A voltage sag domain identification system based on multiple uncertainty scenario generation

Abstract

This specification discloses a voltage sag domain identification system based on multiple uncertainty scenario generation, including a processor, a photovoltaic monitoring device, a power monitoring device, and control hardware. The processor is configured to: collect photovoltaic output power information from each photovoltaic site based on the photovoltaic monitoring devices deployed on the distribution network, and train a deep convolutional generative adversarial network based on the photovoltaic output power information; generate photovoltaic output scenarios using the deep convolutional generative adversarial network; and determine the voltage sag domain identification result corresponding to the given parameters and sensitive load threshold based on the photovoltaic output scenario, given parameters, sensitive load threshold, and structural parameters of the power system. This specification improves the accuracy of scenario generation, making the voltage sag domain characterization of distributed photovoltaic access more accurate, and improving the accuracy of voltage sag domain identification.

Description

Technical Field

[0001] This specification relates to the field of voltage sag domain identification, and in particular to a voltage sag domain identification system generated based on multiple uncertainty scenarios. Background Art

[0002] The voltage sag domain refers to the set of grid fault points that cause concern and affect the production equipment of sensitive users on the bus. Currently, a variety of methods have been used to identify the voltage sag domain, such as the critical distance method, the fault point method, and the analytical method. The critical distance method is to identify the voltage sag domain by calculating the critical fault point that causes a voltage sag on sensitive loads in the distribution network and the distance between this point and the bus where the sensitive load is located. The fault point method refers to selecting some virtual fault points on the line and using the short-circuit calculation method to obtain the voltage sag amplitude information of the bus where the sensitive load is located when a short-circuit fault occurs at each fault point, so as to determine whether the virtual fault point is within the voltage sag domain of the sensitive load. The analytical method is a method for calculating the voltage sag domain based on the analytical formula of the sag amplitude, which is proposed based on the comprehensive consideration of the advantages and disadvantages of the critical distance method and the fault point method and the analysis of short-circuit faults in the power system.

[0003] The widespread integration of distributed photovoltaics today introduces uncertainty on the source side, leading to new patterns in the propagation of voltage sags. Output will be affected by multiple complex factors, including light intensity, temperature variations, and load fluctuations, resulting in volatility. Furthermore, the occurrence of voltage sag events in the distribution network is random. Therefore, in the context of distributed photovoltaic integration into the distribution network, the output fluctuations of multiple units and the randomness of voltage sag events will introduce multiple uncertainties to the distribution network, increasing the difficulty of accurately identifying the voltage sag domain. Existing studies on voltage sag domain identification often focus on deterministic power sources, assuming that the output power of distributed photovoltaics remains constant. This ignores the fact that distributed photovoltaic output is affected by the actual environment and exhibits a certain degree of randomness and time-varying properties. Furthermore, the output power of photovoltaic units is primarily related to light radiation, and the meteorological conditions in a local area are correlated. Therefore, the output of distributed photovoltaics in the same region exhibits a certain degree of temporal and spatial correlation.

[0004] Existing photovoltaic output generation often regards photovoltaic units as independent and only generates output for a single independent photovoltaic unit, ignoring the correlation between units. This leads to low accuracy of scene generation and makes existing voltage sag domain identification methods inapplicable. Summary of the Invention

[0005] One of the embodiments of the present specification provides a voltage sag domain recognition system based on multiple uncertainty scenarios, the system including a processor, a photovoltaic monitoring device, a power monitoring device and control hardware; the processor is configured to: based on the photovoltaic monitoring devices deployed at each photovoltaic site on the distribution network, collect photovoltaic output power information of each photovoltaic site, and train a deep convolutional generative adversarial network based on the photovoltaic output power information; generate photovoltaic output scenarios using the deep convolutional generative adversarial network; determine the voltage sag domain recognition result corresponding to the given parameters and sensitive load threshold based on the photovoltaic output scenario, given parameters, sensitive load threshold and structural parameters of the power system; generate a voltage reduction response instruction based on the voltage sag domain recognition result; and reduce the voltage. The response instructions include instructing the power monitoring device on the monitoring frequency, monitoring accuracy, upload interval and alarm threshold; sending the voltage reduction response instruction to the power monitoring device in the voltage sag domain; the power monitoring device is configured to: collect the power parameter sequence in the distribution network at the monitoring frequency and monitoring accuracy, and upload the power parameter sequence to the processor at the upload interval; determine whether the voltage data in the power parameter sequence is lower than the alarm threshold; in response to being lower than the alarm threshold, send an alarm signal to the processor; the processor is further configured to: determine the estimated impact load corresponding to the node where the power monitoring device is located based on the alarm signal; generate a control instruction and send it to the control hardware corresponding to the estimated impact load to control the control hardware to perform compensation work. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein:

[0007] Figure 1 This is an exemplary scenario diagram of the voltage sag domain identification system generated based on multiple uncertainty scenarios as shown in this specification;

[0008] Figure 2 A schematic diagram of a process for determining a voltage sag domain identification result by a processor as shown in this specification;

[0009] Figure 3 A schematic diagram of the flow of compensation work for the processor and control hardware shown in this specification;

[0010] Figure 4 This is a diagram of the data format for the input deep convolutional generative adversarial network shown in this specification;

[0011] Figure 5 This is a schematic diagram of the deep convolutional generative adversarial network generator model structure shown in this specification;

[0012] Figure 6This is a schematic diagram of the deep convolutional generative adversarial network discriminator model structure shown in this specification;

[0013] Figure 7 This is a schematic diagram of the Newton-Raphson method power flow calculation process shown in this manual;

[0014] Figure 8 This is a schematic diagram for calculating the voltage sag amplitude shown in this manual;

[0015] Figure 9 This is a schematic diagram of the golden section search process shown in this manual. DETAILED DESCRIPTION

[0016] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0017] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0018] Flowcharts are used throughout this specification to illustrate the operations performed by systems according to embodiments of this specification. It should be understood that preceding or following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0019] It should be noted that, unless there is a conflict, the embodiments in this application and the features described in the embodiments can be combined with each other. The application is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0020] refer to Figure 1 This specification provides a voltage sag domain identification system based on multiple uncertainty scenarios, which may include a processor 10, a photovoltaic monitoring device 20, a power monitoring device 30, and control hardware 40.

[0021] The processor 10 is used to process data and / or information obtained from the photovoltaic monitoring device 20, the power monitoring device 30, and the control hardware 40. In some embodiments, the processor 10 may include one or more hardware processors 10, such as a central processing unit, a programmable logic device, etc.

[0022] The photovoltaic monitoring device 20 is a device for monitoring the working status of each photovoltaic site (e.g., photovoltaic group). In some embodiments, the photovoltaic monitoring device 20 may include but is not limited to a smart meter, a voltage / power sensor, a photovoltaic array monitor, etc.

[0023] In some embodiments, the photovoltaic monitoring device 20 can be used to collect photovoltaic output power information of each photovoltaic site.

[0024] The power monitoring device 30 is provided in the power distribution network and is used to obtain the operation information of the power distribution network (eg, voltage, current, etc.). In some embodiments, the power monitoring device 30 may include but is not limited to a voltage transformer, a current transformer, and a smart meter.

[0025] The control hardware 40 is a device for compensating the load. In some embodiments, the control hardware 40 may include one or more of a backup power supply, a dynamic voltage regulator, and a load switch.

[0026] In some embodiments, the processor 10 , the photovoltaic monitoring device 20 , the power monitoring device 30 and the control hardware 40 may be connected to each other via wired or wireless communication.

[0027] like Figure 1 As shown, in some embodiments, the processor 10 is configured to perform one or more of the following steps:

[0028] Step 110 : Based on the photovoltaic monitoring device 20 deployed at each photovoltaic site on the power distribution network, the photovoltaic output power information of each photovoltaic site is collected, and a deep convolutional generative adversarial network is trained based on the photovoltaic output power information.

[0029] In some embodiments, the photovoltaic output power information is the output power corresponding to each photovoltaic site. In some embodiments, the processor 10 can collect photovoltaic output power information of each photovoltaic site over a period of time (such as one year) through the photovoltaic monitoring device 20.

[0030] In some embodiments, processor 10 trains a deep convolutional generative adversarial network based on photovoltaic output power information, so that the trained deep convolutional generative adversarial network can generate photovoltaic output scenarios, thereby simulating multiple uncertain scenarios in the power distribution network. The photovoltaic output scenarios include photovoltaic output power, and the adversarial network can generate photovoltaic output scenarios that are more comprehensive than actual photovoltaic output scenarios.

[0031] The specific process of generating photovoltaic output scenarios using Deep Convolutional GAN ​​(DCGAN) is as follows:

[0032] First, preprocess the data: In this manual, the input data for generating photovoltaic output scenarios is the photovoltaic output power information of N sites for one year. Assuming that there are 365 days in a year, the data format of the photovoltaic output power information of N sites for one year is converted into a three-dimensional matrix, and the data size is expressed as N×T×D, where N is the total number of photovoltaic sites; T is 24, indicating 24 hours of data; D is 365, indicating that there are 365 days in a year. In addition, the historical photovoltaic data is divided into rainy season photovoltaic data and dry season photovoltaic data. The photovoltaic power information of all sites on each day can be recorded as {x n,t} in the form of a two-dimensional matrix, where n is the number of sites, t represents the time, and x n,t Represents the photovoltaic output power information of the nth site at time t. The input matrix form is shown in formula (1):

[0033]

[0034] Before inputting data into the model, it is necessary to perform feature scaling on the data, that is, mapping the original data to a specific range, removing the unit and unifying the dimension, and turning it into a pure data sample, that is, normalizing and standardizing the data. Data normalization is to limit the data to a certain range, usually mapping the data to the range of -1 to 1 or 0 to 1. The former is also called Min-Max normalization. The commonly used Min-Max normalization calculation formula is shown in formula (2):

[0035]

[0036] The data scaling method used by the scene generation model is Min-Max normalization. The data format obtained after the above operation is shown in formula (2).

[0037] Generative Adversarial Network is a deep learning framework that represents a class of generative models. The structure of the generative adversarial network model is as follows: Figure 3 As shown in the figure, unlike the structure of a typical neural network, a generative adversarial network (GAN) is an adversarial framework consisting of two interconnected neural networks. These two networks are generally composed of deep networks. One network, called the Generative Network, is used to learn the unknown distribution of data samples and hopes that the generated samples can deceive the true and false judgment of the discriminator network; the other network, called the Discriminative Network, is used to distinguish between the real input samples and the generated samples as much as possible.

[0038] The training goal of the generator is to make the probability distribution P of the generated sample G(z) G As close as possible to the probability distribution P of the real sample x r The training goal of the discriminator is to determine whether its input is a real sample or a generated sample as accurately as possible, and the discrimination result will be fed back in the form of a gradient function to optimize the network structure of the generator and discriminator.

[0039] During the training process of these two networks, one side is fixed to update the parameters of the other side, and this process is repeated iteratively. The discriminator network feeds back the judgment results of the input samples to the generator network, so that the generator network continuously adjusts its own parameters to generate more realistic samples. The discriminator network adjusts its own parameters based on the continuously generated samples to better discover the differences in the input samples. The generator network continuously improves the quality of the generated samples, while the discriminator network continuously improves its discrimination ability. After the above-mentioned adversarial training, the generator network finally captures the potential distribution of the real data and reaches a Nash equilibrium state, that is, the discriminator D cannot determine whether its input is a real sample or a generated sample. At this time, it can be considered that the generator G has learned the probability distribution of the real sample, that is, the generated sample G(z) of the generator G and the real sample both obey the probability distribution P r .

[0040] The generator (G) and discriminator (D) of the generative adversarial network are not expressed in the form of explicit functions, and the choice of network structure is very flexible. For the convenience of expression, it is necessary to define the relevant symbols. The distribution law of historical data x is denoted as P r , and define a noise variable z. This noise variable is usually derived from an existing simple distribution P z The sampling is performed using a Gaussian distribution or a uniform distribution.

[0041] The generator performs upsampling through a fully connected layer network and transposed convolution, mapping the noise variable z to a generated data space G(z), and denoting its data distribution as P G Because the noise input to the generator is a random variable, each time a new noise z is input, the output is also a new variable. The input to the discriminator is either a real sample x or a generated sample G(z). The input sample is downsampled through the fully connected layer network, and the discriminator outputs a probability value to judge the input sample.

[0042] The goal of the Generative Adversarial Network is to generate realistic samples so that the discriminator network cannot distinguish between true and false. To achieve this goal, it is necessary to define the loss function L for the generator network training. G and the loss function L for discriminator network training GWhen the discriminator network is fixed and the generator network is trained, the probability of the generated sample G(z) should be larger, and the loss function L G Therefore, the generator network can use the loss function defined by formula (2):

[0043]

[0044] The training goal of the discriminator network is to distinguish P as much as possible. r and P G When the parameters θ of the generator network are fixed G , update the discriminator network parameters θ D When , the greater the difference in discrimination, the stronger the judgment ability of the discriminator network, that is, maximizing the difference between E[D(·)] and E[D(G(·))]. According to the basic principle of generative adversarial networks, when the discriminator network can distinguish the input samples well, its loss function L D Therefore, the loss function of the discriminator network can be defined as formula (3):

[0045]

[0046] The zero-sum game between the two networks is denoted as V(D,G). To optimize the loss function, each network must update its own network parameters based on the updates of the other network. The two networks are trained alternately, updating their own parameters until the adversarial network reaches a Nash equilibrium. When the training converges, a pair of optimal parameters is obtained. Because there are multiple extreme points in the high-dimensional data space, the parameters at this time and are the two extreme points of V(D,G). The principle of generative adversarial network is a minimax optimization problem, which can be defined as follows:

[0047]

[0048] Where V(D,G) represents a binary cross entropy function, the ultimate goal of which is to minimize the probability distribution P of the generated samples. G And the true sample probability distribution P r JS between ( Jensen-Shannon ) divergence.

[0049] DCGAN combines convolutional neural networks to process images. The network structures of the DCGAN generator model and the discriminator model are as follows: Figure 4 and Figure 5 shown.

[0050] Compared with traditional generative adversarial networks (GANs), DCGAN has undergone structural modifications, which can make the combination of GAN and CNN in DCGAN more stable. The characteristics of deep convolutional generative adversarial networks include: using fully convolutional networks, eliminating fully connected layers, and using batch normalization.

[0051] Use a fully convolutional network: Using strided convolution instead of deterministic spatial pooling function (maxpooling) allows the network to learn its own spatial downsampling. Using this approach in the generator allows it to learn its own spatial upsampling and discriminator.

[0052] Eliminating fully connected layers: The most powerful example is global average pooling, which has been used in state-of-the-art image classification models. Global average pooling improves model stability but hurts convergence speed. A middle ground of connecting the top convolutional features directly to the input and output of the generator and discriminator, respectively, works well. The first layer of a GAN takes uniform noise Z as input and can be called fully connected because it is just a matrix multiplication, but the result is reshaped into a 4D tensor and used as the beginning of a convolutional stack. For the discriminator, the last convolutional layer is flattened and then fed into a single sigmoid output.

[0053] Use batch normalization: Transform the input of each unit to have zero mean and unit variance to stabilize learning. This has proven to be a very important means of accelerating convergence and mitigating overfitting in deep learning. This helps deal with training issues that arise from improper initialization and helps gradients flow in the updated model. It turns out that this is crucial for getting the deep generator to start learning, preventing the generator from collapsing all samples to a single point, a common failure mode observed in GANs. However, directly applying batch normalization to all layers can lead to sample oscillations and model instability, so batch normalization is only used on the output layer of the generator and the input layer of the discriminator.

[0054] Step 120, generating a photovoltaic output scenario using a deep convolutional generative adversarial network;

[0055] In some embodiments, after performing the data preprocessing in step 110, the processor may use randomly sampled noise as input to the DCGAN generator and the historical output data of each PV site as input to the discriminator. The deep convolutional generative adversarial network is trained using the training data until a Nash equilibrium is reached. Upon completion of DCGAN training, a PV output scenario generated by the generator is obtained that is similar to the real data.

[0056] Step 130 : Based on the photovoltaic output scenario, given parameters, sensitive load thresholds, and structural parameters of the power system, a voltage sag domain identification result corresponding to the given parameters and the sensitive load thresholds is determined.

[0057] In some embodiments, the given parameters may be power system distribution network parameters or given distribution network parameters. The given parameters may include resistance, reactance, conductance, susceptance, reactive power, active power, generator parameters, transformer parameters, transmission line parameters, load parameters, etc.

[0058] Sensitive loads are electrical devices (loads) in a power distribution network that may malfunction or experience reduced functionality due to voltage fluctuations or sudden changes. A brief drop in voltage may affect the normal operation of sensitive loads, potentially causing damage or production interruptions. In some embodiments, the sensitive load threshold can be set based on experience or the actual requirements of the power distribution network. When the operating voltage of a sensitive load falls below the sensitive load threshold, it indicates that the operation of the sensitive load may be affected.

[0059] In some embodiments, the structural parameter of the power system may be a topological parameter of the power system.

[0060] The voltage sag domain identification result is the voltage sag domain under the current PV output scenario. The voltage sag domain identification result may include one or more fault points corresponding to sensitive loads. Sensitive loads are electrical equipment that are affected by voltage and thus fail.

[0061] In some embodiments, the processor 10 may determine, using a preset formula or algorithm, multiple voltage sag domains corresponding to given distribution network parameters and sensitive load thresholds based on the photovoltaic output scenario, given parameters, sensitive load thresholds, and structural parameters of the power system, and determine a voltage sag domain identification result based on the multiple voltage sag domains. For more information on determining the voltage sag domain identification result based on the multiple voltage sag domains, please refer to the relevant description below.

[0062] Step 140: Generate a voltage reduction response instruction based on the voltage sag domain identification result.

[0063] In some embodiments, the voltage drop response instruction includes instructions for the power monitoring device 30's monitoring frequency, monitoring accuracy, upload interval, and alarm threshold. Based on the location of the voltage sag domain corresponding to the voltage sag domain identification result, the processor 10 can generate a voltage drop response instruction for the power monitoring device 30 at that location. In some embodiments, the power monitoring device 30 can increase the intensity of its monitoring of the power distribution network based on the voltage drop response instruction.

[0064] In some embodiments, the monitoring frequency refers to the number of times the power monitoring device 30 collects relevant power parameters within a preset time period (e.g., within one minute), the monitoring accuracy refers to the amount of data collected by the power monitoring device 30 during a single collection, and the upload interval refers to the interval between two consecutive uploads of the collected relevant power parameters by the power collection device. For example, a voltage reduction response instruction may include instructing the power monitoring device 30 to collect relevant power parameters once per second and upload the data to the processor 10 every 30 seconds.

[0065] In some embodiments, the alarm threshold is a threshold used by the power harvesting device to determine whether an alarm should be issued, and can be determined by an expert. For example, when the power harvesting device is performing data collection, if the voltage value in the collected data is less than the alarm threshold, the power harvesting device immediately uploads the current data without waiting for the next upload cycle and may also send an alarm signal to the processor 10 as appropriate.

[0066] Step 150: Send the voltage reduction response instruction to the power monitoring device 30 in the voltage sag domain.

[0067] In some embodiments, the processor 10 may determine a plurality of power monitoring devices 30 within a voltage sag domain according to the location of the power distribution network, and send a voltage reduction response instruction to the power monitoring devices 30 .

[0068] refer to Figure 2 In some embodiments, after receiving the voltage reduction response instruction, the power monitoring device 30 is configured to perform one or more of the following steps:

[0069] Step 210 : Collect the power parameter sequence in the power distribution network at the monitoring frequency and the monitoring accuracy, and upload the power parameter sequence to the processor 10 at the upload interval.

[0070] In some embodiments, the relevant power parameters collected by the power monitoring device 30 can be used to construct a power parameter sequence in chronological order, and the elements in the sequence correspond to the collected parameter values.

[0071] Step 220: Determine whether the voltage data in the power parameter sequence is lower than the alarm threshold.

[0072] In some embodiments, when the voltage data in the power parameter sequence is lower than an alarm threshold, it indicates that sensitive loads may be affected and require further processing.

[0073] Step 230 : In response to the value being lower than the alarm threshold, sending an alarm signal to the processor 10 .

[0074] The alarm signal is used to remind affected users (loads) to adjust the power consumption characteristics of sensitive loads, for example, to remind users to turn off sensitive loads, reduce the load of sensitive loads, etc. For more description of the alarm threshold, please refer to the relevant content of step 150 above.

[0075] In some embodiments, in order to reduce the impact on sensitive loads, after receiving the alarm signal, the processor 10 is further configured to perform one or more of the following steps:

[0076] Step 240 : Determine the estimated impact load corresponding to the node where the power monitoring device 30 is located based on the alarm signal.

[0077] The estimated impacted loads are one or more sensitive loads expected to be affected within the voltage sag domain. In some embodiments, the processor 10 can determine the estimated impacted load corresponding to the node where the power monitoring device 30 is located based on the alarm signal and the location relationship between the power monitoring device 30 and the sensitive loads in the power distribution network. For example, all sensitive loads on a certain line within the voltage sag domain can be considered as the estimated impacted loads.

[0078] Step 250 : Generate a control instruction and send it to the control hardware 40 corresponding to the estimated impact load to control the control hardware 40 to perform compensation work.

[0079] In some embodiments, the control instructions may include operating parameters or instructions for different devices, depending on the actual situation of the control hardware 40. Compensation is to control the control hardware 40 to operate based on the operating parameters in the control instructions, thereby compensating for the estimated impact load to reduce the impact on sensitive loads.

[0080] In some embodiments, the control hardware 40 may include one or more of a backup power supply, a dynamic voltage regulator, and a load switch; and the control instructions include one or more of a backup power supply instruction, a voltage self-regulation instruction, and a switch instruction.

[0081] The backup power supply is configured to: after receiving the backup power supply instruction, provide power supply corresponding to the estimated affected load; the dynamic voltage regulator is configured to: after receiving the voltage self-adjustment instruction, provide a compensation voltage corresponding to the estimated affected load; the load switch is configured to: after receiving the switch instruction, control the on and off of the estimated affected load and the distribution network.

[0082] The estimated impact loads in the voltage sag region are processed accordingly by the control hardware 40, so that in some cases, sensitive loads can continue to operate normally or damage to sensitive loads caused by voltage fluctuations can be avoided.

[0083] This specification proposes a voltage sag domain recognition system based on multiple uncertainty scenarios. It utilizes a deep convolutional generative adversarial network to track and simulate photovoltaic output characteristics, focusing on the inherent laws of distributed photovoltaic output and exploring the spatiotemporal correlations of the outputs of multiple distributed photovoltaic units. By accounting for the randomness and correlation of distributed photovoltaic unit output, it generates artificial data with the same dimensions and similar probability distribution as the original photovoltaic output data.

[0084] In some embodiments, the processor 10 is further configured to perform one or more of the following steps:

[0085] Based on the photovoltaic output scenario, the Newton-Raphson method is used to calculate the power flow to determine the voltage of each node in the distribution network before the fault.

[0086] Obtain the current bus from the distribution network lines. Based on given parameters, calculate the impedance matrix of each node in the distribution network by adding branches or inverting the admittance matrix. Furthermore, based on the voltage of each node before the fault and the impedance matrix of each node, determine the voltage sag amplitude at the node where the sensitive load is located when different types of short-circuit faults occur at each node on the current bus.

[0087] Determine the voltage sag amplitude vector of the bus node based on the voltage sag amplitude at the node where the sensitive load is located when different types of short-circuit faults occur at each node of the current bus; compare the voltage sag amplitude vector of the bus node with the sensitive load threshold to obtain a difference vector; and obtain the line association vector based on the difference vector;

[0088] Based on the line correlation vector, determine whether the current bus meets the analysis conditions;

[0089] In response to the condition not being satisfied, the current bus is not within the voltage sag region, and the next line is selected from the power distribution network as the current bus to continue the determination;

[0090] In response to satisfying the following conditions: the current bus is analyzed using the Newton quadratic interpolation method to obtain an analytical expression for the voltage sag amplitude and a fault voltage equation for the current bus; and based on the fault voltage equation, the portion of the current bus within the voltage sag domain is obtained, and the next line in the distribution network is selected as the current bus for further determination;

[0091] When the traversal and iteration of all lines in the distribution network are completed, multiple voltage sag domains corresponding to the given parameters and sensitive load thresholds are obtained, and the union of the multiple voltage sag domains is the voltage sag domain identification result.

[0092] In some embodiments, determining the voltage of each node of the power distribution network before a fault using the Newton-Raphson method power flow calculation method includes:

[0093] After the deep convolutional generative adversarial network generates the photovoltaic output scenario, the voltage at each node before the fault is calculated using the Newton-Raphson method. The Newton-Raphson method is a numerical method for efficiently solving nonlinear equations. When solving power flow calculation problems, the Newton-Raphson method is mainly used for solution calculation, and the function is gradually linearized using the Taylor series. This method has the characteristics of fast convergence speed and small error, and is an efficient method for solving complex nonlinear equations. Assume that the expression of the n-dimensional nonlinear equation system is:

[0094]

[0095] By linearly expanding the stepwise objective function through the first-order Taylor equation, we can obtain the equation:

[0096]

[0097] Will and Y ij Substituting the power equations of active power and reactive power, we obtain the corresponding nonlinear equation expression of the power network:

[0098]

[0099] Further optimization calculations can yield the modified equation based on the Newton-Raphson method:

[0100]

[0101] Where: is the node voltage; Y ij =G ij +jB ij is the node admittance.

[0102] like Figure 6 As shown, the calculation process is as follows:

[0103] Based on the clear grid structure parameters, the actual data is substituted into the admittance matrix to form the admittance matrix, and the offset of each parameter (such as node voltage, reactive power, active power, etc.) is calculated according to the given initial value.

[0104] If the error meets the required accuracy, the loop is exited and the result is output. If the error does not meet the required accuracy, the Jacobian matrix is ​​solved and the voltage is corrected using the corrected equations. The loop ends and the result is output. Otherwise, the loop continues.

[0105] In some embodiments, the processor 10 is further configured to:

[0106] First, based on the given parameters, the impedance matrix of each node in the network is calculated by adding branches or inverting the admittance matrix. Then, the voltage sag amplitude of the node where the sensitive load is located when different types of short-circuit faults occur at each node is obtained according to formulas (9) to (15). Figure 7 As shown in Figure 1, it is a schematic diagram for calculating the voltage sag amplitude.

[0107] In some embodiments, different types of short circuit faults include three-phase short circuit fault, single-phase ground short circuit fault, two-phase short circuit fault and two-phase ground short circuit fault. Assume that there is a fault point K:

[0108] When a three-phase short circuit fault occurs at the fault point K, since it is a symmetrical balanced fault, only the positive sequence is considered, and the three-phase voltage sag amplitudes at the sensitive load node S are the same. The voltage sag amplitude of one phase is:

[0109]

[0110] Where: is the voltage sag amplitude at point S; is the positive sequence self-impedance; is the positive sequence mutual impedance; is the voltage before the fault at point S; is the voltage before the fault at point K.

[0111] From formula (9), we can see that the voltage sag amplitude at point S is This is related to the system's structural parameters and pre-fault operating status. The pre-fault operating status refers to whether the distribution network is operating normally, which can be determined through pre-fault power flow calculations. When an asymmetrical short circuit occurs at fault point K, with phase A being the special phase, the symmetrical component method is required for analysis.

[0112] When a single-phase ground short circuit fault occurs at fault point K with phase A as the special phase, the voltage sag amplitudes at point S are as follows:

[0113]

[0114] When a two-phase short circuit fault occurs on phases B and C, the three-phase voltage sag amplitudes at point S are as follows:

[0115]

[0116] When a two-phase ground short circuit fault occurs on phases B and C, the three-phase voltage sag amplitudes at point S are as follows:

[0117]

[0118] In formulas (9) to (12): are the three-phase voltage sag amplitudes at the sensitive node S respectively; are the positive, negative and zero sequence self-impedance and mutual impedance; α=e j120° is the rotation factor.

[0119] When a short-circuit fault occurs on the system bus, its self-impedance and mutual impedance can be directly called from the node impedance matrix; however, when a short-circuit fault occurs at a certain point on the line, its self-impedance and mutual impedance need to be calculated by introducing the position variable p (0≤p≤1) and combining the node impedance matrix. Point S is the bus node where the sensitive load is located, and Z C is the sequence impedance of line FT. When the fault point K moves on line FT, its three-sequence self-impedance and the three-sequence mutual impedance between the fault point K and S Both can be represented by the impedance matrix Z and the position variable p:

[0120]

[0121]

[0122] Where: are the sequence self-impedances of the system bus nodes F and T respectively; They are the sequence mutual impedances of the system bus nodes F and T, the sequence mutual impedances between the bus F and the sensitive load node S, and the sequence mutual impedances between the bus T and the sensitive load node S, which can all be called from the system node impedance matrix; is the line sequence impedance between nodes F and T.

[0123] In addition, the voltage before the fault occurs at the fault point K It can be represented by the fault location variable p:

[0124]

[0125] Therefore, the voltage sag amplitude at point S can be expressed by the pre-fault voltage and the sequence impedances. Substituting Equations (13) to (15) into Equations (9) to (12), we obtain the analytical expression U(p) for the voltage sag amplitude at point S with respect to the position variable p when any short-circuit fault occurs at any fault point.

[0126] In some embodiments, determining the line association vector based on the voltage sag amplitude at the node where the sensitive load is located when different types of short-circuit faults occur at each node of the current bus includes:

[0127] The voltage sag amplitude vector of the node where the sensitive load is located is obtained from the above. The node determination vector B and line association vector L are calculated according to formula (11), and all lines are traversed one by one.

[0128] Calculate the voltage sag amplitude of sensitive load node S when each busbar short circuit fault occurs, and form the n-dimensional vector of busbar node voltage sag amplitude And compare it with the sensitive load voltage sag threshold to get the difference vector ΔU S .

[0129]

[0130] By judging ΔU S The positive or negative value of the vector elements can tell whether each node is within the temporary drop region of the sensitive node. Therefore, the node judgment vector B is introduced:

[0131]

[0132] B i =1 means that busbar i is within the voltage sag range corresponding to the sensitive load; B i = 0 means that busbar i is outside the voltage sag domain corresponding to the sensitive load. Therefore, in order to determine whether each line is included in the voltage sag domain, the line correlation vector L is introduced:

[0133]

[0134] Where: B i_F and B i_T It is the determination factor of busbar sag of connected line.

[0135] In some embodiments, based on the line association vector, it is determined whether the current bus satisfies the analysis conditions. In response to not satisfying the conditions, the current bus is not within the voltage sag domain, and the next line is selected from the distribution network as the current bus. In response to satisfying the conditions: the current bus is analyzed by Newton's quadratic interpolation method to obtain the analytical expression of the voltage sag amplitude and the fault voltage equation of the current bus; and, based on the fault voltage equation, the portion of the current bus within the voltage sag domain is obtained, and the next line is selected from the distribution network as the current bus.

[0136] The analysis conditions include: If L i =0, indicating that the line is not in the voltage sag region, and the next line is calculated directly; if L i =1, indicating that one of the first and last nodes of this line is in the temporary sag region, so it can be known that part of line i is in the temporary sag region and there is a unique critical point on the line; if L i =2, indicating that the first and last nodes of this line are both within the voltage sag region. The golden section search method is first used to solve the maximum value U of the voltage sag amplitude curve. max and compare it with the sensitive load voltage sag threshold U th Compare. If U max th ​, indicating that this line is completely in the temporary drop region and there is no critical point, then directly calculate the next line; if U max ≥U th , indicating that the line section i is located in the temporary sag region and there are two critical points on the line.

[0137] The whole process of the golden section search method is to find p a ≤p≤p b (p a =0,p b =1) in which the voltage sag at the PCC point is the maximum value. max . Use p max As an interpolation point, it can ensure that the interpolation curve passes through the maximum value of the voltage sag amplitude, providing a good initial value point for the secant iteration. Figure 8 shown.

[0138] If the current busbar meets the analysis conditions, calculate the critical point.

[0139] The critical point refers to the fault location in the distribution network that causes the voltage sag amplitude at the busbar where the sensitive load is located to be equal to the voltage sag threshold of the sensitive load. i =1, 2, calculate the critical point. i =1, directly use (0,U F )、(0.5,U 0,5 ) and (1,U T )3 points as interpolation points, and the voltage sag amplitude analytical expression U(p) and the fault voltage equation are obtained by Newton quadratic interpolation method. L i =2, use (0,U F )、(p max ,U max ) and (1,U T )3 points are used as interpolation points for the Newton quadratic interpolation method to obtain the analytical expression for the voltage sag amplitude and the fault voltage equation.

[0140] Then the root p of the above fault voltage equation is ia As the initial iteration value of the secant iteration method, the accurate critical point position is obtained through iteration. The iterative expression of the critical fault distance based on the secant iteration method is as follows:

[0141]

[0142] Its convergence conditions are:

[0143] ||U(p k+1 )|-U th |<ε (20)

[0144] The secant iteration method is an algorithm that approximates the exact root and does not require the calculation of the differential of the voltage sag amplitude equation of the sensitive load. Therefore, it is more efficient than the Newton iteration method.

[0145] When the traversal and iteration of all lines in the distribution network are completed, multiple voltage sag domains corresponding to the given parameters and sensitive load thresholds are obtained. The union of the multiple voltage sag domains is the voltage sag domain identification result corresponding to the photovoltaic output scenario.

[0146] The voltage sag domain identification system described in this manual, which is based on the generation of multiple uncertainty scenarios, uses the short-circuit calculation as the basis, and uses the quadratic interpolation method and the numerical solution of nonlinear equations to optimize the sag domain calculation process, classify and calculate different lines, and reduce the calculation steps.

[0147] Compared with the existing voltage sag domain identification method, this method takes into account the impact of the dynamic output of distributed photovoltaic units on the voltage sag characteristics, as well as the randomness and spatiotemporal correlation of photovoltaic output itself, thereby improving the accuracy of scene generation, making the voltage sag domain characterization of distributed photovoltaic access more accurate, and improving the accuracy of voltage sag domain identification.

[0148] The processor 10 may also directly determine the voltage sag domain identification result through a machine learning model. In some embodiments, the processor 10 is further configured to:

[0149] Based on given parameters, power parameter sequence, PV output power information, line basic data, future sunlight data and sensitive load thresholds, a power characteristic map is constructed; the power characteristic map is input into the voltage sag risk model to obtain the voltage sag risk area; and multiple voltage sag domains corresponding to the given parameters and sensitive load thresholds within the voltage sag risk area are calculated to determine the voltage sag domain identification result.

[0150] In some embodiments, the line basic data is the line characteristics of the distribution network, which can be determined by accessing the distribution network configuration information. The line basic data may include one or more of the line physical data, the type of each intersection, the intersection connection method, the load type, and the photovoltaic equipment type. In some embodiments, the future light data includes the light intensity at different times within a period of time (such as within a day), and the future light data can be obtained by accessing an external weather database. For more descriptions of given parameters, power parameter sequences, photovoltaic output power information, and sensitive load thresholds, please refer to the relevant content above.

[0151] A power signature graph is a graph consisting of nodes and the edges between them. In some embodiments, the nodes of the power signature graph include sensitive load nodes, historical fault nodes, line intersection nodes, and photovoltaic access nodes. A historical fault node is a node where a fault has occurred in the past; a line intersection node is a node at the intersection of a busbar and a branch line in a distribution network.

[0152] In some embodiments, the attributes of the nodes in the power characteristic graph may include power parameters, historical fault records, and regional environmental data.

[0153] The power parameters are the current and historical voltage, current, etc. of the node. The power parameters can be obtained based on the power parameter sequence corresponding to the node.

[0154] The historical fault records may include the cause of the fault, the type of fault, and the time of the fault. The historical fault records can be obtained by reading the running database. If the node has never experienced a fault, the historical fault records may be empty.

[0155] Regional environmental data refers to the environmental data of the region where the node is located. The regional environmental data may include temperature, precipitation, etc., and can be obtained through sensors or by accessing an external weather database.

[0156] In some embodiments, the nodes in the power characteristic graph may further include additional node attributes according to the types of the nodes.

[0157] In some embodiments, when the node is a sensitive load node, the node attributes may further include: load type, historical voltage sag records, and sensitive load threshold.

[0158] The load type indicates the type of specific load connected to the node (such as whether the electrical equipment is a CNC machine tool, a server, or an X-ray machine, etc.). The load type can be obtained by accessing the database.

[0159] Historical voltage sag records are records of voltage sags corresponding to performance degradation or failure of sensitive load equipment. The voltage sag records may include the cause of the sag (such as the type of fault), sag amplitude, sag duration, sag occurrence time, etc. The historical voltage sag records can be obtained by accessing the operation database.

[0160] In some embodiments, when the node is a line intersection node, the node attributes may also include: intersection type (such as T-type, cross type), intersection connection method (such as direct connection, connection through a switch device, or connection through a transformer), and distribution power parameters; wherein, the intersection type and intersection connection method can be obtained by accessing a database, and the distribution power parameters may include information such as voltage and current corresponding to the upstream and downstream lines of the node, which can be obtained through a power parameter sequence.

[0161] In some embodiments, when the node is a photovoltaic access node, the node attributes may also include: photovoltaic output power information, historical sunlight data, photovoltaic device type, and future sunlight data. Similar to future sunlight data, historical sunlight data can also be obtained by accessing an external weather database.

[0162] In some embodiments, the edges of the power profile graph correspond to power lines between nodes. In some embodiments, the edges of the power profile graph may have a direction consistent with the current in the power line. The attributes of the edges in the power profile graph may include line physical data (such as the length, cross-section, and material of the power line) and line power parameters in the power parameters. The line physical data and power parameters may be obtained by accessing a database.

[0163] In some embodiments, the voltage sag risk model may be a GNN (Graph Neural Networks), which can be trained using training data. The input of the voltage sag risk model is the power characteristic map, and the output of the model is the voltage sag risk area.

[0164] In some embodiments, a voltage sag risk model can be trained using multiple labeled training data. Specifically, the multiple labeled training data can be input into the voltage sag risk model. A loss function is constructed using the labels and the results of the initial voltage sag risk model. Based on the loss function, the parameters of the initial voltage sag risk model are iteratively updated using gradient descent or other methods. Model training is completed when preset conditions are met, resulting in a trained voltage sag risk model. Preset conditions may include convergence of the loss function or a threshold number of iterations.

[0165] In some embodiments, the training samples include a sample power characteristic graph constructed based on sample given parameters, a sample power parameter sequence, sample photovoltaic output power information, sample line basic data, sample future sunlight data, and sample sensitive load thresholds. Similar to the power characteristic graph, the sample power characteristic graph is a graph consisting of nodes and edges between nodes. The nodes of the sample power characteristic graph include sample sensitive load nodes, sample historical fault nodes, sample line crossing nodes, and sample photovoltaic access nodes; the edges of the sample power characteristic graph are edges between sample nodes.

[0166] In some embodiments, the label corresponding to the training sample is the area of ​​the voltage sag domain corresponding to the sample sensitive load, and the label can be determined based on the actual scenario corresponding to the sample power characteristic diagram or determined through software simulation.

[0167] In some embodiments, after the voltage sag risk model outputs the voltage sag risk area, the processor 10 can determine whether the bus within the voltage sag risk area meets the analysis conditions based on the method described above, obtain multiple voltage sag domains, and then obtain a voltage sag domain identification result.

[0168] The voltage sag risk model is used to determine the voltage sag risk area with a relatively high voltage sag risk, so that the processor 10 does not need to traverse all lines in the power distribution network, which greatly improves the speed of determining the voltage sag domain identification result and improves the response rate of the system.

[0169] In some embodiments, the processor 10 is further configured to determine a sensitive load threshold based on the load type, load aging, and load rating of the sensitive load. In some embodiments, the load aging can be represented by the accumulated operating hours of the sensitive load, and the load type and load rating can be determined by accessing a database.

[0170] In some embodiments, the processor 10 can construct a sensitive load characteristic vector based on the load type, load aging degree, and load rated parameters of the sensitive load. The load type, load aging degree, and load rated parameters can respectively correspond to a dimension of the sensitive load characteristic vector. In some embodiments, the sensitive load characteristic vector can also include other dimensions, such as the dimension corresponding to the current operating temperature of the load.

[0171] In some embodiments, the processor 10 may determine a sensitive load threshold by performing vector matching in a vector database based on the sensitive load feature vector. The vector database is constructed by multiple sets of reference sensitive feature vectors and corresponding reference sensitive load thresholds. The processor 10 may match the sensitive load feature vector with a matching reference sensitive feature vector and use the reference sensitive load threshold corresponding to the reference sensitive feature vector as the sensitive load threshold.

[0172] In some embodiments, the vector matching method can be to select the reference sensitive feature vector with the closest vector distance (such as Euclidean distance or cosine distance, etc.) as the matching reference sensitive feature vector. In some embodiments, other vector matching methods can also be used, such as fast similarity search, etc.

[0173] In some embodiments, multiple sets of reference sensitive feature vectors and corresponding reference sensitive load thresholds in a vector database can be obtained in the following manner: first, conduct experiments on the reference sensitive load and record its sensitive load type, load aging degree, and load rated parameters to construct a reference sensitive feature vector; then, during the experiment, conduct experiments on the reference sensitive load with voltage sags of varying magnitudes, and record the sensitive load threshold corresponding to the load as the reference sensitive load threshold. For example, assuming that the rated voltage of the reference sensitive load is 220V, its operating voltage can be gradually reduced, such as to 219V, 218V, etc. for experimentation. If it is found that the sensitive load does not operate normally (or exhibits an abnormality) when the voltage is lower than 215V, the reference sensitive load threshold is 215V.

[0174] By building a vector database, factors such as sensitive load type and load aging degree can be taken into account, and the sensitive load threshold can be determined more conveniently and accurately.

[0175] In order to obtain a voltage sag risk model with better performance and improve the learning effect of the training data, in some embodiments, the processor 10 may use a two-stage training method to train the voltage sag risk model.

[0176] In some embodiments, the training process of the voltage sag risk model includes an initial training phase and an intensive training phase respectively performed using training data; the training data used in the initial training phase and the intensive training phase are consistent with those described above, that is, the training data include training samples and labels corresponding to the training samples; the training samples include sample power characteristic maps constructed based on sample given parameters, sample power parameter sequences, sample photovoltaic output power information, sample line basic data, sample future illumination data, and sample sensitive load thresholds, and the labels corresponding to the training samples are the areas of the voltage sag domain corresponding to the sample sensitive loads.

[0177] The difference between the training data used in the initial training phase and the intensive training phase lies in the different data sources used to construct the training data. In some embodiments, the initial training phase uses a general dataset acquired from a cloud platform for training, while the intensive training phase uses data collected from the actual distribution network for training.

[0178] The training data used in the initial training phase comes from the cloud platform, which may contain distribution network data sets under multiple different scenarios, different scales, different weather conditions, etc., so that the processor 10 can quickly obtain a large amount of training data used in the initial training phase, and at the same time, the trained model has good generalization ability and can better identify and handle voltage sag risks.

[0179] The training data used in the enhanced training phase comes from data actually collected from the distribution network, making the data used in training closer to actual application scenarios and improving the performance of the model in practical applications.

[0180] In some embodiments, the number of samples corresponding to power grids of different complexity levels in the training data of the initial training phase is not less than a preset threshold, and the preset threshold is determined based on the complexity of the corresponding power grid. In some embodiments, the preset threshold may be positively correlated with the complexity of the power grid.

[0181] In some embodiments, a more complex power grid corresponds to more samples (such as data collected within 10 days of the power grid), and a less complex power grid corresponds to fewer samples (such as data collected within 3 days of the power grid), so that the model in the initial training stage has more samples to learn from the more complex power grid, thereby ensuring the generalization ability of the model.

[0182] In some embodiments, the complexity of a power grid can be determined based on the topology of the power grid itself, the complexity of the devices connected to the power grid, and the weather complexity of the area. In some embodiments, the complexity of the power grid can be determined based on a weighted sum of the topology of the power grid itself, the complexity of the devices connected to the power grid, and the weather complexity of the area. The weights can be determined based on actual conditions to reflect the importance attached to a particular factor.

[0183] In some embodiments, the greater the number of devices connected to the power grid and the greater the types of devices connected to the power grid, the higher the device complexity. In some embodiments, weather complexity can be represented by the mean variance of temperature, precipitation, sunlight, etc. over a period of time (e.g., within a day).

[0184] In some embodiments, the topology of the power grid itself can be obtained by first abstracting the power grid structure into a graph consisting of nodes and edge weights. Nodes correspond to the connection points and cross-connections between wires, while edge weights represent the wires themselves. Topological metrics such as the number of loops, the number of nodes and edges, network density, and node degree distribution in the graph are then calculated to determine the topological complexity of the power grid.

[0185] In some embodiments, the number of rings can be calculated using a ring detection algorithm from graph theory. The network density can be calculated by calculating the ratio of the number of edges in the graph to the number of maximized edges (assuming that there are edges between every two nodes). The node degree distribution can be calculated using a degree distribution algorithm from graph theory. In some embodiments, the greater the number of rings, the greater the number of nodes and edges, the greater the network density, and the greater the average clustering coefficient, the higher the complexity.

[0186] Using a two-stage training approach to train the voltage sag risk model can quickly obtain a large amount of training data used in the initial training stage. At the same time, the trained model has good generalization capabilities, which can better identify and handle voltage sag risks. In addition, using actual data for enhanced training can also improve the performance of the model in practical applications.

[0187] In order to make the photovoltaic output scenario generated by the deep convolutional generative adversarial network more robust, in some embodiments, the processor 10 is further configured to: generate multiple groups of randomly sampled noises with different noise characteristics and their training subsets based on the preprocessed photovoltaic output data, where the noise characteristics reflect the distribution information of the photovoltaic output; and train the deep convolutional generative adversarial network based on the multiple groups of randomly sampled noises with different noise characteristics and their corresponding training subsets.

[0188] In some embodiments, processor 10 may partition the pre-processed photovoltaic power information in step 110 to generate random sampled noise with different noise characteristics. In some embodiments, processor 10 may partition the photovoltaic power information by season and / or by light intensity to better reflect the variation of photovoltaic power in different seasons or under different light conditions.

[0189] In some embodiments, the processor 10 can use non-parametric methods (such as kernel density estimation, empirical cumulative distribution function, Copula model) to generate multiple groups of random sampling noises with different noise characteristics based on the photovoltaic output power information divided by season and / or by light intensity.

[0190] In some embodiments, when using the above-mentioned multiple groups of randomly sampled noises with different noise characteristics and their corresponding training subsets to train a deep convolutional generative adversarial network, hybrid training based on the training subsets or independent training based on the training subsets can be performed according to actual needs.

[0191] In subset-based hybrid training, a training subset (or a batch in a training subset) is randomly selected from multiple subsets for training in each iteration of the deep convolutional generative adversarial network to ensure that the generator and discriminator are exposed to data from different subsets during training, thereby learning a wider range of photovoltaic output patterns, allowing the generator to be exposed to a wider range of data distributions, thereby learning the diversity and uncertainty of photovoltaic output.

[0192] In subset-based independent training, multiple sub-models corresponding to different seasons or light intensities are obtained after training. In some embodiments, the processor 10 can fuse these sub-models to form a comprehensive deep convolutional generative adversarial network. Independent training allows the generators of each subset to focus on learning the unique distribution characteristics of that subset. This targeted training approach can generate more realistic photovoltaic output scenarios, which is particularly suitable for applications with high requirements for specific environmental conditions.

[0193] Although the embodiments of the present specification have been shown and described, it will be understood by those skilled in the art that various equivalent changes, modifications, substitutions and variations may be made to these embodiments without departing from the principles and spirit of the present specification, and the scope of the present specification is defined by the appended claims and their equivalents.

Claims

1. A voltage sag domain identification system based on multiple uncertainty scenarios, characterized in that: The system includes a processor, a photovoltaic monitoring device, a power monitoring device and control hardware; The processor is configured to: Based on the photovoltaic monitoring device deployed at each photovoltaic site on the power distribution network, photovoltaic output power information of each photovoltaic site is collected, and a deep convolutional generative adversarial network is trained based on the photovoltaic output power information; Generate photovoltaic output scenarios using the deep convolutional generative adversarial network; Determining a voltage sag domain identification result corresponding to the given parameters and the sensitive load threshold based on the photovoltaic output scenario, given parameters, a sensitive load threshold, and structural parameters of the power system; Based on the photovoltaic output scenario, the voltage of each node of the distribution network before the fault is determined using the Newton-Raphson method power flow calculation method; Obtaining a current bus from the lines of the distribution network, calculating the impedance matrix of each node of the distribution network by an additional branch method or an inversion of the admittance matrix according to the given parameters, and determining, based on the voltage of each node before the fault and the impedance matrix of each node, the voltage sag amplitude at the node where the sensitive load is located when different types of short-circuit faults occur at each node on the current bus; Determining a voltage sag amplitude vector of a bus node based on the voltage sag amplitude at the node where the sensitive load is located when different types of short-circuit faults occur at each node of the current bus; Comparing the voltage sag amplitude vector at the busbar node with the sensitive load threshold to obtain a difference vector; and obtaining a line correlation vector based on the difference vector; Based on the line association vector, determining whether the current bus satisfies an analysis condition; In response to the condition not being satisfied, the current bus is not within the voltage sag region, and a next line is selected from the power distribution network as the current bus to continue the determination; In response to satisfying: analyzing the current bus by Newton quadratic interpolation method to obtain an analytical expression for the voltage sag amplitude and a fault voltage equation of the current bus; and, based on the fault voltage equation, obtaining a portion of the current busbar within the voltage sag region, and selecting a next line from the power distribution network as the current busbar to continue determination; When the traversal and iteration of all lines in the power distribution network are completed, a plurality of voltage sag domains corresponding to the given parameters and the sensitive load threshold are obtained, and a union of the plurality of voltage sag domains is the voltage sag domain identification result; Based on the voltage sag domain identification result, a voltage reduction response instruction is generated; the voltage reduction response instruction includes instructing the power monitoring device on the monitoring frequency, monitoring accuracy, upload interval period and alarm threshold; sending the voltage reduction response instruction to a power monitoring device in a voltage sag domain; The power monitoring device is configured to: collecting a power parameter sequence in the power distribution network at the monitoring frequency and the monitoring accuracy, and uploading the power parameter sequence to the processor at the upload interval period; determining whether voltage data in the power parameter sequence is lower than the alarm threshold; in response to falling below the alarm threshold, sending an alarm signal to the processor; The processor is further configured to: Determining an estimated impact load corresponding to the node where the power monitoring device is located based on the alarm signal; Generate a control instruction and send it to the control hardware corresponding to the estimated impact load to control the control hardware to perform compensation work.

2. The system according to claim 1, wherein The deep convolutional generative adversarial network includes: using a fully convolutional network, canceling the fully connected layer and using batch normalization; After preprocessing the photovoltaic output power information, randomly sampled noise is used as input to the generator of the deep convolutional generative adversarial network, and the historical output data of each photovoltaic site is used as input to the discriminator of the deep convolutional generative adversarial network. The deep convolutional generative adversarial network is trained using the training data until a Nash equilibrium is reached. After the deep convolutional generative adversarial network training is completed, the photovoltaic output scene generated by the generator that is similar to the real data is obtained.

3. The system according to claim 1, wherein: The processor is further configured to: Based on the structural parameters of the power system being clarified, actual data is substituted into the admittance matrix to form the admittance matrix, and the offset of each parameter is calculated according to a given initial value; Perform error analysis, and in response to the error meeting the error precision, jump out of the loop and output the result; in response to the error not meeting the error precision, continue to solve the Jacobian matrix, and solve the correction voltage through the correction equation, and perform the error analysis again.

4. The system according to claim 1, wherein: The different types of short circuit faults include three-phase short circuit fault, single-phase ground short circuit fault, two-phase short circuit fault and two-phase ground short circuit fault; When the short-circuit fault is the three-phase short-circuit fault, the processor is configured to: When the fault point When the three-phase short circuit fault occurs at the node, it is a symmetrical balanced fault, only the positive sequence is considered, and the sensitive load node The three-phase voltage sag amplitudes at the same location are the same, and the voltage sag amplitude of one phase is: in, for The voltage sag amplitude at point is the positive sequence self-impedance, is the positive sequence mutual impedance, for Voltage before point fault, for Voltage before point fault; Voltage sag amplitude at point It is related to the structural parameters of the power system and the operating state of the power system before the failure. Occurrence When the phase is a special phase, the asymmetric short circuit fault is analyzed using the symmetrical component method; When the short circuit fault is the single-phase to ground short circuit fault, the processor is configured to: When the fault point Occurrence When the phase is a special phase, the single-phase ground short circuit fault occurs. The voltage sag amplitudes at the points are as follows: in, yes At the point Phase voltage sag amplitude, yes point Phase voltage sag amplitude, yes At the point Phase voltage sag amplitude; for point Phase voltage before fault, for point Phase voltage before fault, for point Phase voltage before fault; for Zero sequence self impedance, for Point positive sequence self-impedance, for Point negative sequence self-impedance; for Point and The zero-sequence mutual impedance of the point, for Point and The positive sequence mutual impedance of the point, for Point and Negative sequence mutual impedance of the point; for Voltage before point fault; is the rotation factor; When the short-circuit fault is the two-phase short-circuit fault, the processor is configured to: when Harmony When the two-phase short circuit fault occurs, the The expression of the three-phase voltage sag amplitude at point is: When the short circuit fault is the two-phase-to-ground short circuit fault, the processor is configured to: when Harmony When the two-phase ground short circuit fault occurs, The three-phase voltage sag amplitudes at the points are as follows: When the two-phase ground short circuit fault occurs on the power system bus, the self-impedance and mutual impedance are directly called from the impedance matrix of each node of the distribution network; however, when the short circuit fault occurs at a certain point on the line, the calculation of the self-impedance and the mutual impedance needs to introduce the position variable The joint node impedance matrix is ​​obtained. Point is the busbar node where the sensitive load is located. is the sequence impedance of line FT, when the fault point On the line FT When moving upward, the third-sequence self-impedance and failure points and Three-sequence mutual impedance between points All by the impedance matrix and position variables express: Where: 、 are the zero-sequence self-impedance, positive-sequence self-impedance, and negative-sequence self-impedance of the system bus nodes F and T, respectively; 、 、 They are the mutual impedances of each sequence of system bus nodes F and T, bus F and sensitive load nodes The mutual impedance between each sequence, busbar T and sensitive load nodes The mutual impedances of each sequence between them are all called from the impedance matrix of each node in the distribution network. is the line sequence impedance between nodes F and T, Fault point On the line Position variables on ; The fault point Voltage before fault By fault location variable To express: in, is the voltage of busbar node F before the fault occurs, is the voltage at busbar node T before the fault occurs, Fault point On the line FT Position variables on ; The voltage sag amplitude of the point is represented by the voltage before the fault and the impedance of each sequence, and it is obtained that when any short circuit fault occurs at any fault point, The magnitude of voltage sag at a point is related to the position variable Functional expression of .

5. The system according to claim 1, wherein: The expression of the difference vector is: in, The node where the sensitive load is located when a short circuit fault occurs on bus 1 The absolute value of the voltage amplitude, The node where the sensitive load is located when a short circuit fault occurs on bus 2 The absolute value of the voltage amplitude, The node where the sensitive load is located when a short circuit fault occurs on bus n The absolute value of the voltage amplitude; is the voltage sag threshold for sensitive loads; Indicates the node where the sensitive load is located when a short circuit fault occurs on bus 1 The difference between the absolute value of the voltage amplitude and the voltage sag threshold of the sensitive load, Indicates the node where the sensitive load is located when a short circuit fault occurs on bus 2 The difference between the absolute value of the voltage amplitude and the voltage sag threshold of the sensitive load, Indicates the node where the sensitive load is located when a short circuit fault occurs on bus n The difference between the absolute value of the voltage amplitude and the voltage sag threshold of the sensitive load, Indicated by 、 、 The difference vector composed of: By judgment The positive and negative elements in the difference vector are used to determine whether each node is within the temporary drop region of the sensitive node, and the node determination vector is introduced. B : in, Indicates the judgment result of bus 1, Indicates the judgment result of bus 2, Indicates the judgment result of busbar n, Indicates busbar The judgment result of represents the node decision vector; Indicates busbar The node where the sensitive load is located when a short circuit fault occurs The difference between the absolute value of the voltage amplitude and the voltage sag threshold of the sensitive load; Indicates busbar Within the voltage sag range corresponding to sensitive loads; It means bus Outside the voltage sag domain corresponding to the sensitive load, the inclusion of each line in the voltage sag domain is determined, and the line association vector is introduced. : Where: represents the line association vector, Indicates the result of the judgment that line 1 is included in the temporary sag domain. Indicates the result of the determination of whether line 2 is included in the temporary sag domain. Indicates the result of determining whether line m is included in the sag domain; is the temporary drop judgment result of busbar node F of line 1, is the temporary drop judgment result of busbar node T of line 1, is the temporary drop judgment result of busbar node T of line 2, is the temporary drop judgment result of busbar node F of line m, is the temporary sag determination result of busbar node T of line m; The determining whether the current bus satisfies the analysis condition based on the line association vector includes: like , indicating that the line is not in the voltage sag region, and the next line is calculated directly; if , indicating that one of the first and last nodes of this line is in the temporary drop region, then the line Part of it is located in the temporary drop region, and there is only one critical point on the line; if , indicating that the first and last nodes of this line are both within the voltage sag region, so the golden section search method is first used to solve the maximum value of the voltage sag amplitude curve. and voltage sag threshold with sensitive loads To compare; if , indicating that this line is completely within the temporary drop region and there is no critical point, then the next line is calculated directly; if , explaining the line part Located in the temporary sag region, and there are two critical points on the line; The whole process of the golden section search method is to find The point where the voltage sag at the common connection point reaches its maximum value ,use As the interpolation point, it ensures that the interpolation curve passes through the maximum value of the voltage sag amplitude, providing an initial value point for the secant iteration.

6. The system according to claim 1, wherein: The processor is configured to: The root of the fault voltage equation is As the initial iteration value of the secant iteration method, the accurate critical point position is obtained through iteration. The critical fault distance iteration expression according to the secant iteration method is as follows: in, Indicates the The critical fault distance solved by the second time is Indicates the The critical fault distance solved by this method is Indicates the The critical fault distance solved by the second time is Indicates the position variable is of The voltage sag amplitude at the point Indicates the position variable is of The voltage sag amplitude at the point is the voltage sag threshold for sensitive loads; The convergence condition of the secant iteration method is: in, Indicates the position variable is of The voltage sag amplitude at the point is the voltage sag threshold for sensitive loads, Indicates the convergence threshold.

7. The system according to claim 1, wherein: The control hardware includes one or more of a backup power supply, a dynamic voltage regulator, and a load switch; the control instructions include one or more of a backup power supply instruction, a voltage self-regulation instruction, and a switch instruction; The backup power supply is configured to: after receiving the backup power supply instruction, provide power supply corresponding to the estimated impact load; The dynamic voltage regulator is configured to: after receiving the voltage self-adjustment instruction, provide a compensation voltage corresponding to the estimated impact load; The load switch is configured to: after receiving the switch instruction, control the connection and disconnection of the estimated impact load and the power distribution network.

8. The system according to claim 1, wherein: The processor is further configured to: constructing a power characteristic map according to the given parameters, the power parameter sequence, the photovoltaic output power information, line basic data, future light data, and sensitive load thresholds; Inputting the power characteristic diagram into a voltage sag risk model to obtain a voltage sag risk area; A plurality of voltage sag regions corresponding to the given parameter and the sensitive load threshold in the voltage sag risk area are calculated to determine the voltage sag region identification result.

9. The system according to claim 8, wherein: The training process of the voltage sag risk model includes an initial training phase and an intensive training phase, each performed using training data. The initial training phase constructs the training data for training based on a general data set obtained on a cloud platform. In the intensive training stage, the training data is constructed based on the data actually collected from the power distribution network for training; The training data includes training samples and labels corresponding to the training samples; The training samples include a sample power characteristic map constructed based on sample given parameters, a sample power parameter sequence, sample photovoltaic output power information, sample line basic data, sample future light data, and a sample sensitive load threshold; the label corresponding to the training sample is the area of ​​the voltage sag domain corresponding to the sample sensitive load; In the training data of the initial training phase, the number of samples corresponding to power grids of different complexity levels is not less than a preset threshold, and the preset threshold is determined based on the complexity level of the corresponding power grid.

Images