107 results about "Voltage instability" patented technology

The invention relates to the technical field of micro-grids, and discloses a micro-grid real-time load balancing scheduling method and system based on deep reinforcement learning, and the system comprises a multi-source sensing module, an intelligent decision module, a safety protection module, an execution control module, a digital twin module and an energy efficiency evaluation module. When real-time load balancing scheduling of the micro-grid is carried out, a multi-time-scale scheduling strategy is generated in real time by dynamically coordinating economical efficiency, environmental protection and power supply reliability targets through a deep reinforcement learning agent, so that the problems of high operation cost, standard exceeding of carbon emission and voltage instability caused by a single optimization target in a traditional method are further solved, and the real-time load balancing scheduling of the micro-grid is realized. According to the method, the multi-dimensional collaborative optimization of the micro-grid in a complex operation environment is ensured, and meanwhile, a cloud global optimization module generates a long-cycle strategy, so that the problems of response delay and insufficient expandability of a centralized control architecture are further solved, and the real-time power balance capability in a high-permeability renewable energy source scene is improved.

The invention discloses a reactive voltage bimodal control method and system suitable for a new energy power station, and belongs to the technical field of power system voltage control. The invention provides a dual-stage control optimization mechanism based on cooperation of a distributed phase modifier and a static var compensator in order to solve the problems of difficult steady-state voltage regulation and transient voltage instability of a new energy power station caused by wind-light output fluctuation and system short-circuit capacity reduction. According to the method, in steady-state operation, minimization of grid-connected point voltage deviation and maximization of dynamic reserve capacity of a phase modifier are taken as targets, reactive power output of two types of equipment is optimally distributed, and a proper amount of dynamic margin is reserved to support transient requirements; when it is detected that the voltage sag exceeds a safety threshold value, a transient response mode is immediately switched to, that is, phase modifier strong excitation control is activated, and reactive power output, reduced due to low-voltage limitation, of the static reactive power compensator is compensated; and when the voltage enters a recovery stage, triggering the phase modifier to reduce the output in advance through a pre-action instruction, and delaying to recover the steady state mode after the switching of the static var compensator is completed. A double safety protection mechanism is embedded in the whole control process, whether the grid-connected point voltage is in a safety interval or not is verified in real time, and the minimum operation interval of the switching equipment is forced to be executed. Simulation results show that the method can remarkably improve the voltage operation index of the new energy power station, the steady-state voltage fluctuation amplitude is greatly reduced, the transient fault recovery time is obviously shortened, the overvoltage peak value is effectively restrained to be within a safe range, and the industrial problem that the steady-state adjustment precision and the transient supporting capacity cannot be both considered by single reactive power equipment is solved.

The embodiment of the invention provides a voltage instability risk assessment and high-risk scene screening method and related equipment, and belongs to the field of power systems and automation thereof. The method comprises the following steps: extracting a voltage distribution balance degree according to a spatial distribution characteristic of a sample; constructing a voltage instability risk assessment index in combination with the voltage distribution balance degree, the new energy transmission margin ratio and the voltage out-of-limit risk factor; according to the voltage instability risk assessment index, abnormal samples in the sample set are screened through an isolation forest algorithm; performing K-means clustering analysis on the screened abnormal samples to subdivide the candidate scene into subclass clusters with clear risk characteristics; performing class cluster risk assessment according to a clustering result to obtain a class cluster comprehensive score, and dividing class clusters into different risk levels; through dispersion analysis, a centralized extreme scene and a discrete extreme scene are distinguished, and class cluster center and boundary scene screening is carried out respectively. According to the invention, efficient and comprehensive high-risk scene screening can be realized.

The invention discloses a transient stability analysis method for a network-building type energy storage inverter based on torque enhancement control. The transient stability analysis method comprises the following steps: step 1, constructing a network-building type energy storage inverter model based on torque enhancement control; step 2, transient stability analysis of the net-building type energy storage inverter: 2.1, an energy function method, 2.2, influences of parameters on an attraction area, and taking a damping coefficient, line impedance and reference active power which influence a swing equation as variables, so as to obtain the transient stability of the net-building type energy storage inverter; transient power angle instability of the network-building type energy storage inverter is essentially caused by imbalance between the reference active power and the output active power, and the transient stability margin can be improved by reducing the reference active power during the fault period. The method has the beneficial effects that the problems of active power fluctuation and voltage instability of the grid-forming type energy storage inverter are considered, so that the fluctuation can be effectively suppressed and the oscillation can be reduced when the voltage of the system is suddenly changed.

The invention relates to the technical field of power grid monitoring, in particular to a fault monitoring method, system and equipment for a small power generation and distribution system. According to the method, fluctuation characteristics of monitoring signals are analyzed, fluctuation time periods are determined, fluctuation trends are obtained through the lengths of the fluctuation time periods and voltage instability, and short-term fluctuation time periods and long-term fluctuation time periods are obtained through classification. And analyzing each time point one by one, and further screening out a superposed short-term fluctuation time period in the long-term fluctuation time periods through the voltage value difference between the continuous time points. And for the superposed short-term fluctuation time period, the continuation range is adjusted through the fluctuation trend characteristics, and a monitoring signal with accurate characteristic information is obtained. According to the method, the superposed short-term fluctuation time period is effectively extracted, wavelet transform is used for reconstruction, the monitoring signal with accurate feature information is obtained, the power grid monitoring effect can be improved, and subsequent power control over the micro-grid is facilitated.

The invention discloses a transient voltage instability mode-oriented model parameter interpretability analysis method, which comprises the following steps of: 1) generating a plurality of training samples of different fault types through simulation, and extracting feature information of each bus node after fault clearing and a stability label of the sample as original data; 2) inputting the generated original data training sample into a TVSA model based on Transformer for training, and collecting instability mode samples which are difficult to recognize by the model in the training process; and 3) analyzing the relation between different instability mode samples and different parameters in the TVSA model, and quantifying the contribution between the different parameters of the TVSA model and the different instability mode samples by using an SHAP value. According to the method, by analyzing the relation between the TVSA model parameters and the transient voltage instability mode, the evaluation rule of the model for evaluating the instability mode is understood more deeply, so that the evaluation rule of the model is more transparent, and the interpretability and controllability of the model are improved.

The invention provides a receiving end system transient voltage stability evaluation method and device, and belongs to the field of power system operation control. The method comprises the following steps: firstly, acquiring voltage time sequence data after a fault of a receiving-end system based on a sliding time window sampling method, secondly, performing dimension reduction optimization processing on the acquired voltage time sequence data, removing noise and redundant information of the time sequence data, improving feature extraction efficiency and quality, and further improving feature extraction accuracy. And inputting the voltage time sequence data subjected to dimension reduction optimization processing into a trained transient voltage prediction model to obtain a transient voltage prediction value of a next moment output by the transient voltage prediction model, and finally performing voltage instability evaluation on the receiving end system according to the transient voltage prediction value of the next moment. And the efficiency and the accuracy of voltage instability evaluation are improved.

The invention discloses a transient reactive power recovery control method, system and device for a new energy station and a storage medium, and the method comprises the steps: obtaining dynamic model parameters of a target new energy station, obtaining near-region power grid parameters of the target new energy station, building a near-region simulation model of the new energy station, carrying out the fault simulation of a near-region station of the target new energy station, and carrying out the fault simulation of the near-region station of the target new energy station. Identifying a target site causing transient voltage instability, and setting a fault occurring on the target site as a target fault; taking the maximum reactive power output and the reactive power recovery rate as optimization variables, constructing a multi-objective optimization function, and setting differentiation constraints; and carrying out iterative solution on the optimization function, evaluating system stability responses under different parameter combinations, and outputting an optimal minimum active output and an active recovery rate as a transient active recovery strategy of the new energy station. By optimizing the transient reactive power recovery control strategy of the new energy station after the power grid fault, the transient voltage stability of the near area of the new energy station is improved.

The invention discloses a power distribution network risk assessment method and system. The method comprises the following steps: defining an extreme high temperature; constructing an evaluation index system; an extreme high temperature and power distribution network temperature and load coupling relation model, a load surge risk evaluation model, an equipment overload and fault probability evaluation model and a voltage instability evaluation model are constructed by using indexes in the evaluation index system, so that a power distribution network predicted load, an overload probability, an equipment fault probability and a voltage stability margin are obtained respectively; and constructing a risk assessment model for assessing the risk of the power distribution network at the extreme high temperature. According to the invention, through cooperation of accurate temperature and load coupling relation modeling and multi-dimensional risk assessment index system construction, the risk assessment accuracy is improved; the problems that in the prior art, load increase in extreme high temperature weather is not accurately estimated, the fault risk of power distribution network equipment in a high temperature environment cannot be effectively evaluated, and the voltage stability problem caused by extreme high temperature is difficult to comprehensively measure are solved.

The invention is suitable for the technical field of electronic circuits, and provides a DC / DC and super capacitor cooperative control system of a station DC flexible intelligent bus coupler device, which comprises a bus coupler device, a DC bus, a bidirectional DC / DC converter and a super capacitor energy storage unit, the system is used for controlling the bidirectional DC / DC converter and the super capacitor energy storage unit to operate cooperatively so as to maintain the voltage stability of the DC bus. Monitoring the actual voltage value of the DC bus in real time; according to the deviation between the actual voltage value and the set value, the instantaneous output power proportion of the super capacitor energy storage unit and the steady-state output power proportion of the bidirectional DC / DC converter are dynamically adjusted; and when it is detected that the DC bus voltage deviation exceeds a preset threshold value, the super capacitor energy storage unit is preferentially controlled to carry out instantaneous power compensation, and the output power of the bidirectional DC / DC converter is adjusted to carry out steady-state power following. The problems of bus voltage transient instability, super capacitor over-discharge aging and low system operation efficiency are solved.

The invention discloses a transient stability enhancement control method and device for a network-forming converter, a terminal and a medium. According to the scheme, on the basis of matching control logic, a virtual power angle difference value is introduced to serve as an additional control variable, so that the converter can respond to direct-current voltage fluctuation and power angle deviation at the same time; therefore, when the phase jump or power fluctuation of the power grid occurs, the output angular frequency of the grid-forming converter can quickly respond to the phase jump by dynamically adjusting the virtual power angle reference value, so that the stability of the direct-current bus voltage is enhanced, and the phenomena of power angle oscillation and voltage instability in the transient process are inhibited.

The present application relates to the technical field of power system stability control, and is a steady-state voltage control method and system for reducing transient voltage instability risk of a new energy collection station, the method comprising: establishing a new energy collection station bus transient voltage model of a new energy sending end power grid after a DC bipolar blocking fault; setting a new energy collection station transient voltage instability limit of the new energy sending end power grid after the DC bipolar blocking fault; and setting a steady-state voltage control threshold for reducing the transient voltage instability risk of the new energy collection station bus based on the new energy collection station bus transient voltage model. The present application can achieve the purpose of reducing transient voltage instability risk by controlling the steady-state operating voltage of a high-proportion new energy sending end power grid without increasing dynamic reactive power compensation equipment. The present application is used to solve the problem of transient voltage instability caused by new energy off-grid of a new energy collection station of a DC sending end power grid after a DC fault due to excessively high transient voltage caused by excessively high steady-state operating voltage of the power grid.

The invention discloses a current-limiting control method based on a network-forming static var generator. The current-limiting control method comprises the following steps: inputting an external direct-current voltage, stabilizing the voltage by a capacitor, and then outputting the voltage to an inverter bridge; the inverter bridge generates controllable alternating current through space vector modulation; the inductive filter filters high-frequency harmonic output end voltage; the terminal voltage amplitude and phase are monitored in real time, and current-limiting control is triggered based on the phase deviation between the voltage and the virtual internal potential when the voltage of the power grid drops; the terminal voltage interacts with ideal power grid voltage at a common coupling point through power grid impedance to generate PCC voltage; pCC voltage and output current are detected, and instantaneous power is calculated; the power signal is filtered and de-noised and then a modulation instruction is generated by the current-limiting controller and is fed back to the inverter bridge to form a closed loop. The reactive power supporting voltage is injected preferentially, the voltage drop amplitude is remarkably reduced, the inertia damping supporting capacity of the system is enhanced, power grid fault recovery is accelerated, and meanwhile the voltage instability problem caused by a traditional current limiting strategy is avoided.

The invention relates to the technical field of power distribution network control, in particular to an emergency generator set starting control method and system based on energy dispatching optimization, and the method comprises the steps: carrying out the voltage distribution calculation of a to-be-controlled power distribution network based on a historical operation period set, and obtaining a plurality of load node voltage amplitude sets, selecting a plurality of emergency risk nodes according to the plurality of load node voltage amplitude sets, calculating the number of emergency generators according to the current power distribution network vacancy power and the emergency rated generation power, and setting an emergency generator starting position set according to the number of emergency generators and the plurality of emergency risk nodes, according to the method, the accuracy and the response efficiency of emergency power generation of the power distribution network can be improved, and the voltage instability risk of the power distribution network is reduced.

The utility model discloses a dimming circuit, a lighting module and a clothes airing machine, the voltage output to a light source is adjusted by a voltage adjusting module, so that the output voltage meets the power demand of the light source, a PWM signal is converted into a stable direct-current voltage signal which is not easy to interfere by a PWM signal conversion module, and the power demand of the light source is satisfied. The controller controls the switching circuit to adjust the current output to the light source according to a feedback signal of the feedback module, so that the brightness of the light source is adjusted, the problem that the light source flickers in the dimming process due to unstable voltage or PWM interference can be avoided, and the stability of light source display is improved through the PWM signal conversion module.

The application discloses a power grid transient voltage instability expected fault tracing method and system, comprising: obtaining a two-dimensional feature vector corresponding to each fault scene in an expected fault set and a transient voltage stability conclusion label; determining a core instability set and a critical observation set of the fault scene based on the two-dimensional feature vector and the transient voltage stability conclusion label; clustering the core instability set and the critical observation set, and performing multi-dimensional feature imaging based on the clustering result to obtain a feature image corresponding to each instability mode cluster; and performing tracing analysis based on the feature image to obtain a tracing result. The application realizes intelligent focusing on key scenes and automatic induction of instability modes based on existing batch discrimination results and mechanism features through a customized screening, clustering and attribution process, and generates a structured analysis report which can directly support operation cognition.

The invention discloses a discharge management method and system based on UPS inversion and voltage regulation and control, and relates to the technical field of uninterruptible power supplies, and the system comprises a battery state sensing module, a load power monitoring module, a battery health assessment module, an inverter operation boundary calculation module, a voltage regulation and control execution module, a discharge termination control module, an energy recovery power supply module and the like. The core of the method is as follows: collecting battery and load data in real time, dynamically correcting a discharge termination voltage threshold by combining a battery aging model, and calculating a dynamic voltage lower limit constraint required by an inverter; in the discharging process, the stability of the voltage of the direct-current bus is ensured by reducing the power of the inverter or starting the dual-mode regulation and control of the booster circuit; and finally, battery electric energy is inverted into standard alternating current to be used by a load, and traditional resistor energy consumption is replaced. According to the invention, the problems of unstable voltage, energy waste, battery life loss, poor dynamic adaptability and the like in the traditional UPS discharge management are solved, and the high efficiency, safety and intelligence of the discharge process are realized.

The invention provides a bus residual voltage holding device based on distributed reactive compensation, and belongs to the technical field of bus residual voltage holding of an electric power system, and the device comprises a short circuit fault identification module which is used for monitoring the current of the electric power system, and when a current amplitude criterion Ig is greater than or equal to 2Ie and a current change rate criterion di / dt is greater than or equal to 25kA / s, determining that a short circuit fault occurs; the exciting current switching module comprises a normal exciting current loop and a residual voltage regulation exciting current loop, and is used for switching exciting current into residual voltage regulation exciting current when a short-circuit fault occurs through switching of a switch K; according to the method, optimization and improvement are carried out from two aspects of fault judgment and fault recovery, and the time period from abrupt drop to recovery of the bus voltage is shortened; the large-area power failure risk caused by voltage instability can be greatly reduced, the power supply reliability of key livelihood facilities of hospitals, traffic, communication and the like is improved, and the social public safety and stability are maintained.

The invention discloses a novel transient voltage instability discrimination method for a power system. The method comprises the steps of obtaining dynamic response data of a new energy unit in a fault ride-through process; according to the dynamic response data, extracting correlation characteristics of the active current and the terminal voltage; according to the correlation characteristics, constructing a transient voltage instability criterion; and carrying out transient voltage stability evaluation judgment according to a transient voltage instability criterion in combination with a Lyapunov index to obtain a judgment result. According to the method, the actually measured response data can be directly utilized to carry out transient voltage discrimination, so that the interference of complex factors such as a system operation mode and a network structure is avoided. The method has the advantages of being small in calculation amount, small in required measurement information amount, good in timeliness and the like, and the discrimination efficiency and practicability are improved.

The invention discloses a phase modifier configuration method and system for improving transient voltage stability of a power grid. The method comprises the following steps: monitoring alternating voltage of each bus node in the power grid; scanning an alternating current anticipated fault set of the power grid, calculating the voltage stability margin of each bus node, judging the fault which causes the voltage stability margin of any bus node to be less than 0 as a voltage instability fault, and adding the voltage instability fault set; executing an iterative optimization process for each fault in the voltage instability fault set; traversing all faults in the voltage instability fault set, completing phase modifier configuration through iterative optimization, and outputting a final phase modifier configuration scheme; according to the invention, reactive power can be emitted as much as possible at the fault moment, direct-current commutation failure is suppressed, new energy low-voltage penetration scale is reduced, and transient voltage stability of a power grid is improved.

This application relates to an optimized configuration method for improving the voltage stability of hollow power grids using SVG (Static Var Generator) architecture. The method includes: calculating the minimum singular value of the system Jacobian matrix based on power grid data; constructing a comprehensive evaluation model for weak nodes; calculating the node weakness index under various scenarios; constructing a static optimization configuration model; conducting analysis under a preset fault set; constructing a two-layer evaluation framework combining equipment-level and system-level analysis; quantifying the improvement of system transient voltage stability by candidate schemes; and comprehensively comparing and selecting the optimal configuration scheme that meets the requirements for transient stable voltage stability. This invention achieves accurate identification of weak nodes in the voltage stability of hollow power grids, significantly improving both the static and transient voltage stability margins of the system. It effectively solves the technical problems of voltage instability and poor transient recovery under high-proportion power electronics access, thereby improving the safety and anti-disturbance capability of power grid operation.

The present invention belongs to the technical field of power supply and power detection, and specifically relates to a detection circuit and an evaluation method for the output voltage quality of a variable-frequency power supply for high-voltage tests. The technical solution adopted is as follows: After adjusting the output frequency of the variable-frequency power supply to be tested to a maximum of 300 Hz, adjust the output voltage to reach a maximum of 350 V in steps of 5 V. Adjust the internal impedance of the variable load device to make the output of the variable-frequency power supply reach a maximum current of 1142 A, and calculate the total harmonic distortion THD of the output voltage waveform of the variable-frequency power supply to be tested by a waveform analyzer. While maintaining the maximum output voltage and maximum output current of the variable-frequency power supply to be tested, adjust the power interference generator to make the input voltage of the variable-frequency power supply fluctuate within ±5%, and calculate the output voltage instability ΔU% of the variable-frequency power supply at this time by a waveform analyzer. After the entire test is completed, reduce the output voltage through the variable-frequency power supply control box and disconnect the input of the variable-frequency power supply. The method of the present invention is simple, practical and efficient, and the results are reliable.

The invention provides a new energy site selection method based on node correlation line loss sensitivity and volatility constraint, comprising the steps of establishing a new energy output model, and performing load flow calculation based on typical operation conditions of a main network; calculating a typical sensitivity factor, and modeling the uncertainty of the new energy output to solve the sensitivity factor under the uncertainty condition; and constructing a new energy site selection planning model according to the sensitivity factor and the power grid operation constraint condition under the uncertain condition, and solving to obtain a site selection plan. According to the invention, by calculating the sensitivity factor under the uncertain condition, the influence of new energy access to different positions on the stability of the system is quantified; and meanwhile, modeling is carried out for the output uncertainty of the new energy station, the new energy output uncertainty is used as a fluctuation constraint, and new energy site selection planning is carried out, so that high-risk sensitive nodes can be actively avoided, the line loss dramatic increase and voltage instability risks caused by new energy fluctuation are reduced, and stable and efficient operation of a novel power system is guaranteed.

This invention relates to the field of power system stability control technology, and is a wind power converter control method and system for reducing the risk of transient voltage instability at wind power collection stations. The method includes: establishing a transient voltage model of the wind power collection station in the renewable energy sending-end grid after a DC bipolar blocking fault; establishing a reactive power control model of the wind power converter under the transient voltage control mode based on active power output; and setting transient voltage instability limits for the wind power collection station in the renewable energy sending-end grid after a DC bipolar blocking fault. This invention can fully leverage the rapid reactive power control advantages of the wind power converter when the transient voltage instability risk of the wind power collection station is caused by the UHVDC bipolar blocking in the renewable energy sending-end grid, thereby reducing the peak transient voltage of the wind power collection station, preventing the wind farm units connected to the wind power collection station from tripping and disconnecting from the grid due to high voltage ride-through failure, thus reducing the risk of transient voltage instability at the wind power collection station and improving the transient voltage stability of the system.

The invention relates to a wide-area safety control method and system for a network construction type power electronic power system, belongs to the technical field of safety protection of the power electronic power system, and solves the problem that the network construction type power electronic power system is easy to generate voltage instability under large interference in the existing method. Comprising the following steps: constructing a dynamic energy model of each subsystem on the basis of instantaneous values of electrical quantities of ports of the networking type power electronic power system before and after an N-2 fault; based on the dynamic energy model of each subsystem, calculating to obtain an interaction energy change rate of the power system; when the interaction energy change rate of the power system is greater than 0, screening to obtain first, second and third interaction energy items having great influence on instability of the power system; and on the basis of the first, second and third interaction energy items, calculating to obtain a rectifier current instruction value, and issuing the rectifier current instruction value to the rectifier to compensate the instability influence of the power system, thereby realizing wide-area safety control of the power system after the N-2 fault.

The present invention discloses a method and system for simulating the electromechanical transient state of power system voltage stability. The method obtains data after the system is disturbed and uses a parameter identification algorithm to obtain the time constant for the load to recover to a steady state, as well as the proportional coefficients related to the static active load and reactive load. A conventional ZIP static load model is listed, and a dynamic ZIP load model is constructed using a proportional-integral-differential (PID) and a limiting step to reflect the input-output relationship between active and reactive loads and equivalent impedances. The system equilibrium point is determined based on the results of steady-state power flow calculations, and all dynamic equations of the entire network are linearized at the equilibrium point to obtain a state-space model. The eigenvalues ​​of the state matrix are calculated, and the voltage stability of the busbar where the load is located is determined based on the positive and negative signs of the real parts of the relevant eigenvalues. A dynamic time-domain simulation is performed on the adjusted system, and an N-1 or N-2 line fault is imposed on the entire network to simulate the voltage collapse scenario that may occur in the system. This provides theoretical support for proposing countermeasures after voltage instability.

The invention discloses a multi-task transient voltage stability evaluation method based on TVSDTNet feature enhancement. The multi-task transient voltage stability evaluation method comprises the following steps: constructing time sequence electrical measurement data information; constructing a multi-task transient voltage stability evaluation model based on TVSDTNet feature enhancement; dividing the transient voltage stability evaluation problem into two mutually associated sub-tasks, namely a task I and a task II; defining a voltage instability node complete coverage rate fcr, a voltage stabilization node complete coverage rate tcr and a geometric mean value Gm of the voltage instability node complete coverage rate fcr and the voltage stabilization node complete coverage rate tcr so as to evaluate the capability of the multi-task transient voltage stability evaluation model for accurately identifying and dividing transient voltage instability nodes or regions; and based on the constructed multi-task transient voltage stability evaluation model, evaluation of the transient voltage stability state and accurate identification and division of voltage instability nodes or regions are realized. According to the method, expression of time sequence electrical measurement data information can be effectively enhanced, transient voltage stability evaluation of the system is realized, and voltage instability nodes or regions can be accurately divided.

The invention provides a reactive voltage dynamic optimization method considering wind-thermal power generation through direct current transmission, and the method comprises the following steps: S1, building a reactive voltage optimization model of a wind power injection LCC-HVDC alternating-current and direct-current system, and setting constraint conditions; s2, measuring the transient overvoltage suppression effect of the operation parameters through a transient overvoltage suppression index, evaluating and screening key optimization parameters, and constructing a parameter dynamic optimization control system structure; and S3, carrying out calculation learning by using a deep fuzzy neural network, dynamically generating a STATCOM parameter optimization instruction, realizing dynamic reactive voltage optimization, and analyzing an optimization result. The invention provides a reactive voltage dynamic optimization method considering wind-thermal power generation and direct-current transmission, which takes key operation parameters considering wind power injection and a high-voltage direct-current transmission system as input quantities to carry out learning calculation, and carries out dynamic optimization on STATCOM parameters, so that the reactive support level of the STATCOM is dynamically adjusted under the transient extreme condition of the system, and the system stability is improved. The voltage instability condition is improved, and the system reliability is improved.

This invention discloses an LLC resonant converter with a wide voltage range input, belonging to the field of power electronics technology, including a DC voltage source V. in First bus voltage divider capacitor C in1 Second bus voltage divider capacitor C in2 First full-bridge switch Q1, second full-bridge switch Q2, third full-bridge switch Q3, fourth full-bridge switch Q4, first bidirectional switch Q5, second bidirectional switch Q6, first resonant inductor L r1 Second resonant inductor L r2 First resonant capacitor C r1 Second resonant capacitor C r2 First excitation inductor L m1 Second excitation inductor L m2 Transformer TR1, Transformer TR2, First rectifier diode D7, Second rectifier diode D8, Third rectifier diode D9, Fourth rectifier diode D 10 Output filter capacitor C o And load R. This invention can effectively eliminate the situation of instantaneous input voltage instability without increasing the complexity of the main control circuit, and ensure the normal operation of downstream electrical equipment.

This invention discloses a distribution network voltage control method based on safety constraints and online hyperparameter optimization. The invention constructs a distribution network voltage state transition model under no-communication conditions; derives a stability criterion based on Banach's fixed-point theorem and solves for the stability safety constraints of the action gain of each controlled node; configures an independent reinforcement learning control agent for each controlled node and applies stability safety constraints and equipment capacity constraints; trains the agent using a group relative policy optimization algorithm, updating the policy network parameters based on the relative advantage value of the trajectory within the group; employs a hyperparameter optimization method based on a multi-armed slot machine to optimize the reinforcement learning training hyperparameters online; and achieves cross-scenario migration of the reinforcement learning control agent through parameter remapping and incremental training when the distribution network scenario changes. This invention can realize distribution network voltage control, reduce the risk of voltage instability, reduce the computational overhead of hyperparameter optimization, and achieve rapid cross-scenario migration and adaptation.