272 results about "Voltage sag" patented technology

The invention relates to the technical field of power grid monitoring, and discloses a voltage sensor multi-parameter real-time monitoring method and device in an Internet of Things environment. According to the method, real-time voltage fluctuation data of a target area is acquired by deploying a multi-channel voltage sensor array and is transmitted to an edge computing node; dynamic feature extraction is executed in the edge nodes, and a multi-dimensional feature matrix containing voltage fluctuation ratio, harmonic distortion and phase deviation features is generated; identifying voltage sag, overvoltage and harmonic resonance event characteristics based on an anomaly detection model; spatial correlation modeling is carried out in combination with power grid topological structure parameters, the coupling strength of adjacent sensor node parameters is calculated, and a multi-parameter correlation map containing event propagation paths and influence ranges is generated; inputting the voltage into a diagnosis model to generate a power grid state diagnosis report, and dynamically adjusting the sampling frequency and filtering parameters of the voltage sensor according to the power grid state diagnosis report. According to the method, real-time monitoring and analysis of multiple parameters of the power grid can be realized, and comprehensive support is provided for power grid state evaluation.

The invention discloses an electricity utilization information acquisition intelligent configuration method based on a pattern recognition algorithm, and relates to the technical field of intelligent power grids, and the method comprises the steps: collecting a directional data stream, inputting a federal map neural network to construct a power distribution network physical connection relation, and generating a spatio-temporal topological feature vector; extracting a current effective value component of the directional data flow as an electrical load sequence, extracting an equipment state code to identify a voltage sag event, injecting voltage sag event associated disturbance into the electrical load sequence in combination with an event propagation path weight of a spatio-temporal topological feature vector, and generating an anti-fact sample set; and compressing the new configuration strategy through a knowledge distillation engine, and outputting an event response logic and a parameter adjustment instruction to form an executable configuration strategy. According to the method, through anti-fact sample generation and reinforcement learning optimization under spatial-temporal topological feature vector constraint, a physical rule deep embedding decision is realized.

The invention relates to a reconfigurable battery energy storage system grid-connected and off-grid seamless switching control method and device. The method comprises the following steps of: sensing a real-time power grid state, pre-judging a system operation mode, and acquiring a millisecond-level panoramic information flow of the power grid state through a high-speed sampling voltage sensor, a high-speed sampling frequency sensor, a high-speed sampling phase sensor and a high-speed sampling communication interface. And pre-judging the stability and disturbance trend of the power grid through a deep learning algorithm, executing a power distribution and voltage support algorithm in grid-connected and off-grid modes, and calculating an optimal switching opportunity point and a system reconstruction target topology scheme. Meanwhile, the harmonic distortion rate and the voltage sag depth are calculated in real time through discrete Fourier transform, so that a mode pre-judgment mechanism is automatically triggered. After switching, key parameters such as voltage, frequency and power are automatically corrected through real-time sampling and observation, and zero-sensing switching is achieved. The method can effectively improve the response speed and stability of the battery energy storage system when the power grid fails, and guarantees the safe operation of the power grid.

The invention relates to the technical field of electric energy identification, in particular to an energy consumption identification system based on a power transformation aliasing scene, which comprises a disturbance boundary extraction module, a boundary stability judgment module, an aliasing state identification module, a periodic power calculation module and an energy consumption attribution judgment module. According to the method, a voltage sag record with a phase offset characteristic is formed through continuous tracking of the periodic voltage fluctuation starting and ending point indexes, a stable fluctuation judgment mechanism is constructed in combination with offset statistics, and accurate identification of aliasing sections is realized by means of disturbance amplitude and frequency extraction. A power sequence is constructed on the basis of voltage and current synchronous sampling values, period integration is completed, a high-precision calculation result of energy consumption is formed, fine division of cross interference period energy consumption under the condition of no physical isolation is achieved, dependence of external metering equipment is avoided, independent quantization of overlapping load energy consumption is achieved, and the calculation efficiency is improved. And a feasible means is provided for energy efficiency evaluation in a non-intrusive load identification and high-coupling scene.

The invention relates to the technical field of voltage sensitivity photovoltaic stability regulation and control of a power distribution network, in particular to a multi-parameter photovoltaic grid-connected voltage stability control method, system equipment and a medium, and aims to improve the transient modeling precision by constructing a second-order equivalent transient model of a photovoltaic system and decoupling a mapping relation between phase-locked loop parameters and equivalent inertia and damping; quantifying a transient stability boundary under voltage disturbance based on a phase-locked loop sensitive parameter, and determining a photovoltaic power angle critical safety threshold; for the whole voltage fluctuation process, dynamically and cooperatively regulating and controlling phase-locked loop parameters according to the voltage and frequency of the power grid; equivalent damping and inertia suppression oscillation are enhanced in the voltage drop period, inertia acceleration recovery is reduced while high damping is maintained in the voltage recovery period, rated parameters are reset in the steady state, the transient stability of the system for coping with voltage sag is remarkably improved, and the risk of power angle instability is avoided.

Disclosed is a method and system for SE voltage sag control based on flexible multiplexing of an energy storage system. The present disclosure achieves controlling of an early stage of the voltage sag using a supercapacitor, and continuous controlling of a late stage of the voltage sag using the energy storage system; achieves real-time accurate detection of the voltage sag on a grid side and a load side; achieves optimal energy compensation through flexible switching in an input stage and an output stage to prevent SE from tripping due to a phase jump caused by the optimal energy compensation; on a DC / DC side, performs power frequency division control based on a difference in response features between the supercapacitor and the lithium battery energy storage system; on a DC / AC side, provides a composite control system including a voltage feedforward loop, a voltage feedback outer loop, and a current feedback inner loop.

The invention belongs to the technical field of electric energy quality control, and provides an energy storage type medium-voltage voltage sag and interruption treatment device and a control method thereof.The energy storage type medium-voltage voltage sag and interruption treatment device is arranged between a large power grid and a load in series and comprises a series converter PCS1, a parallel converter PCS2, an energy storage module, an injection type series transformer T1, a parallel transformer T2, a bypass static switch STS and a bypass relay KM1; wherein the injection type series transformer T1 is connected with a large power grid, and the parallel transformer T2 is connected with a load; the series converter PCS1 is connected with the injection type series transformer T1 through the bypass static switch STS and the bypass relay KM1, and compensation voltage is generated in real time through the injection type series transformer T1; the parallel converter PCS2 is respectively connected with the parallel transformer T2 and the common direct current busbar; and the energy storage module is arranged on the common direct current busbar between the series converter PCS1 and the parallel converter PCS2 in parallel.

The invention provides an optimal configuration method and device for a magnetic reactance type dynamic voltage restorer, and relates to the technical field of optimal configuration, and the method specifically comprises the steps: obtaining the historical voltage sag event data of a target power distribution bus and the electrical parameters of a downstream load motor; screening a to-be-compensated event set based on the principle that the sag depth exceeds a load tolerance threshold and the duration is less than the critical stall time, and determining a compensation strategy according to a comparison result of a phase jump angle maximum value and the threshold; the maximum compensation voltage is determined according to the maximum sag depth, the rated output current is determined according to the load parameters, the theoretical energy required for compensating the longest event is calculated based on the compensation strategy, and the actually required energy is determined in combination with the energy correction coefficient of the device topology; and finally, generating an optimal configuration scheme based on the compensation strategy, the maximum compensation voltage, the rated output current and the actually required energy. According to the invention, accurate mapping from power grid measured data to device key parameters is realized.

The invention relates to a modular intelligent power distribution cabinet safety management method based on the Internet of Things, particularly discloses a modular intelligent power distribution cabinet safety management method based on the Internet of Things, and aims to solve the problems that a traditional power distribution cabinet monitoring system is poor in expansibility, weak in fault recognition capability and rigid in protection strategy. The method comprises the following steps: deploying a modularized sensing unit with a standardized interface to realize plug and play; multi-dimensional data of current, voltage, temperature and arc light are synchronously acquired at a high sampling rate; data are fused on the edge side through Kalman filtering, and key features such as harmonic distortion rate, voltage sag depth, temperature gradient change rate and electric arc energy accumulation value are extracted; performing dynamic risk assessment by using a five-layer deep belief network model, and triggering early warning when the high risk probability exceeds a threshold value; adaptively adjusting an overcurrent protection constant value, opening delay and isolation logic according to an evaluation result; and the edge-cloud coevolution is realized by continuously optimizing the model and the strategy through cloud reinforcement learning.

A power failure anomaly recognition method and apparatus. The method comprises: acquiring cluster data from a target cluster (S1); on the basis of the cluster data, acquiring distribution transformer data of each distribution transformer at each moment, the distribution transformer data comprising three-phase voltage imbalance, a three-phase voltage, the fluctuation amplitude of a phase current corresponding to voltage sag, a three-phase current, the sag amplitude of a three-phase instantaneous total active power, and the sag amplitude of each phase current (S2); on the basis of the distribution transformer data, screening out a corresponding distribution transformer that meets a first preset anomaly condition, so as to achieve preliminary anomaly recognition (S3); and, on the basis of the distribution transformer data, performing in-depth anomaly recognition on the distribution transformer that meets the first preset anomaly condition, so as to screen out a corresponding distribution transformer that meets a second preset anomaly condition and obtain a distribution transformer having power failure anomaly (S4). On the basis of the three-phase voltage imbalance, the three-phase voltage, the three-phase current and other distribution transformer data, preliminary anomaly recognition and in-depth anomaly recognition are performed; compared with manual inspection, the present method reduces manual workload and eliminates factors that affects power failure anomaly recognition such as limited human energy, thereby improving the timeliness and accuracy in power failure anomaly recognition.

The invention relates to a low-voltage ride-through control method for a network-forming converter based on key control parameters. The low-voltage ride-through control method comprises the following steps: step 1, designing an active and reactive self-adaptive updating method during voltage sag; 2, introducing a virtual inductor Lv to carry out linear correction on a reactive power regulation coefficient x; 3, based on the improved virtual damping Dp, the transient state power angle stability of the network construction type converter system of the VSG architecture is enhanced; the filtering time constant Ts of damping is improved, and the variable damping gain Dp'changes the static-dynamic power angle stability of the grid-forming converter; and step 4, improving a reactive voltage regulation link of the network construction type converter by improving a reactive integral channel. According to the method, from the two aspects of power closed-loop control and synchronous stable control, the severity of a fault is judged by detecting the amplitude of an output voltage, and meanwhile, active and reactive power reference values are adaptively changed to realize power closed-loop control. And the reliability and the stability of voltage control in the transient process are jointly improved.

The invention relates to the technology of power electronics and electric energy quality control, in particular to an energy storage type UPQC and switch state prediction control method based on improved model prediction control, which comprises a series active filter, a parallel active filter, a direct current bus, an energy storage system and a controller, according to the control method, an energy storage power and charge state dynamic equation is introduced into an MPC prediction model, and a multi-objective cost function is designed. And the controller predicts and evaluates the candidate switching vector in each sampling period based on a finite control set model predictive control strategy, and outputs an optimal switching state through value function optimization, thereby realizing collaborative optimization of electric energy quality management and energy storage energy management. According to the method, the dynamic response capability and compensation precision of the UPQC under the working conditions of voltage sag / sag, imbalance, harmonic waves and load fluctuation are remarkably improved, meanwhile, the energy storage utilization efficiency and the system stability are improved, and the method is suitable for a power distribution network with new energy high permeability and large load fluctuation.

The invention discloses a voltage sag state estimation method and system based on complex task decomposition reasoning, and the method comprises the steps: firstly solving actual problems in a physical world through guiding LLM by employing a mathematical tool, and giving text output fitting the reality through combining the mathematical tool and the feedback of a thinking tree architecture simulating human thinking behaviors; in order to solve the practical problem of the physical world, the invention constructs a physically-driven DGCN model, and the output of a mathematical tool better fits the practical situation by combining a multi-layer graph convolution layer and taking a power grid topology connection relationship as a physical constraint condition. And finally, introducing an improved DGCN model based on cooperative training and cross-power-grid regional knowledge migration, and improving the overall generalization and adaptability of LLM when voltage sag state estimation is carried out on unknown power grid topology.

The utility model provides a voltage sag resistant circuit and a motor, the circuit comprises an energy storage module, the energy storage module comprises a first capacitor, a second capacitor, a first diode, a second diode and a third diode, the second end of the first capacitor is connected to the cathode of a first diode, and the anode of the first diode is grounded; the cathode of the second diode is connected to the energy exchange end of the circuit, the anode of the second diode is connected to the first end of the second capacitor, and the second end of the second capacitor is grounded; the anode of the third diode is connected between the first capacitor and the first diode, and the cathode of the third diode is connected between the second diode and the second capacitor. According to the anti-voltage sag circuit and the motor, the motor can be kept running continuously when voltage sag occurs. In addition, the circuit and the motor are small in size and low in cost, and the power factor of the system can be improved.

The invention provides an electric energy quality control method and system based on an energy storage system, relates to the technical field of electric energy quality control, and aims to identify collaborative disturbance attributes during voltage sag and three-phase imbalance through dynamic distortion information, perform scheduling amplitude limiting compensation on the collaborative disturbance attributes, and improve the control accuracy of the electric energy quality. Obtaining a layered amplitude limiting inflection point when the electric energy in the energy storage system is intelligently scheduled in the load-storage balance constraint region; carrying out fusion correction on the circulation out-of-limit deviation, generating a dynamic peak regulation criterion when the power grid carries out energy storage transfer adjustment in multiple time scales, and further determining a regulation and control guidance strategy during electric energy balance regulation and control in the energy storage system according to the dynamic peak regulation criterion; and performing tolerance adaptation control on the power quality of the power distribution network in the composite disturbance scene according to the hierarchical amplitude limiting inflection point and the regulation and control guidance strategy. According to the invention, tolerance adaptation control can be carried out on the power quality of the power distribution network in a composite disturbance scene, so that the power quality management and control efficiency under the participation of an energy storage system is improved.

The invention discloses a multi-mode fault ride-through control method of a network-forming type energy storage converter, which relates to the technical field of converter control and comprises the following steps of: acquiring node voltage amplitude, voltage phase angle, system frequency and harmonic component, and filtering acquired data; according to the method, the operation region is calculated based on the real-time filtering data, the electromagnetic transient energy and the rotation kinetic energy component, so that the network-forming type energy storage converter intelligent body at different spatial positions can obtain differentiated control margins during the fault period; the operation area of the network-forming energy storage converter intelligent body which is close to a fault point and is seriously influenced by voltage sag or frequency fluctuation can automatically contract during a fault period; the operation area of the network-forming type energy storage converter intelligent body which is far away from the fault point and is slightly disturbed by the fault is kept relatively loose, and the technical problems that control close to the fault point is insufficient and control resources far away from the fault point are wasted due to one-time cutting of a traditional fixed operation area are effectively solved.

The invention relates to the technical field of electric energy quality treatment, in particular to a collaborative treatment system and method based on multi-class electric energy quality adjustment resources. The system comprises an electric energy quality disturbance generation device, an electric energy quality interference source device, a harmonic current generation device, a line impedance simulation device, a data acquisition device, an electric energy quality diagnosis module and a coordinated scheduling module. According to the invention, independent or coupled simulation of various disturbance types such as voltage sag, harmonic wave, imbalance and flicker is supported based on various types of power quality regulation resources, optimal scheduling and cooperative control of various types of regulation resources such as source, network and load are realized, modular design is realized, plug and play and test verification of various treatment devices are supported, and the power quality regulation system is suitable for large-scale popularization and application. Through line impedance simulation and multi-working-condition setting, an actual power grid operation environment is approached, and the system is especially suitable for a high-proportion new energy and power electronic equipment access scene.

The invention discloses a network construction type converter low voltage ride through control method and system based on voltage sag depth dynamic adjustment, and a storage medium. The method comprises the following steps: dividing voltage sag depth grades; collecting a grid-connected point voltage signal for preprocessing, calculating the voltage drop depth according to the preprocessed voltage, and judging the level of the voltage drop depth; if the voltage sag depth is in a normal state, traditional VSG control is executed to complete low voltage ride through, otherwise, the reactive-voltage sag coefficient, the output reactive power and the virtual impedance are updated according to the voltage sag depth; when the voltage drop is not recovered to a normal state or is recovered to be normal but does not last for a set time, continuously carrying out the process after dividing the depth grade of the voltage drop, otherwise, adjusting the droop coefficient according to discretization exponential attenuation, and recovering the active power according to a discretization active slope recovery strategy; according to the invention, the power grid support efficiency and safety in the low voltage ride through process can be improved, and secondary oscillation in the recovery period can be avoided.

The invention discloses a power supply protection type power grid electric energy regulation and control method and system based on optical storage flexible direct current, and the method comprises the steps: connecting the head end of a distribution transformer with the middle and rear ends of a line through a dual-port flexible direct current system, and configuring a plug-and-play energy storage / photovoltaic interface at a direct current side; wherein the converter D1 is connected with the head end of the low-voltage side of the distribution transformer, and the converter D2 is arranged in a voltage-sensitive user concentration area; based on the voltage threshold real-time monitoring result, triggering multi-mode operation of the D1-D2 bidirectional converter, including: when the terminal voltage is lower than a low threshold, starting a D1-D2 power supply mode; when the voltage is higher than a high threshold value, switching to a D2-D1 energy storage charging mode; when 50%-90% of voltage sag is detected, double converters are started for combined power supply; through linkage of rapid turn-off of a thyristor switch and an optical storage system, an emergency power supply channel of D2-users is established when a power grid fails. The power supply quality and the power supply reliability of the power distribution network can be improved.

The invention discloses a battery cluster short circuit rapid identification method and device based on voltage sag. The method comprises the following steps: acquiring a total voltage real-time value of a battery cluster in a current detection period; calculating an inter-frame total voltage change real-time value of the battery cluster based on the total voltage historical value of the battery cluster in the previous detection period; judging whether the inter-frame total voltage change real-time value is greater than or equal to a preset voltage abrupt change threshold value or not; and if yes, judging that the battery cluster has a short-circuit fault, and triggering a protection action. The inter-frame change of the total voltage of the battery cluster is monitored in real time and compared with the preset threshold value, millisecond-level rapid identification and protection of the full-range short-circuit current are achieved, and the technical problem that in an existing energy storage system protection system, due to the inverse time limit characteristic of a circuit breaker and the BMS delay criterion, medium and low short-circuit current cannot be rapidly cut off is effectively solved.

The invention relates to an under-voltage protection circuit and electronic equipment. The under-voltage protection circuit comprises an energy storage circuit, a comparison circuit and a bleeder circuit. The energy storage circuit is used for accessing power supply voltage. A first input end of the comparison circuit is connected with the energy storage circuit, and a second input end is connected with power supply voltage; the control end of the bleeder circuit is connected with the output end of the comparison circuit, the input end of the bleeder circuit is connected with voltage to be discharged, and the output end of the bleeder circuit is grounded. When the power supply voltage is greater than or equal to a preset under-voltage threshold value, the energy storage circuit is charged, and the comparison circuit outputs a first level signal; under the condition that the power supply voltage is smaller than the preset under-voltage threshold value, the energy storage circuit discharges, and the comparison circuit outputs a second level signal; the bleeder circuit bleeds the voltage to be discharged according to the second level signal and stops discharging according to the first level signal. When the power supply voltage drops suddenly, the bleeder circuit can rapidly discharge the to-be-discharged voltage, thereby reducing the damage risk of the internal module of the PMIC caused by abnormal power failure, and improving the use reliability of the PMIC.

The invention relates to the technical field of factory power supply stability control, in particular to a factory power supply stability control method and system. The method comprises the following steps: obtaining an AC power transmission operation log from a factory power supply control center, and extracting fault abnormal state data; then, carrying out voltage sag intermittent amplitude analysis on the data, and carrying out loss quantitative simulation on the overload performance of the transformer based on an analysis result; and finally, making a dynamic compensation load intelligent balancing strategy by using transformer overload performance loss quantification data, and sending the strategy to a factory power supply control center to ensure power supply stability and load balancing. According to the invention, the factory power supply stability control technology is optimized, so that the factory power supply stability control technology is more perfect.

The invention provides a time-delay-free voltage sag method and equipment, and relates to the technical field of intelligent control. When voltage sag is caused by a power grid side fault, an energy storage device automatically injects current into a power grid side through an electric reactor, voltage drop is formed on the electric reactor, and stability of load side voltage is guaranteed; during treatment, the main control device CCU monitors the duration of voltage drop of the power grid; and if the duration exceeds a preset time-delay constant value, a continuous fault is determined, a control signal is output immediately, a power grid side switch S1 of each energy storage unit is tripped off, current injection to the fault power grid is cut off, and at the moment, the load is independently supported by the energy storage device T. According to the invention, when slight voltage sag occurs at the power grid side, the load does not need to be cut off from the power grid, and real non-delay treatment is realized.

The invention discloses a power distribution network voltage sag monitoring point multi-target selection method considering a distributed power supply low voltage ride through characteristic. The method comprises the following steps: providing a distributed power supply low voltage ride through strategy; deriving a voltage sag amplitude analytical expression under various short circuit fault types considering the low voltage ride through characteristic of the distributed power supply; introducing a position variable to construct a function relation between a voltage sag amplitude and a fault position; solving a voltage sag domain critical point by using a differential evolution algorithm; based on the sag domain critical point, establishing a monitoring point multi-target selection model taking economical efficiency, redundancy and construction urgency minimization as a target function; solving the established monitoring point multi-target selection model by adopting a multi-target particle swarm algorithm to obtain a Pareto optimal solution set; and according to the obtained Pareto optimal solution set, adopting an ideal point method to screen out an optimal point distribution scheme. According to the method, the voltage sag domain can be accurately divided, and multi-objective optimization of economical efficiency, low redundancy and low construction urgency of monitoring point layout is realized on the premise of satisfying panoramic observability.

A voltage sag homologous identification method and system based on association rule mining, relating to the technical field of power quality mitigation. Transactions are formed by means of screened candidate homologous sag events, a transaction table is formed, a plurality of frequent itemsets are screened on the basis of the support of each itemset in the transaction table, so as to construct a canonical-order tree corresponding to the transaction table, thereby reducing the number of misleading transactions and improving the effectiveness of voltage sag homologous identification. In addition, association rules for candidate homologous sag events corresponding to every two frequent itemsets are determined by means of the canonical-order tree, waveform similarity comparison is performed on voltage waveforms corresponding to the candidate homologous sag events, and whether the two candidate homologous sag events are homologous sag events is determined, thereby improving the accuracy of voltage sag event homologous identification.

A transient stability control method and apparatus for a wind-thermal-bundled system. The method comprises: acquiring in real time terminal voltage of a doubly-fed induction generator when the wind-thermal-bundled system experiences a fault (S1); in response to the terminal voltage of the doubly-fed induction generator being within a first voltage sag interval, increasing a reactive current injection coefficient of the doubly-fed induction generator on the basis of a preset adjustment rule, to reduce the swing amplitude of a synchronous generator during an acceleration phase under fault conditions (S2); in response to the terminal voltage of the doubly-fed induction generator being within a second voltage sag interval, increasing the reactive current injection coefficient of the doubly-fed induction generator on the basis of the adjustment rule, to reduce the swing amplitude of the synchronous generator during the acceleration phase and the swing amplitude thereof during a deceleration phase under fault conditions (S3); and in response to the terminal voltage of the doubly-fed induction generator being within a third voltage sag interval, decreasing the reactive current injection coefficient of the doubly-fed induction generator on the basis of the adjustment rule, to reduce the swing amplitude of the synchronous generator during the deceleration phase under fault conditions (S4).

The invention discloses a power grid voltage stability evaluation method and system, which are applied to the field of voltage stability evaluation, and the method comprises the steps: determining a low-frequency component and a high-frequency component of each node of a target power grid; voltage sag information of the corresponding node is obtained; determining a first target node according to an analysis result of the voltage sag information; determining a high-frequency modeling mode of each node based on the voltage sag information; analyzing the high-frequency component, and determining a target frequency band; in the target frequency band, determining the corresponding node as a second target node based on an analysis result of the high-frequency operation model; and obtaining a stability evaluation result of the target power grid based on the first target node, the second target node and the topological information, and at least adjusting the switching group number of the parallel capacitor group of the target power grid according to the stability evaluation result. The power grid voltage stability assessment method and system provided by the invention can accurately assess the power grid voltage stability and provide an accurate basis for the control of the power grid voltage.

The invention relates to a GAT-based industrial user voltage sag sensitivity degree evaluation method and equipment, and the method comprises the steps: obtaining the characteristics, types and equipment connection relations of sensitive equipment influenced by voltage sag, constructing a topological graph, inputting the topological graph into a trained graph attention neural network, outputting a voltage sag sensitivity evaluation result, and carrying out the evaluation of the sensitivity degree of the industrial user voltage sag. Wherein the graph attention neural network is constructed by embedding a GAL layer in a message passing graph neural network, the GAL layer calculates an attention coefficient between nodes in a topological graph by using an attention mechanism, weighted aggregation is performed by using an update function, iterative update of node features is completed, and a voltage sag sensitivity evaluation result is finally mapped and output. Compared with the prior art, the method has the advantages of improving the evaluation accuracy and the like.

The invention relates to the technical field of electric power systems, and discloses a voltage sag source identification method, system and device, a medium and a product, and the method comprises the steps: obtaining a voltage sag waveform at a preset measurement point on a power grid line, extracting the frequency domain characteristics and time domain characteristics of the voltage sag waveform, and carrying out the recognition of a voltage sag source based on an attention mechanism; and performing weighted fusion on the frequency domain features and the time domain features, inputting weighted feature vectors into a plurality of pre-trained classifiers based on a KAN network, outputting sub-classification results of the plurality of voltage sag sources, and fusing the sub-classification results of the plurality of voltage sag sources to obtain a classification result of the voltage sag sources. Therefore, the internal association of the voltage sag source among different levels is effectively mined by using the strong nonlinear fitting capability of the KAN network and a feature sharing mechanism under a multi-task learning framework, the adaptability and classification precision of the model to a complex disturbance scene are improved, and the accuracy and reliability of voltage sag source identification are improved.

The invention provides a cooperative low-voltage ride-through control method and related device based on a network construction type and network following type three-terminal interconnection system, and the method comprises the steps: triggering a cooperative low-voltage ride-through control mechanism in response to a voltage drop fault generated at an AC side connected with a network construction type converter; performing cooperative control on each converter based on the mechanism; wherein the control network construction type converter only undertakes AC side voltage establishment and current safety survival functions, realizes current limiting control through adaptive virtual impedance, and does not participate in DC side energy adjustment of a common DC bus; the DC voltage control type grid-following converter is controlled to suppress DC voltage double-frequency fluctuation of the common DC bus, and actively absorb and compensate double-frequency power disturbance introduced by the grid-forming converter; and controlling the active power control type grid-following converter to avoid active power adjustment during the voltage drop fault period. A collaborative low-voltage ride through control mechanism is provided, the direct-current voltage fluctuation is reduced, and the overall low-voltage ride through capacity of the system is improved.