Flexible DC transmission fault ride-through control methods, devices, equipment, and storage media
By acquiring the operating parameters of the flexible DC transmission system in real time and generating control commands using a strategy network, the problem of the flexible DC transmission system being unable to adaptively adjust the converter reference signal under fault conditions is solved. This achieves effective suppression of power supply overcurrent and DC bus overvoltage, and improves the system's fault ride-through capability and control efficiency.
Patent Information
- Application Number
- CN202611034422.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-07-13
- Publication Date
- 2026-11-17
AI Technical Summary
Existing flexible DC transmission systems cannot adaptively adjust the converter reference signal under fault conditions, making it difficult to simultaneously suppress power supply overcurrent and DC bus overvoltage. Traditional methods show significant deterioration in control performance under non-design conditions, and hardware protection circuits lose controllability.
By acquiring the operating parameters of the flexible DC transmission system in real time, forward computation is performed using a trained strategy network to generate control commands to regulate the generator-side and grid-side converters. The network parameters are optimized by combining an enhanced stochastic search algorithm, and a piecewise weighted penalty objective function is designed to coordinate the suppression of rotor overcurrent and DC bus overvoltage.
It achieves adaptive adjustment of the converter reference signal without changing the system hardware structure, effectively balancing the suppression of power supply overcurrent and DC bus overvoltage, and improving the system's fault ride-through capability and control efficiency.
Smart Images

Figure CN123121774A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of power systems, and includes, but is not limited to, a flexible DC transmission fault ride-through control method, apparatus, equipment, and storage medium. Background Technology
[0002] With the rapid development of large-scale offshore wind farms and onshore wind power bases, flexible direct current transmission (VSC-HVDC) technology based on voltage source converters has become an important solution for long-distance, large-capacity wind power transmission. In such systems, when a fault occurs in the DC transmission line or the receiving-end AC grid, the fault effect is transmitted to the sending-end power supply side through DC voltage changes and power imbalances. This leads to problems such as sudden voltage drops, rotor overcurrent, and DC bus overvoltage on the power supply side, which can trigger generator protection actions on the power supply side, resulting in large-scale grid disconnection. Therefore, there is an urgent need for a fault ride-through intelligent control method that can simultaneously address power supply overcurrent and DC bus overvoltage suppression. Summary of the Invention
[0003] In view of this, the flexible DC transmission fault ride-through control method, apparatus, equipment, and storage medium provided in the embodiments of this application can realize intelligent fault ride-through control that takes into account both power supply overcurrent and DC bus overvoltage suppression.
[0004] The flexible DC transmission fault ride-through control method, apparatus, equipment, and storage medium provided in this application are implemented as follows: One aspect of this application provides a flexible DC transmission fault ride-through control method for controlling a flexible DC transmission system. The flexible DC transmission system includes a wind turbine, a generator-side converter, a generator-side DC bus, a grid-side converter, an AC collecting bus, a sending-end converter station, a DC transmission line, a receiving-end converter station, and a receiving-end AC grid. The method includes: The set of operating parameters of the flexible DC transmission system is acquired in real time, including the grid connection point voltage amplitude collected at the connection point between the AC side of the sending-end converter station and the AC collecting bus. When the voltage amplitude at the grid connection point is less than the first amplitude threshold, an observation vector characterizing the working state of the power supply side of the flexible DC transmission system is determined based on the set of operating parameters. The trained policy network performs forward computation based on the observation vector to obtain an instruction vector including at least one control instruction. The machine-side converter and the grid-side converter are controlled according to the command vector.
[0005] In one possible implementation, the method further includes: If the duration for which the voltage amplitude at the grid connection point is greater than the second amplitude threshold is greater than the time threshold, control of the generator-side converter and grid-side converter of the flexible DC transmission system shall be stopped.
[0006] In one possible implementation, the set of operating parameters further includes the d-axis and q-axis components of the wind turbine rotor current, the mechanical angular velocity of the wind turbine rotor, the voltage of the DC bus on the turbine side, and the active and reactive power calculated from the voltage and current at the stator outlet of the wind turbine.
[0007] In one possible implementation, the control commands in the command vector include the active power command of the outer loop of the machine-side converter, the reactive power command of the outer loop of the machine-side converter, and the DC bus voltage command of the outer loop of the grid-side converter.
[0008] In one possible implementation, the method further includes: A dynamic mathematical model of the power supply side of the flexible DC transmission system is established, and the dynamic data model is written into the simulator corresponding to the flexible DC transmission system to obtain the model of the flexible DC transmission system. The power supply side of the flexible DC transmission system includes the wind turbine, the generator-side converter, the grid-side converter, and the generator-side DC bus. The flexible DC transmission system model was run multiple times and simulation parameters were collected in real time to obtain a sample parameter set. An enhanced random search is performed on the policy network based on the sample parameter set to update the parameters of the policy network; If the preset convergence conditions are met, the parameter update of the policy network is stopped, and the training of the policy network is completed.
[0009] In one possible implementation, the step of performing an enhanced random search on the policy network based on the sample parameter set to update the parameters of the policy network includes: By sampling N perturbation directions using a normal distribution, and by adding and subtracting the parameters of the policy network based on each perturbation direction, 2N sets of parameters for the policy network are obtained. The sample parameter set is input into each of the policy networks with different parameters to obtain the corresponding observation vector; The flexible DC transmission system model is controlled to operate based on the observation vectors described above, and the corresponding weighted penalty objective function value is determined based on the operation results. The maximum preset value of the two weighted penalty objective functions is determined based on the parameters of the policy network.
[0010] In one possible implementation, the weighted penalty objective function includes a rotor current penalty term and a DC bus voltage penalty term; The rotor current penalty term is ,in, This refers to the rotor current amplitude. The preset rotor rated current amplitude, and The default negative penalty coefficient is set, and ; The DC bus penalty item is: ,in, The rated voltage of the DC bus on the machine side. and The default negative penalty coefficient is set, and .
[0011] Another aspect of this application embodiment provides a flexible DC transmission fault ride-through control device for controlling a flexible DC transmission system. The flexible DC transmission system includes a wind turbine, a generator-side converter, a generator-side DC bus, a grid-side converter, an AC collecting bus, a sending-end converter station, a DC transmission line, a receiving-end converter station, and a receiving-end AC grid. The device includes: The parameter acquisition module is used to acquire the set of operating parameters of the flexible DC transmission system in real time. The set of operating parameters includes the grid connection point voltage amplitude collected at the connection point between the AC side of the sending-end converter station and the AC collecting bus. The vector determination module is used to determine, based on the set of operating parameters, an observation vector characterizing the operating state of the power supply side of the flexible DC transmission system when the voltage amplitude at the grid connection point is less than a first amplitude threshold. The control instruction reasoning module is used to perform forward computation based on the observation vector through the trained policy network to obtain an instruction vector including at least one control instruction. A converter control module is used to control the machine-side converter and the grid-side converter according to the command vector.
[0012] In one possible implementation, the device further includes: The stop control module is used to stop controlling the generator-side converter and grid-side converter of the flexible DC transmission system when the duration of the voltage amplitude at the grid connection point being greater than the second amplitude threshold is greater than the time threshold.
[0013] In one possible implementation, the set of operating parameters further includes the d-axis and q-axis components of the wind turbine rotor current, the mechanical angular velocity of the wind turbine rotor, the voltage of the DC bus on the turbine side, and the active and reactive power calculated from the voltage and current at the stator outlet of the wind turbine.
[0014] In one possible implementation, the control commands in the command vector include the active power command of the outer loop of the machine-side converter, the reactive power command of the outer loop of the machine-side converter, and the DC bus voltage command of the outer loop of the grid-side converter.
[0015] In one possible implementation, the device further includes: The model building module is used to establish a dynamic mathematical model of the power supply side of the flexible DC transmission system and write the dynamic data model into the simulator corresponding to the flexible DC transmission system to obtain a model of the flexible DC transmission system. The power supply side of the flexible DC transmission system includes the wind turbine, the generator-side converter, the grid-side converter, and the generator-side DC bus. The training set acquisition module is used to run the flexible DC transmission system model multiple times and collect simulation parameters in real time to obtain a sample parameter set. The parameter update module is used to perform an enhanced random search on the policy network based on the sample parameter set in order to update the parameters of the policy network. The network determination module is used to stop updating the parameters of the policy network and complete the training of the policy network when a preset convergence condition is met.
[0016] In one possible implementation, the step of performing an enhanced random search on the policy network based on the sample parameter set to update the parameters of the policy network includes: By sampling N perturbation directions using a normal distribution, and by adding and subtracting the parameters of the policy network based on each perturbation direction, 2N sets of parameters for the policy network are obtained. The sample parameter set is input into each of the policy networks with different parameters to obtain the corresponding observation vector; The flexible DC transmission system model is controlled to operate based on the observation vectors described above, and the corresponding weighted penalty objective function value is determined based on the operation results. The maximum preset value of the two weighted penalty objective functions is determined based on the parameters of the policy network.
[0017] In one possible implementation, the weighted penalty objective function includes a rotor current penalty term and a DC bus voltage penalty term; The rotor current penalty term is ,in, This refers to the rotor current amplitude. The preset rotor rated current amplitude, and The default negative penalty coefficient is set, and ; The DC bus penalty item is: ,in, The rated voltage of the DC bus on the machine side. and The default negative penalty coefficient is set, and .
[0018] The electronic device provided in this application includes a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the program, it implements the method described in this application.
[0019] The computer-readable storage medium provided in this application embodiment stores a computer program thereon, which, when executed by a processor, implements the method provided in this application embodiment.
[0020] The flexible DC transmission fault ride-through control method, apparatus, equipment, and storage medium provided in this application, in response to receiving user input information from a target user, parses the user input information to determine at least one user intent. Based on the at least one user intent, it determines at least one user-required service and the corresponding standard processing procedure for each user-required service. User-required services whose user information for the target user meets the corresponding preconditions are identified as target-required services. Based on the standard processing procedure and corresponding atomic capability set for each target-required service, a combined service processing procedure for the target user is generated. This application can automatically and accurately parse user intent from user input information to intelligently obtain at least one user-required service and automatically generate flexible combined service processing procedures based on atomic capabilities, improving the efficiency of generating combined services and the quality of automatically generated results. Attached Figure Description
[0021] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0022] Figure 1 A flowchart is shown for a flexible DC transmission fault ride-through control method according to an embodiment of this application; Figure 2 A schematic diagram of a flexible DC transmission fault ride-through control system according to an embodiment of this application is shown; Figure 3 A schematic diagram of a flexible DC transmission fault ride-through control device according to an embodiment of this application is shown; Figure 4A schematic diagram of an electronic device according to an embodiment of this application is shown. Detailed Implementation
[0023] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the specific technical solutions of this application will be further described in detail below with reference to the accompanying drawings of the embodiments of this application. The following embodiments are used to illustrate this application, but are not intended to limit the scope of this application.
[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.
[0025] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.
[0026] It should be noted that the terms "first, second, third" used in the embodiments of this application are used to distinguish similar or different objects and do not represent a specific order of objects. It can be understood that "first, second, third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.
[0027] The flexible DC transmission fault ride-through control method of this application embodiment can be executed by any electronic device. Specifically, it can acquire the set of operating parameters of the flexible DC transmission system through an electronic device, determine whether a fault has occurred in the system based on the set of operating parameters, and generate corresponding control commands for regulation in the event of a fault. This electronic device may include, but is not limited to, mobile phones, wearable devices (such as smartwatches, smart bracelets, smart glasses, etc.), tablet computers, laptops, vehicle terminals, PCs (Personal Computers), etc. The functions implemented by this method can be achieved by a processor in the electronic device calling program code. Of course, the program code can be stored in a computer storage medium. Therefore, the electronic device includes at least a processor and a storage medium.
[0028] The flexible DC transmission fault ride-through control method of this application can be used in any application scenario that requires flexible DC transmission fault identification and fault ride-through control, such as large-scale new energy grid connection and transmission scenarios such as offshore wind power transmission and onshore new energy base transmission.
[0029] Existing technologies address faults in flexible DC transmission systems primarily at two levels. At the system level, existing research has proposed achieving system-level power balance and voltage regulation through methods such as configuring energy-consuming devices at the sending-end converter station and adjusting the converter station's power reference value. However, system-level control strategies only adjust macroscopic operating parameters at the converter station side, lacking direct control over the microscopic operating states of individual converters within the flexible DC transmission system. At the power supply side of the flexible DC transmission system, traditional fault ride-through schemes mainly rely on preset fixed reference values or simple limiting protection logic. When the voltage drop at the power supply side exceeds the preset range, the active power reference value is directly stepped down to a fixed value, or hardware protection circuits (such as crowbar circuits) are used to short-circuit the rotor to limit overcurrent.
[0030] Therefore, the relevant technologies for dealing with faults in flexible DC transmission systems have the following limitations: First, fixed reference values cannot be adaptively adjusted according to different fault severity and power supply operating conditions, and the control effect deteriorates significantly under non-design conditions; Second, the system converter loses controllability during the operation of hardware protection circuits and cannot provide grid support capabilities; Third, traditional methods cannot simultaneously take into account the two mutually coupled control objectives of power supply overcurrent suppression and DC bus overvoltage suppression.
[0031] Therefore, there is an urgent need for a fault ride-through intelligent control method that can adaptively adjust the converter reference signal according to the real-time operating status of the flexible DC transmission system without changing the converter hardware structure, while also taking into account power supply overcurrent and DC bus overvoltage suppression.
[0032] The following describes in detail the flexible DC transmission fault ride-through control scheme of this application embodiment with reference to the accompanying drawings.
[0033] Figure 1 A flowchart illustrating a flexible DC transmission fault ride-through control method according to an embodiment of this application is shown. Figure 1 As shown, the flexible DC transmission fault ride-through control method of this application embodiment may include the following steps S10-S40.
[0034] Optionally, the method in this application embodiment is used to control a flexible DC transmission system, which includes a wind turbine, a generator-side converter, a generator-side DC bus, a grid-side converter, an AC collecting bus, a sending-end converter station, a DC transmission line, a receiving-end converter station, and a receiving-end AC grid.
[0035] For ease of description, the flexible DC transmission fault ride-through control method of this application embodiment is described using an electronic device as the execution subject. It should be understood that the execution subject of this application embodiment can also be a processor or chip in an electronic device, and this application embodiment does not impose any limitations.
[0036] Step S10: Obtain the set of operating parameters of the flexible DC transmission system in real time.
[0037] In one possible implementation, at least one operating parameter of the flexible DC transmission system is acquired in real time via electronic devices to obtain a set of operating parameters for the flexible DC transmission system. This process may involve acquiring the set of operating parameters multiple times at a preset time period, where at least one operating parameter in the set represents a corresponding attribute of the flexible DC transmission system. Each operating parameter can be acquired using sensing devices installed within the flexible DC transmission system.
[0038] Optionally, the set of operating parameters in this application embodiment may include the grid connection point voltage amplitude collected at the connection point between the AC side of the sending-end converter station and the AC collecting bus, as well as the d-axis component of the wind turbine rotor current. and q-axis components Mechanical angular velocity of wind turbine rotor Voltage of the DC bus on the machine side The active power calculated from the voltage and current at the stator outlet of the wind turbine generator. and reactive power Furthermore, this set of operating parameters may also include other operating parameters that can characterize at least one component property of the flexible DC transmission system.
[0039] In some embodiments, the d-axis and q-axis components of the motor rotor current can be obtained by sensors installed on the wind turbine rotor windings to reflect the real-time current state of the generator rotor. The mechanical angular velocity of the wind turbine rotor can be obtained by sensors installed on the wind turbine main shaft to reflect the rotational speed of the generator after the wind turbine captures wind energy. The voltage of the generator-side DC bus can be obtained by sensors installed on the DC bus capacitor between the generator-side converter and the grid-side converter. The active and reactive power calculated from the voltage and current at the stator outlet of the wind turbine generator are derived from the voltage and current at the stator outlet of the power source generator, directly reflecting the power delivered by the generator set to the collection system. The grid connection point voltage amplitude is acquired by sensors installed at the connection point between the AC side of the sending-end converter station and the AC collection bus. Although the acquisition location is close to the converter station, it is still topologically part of the rectifier side of the DC transmission line.
[0040] Step S20: When the voltage amplitude at the grid connection point is less than the first amplitude threshold, determine the observation vector characterizing the working state of the power supply side of the flexible DC transmission system based on the set of operating parameters.
[0041] In one possible implementation, the electronic equipment can determine whether a fault has occurred in the current flexible DC transmission system based on the grid connection point voltage amplitude after each acquisition of the operating parameter set. For example, the electronic equipment can pre-set a first amplitude threshold, and determine that a fault has occurred in the current flexible DC transmission system if the grid connection point voltage amplitude is less than the first amplitude threshold, requiring control of both the generator-side converter and the grid-side converter.
[0042] Optionally, the first amplitude threshold can be the product of the rated voltage amplitude at the grid connection point and a preset voltage drop trigger factor, meaning the electronic device can withstand voltage drops at the grid connection point. satisfy At that time, it was determined that a fault had occurred in the current flexible DC transmission system, and the current moment was further determined. To address the fault control startup time of both the generator-side converter and the grid-side converter, among which, The rated voltage amplitude at the grid connection point. This is the preset voltage drop start-up coefficient.
[0043] In some embodiments, when a fault is determined in the current flexible DC transmission system, the electronic device can determine an observation vector characterizing the operating state of the power source side of the flexible DC transmission system based on a set of operating parameters, and then determine a control strategy based on this observation vector. For example, the electronic device can directly determine the observation vector based on the set of operating parameters. ,in, and These are the rotor currents. Axial components and Axial components, The mechanical angular velocity of the generator rotor. This refers to the DC bus voltage on the machine side. and These represent the active power and reactive power output by the DC transmission system, respectively. This refers to the voltage amplitude at the AC side grid connection point.
[0044] Furthermore, in this embodiment, after determining the observation vector, the observation vector can be normalized to obtain an optimized observation vector. ,in, This represents the initial observation vector for the flexible DC transmission system. The mean of the observed vector components. This represents the running standard deviation of each component of the observation vector.
[0045] Step S30: The trained policy network performs forward computation based on the observation vector to obtain an instruction vector including at least one control instruction.
[0046] In some embodiments, when an electronic device determines that a fault has occurred in the current flexible DC transmission system, it determines an observation vector and performs forward computation based on this observation vector using a trained policy network to obtain a command vector including at least one control command. Optionally, the control command in the command vector is used to control the generator-side converter and the grid-side converter, and may include, for example, the active power command of the generator-side converter outer loop, the reactive power command of the generator-side converter outer loop, and the DC bus voltage command of the grid-side converter outer loop.
[0047] For example, in the embodiments of this application, the instruction vector determined by the policy network based on the observation vector can be... ,in, This refers to the active power command for the outer loop of the generator-side converter. This refers to the reactive power command for the outer loop of the generator-side converter. This is the DC bus voltage command for the outer ring of the grid-side converter.
[0048] Step S40: Control the machine-side converter and the grid-side converter according to the command vector.
[0049] In one possible implementation, after determining the command vector, the electronic equipment can control both the generator-side converter and the grid-side converter according to the command vector. During the control of the flexible DC transmission system, the electronic equipment also acquires a set of operating parameters in real time and can stop the converter control when preset stop control conditions are met.
[0050] Optionally, the stop control condition in this embodiment can be that the duration for which the grid connection point voltage amplitude is greater than the second amplitude threshold is greater than a time threshold. That is, when the duration for which the grid connection point voltage amplitude is greater than the second amplitude threshold is greater than the time threshold, the control of the machine-side converter and grid-side converter of the flexible DC transmission system is stopped. The second amplitude threshold can be the product of a preset voltage recovery coefficient and the rated voltage amplitude at the grid connection point. satisfy In the case of determining For the fault control release time, in Stop fault control at any time. This is the preset voltage recovery coefficient. The rated voltage amplitude at the grid connection point. This is the time threshold. That is, in... Voltage amplitude at grid connection point at any time satisfy At the grid connection point voltage amplitude satisfy In this case, The fault ride-through control is defined as the operating time interval during which the electronic equipment controls the machine-side converter and the grid-side converter.
[0051] In some embodiments, the policy network of this application uses the observation vector of the flexible DC transmission system as input and the command vector of the converter as output. The policy network consists of multiple fully connected neuron layers, and the connection weights between neurons in each layer constitute the policy network parameters. This policy network can be trained using Augmented Random Search (ARS). This process can be assisted by a flexible DC transmission system model obtained through simulation. Optionally, a dynamic mathematical model of the power source side of the flexible DC transmission system can be established first, and the dynamic data model can be written into the simulator corresponding to the flexible DC transmission system to obtain the flexible DC transmission system model. The power source side of the flexible DC transmission system includes wind turbines, generator-side converters, grid-side converters, and generator-side DC buses. The flexible DC transmission system model is run multiple times, and simulation parameters are collected in real time to obtain a sample parameter set. Augmented random search is performed on the policy network based on the sample parameter set to update the policy network parameters. When a preset convergence condition is met, the parameter update of the policy network is stopped, and the training of the policy network is completed.
[0052] Optionally, the dynamic mathematical model of the power supply side of the flexible DC transmission system established during the simulation process of the embodiments of this application covers four components: power generator, generator-side converter, grid-side converter, and generator-side DC bus connecting the generator-side converter and the grid-side converter.
[0053] In the mathematical model, the power generator converts wind energy into electrical energy, and its mechanical output power... Wind energy capture formula The decision, among which, air density, The radius of the wind turbine blade. For the incoming wind speed, The wind energy utilization coefficient, For the tip speed ratio, It is the propeller pitch angle.
[0054] The generator-side converter controls the active and reactive power output of the power supply generator, which operates synchronously. The rotor voltage equation in the coordinate system is:
[0055]
[0056] in, and These are the rotor voltages. Axial components and Axial components, For rotor winding resistance, For rotor leakage inductance, and These are the rotor currents. Axial components and Axial components, The slip angular frequency, The synchronization angular frequency, This is the rotor electrical angular frequency. The machine-side converter adopts a dual-closed-loop vector control structure, with the outer loop being the power loop and the inner loop being the current loop.
[0057] The outer ring is based on the active power command. and reactive power command Generate rotor current respectively Axis reference value and Axis reference value The inner loop tracks the aforementioned current reference value and outputs the rotor voltage. The control objective of the grid-side converter is to maintain the DC bus voltage on the generator side. For stability, it also adopts a dual closed-loop control structure, with the outer loop controlling according to the DC bus voltage command. Generate a grid-side current reference value, and the inner loop tracks the current reference value and outputs the grid-side voltage.
[0058] The voltage dynamics of the DC bus on the machine side are given by the equation Description, in which, This is the DC bus capacitance value. This refers to the DC bus voltage on the machine side. The active power transmitted by the generator-side converter. This refers to the active power transmitted by the grid-side converter.
[0059] The output active power of the power generator set and output reactive power Calculated from stator side voltage and current:
[0060]
[0061] in, and These are the stator voltages. Axial components and Axial components, and These are the stator currents. Axial components and Axial components.
[0062] The policy network in this embodiment adopts a fully connected feedforward neural network structure, comprising a total of Layers, each layer contains One neuron. The policy network uses the observation vector of the flexible DC transmission system. For input, after Forward computation followed by instruction vector For the output, where, The parameter is The forward computation function of the policy network, This is the normalized observation vector. Observation vector of the flexible DC transmission system. Defined as The definitions of each component are as described above. This observation vector compiles key electrical quantities characterizing the converter's operating state, including the rotor current component. and DC bus voltage directly reflects overcurrent risk. Reflecting overvoltage risk, grid connection point voltage Reflects the severity of the fault, active power reactive power and mechanical angular velocity It reflects the power balance state.
[0063] Instruction vector Defined as ,in, This refers to the active power command for the outer loop of the generator-side converter, and its value range is... , This refers to the rated active power of the wind turbine generator set. This is the reactive power command for the outer loop of the generator-side converter; This refers to the DC bus voltage command for the outer loop of the grid-side converter, and its value range is... , and These are the lower and upper limits of the permissible DC bus voltage, respectively.
[0064] After determining the strategy network structure, the embodiments of this application can run a simulated flexible DC transmission system model, monitor the set of operating parameters in the simulation model in real time, and obtain the voltage amplitude at the grid connection point on the power source side. .when Fault start criterion satisfied When the system fault has been transmitted to the power supply side, record that moment. To enable fault control startup time, immediately switch to the instruction vector output by the policy network. .in The rated voltage amplitude at the grid connection point. This is the voltage sag initiation factor. When... Fault clearance criteria satisfied And this condition is If the condition remains true continuously within the interval, the fault is considered cleared, and this moment is recorded. The fault control clearance time is used to restore the machine-side converter reference signal to its normal value. The voltage recovery coefficient, This represents the minimum duration for which the voltage remains stable.
[0065] The acquisition of the aforementioned operating parameters and the regulation of the converter based on the command vector are all performed on a simulated flexible DC transmission system model. During the regulation of the converter in the simulation model, the policy network parameters are optimized using an enhanced stochastic search algorithm to train the policy network. The enhanced stochastic search algorithm is a gradient-free optimization method. Its core idea is to perform a random perturbation search in the parameter space of the policy network and estimate the parameter update direction by comparing the difference between the objective functions of forward and reverse perturbations. This algorithm has the following characteristics: First, it does not require calculating the gradient of the objective function with respect to the parameters and does not rely on the backpropagation algorithm, making it simple to implement; second, it selects the objective function with the highest value... Parameters are updated in one direction, improving search efficiency; third, the standard deviation of the objective function value is used... Normalization enhances the numerical stability of the training process.
[0066] In some embodiments of this application, the initial parameters of the policy network can be predetermined, for example, the parameters of the policy network can be initialized. Initialize the observation statistics as a zero matrix. and This application embodiment treats the fault control process of each fault in the flexible DC transmission system model as an iterative training process of the policy network. In each iteration, N disturbance directions are sampled using a normal distribution, and the parameters of the policy network are obtained by adding and subtracting based on each disturbance direction, resulting in 2N sets of policy network parameters. The sample parameter sets are input into each policy network with different parameters to obtain corresponding observation vectors. The flexible DC transmission system model is controlled according to each observation vector, and the corresponding weighted penalty objective function value is determined based on the operation results. The two largest preset weighted penalty objective function values are then used to determine the policy network parameters.
[0067] For example, in the first In this iteration, the embodiments of this application follow the standard normal distribution. Independent sampling random perturbation direction to ,in for 3D identity matrix For policy network parameters The total dimension This represents the number of sampling directions. For each perturbation direction... Construct positive parameters and inverse parameter ,in, For the perturbation step size, Integer and The 2N sets of parameters were deployed in a model of a flexible DC transmission system and simulations were run to collect the objective function values. and The observation vectors are normalized during the simulation. .in, The mean of the observed vector components. This represents the running standard deviation of each component of the observation vector. The group policy network parameters are deployed in the converter model of the flexible DC transmission system, during the fault ride-through time interval. Internal simulation, utilizing normalized observation vectors The instruction vector is computed as input to the policy network. Collect the objective function values corresponding to each set of parameters. and The weighted penalty objective function value is obtained by summing the results. The value with the highest weighted penalty objective function value is then selected. The directions constitute the preferred set. ,in Integer and Calculate the standard deviation of the weighted penalized objective function values in the preferred set. Update the strategy network parameters according to the following formula: Simultaneously update the observed mean vector. and observed standard deviation vector ,in, The learning rate is used. Since the simulations for each perturbation direction are independent, parallel computing techniques can be used to run them simultaneously. One simulation example can significantly shorten the training time.
[0068] In some embodiments, the weighted penalty objective function determined in this application includes a rotor current penalty term and a DC bus voltage penalty term, thus enabling the determination of the weighted penalty objective function. Fault travel time interval Objective function at each time step The sum of discounts ,in The discount factor. Objective function at each time step. Rotor current penalty term DC bus voltage penalty term It consists of two parts. .
[0069] Optionally, rotor current penalty term The design principle is the rotor current amplitude The closer to the rated value The smaller the penalty, the better. Apply a larger penalty factor during overcurrent to prioritize equipment safety. DC bus voltage penalty term. Following the same principle, the penalty coefficient is related to the rotor current. and Penalty factor greater than DC bus voltage and This reflects that suppressing rotor overcurrent has a higher priority than suppressing DC bus overvoltage.
[0070] Among them, the rotor current penalty term Defined as , This refers to the rotor current amplitude. This is the rated current amplitude of the rotor. and All are preset negative penalty coefficients, and DC bus voltage penalty term Defined as , This is the rated voltage of the DC bus on the machine side. and All are preset negative penalty coefficients, and .
[0071] If the policy network is trained on a local electronic device, it can be used directly after training. If the policy network is trained on another device, the measurement network can be deployed on the local electronic device. This deployment process involves transferring the trained policy network and its parameters... and observation statistics , This is integrated into the local electronics of the converter in the flexible DC transmission system. This electronics performs forward computation of the strategy network in each control cycle, with a computational load far less than traditional optimization solutions, meeting the timeliness requirements of real-time control. During normal operation, the converter uses conventional reference signals. When the fault detection module triggers the fault initiation criterion, it automatically switches to the command vector output by the strategy network. When the fault clearance criterion is met, the signal is smoothly restored to the normal reference signal.
[0072] Figure 2 A schematic diagram of a flexible DC transmission fault ride-through control system according to an embodiment of this application is shown. Figure 2As shown, the flexible DC transmission fault ride-through control system of this application embodiment may include a flexible DC transmission system and electronic equipment for controlling the flexible DC transmission system. The flexible DC transmission system includes a wind turbine, a generator-side converter, a generator-side DC bus, a grid-side converter, an AC collecting bus, a sending-end converter station, a DC transmission line, a receiving-end converter station, and a receiving-end AC grid. The electronic equipment can acquire a set of operating parameters of the flexible DC transmission system in real time. When the voltage amplitude at the grid connection point is less than a first amplitude threshold, an observation vector characterizing the operating state of the power source side of the flexible DC transmission system is determined based on the set of operating parameters. A trained policy network performs forward computation based on the observation vector to obtain a command vector including at least one control command. The generator-side converter and the grid-side converter are controlled according to the command vector. Furthermore, when the duration of the grid connection point voltage amplitude being greater than a second amplitude threshold is greater than a time threshold, the control of the generator-side converter and the grid-side converter of the flexible DC transmission system is stopped. The policy network can be trained using an enhanced random search algorithm.
[0073] In one possible implementation, this application embodiment achieves low-cost fault ride-through capability enhancement by deploying a lightweight policy network at the software level, without altering the hardware structure of the flexible DC transmission system converter or the existing dual-loop control framework. The policy network employs an Augmented Stochastic Search (ARS) algorithm during the training phase, eliminating the need to calculate complex gradients. This algorithm offers advantages such as fewer hyperparameters, faster convergence, and support for highly parallel simulation, significantly improving the optimization efficiency of control strategies in complex power system models. Regarding control performance, by designing a piecewise weighted penalty objective function, it effectively coordinates the dual suppression objectives of rotor overcurrent and DC bus overvoltage, prioritizing generator rotor equipment safety using differentiated penalty coefficients while also ensuring smooth power recovery after a fault. Furthermore, the network's forward computation is minimal during online deployment, meeting the stringent timeliness requirements of real-time control. This provides an economical, efficient, and adaptive intelligent engineering solution for new energy flexible DC transmission systems.
[0074] It should be understood that although the steps in the above flowcharts are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the above flowcharts may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.
[0075] Based on the foregoing embodiments, this application provides a flexible DC transmission fault ride-through control device. The device includes various modules and units included in each module, which can be implemented by a processor; of course, it can also be implemented by specific logic circuits. In the implementation process, the processor can be a central processing unit (CPU), microprocessor (MPU), digital signal processor (DSP), or field programmable gate array (FPGA), etc.
[0076] Figure 3 A schematic diagram of a flexible DC transmission fault ride-through control device according to an embodiment of this application is shown. Figure 3 As shown, a flexible DC transmission system is used to control a flexible DC transmission system, which includes a wind turbine, a generator-side converter, a generator-side DC bus, a grid-side converter, an AC collecting bus, a sending-end converter station, a DC transmission line, a receiving-end converter station, and a receiving-end AC grid. An embodiment of this application provides a flexible DC transmission fault ride-through control device, which includes: Parameter acquisition module 30 is used to acquire the set of operating parameters of the flexible DC transmission system in real time. The set of operating parameters includes the grid connection point voltage amplitude collected at the connection point between the AC side of the sending-end converter station and the AC collecting bus. The vector determination module 31 is used to determine, based on the set of operating parameters, an observation vector characterizing the working state of the power supply side of the flexible DC transmission system when the voltage amplitude at the grid connection point is less than a first amplitude threshold. The control instruction reasoning module 32 is used to perform forward calculation based on the observation vector through the trained policy network to obtain an instruction vector including at least one control instruction. The converter control module 33 is used to control the machine-side converter and the grid-side converter according to the command vector.
[0077] In one possible implementation, the device further includes: The stop control module is used to stop controlling the generator-side converter and grid-side converter of the flexible DC transmission system when the duration of the voltage amplitude at the grid connection point being greater than the second amplitude threshold is greater than the time threshold.
[0078] In one possible implementation, the set of operating parameters further includes the d-axis and q-axis components of the wind turbine rotor current, the mechanical angular velocity of the wind turbine rotor, the voltage of the DC bus on the turbine side, and the active and reactive power calculated from the voltage and current at the stator outlet of the wind turbine.
[0079] In one possible implementation, the control commands in the command vector include the active power command of the outer loop of the machine-side converter, the reactive power command of the outer loop of the machine-side converter, and the DC bus voltage command of the outer loop of the grid-side converter.
[0080] In one possible implementation, the device further includes: The model building module is used to establish a dynamic mathematical model of the power supply side of the flexible DC transmission system and write the dynamic data model into the simulator corresponding to the flexible DC transmission system to obtain a model of the flexible DC transmission system. The power supply side of the flexible DC transmission system includes the wind turbine, the generator-side converter, the grid-side converter, and the generator-side DC bus. The training set acquisition module is used to run the flexible DC transmission system model multiple times and collect simulation parameters in real time to obtain a sample parameter set. The parameter update module is used to perform an enhanced random search on the policy network based on the sample parameter set in order to update the parameters of the policy network. The network determination module is used to stop updating the parameters of the policy network and complete the training of the policy network when a preset convergence condition is met.
[0081] In one possible implementation, the step of performing an enhanced random search on the policy network based on the sample parameter set to update the parameters of the policy network includes: By sampling N perturbation directions using a normal distribution, and by adding and subtracting the parameters of the policy network based on each perturbation direction, 2N sets of parameters for the policy network are obtained. The sample parameter set is input into each of the policy networks with different parameters to obtain the corresponding observation vector; The flexible DC transmission system model is controlled to operate based on the observation vectors described above, and the corresponding weighted penalty objective function value is determined based on the operation results. The maximum preset value of the two weighted penalty objective functions is determined based on the parameters of the policy network.
[0082] In one possible implementation, the weighted penalty objective function includes a rotor current penalty term and a DC bus voltage penalty term; The rotor current penalty term is ,in, This refers to the rotor current amplitude. The preset rotor rated current amplitude, and The default negative penalty coefficient is set, and ; The DC bus penalty item is: ,in, The rated voltage of the DC bus on the machine side. and The default negative penalty coefficient is set, and .
[0083] The descriptions of the above device embodiments are similar to those of the above method embodiments, and have similar beneficial effects. For technical details not disclosed in the device embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.
[0084] It should be noted that, in the embodiments of this application... Figure 3 The module division of the flexible DC transmission fault ride-through control device shown is illustrative and represents only one logical functional division; in actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of this application can be integrated into a single processing unit, exist as separate physical units, or be integrated into a single unit with two or more units. The integrated units can be implemented in hardware, as software functional units, or a combination of both.
[0085] It should be noted that, in the embodiments of this application, if the above-described methods are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks. Thus, the embodiments of this application are not limited to any specific hardware and software combination.
[0086] Figure 4 A schematic diagram of an electronic device according to an embodiment of this application is shown. For example... Figure 4 As shown in the figure, this application provides an electronic device, which can be a server, and its internal structure diagram can be as follows. Figure 4As shown, the electronic device includes a processor 420, a memory, and a transceiver 440 connected via a system bus 410. The processor 420 provides computing and control capabilities. The memory includes a non-volatile storage medium 431 and internal memory 432. The non-volatile storage medium 431 stores an operating system, computer programs, and a database. The internal memory 432 provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium 431. The database stores data. The transceiver 440 communicates with external terminals via a network connection. The computer program is executed by the processor 420 to implement the aforementioned methods.
[0087] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor 420, implements the steps of the method provided in the above embodiments.
[0088] This application provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the steps in the method provided in the above-described method embodiments.
[0089] Those skilled in the art will understand that Figure 4 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 electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.
[0090] In one possible implementation, the apparatus provided in this application can be implemented as a computer program, which can be configured as follows: Figure 4 The device operates on the electronic device shown. The memory of the electronic device can store the various program modules that make up the above-described apparatus. The computer program composed of the various program modules causes the processor 420 to execute the steps of the methods in the various embodiments of this application described in this specification.
[0091] It should be noted that the descriptions of the storage medium and device embodiments above are similar to the descriptions of the method embodiments above, and have similar beneficial effects. For technical details not disclosed in the storage medium, storage medium, and device embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.
[0092] It should be understood that the phrases "one embodiment," "an embodiment," or "some embodiments" mentioned throughout the specification mean that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of this application. Therefore, phrases such as "in one possible implementation," "in one embodiment," or "in some embodiments" appearing throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this application, the sequence numbers of the above-described processes do not imply a sequential order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. The sequence numbers of the above-described embodiments are merely for descriptive purposes and do not represent the superiority or inferiority of the embodiments. The descriptions of the various embodiments above tend to emphasize the differences between the various embodiments; their similarities or commonalities can be referred to mutually, and for the sake of brevity, they will not be repeated here.
[0093] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three kinds of relationships. For example, object A and / or object B can represent three situations: object A exists alone, object A and object B exist simultaneously, and object B exists alone.
[0094] It should be noted that, in this document, 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 a 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.
[0095] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple modules or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or modules can be electrical, mechanical, or other forms.
[0096] The modules described above as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules. They may be located in one place or distributed across multiple network units. Some or all of the modules may be selected to achieve the purpose of this embodiment according to actual needs.
[0097] In addition, each functional module in the various embodiments of this application can be integrated into one processing unit, or each module can be a separate unit, or two or more modules can be integrated into one unit; the integrated modules can be implemented in hardware or in the form of hardware plus software functional units.
[0098] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.
[0099] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROMs, magnetic disks, or optical disks.
[0100] The methods disclosed in the several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.
[0101] The features disclosed in the several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.
[0102] The features disclosed in the several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method or device embodiments.
[0103] The above description is merely an embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.
Claims
1. A flexible DC transmission fault ride-through control method, characterized in that, For controlling a flexible DC transmission system, the flexible DC transmission system including a wind turbine, a machine-side converter, a machine-side DC bus, a grid-side converter, an AC collecting bus, a sending-end converter station, a DC transmission line, a receiving-end converter station, and a receiving-end AC grid, the method includes: The set of operating parameters of the flexible DC transmission system is acquired in real time, including the grid connection point voltage amplitude collected at the connection point between the AC side of the sending-end converter station and the AC collecting bus. When the voltage amplitude at the grid connection point is less than the first amplitude threshold, an observation vector characterizing the working state of the power supply side of the flexible DC transmission system is determined based on the set of operating parameters. The trained policy network performs forward computation based on the observation vector to obtain an instruction vector including at least one control instruction. The machine-side converter and the grid-side converter are controlled according to the command vector.
2. The method according to claim 1, characterized in that, The method further includes: If the duration for which the voltage amplitude at the grid connection point is greater than the second amplitude threshold is greater than the time threshold, control of the generator-side converter and grid-side converter of the flexible DC transmission system shall be stopped.
3. The method according to claim 1, characterized in that, The set of operating parameters also includes the d-axis and q-axis components of the wind turbine rotor current, the mechanical angular velocity of the wind turbine rotor, the voltage of the DC bus on the turbine side, and the active and reactive power calculated from the voltage and current at the stator outlet of the wind turbine.
4. The method according to claim 1, characterized in that, The control commands in the command vector include the active power command of the outer loop of the machine-side converter, the reactive power command of the outer loop of the machine-side converter, and the DC bus voltage command of the outer loop of the grid-side converter.
5. The method according to claim 1, characterized in that, The method further includes: A dynamic mathematical model of the power supply side of the flexible DC transmission system is established, and the dynamic data model is written into the simulator corresponding to the flexible DC transmission system to obtain the model of the flexible DC transmission system. The power supply side of the flexible DC transmission system includes the wind turbine, the generator-side converter, the grid-side converter, and the generator-side DC bus. The flexible DC transmission system model was run multiple times and simulation parameters were collected in real time to obtain a sample parameter set. An enhanced random search is performed on the policy network based on the sample parameter set to update the parameters of the policy network; If the preset convergence conditions are met, the parameter update of the policy network is stopped, and the training of the policy network is completed.
6. The method according to claim 5, characterized in that, The step of performing an enhanced random search on the policy network based on the sample parameter set to update the parameters of the policy network includes: By sampling N perturbation directions using a normal distribution, and by adding and subtracting the parameters of the policy network based on each perturbation direction, 2N sets of parameters for the policy network are obtained. The sample parameter set is input into each of the policy networks with different parameters to obtain the corresponding observation vector; The flexible DC transmission system model is controlled to operate based on the observation vectors described above, and the corresponding weighted penalty objective function value is determined based on the operation results. The maximum preset value of the two weighted penalty objective functions is determined based on the parameters of the policy network.
7. The method according to claim 6, characterized in that, The weighted penalty objective function includes a rotor current penalty term and a DC bus voltage penalty term; The rotor current penalty term is ,in, This refers to the rotor current amplitude. The preset rotor rated current amplitude, and The default negative penalty coefficient is set, and ; The DC bus penalty item is: ,in, The rated voltage of the DC bus on the machine side. and The default negative penalty coefficient is set, and .
8. A flexible DC transmission fault ride-through control device, characterized in that, For controlling a flexible DC transmission system, the flexible DC transmission system including a wind turbine, a machine-side converter, a machine-side DC bus, a grid-side converter, an AC collecting bus, a sending-end converter station, a DC transmission line, a receiving-end converter station, and a receiving-end AC grid, the device includes: The parameter acquisition module is used to acquire the set of operating parameters of the flexible DC transmission system in real time. The set of operating parameters includes the grid connection point voltage amplitude collected at the connection point between the AC side of the sending-end converter station and the AC collecting bus. The vector determination module is used to determine, based on the set of operating parameters, an observation vector characterizing the operating state of the power supply side of the flexible DC transmission system when the voltage amplitude at the grid connection point is less than a first amplitude threshold. The control instruction reasoning module is used to perform forward computation based on the observation vector through the trained policy network to obtain an instruction vector including at least one control instruction. A converter control module is used to control the machine-side converter and the grid-side converter according to the command vector.
9. An electronic device comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.
