Power quality disturbance monitoring method and device, electronic equipment and storage medium

Abstract

The invention provides a power quality disturbance monitoring method and device, electronic equipment and a storage medium, and belongs to the technical field of power quality monitoring. The invention discloses a power quality disturbance monitoring method. The method comprises the following steps: constructing a mathematical model of a standard signal and a disturbance signal related to power quality; constructing a disturbance data set by using the electric energy quality mathematical model; constructing a power quality disturbance identification model; training a disturbance recognition model by using the disturbance data set; power grid operation data are collected in real time, and the disturbance recognition model is used for monitoring the electric energy quality. By monitoring the power quality disturbance, the disturbance event can be found in time, the characteristic parameters such as the disturbance amplitude and the duration time can be determined, and a basis is provided for improving the power quality.

Description

Technical Field

[0001] The present invention belongs to the technical field of power quality monitoring, and in particular relates to a method, device, electronic equipment and storage medium for monitoring power quality disturbance. Background Art

[0002] With the development of science and technology, the electricity consumption of various industries in my country has increased, and more and more advanced power equipment has been put into use. These power equipment have higher and higher requirements for power quality. However, at present, a large number of users of power quality interference sources represented by distributed photovoltaics, wind power, and electric vehicle charging piles are connected to the power grid, and there are still a large number of nonlinear, volatile and impact loads in the modern power grid, which leads to waveform distortion of the power supply system, causing a series of power quality disturbance problems such as voltage sag, voltage swell, voltage interruption, transient pulse, transient oscillation, etc.

[0003] Disturbance problems directly affect power quality. The increasingly prominent power quality problems have caused huge economic losses to sensitive users represented by microelectronics, semiconductors, biomedicine, etc. Rapid and accurate identification of power quality disturbance events is a prerequisite for promoting the construction of new power systems and improving power quality. Therefore, monitoring of power quality disturbance events is very necessary. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method, device, electronic equipment and storage medium for monitoring power quality disturbance in view of the deficiencies in the prior art.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0006] A method for monitoring power quality disturbances comprises: constructing a mathematical model of standard signals and disturbance signals related to power quality; constructing a disturbance data set using the power quality mathematical model; constructing a power quality disturbance identification model; training the disturbance identification model using the disturbance data set; collecting power grid operation data in real time, and monitoring power quality using the disturbance identification model.

[0007] Furthermore, the method of constructing mathematical models of standard signals and disturbance signals related to power quality includes: constructing a mathematical model of a standard signal; constructing a mathematical model of a single disturbance signal; and constructing a mathematical model of a composite disturbance signal formed by superimposing single disturbance signals.

[0008] Furthermore, the method of constructing a disturbance data set using a mathematical model of power quality includes: randomly generating a power quality disturbance signal by randomly adjusting a parameter range based on a mathematical model of a disturbance signal; randomly generating a normal signal based on a mathematical model of a standard signal; sampling the disturbance signal and the normal signal at a certain sampling frequency, and constructing a power quality disturbance data set based on the sampling results.

[0009] Furthermore, the method of constructing a disturbance data set using a power quality mathematical model also includes: before sampling the disturbance signal and the normal signal, randomly superimposing Gaussian noise with a signal-to-noise ratio of 0-40dB on the normal signal and the disturbance signal.

[0010] Furthermore, the method for constructing a power quality disturbance identification model includes: using an extreme learning machine ELM to construct a neural network function of the power quality disturbance identification model; using a weighted sum of a linear kernel function Linear, a polynomial kernel function Poly, a radial basis function kernel function Rbf and a wavelet kernel function Wav to construct a kernel function of the neural network function.

[0011] Furthermore, the method of training the disturbance recognition model with the disturbance data set includes: using the sampled data in the disturbance data set as input data during training; and using the disturbance signal type, disturbance amplitude and duration corresponding to the sampled data as output data during training.

[0012] A monitoring device for power quality disturbances comprises a construction unit, a training unit and a monitoring unit; the construction unit is used to construct a power quality mathematical model, to construct a disturbance data set using the power quality mathematical model, and to construct a power quality disturbance identification model; the training unit is used to train the disturbance identification model using the disturbance data set; the monitoring unit is used to collect power grid operation data in real time, and to monitor power quality using the disturbance identification model.

[0013] Furthermore, the construction unit and the training unit are located at the cloud center end, the monitoring unit is located at the edge end, and the training unit is also used to send the disturbance recognition model to the monitoring unit.

[0014] An electronic device comprises a processor and a memory; the memory is used to store executable instructions, and the processor is used to execute the instructions to implement the monitoring method.

[0015] A computer-readable storage medium stores instructions, and when the instructions are executed, the monitoring method is implemented.

[0016] Compared with the prior art, the present invention has the following beneficial effects:

[0017] The present invention constructs a mathematical model of standard signals and disturbance signals related to power quality, and randomly generates sampling data under normal and disturbance conditions when the power grid is running according to the mathematical model combined with signal noise, and constructs a disturbance data set with parameters such as the type, disturbance amplitude, and duration of the sampling data and disturbance signal. By constructing a power quality disturbance identification model and training the model with the disturbance data set, the disturbance identification model is finally used to realize the monitoring of disturbance events in power quality. By monitoring power quality disturbances, the present invention can timely discover disturbance events, determine characteristic parameters such as disturbance amplitude and duration, and provide a basis for improving power quality.

[0018] The present invention completes the construction and training of the power quality disturbance identification model at the cloud center end, and sends the power quality disturbance identification model to the edge end, and the edge node device uses the identification model to monitor the power quality disturbance event. Therefore, after obtaining the grid sampling data, the edge contact device of the present invention can complete the monitoring of the power quality disturbance event at the edge end, and there is no need to transmit the sampling data to the cloud center end for unified monitoring and identification by the cloud. On the one hand, it can alleviate the computing pressure of massive data on the centralized monitoring and identification of the cloud center end. On the other hand, the identification model of the edge contact device is uniformly sent down by the cloud center end, so the edge contact device only needs to meet the computing power of data sampling and model identification, which can reduce the hardware requirements of the edge contact device and reduce the application cost. At the same time, the edge contact device directly performs sampling and monitoring and identification, and there is no need to transmit the sampling data over the network, which can reduce the delay in the identification of disturbance events. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The present invention is further described in detail below in conjunction with the accompanying drawings.

[0020] Figure 1 : Flow chart of embodiment 1 of the present invention;

[0021] Figure 2 : A schematic diagram of Embodiment 2 of the present invention;

[0022] Figure 3 : Schematic diagram of embodiment 3 of the present invention. DETAILED DESCRIPTION

[0023] In order to better understand the present invention, the content of the present invention is further clearly described below in conjunction with the embodiments and the accompanying drawings, but the protection content of the present invention is not limited to the following embodiments. In the following description, a large number of specific details are provided to provide a more thorough understanding of the present invention. However, it is obvious to those skilled in the art that the present invention can be implemented without one or more of these details.

[0024] Embodiment 1: The purpose of this embodiment is to provide a method for monitoring power quality disturbances. Figure 1 As shown, the monitoring method comprises:

[0025] S1. Construct a mathematical model of power quality.

[0026] This step constructs a mathematical model related to power quality.

[0027] The signal when the power system is in a stable operating state can be regarded as a standard signal. The standard signal is a sine wave with a constant voltage amplitude and a frequency of 50Hz in the power system. Its mathematical model is x0(t)=sin(ωt), where ω=2πf, f=50Hz.

[0028] Common single disturbance signals in power systems are:

[0029] (1) Voltage sag. Voltage sag refers to a short-term voltage fluctuation phenomenon in which the effective value of the amplitude is reduced to 10%-90% of the rated value, that is, the per-unit value is between 0.1-0.9pu and the duration is 0.01s-1min. The mathematical model of voltage sag is x1(t)={1-k[u(t-t2)-u(t-t1)]}sin(ωt), where ω=2πf, f=50Hz, k is the voltage sag coefficient, 0.1≤k≤0.9, t1 and t2 are the start and end times of the voltage sag respectively, T≤t2-t1≤9T.

[0030] (2) Voltage swell. Voltage swell refers to the voltage fluctuation phenomenon in which the effective value of voltage suddenly changes to 110%-180% of the nominal voltage in a short period of time at a rated frequency of 50Hz, that is, the per-unit value is between 1.1-1.8pu, and the duration is 0.01s-1min. The mathematical model of voltage swell is x2(t)={1+k[u(t-t1)-u(t-t2)}sin(ω), where ω=2πf, f=50Hz, k is the voltage swell coefficient, 0.1≤k≤0.8, t1 and t2 are the start and end times of the voltage swell, respectively, T≤t2-t1≤9T.

[0031] (3) Voltage interruption. Voltage interruption refers to a voltage change when the effective value of the power supply voltage drops below 10% of the nominal voltage and lasts no longer than 1 minute. The mathematical model of voltage interruption is x3(t) = {1-k[u(t-t1)-u(t-t2)}sin(ωt), where ω = 2πf, f = 50Hz, k is the voltage reduction coefficient, 0.9≤k≤1, t1 and t2 are the start and end times of the voltage interruption, respectively, and T≤t2-t1≤9T.

[0032] (4) Transient pulse. Transient pulse refers to the phenomenon of non-industrial frequency, unipolar (positive or negative) extremely short-term change in voltage and current between two steady states. Generally, it is represented by an increase or decrease in frequency. The mathematical model of transient pulse is x4(t)=sin(ωt)+k[u(t-t1)-u(t-t2)], where ω=2πf, f=50Hz, 1≤k≤3, t1 and t2 are the start and end times of the transient pulse, respectively, 1ms≤t2-t1≤3ms.

[0033] (5) Transient oscillation. Transient oscillation refers to the instantaneous disturbance phenomenon of non-power frequency and positive or negative polarity of current, voltage or both when the power system is in a steady state. It is usually represented by the main frequency, duration and amplitude. The mathematical model of transient oscillation is x5(t) = sin(ωt) + k·exp(-(t-t1)τ)·sin(βωt)·[u(t-t1)-u(t-t2)], where ω = 2πf, f = 50Hz, 0.5≤k≤1, τ is the attenuation coefficient, 15≤τ≤130, β is the fundamental frequency coefficient of the oscillation, 14≤β≤30, t1 and t2 are the start and end times of the transient oscillation, respectively, and 0.5T≤t2-t1≤2T.

[0034] (6) Voltage fluctuation. Voltage fluctuation refers to a collection of a series of voltage changes. During normal operation, some loads experience impact power changes, causing the actual voltage to fluctuate greatly in a short period of time and continuously deviate from the rated voltage, so it is also called rapid voltage change. The mathematical model of voltage fluctuation is x6(t) = [1+α·sin(βωt)]·sin(ωt), where ω = 2πf, f = 50Hz, α is the fluctuation amplitude, 0.1≤α≤0.2, and β is the fluctuation frequency, 0.1≤β≤0.5.

[0035] (7) Harmonics. The harmonic order refers to the integer ratio of the harmonic frequency to the fundamental frequency. For example, if the rated frequency is 50 Hz, the harmonic order must be a positive integer > 1, then the 2nd harmonic is 100 Hz, the 3rd harmonic is 150 Hz, the 5th harmonic is 250 Hz, and so on. With the large-scale application of various nonlinear power electronic devices, harmonic currents are injected into the power system, causing the voltage waveform at the common connection point to be distorted. The mathematical model of harmonics is x7(t) = k1sin(ωt) + k3sin(3ωt) + k5sin(5ωt), where ω = 2πf, f = 50 Hz, k1, k3, k5 are the amplitudes of the fundamental, third harmonic, and fifth harmonic, respectively, 0.05≤k1, k3, k5≤0.15, ∑(k i ) 2 =1.

[0036] However, in actual power systems, there are a large number of nonlinear devices and irregular switching devices. Power quality disturbance signals often exist in the form of composite disturbances, which can be regarded as the superposition of single disturbance signals. Common composite disturbance signals include voltage sag + harmonic mathematical models x1(t) + x7(t), voltage swell + harmonic mathematical models x2(t) + x7(t), voltage fluctuation + harmonic mathematical models x6(t) + x7(t), voltage sag + transient oscillation mathematical models x1(t) + x5(t), voltage sag + transient oscillation + harmonic mathematical models x1(t) + x5(t), and voltage sag + transient oscillation + harmonic mathematical models x1(t) + x5(t) + x7(t), and so on.

[0037] S2. Use the mathematical model of power quality to construct the disturbance data set.

[0038] Based on the mathematical model of power quality established in step S1, a power quality disturbance signal (single disturbance signal or composite disturbance signal) is randomly generated by randomly adjusting the range of parameters such as disturbance amplitude and duration; then, several normal signals are randomly generated according to the mathematical model x0(t) of the standard signal in combination with the parameters of the disturbance signal. Since interference may occur in the actual power system, in order to simulate the field environment, Gaussian noise with a signal-to-noise ratio of 0-40dB can also be randomly superimposed on the normal signal and the disturbance signal. Finally, the disturbance signal and the normal signal are sampled at a certain sampling frequency, and the power quality disturbance data set is constructed based on the sampling results.

[0039] In the constructed disturbance data set, each set of data contains sampling data of disturbance signals or normal signals, as well as the specific type, disturbance amplitude and duration of the disturbance signal in the data.

[0040] S3. Construct a power quality disturbance identification model.

[0041] In this step, an extreme learning machine (ELM) is used to construct a power quality disturbance identification model.

[0042] The neural network function of the ELM algorithm can be expressed as f(x) = h(x)β. ELM ensures the accuracy of regression prediction by minimizing the output error, that is, Where L is the number of neurons h(x) in the hidden layer; f O (x) is the function to be predicted consisting of the target value.

[0043] At the same time, the ELM algorithm ensures the generalization ability of the neural network by minimizing the output weight β. Usually β takes its least squares solution, and the calculation method is Where H is the hidden layer matrix of the neural network; is the generalized inverse matrix of the H matrix; O is the predicted target value vector. According to the ridge regression theory, by adding the positive constant 1 / C, the solution will be more stable and have better generalization ability.

[0044] After introducing the kernel function, the constructed disturbance recognition model can be expressed as:

[0045]

[0046] K(x i , x j )=w1K Linear (x i , x j )+w2K Poly (x i , x j )+w3K Rbf (x i , x j )+w4K Wav (x i , x j )

[0047] K Linear (x i , x j )=x i T x j

[0048] K Poly =(γx i T x j +r) d

[0049] K Rbf (x i , x j )=exp(-γ||x i -x j || 2 )

[0050] K Wav (x i , x j )=φ(x i -x j )

[0051] Where K(x i , x j ) is the kernel function, and N is the dimension of the input layer. i , x j) Kernel functions include linear kernel function (Linear), polynomial kernel function (Poly), radial basis function kernel function (Rbf), and wavelet kernel function (Wav), which are mixed kernel functions composed of weighted superposition of the four kernel functions. Linear is a linear kernel function, K Poly is the polynomial kernel function, K Rbf is the radial basis function kernel function, K Wav is a wavelet kernel function, γ is a positive scaling factor, r is a bias, d is the order of the polynomial, φ is a wavelet function that satisfies certain conditions, and w1, w2, w3, and w4 are the weight values ​​corresponding to the four kernel functions.

[0052] S4. Train the perturbation recognition model using the perturbation dataset.

[0053] The sampled data in the perturbation data set is used as the input data during training, and the specific type, perturbation amplitude and duration of the corresponding perturbation signal are used as the output data during training.

[0054] Randomly initialize the hidden layer weights and biases, randomly initialize the weights for each neuron in the hidden layer, and initialize the bias of each hidden neuron. Pass the input data through the kernel function K(x i ,x j ) is converted to the hidden layer output.

[0055] S5. Collect grid operation data in real time and monitor power quality using disturbance identification model.

[0056] In this step, the collection points are used to collect grid operation data such as voltage in the grid in real time for sampling, and the sampled data is input into the disturbance identification model. The disturbance identification model will identify the disturbance event and the specific disturbance type, disturbance amplitude and duration, thereby providing a basis for improving the power quality.

[0057] Embodiment 2: The purpose of this embodiment is to provide a monitoring device for power quality disturbance, which is used to perform the monitoring method of embodiment 1. Figure 2 As shown, the monitoring device 200 includes: a construction unit 201 , a training unit 202 and a monitoring unit 203 .

[0058] The construction unit 201 is used to construct a power quality mathematical model, to construct a disturbance data set using the power quality mathematical model, and to construct a power quality disturbance identification model. Specifically, in combination with Embodiment 1, the construction unit 201 is used to execute steps S1-S3.

[0059] The training unit 202 is used to train the disturbance recognition model with the disturbance data set. Specifically, in combination with Embodiment 1, the training unit 202 is used to execute step S4.

[0060] The monitoring unit 203 is used to collect power grid operation data in real time and to monitor the power quality using the disturbance identification model. Specifically, in combination with Embodiment 1, the monitoring unit 203 is used to execute step S5.

[0061] In the monitoring device 200, the construction unit 201 and the training unit 202 are located at the cloud center, the monitoring unit 203 is located at the edge, and the training unit 202 is also used to send the disturbance recognition model to the detection unit 203. The cloud center and the edge cooperate with each other to realize cloud-edge coordinated power quality disturbance monitoring.

[0062] Regarding the device in this embodiment, the specific manner in which each unit performs operations has been described in detail in Example 1 and will not be elaborated here.

[0063] Those skilled in the art should understand that for the convenience and simplicity of description, the present application only uses the division of the above-mentioned functional modules or units as examples in the device embodiments. In actual applications, the above-mentioned functions can be assigned to different functional modules or units as needed, that is, the internal structure of the device can be divided into different functional modules or units to complete all or part of the functions described above.

[0064] Example 3: See Figure 3 The purpose of this embodiment is to provide an electronic device 300, including at least one processor 301 and one or more memories 302 for storing executable instructions of the processor 301. The processor 301 is used to execute the instructions in the memory 302 to implement the monitoring method described in Example 1.

[0065] The electronic device 300 further includes a bus 304 , and the processor 301 and the memory 302 are connected to each other via the bus 304 , or are connected to each other in other ways.

[0066] The processor 301 is a central processing unit (CPU), a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The processor 301 may also be other devices with processing functions, such as circuits, devices, or software modules, without limitation. In one example, the processor 301 may include one or more CPUs, such as Figure 3 CPU0 and CPU1 in.

[0067] Among them, the memory 302 can be a read-only memory (ROM) or other types of static storage devices that can store static information and / or instructions, or a random access memory (RAM) or other types of dynamic storage devices that can store information and / or instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), magnetic disk storage medium or other magnetic storage devices, etc., without limitation.

[0068] It should be noted that the memory 302 may exist independently of the processor 301 or may be integrated with the processor 301. The memory 302 may be used to store instructions or program codes or some data, etc. The memory 302 may be located inside the electronic device 300 or outside the electronic device 300, without limitation.

[0069] As an optional implementation, the electronic device 300 also includes a communication interface 303. The communication interface 303 is a wired interface (or port), such as a fiber distributed data interface (FDDI), a gigabit Ethernet interface (GE), etc. Alternatively, the communication interface 303 is a wireless interface. The communication interface 303 can be a module, a circuit, a communication interface, or any device capable of achieving communication. The communication interface 303 is used to communicate with other devices or other communication networks, which can be Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc.

[0070] As an optional implementation, the electronic device 300 further includes an input device 305 and an output device 306. Exemplarily, the input device 305 is a keyboard, a mouse, a microphone, a joystick, and the like, and the output device 306 is a display screen, a speaker, and the like.

[0071] It should be noted that the electronic device 300 may be a desktop computer, a portable computer, a network server, a mobile phone, a tablet computer, a wireless terminal, an embedded device, a chip system or a Figure 3 In addition, Figure 3 The components shown in the figure do not constitute a limitation on the terminal device, except Figure 3 In addition to the components shown, the electronic device 300 may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0072] Embodiment 4: The purpose of this embodiment is to provide a computer-readable storage medium.

[0073] All or part of the processes in the above method embodiments can be completed by computer instructions to instruct relevant hardware. The program can be stored in the computer-readable storage medium. When the program is executed, it can implement the monitoring method described in Example 1.

[0074] The computer-readable storage medium may be an internal storage unit of the electronic device of Example 3, such as a hard disk or a memory. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (smart media card, SMC), a secure digital (secure digital, SD) card, a flash card (flash card), etc. Further, the computer-readable storage medium may also include both an internal storage unit of the above-mentioned electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0075] In conjunction with the several embodiments provided in this application, it should be understood that the provided devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0076] In addition, in the embodiment of the device of the present application, each functional module or unit can be integrated into one unit, or each module or unit can exist physically separately, or two or more modules or units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional modules.

[0077] If the above-mentioned integrated unit is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks or optical disks.

[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Other modifications or equivalent substitutions made to the technical solution of the present invention by ordinary technicians in the field should be included in the scope of the claims of the present invention as long as they do not depart from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for monitoring power quality disturbances, characterized in that: include: Construct mathematical models of standard signals and disturbance signals related to power quality; Use mathematical models of power quality to construct disturbance data sets; Construct a power quality disturbance identification model; Train the perturbation recognition model with the perturbation dataset; Collect grid operation data in real time and monitor power quality using disturbance identification models.

2. The method for monitoring power quality disturbance according to claim 1, characterized in that: Methods for constructing mathematical models of standard signals and disturbance signals related to power quality include: Construct mathematical models of standard signals; Construct a mathematical model of a single disturbance signal; Construct a mathematical model of the composite disturbance signal formed by the superposition of single disturbance signals.

3. The method for monitoring power quality disturbance according to claim 1, characterized in that: Methods for constructing disturbance data sets using mathematical models of power quality include: According to the mathematical model of the disturbance signal, the power quality disturbance signal is randomly generated by randomly adjusting the parameter range; Generate normal signals randomly based on the mathematical model of standard signals; The disturbance signal and the normal signal are sampled at a certain sampling frequency, and the power quality disturbance data set is constructed based on the sampling results.

4. The method for monitoring power quality disturbance according to claim 2, characterized in that: The method of constructing a disturbance data set using a power quality mathematical model also includes: before sampling the disturbance signal and the normal signal, randomly superimposing Gaussian noise with a signal-to-noise ratio of 0-40dB on the normal signal and the disturbance signal.

5. The method for monitoring power quality disturbance according to claim 1, characterized in that: Methods for building a power quality disturbance identification model include: The neural network function of the power quality disturbance identification model is constructed using the extreme learning machine ELM; The kernel function of the neural network function is constructed by using the weighted sum of the linear kernel function Linear, the polynomial kernel function Poly, the radial basis function kernel function Rbf and the wavelet kernel function Wav.

6. The method for monitoring power quality disturbance according to claim 1, characterized in that: Methods for training a perturbation recognition model with a perturbation dataset include: Use the sampled data in the perturbation dataset as input data for training; The disturbance signal type, disturbance amplitude and duration corresponding to the sampled data are used as output data during training.

7. A monitoring device for power quality disturbance, characterized in that: It includes construction unit, training unit and monitoring unit; The construction unit is used to construct a power quality mathematical model, to construct a disturbance data set using the power quality mathematical model, and to construct a power quality disturbance identification model; The training unit is used to train the disturbance recognition model with the disturbance data set; The monitoring unit is used to collect power grid operation data in real time and to monitor power quality using a disturbance identification model.

8. The device for monitoring power quality disturbance according to claim 7, characterized in that: The construction unit and the training unit are located at the cloud center end, the monitoring unit is located at the edge end, and the training unit is also used to send a disturbance recognition model to the monitoring unit.

9. An electronic device, characterized in that: It comprises a processor and a memory; the memory is used to store executable instructions, and the processor is used to execute the instructions to implement the monitoring method described in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that: The readable storage medium stores instructions, and when the instructions are executed, the monitoring method described in any one of claims 1 to 6 is implemented.

Images