals via a network connection. When the computer program is executed by the processor A01, it implements the method of any of the above embodiments. The display screen A04 can be a liquid crystal display or an electronic ink display. The input device A05 can be a touch layer covering the display screen, a button, trackball, or touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0110] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0111] The device provided in the embodiments of the present invention includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements the method of any of the above embodiments.

[0112] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0113] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0114] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0115] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0116] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0117] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0118] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0119] It is understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or both. Specifically, non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memories described in the embodiments of this invention are intended to include, but are not limited to, these and any other suitable types of memories.

[0120] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0121] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A data-driven adaptive adjustment method for the inertia and damping of multiple VSGs, characterized in that, The method includes: For each VSG node in a multi-VSG grid-connected system, an agent is used to obtain the optimal moment of inertia and optimal damping coefficient of each VSG node at the current moment. The agent selects an action quantity based on the current state quantity at each time step and evaluates the effect of the action quantity through a reward function for feedback. Through multiple iterations of feedback, the moment of inertia and damping coefficient of each VSG node are automatically adjusted. The state quantity characterizes the operating state of the multi-VSG grid-connected system; the action quantity characterizes the control action taken by the multi-VSG grid-connected system at each time step; and the reward function is used to evaluate the performance of the multi-VSG grid-connected system. The inverter is controlled by the VSG control algorithm based on the optimal moment of inertia and the optimal damping coefficient. The calculation expression for the reward function is as follows: in, This indicates the penalty for VSG related to frequency deviation. This represents the penalty term for the VSG related to the rate of frequency change. This represents the penalty term for frequency deviation between neighboring VSGs. Represents the reward function, , , , , All are penalty coefficients. Indicates the first The frequency deviation of each VSG Indicates the first The rate of change of the frequency of each VSG Indicates the first The frequency of each VSG, Indicates the first The frequency of the VSG, Ω is the frequency of the VSG. A set consisting of adjacent VSG nodes of a VSG node; Based on the optimal moment of inertia and the optimal damping coefficient, the voltage amplitude reference value and frequency are obtained through the VSG control algorithm, including: in, It is the first Virtual rotational inertia of each VSG node; It is the first Virtual damping coefficients of VSG nodes; and Representing the first The active power reference value and actual output active power of each VSG node; For the first The actual operating frequency of each VSG node For the first The actual operating frequency of each VSG node This is the rated frequency value; For frequency-modulated mutual damping, δ is the phase difference between the common coupling point voltage and the grid voltage, and is defined as the power angle; It is the voltage amplitude reference value of the voltage and current dual closed loop; It is the rated voltage amplitude; It is the reactive power-voltage droop coefficient; and These are the reactive power reference value and the actual reactive power output of the VSG, respectively. The derivative of the VSG output frequency.

2. The data-driven adaptive adjustment method for multi-VSG inertia and damping according to claim 1, characterized in that, The state variables are the angular frequency and angular frequency change rate of the current VSG node and its neighboring VSG nodes. The calculation expression for the state variables is as follows: in, Represents state variables. This represents the frequency of the i-th VSG. This represents the rate of change of the frequency of the i-th VSG. This represents the frequency of the j-th VSG. Let Ω represent the frequency change rate of the j-th VSG, and let Ω be the set of adjacent VSG nodes of the i-th VSG node.

3. The data-driven adaptive adjustment method for multi-VSG inertia and damping according to claim 1, characterized in that, The motion quantity refers to the moment of inertia and damping coefficient of this VSG node, and the calculation expression for the motion quantity is as follows: in, Indicates the amount of action. This represents the moment of inertia of the i-th VSG node. This represents the damping coefficient of the i-th VSG node.

4. The data-driven adaptive adjustment method for multi-VSG inertia and damping according to claim 1, characterized in that, Based on the optimal moment of inertia and the optimal damping coefficient, the inverter is controlled using the VSG control algorithm, including: Measure the output current and output voltage of the inverter, and calculate the output power based on the output current and output voltage; Based on the optimal moment of inertia and the optimal damping coefficient, the voltage amplitude reference value and frequency are obtained through the VSG control algorithm; Based on the voltage amplitude reference value and the frequency, an output reference voltage is synthesized; after the output reference voltage passes through a voltage and current dual closed loop, the inverter is controlled by a pulse width modulation unit using a modulation signal.

5. The data-driven adaptive adjustment method for multi-VSG inertia and damping according to claim 4, characterized in that, Calculating the output power based on the output current and the output voltage includes: in, P i Let i be the output active power of the i-th VSG. Q i Let i be the output reactive power of the i-th VSG. Let d be the d-axis component of the inverter's output voltage in the dq coordinate system. Let q be the q-axis component of the inverter's output voltage in the dq coordinate system. Let d be the d-axis component of the inverter's output current in the dq coordinate system. Let q be the q-axis component of the inverter's output current in the dq coordinate system.

6. A data-driven multi-VSG inertia and damping adaptive adjustment system, characterized in that, include: A processor and a memory for storing a computer program capable of running on the processor; wherein, when the processor is used to run the computer program, it performs the steps of the method according to any one of claims 1 to 5.

7. A storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images