An intelligent power distribution monitoring system

Abstract

The present invention relates to the technical field of power distribution monitoring of a micro-distribution system, and discloses an intelligent power distribution monitoring system, including: calculating the operating state parameters of the micro-distribution system according to the collected power distribution information of the micro-distribution system; sending the operating state parameters calculated in real time to the server through a message queue for storage; constructing an operating state parameter time series anomaly detection model using a generative adversarial network; optimizing and solving the model parameters of the constructed operating state parameter time series anomaly detection model; inputting the operating state parameter time series collected in real time into the optimized and solved anomaly detection sub-model to perform real-time monitoring of power distribution anomalies. The present invention obtains the operating state parameters of the power distribution system based on the network topology of the micro-distribution system, realizes the quantitative evaluation of the operating state of the micro-distribution system, adopts the adversarial training method to train the anomaly detection sub-model, and realizes the distribution anomaly monitoring based on the detection difference.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution monitoring of a micro power distribution system, and in particular to an intelligent power distribution monitoring system. Background Art

[0002] The existing intelligent power distribution monitoring methods are all aimed at large and medium-sized power distribution systems such as power grids, and the data indicators collected are highly different. However, in micro-distribution systems, the data indicators are less different, which makes the methods ineffective. Therefore, the existing power distribution monitoring methods are not suitable for micro-distribution systems. Therefore, there is an urgent need to monitor the power distribution of micro-current distribution systems. Summary of the invention

[0003] In view of this, the present invention provides an intelligent power distribution monitoring method, which aims to obtain the operating status parameters of the micro distribution system based on the network topology structure of the micro distribution system, evaluate the operating status of the micro distribution system, and use the generative adversarial network method to construct an operating status parameter time series anomaly detection model, and input the real-time collected operating status parameter time series into the optimized and solved anomaly detection sub-model, and the output result is the detection difference. If the detection difference exceeds the threshold, it means that there is a distribution anomaly in the micro distribution system, thereby realizing real-time monitoring of the micro distribution system.

[0004] To achieve the above object, the present invention provides an intelligent power distribution monitoring method, comprising the following steps:

[0005] S1: deploying a data collector in the network topology of the micro-distribution system, collecting distribution information of the distribution transformer in the micro-distribution system, and calculating the operating state parameters of the micro-distribution system according to the collected distribution information, wherein the distribution information includes current information and voltage information;

[0006] S2: The operating status parameters calculated in real time are sent to the server through the message queue for storage, forming a time series of operating status parameters of the micro-distribution system;

[0007] S3: constructing an operation status parameter time series anomaly detection model using a generative adversarial network, wherein the anomaly detection model includes an operation status parameter data generation sub-model and an anomaly detection sub-model;

[0008] S4: Optimizing and solving the model parameters of the constructed operation status parameter time series anomaly detection model to obtain an optimized anomaly detection sub-model;

[0009] S5: Input the real-time collected operating status parameter time series into the optimized and solved anomaly detection sub-model, and the output result is the detection difference. If the detection difference exceeds the threshold, it means that there is a distribution anomaly in the micro-distribution system, otherwise it is normal.

[0010] As a further improvement method of the present invention:

[0011] Optionally, in step S1, a data collector is deployed in the network topology of the micro-distribution system to collect distribution information of distribution transformers in the micro-distribution system, including:

[0012] The network topology of the micro-distribution system includes a server side, a distribution transformer and electrical equipment, wherein the server side is used to visualize the distribution process, including calculating and viewing the distribution information and the operating status parameters of the micro-distribution system, and the distribution transformer is used to transform the electric energy generated by the generator and distribute the transformed electric energy to the electrical equipment;

[0013] In the embodiment of the present invention, the current emitted by the distribution transformer is a microcurrent, the current unit of the microcurrent is microampere, and the range of the microcurrent is between 100 microamperes and 15000 microamperes. The electrical equipment includes microcurrent beauty instruments and microcurrent medical equipment, etc. Different equipment requires different microcurrents, and the distribution transformer is used to adjust and control the size of the microcurrent;

[0014] A data collector is deployed at the distribution transformer location to collect the distribution information of the distribution transformer in the micro-distribution system, wherein the data collector is used to collect the three-phase micro-current value and the three-phase voltage value in the distribution transformer. The signal representation of the distribution information is:

[0015] ;

[0016] in:

[0017] Indicates distribution transformer Three-phase micro-current signal at time t;

[0018] Indicates distribution transformer Three-phase voltage signal at time t;

[0019] Indicates distribution transformer Power distribution information signal at time t.

[0020] In an embodiment of the present invention, the data collector includes two distribution transformer interfaces, an analog-to-digital converter, an amplifier and a DMA (Direct Memory Access) controller. The distribution transformer interface is used to access the control chip of the distribution transformer, and sample the sampled current signal and the sampled voltage signal of the distribution transformer respectively. Since the signal in the distribution transformer of the micro-distribution system is too small, the amplifier is used to amplify the sampled signal, wherein the amplifier uses negative feedback to reduce the input impedance to implement the method of sampling the signal; the amplified sampled signal is converted into a digital signal by using the analog-to-digital converter, and the converted digital signal is the distribution information. The converted digital signal is directly transferred to the data calculator through the DMA controller, and 128 sample signal points are sampled in each sampling cycle, with 10 sampling cycles as a round; the voltage divider circuit of the distribution transformer performs level raising processing so that the sampled voltage signals are all above 0 volts, and the shunt circuit converts the current into a segmented current for sampling.

[0021] Optionally, in step S1, the operation status parameters of the micro power distribution system are calculated based on the collected power distribution information, including:

[0022] The data calculator receives the power distribution information of the distribution transformer in the micro power distribution system, and calculates the operating state parameters of the micro power distribution system. The calculation process of the operating state parameters is as follows:

[0023] ;

[0024] ;

[0025] ;

[0026] ;

[0027] ;

[0028] ;

[0029] in:

[0030] represents the micro-current unbalance parameter of the micro-distribution system at time t;

[0031] Indicates distribution transformer The three-phase voltages of ABC at time t;

[0032] Indicates distribution transformer The ABC three-phase micro current at time t;

[0033] Indicates distribution transformer The average phase current at time t is Indicates distribution transformer The average phase voltage at time t;

[0034] represents the set of distribution transformers in the micro-distribution system, N is the total number of distribution transformers in the micro-distribution system;

[0035] represents the voltage unbalance parameter of the micro-distribution system at time t;

[0036] is the active power of the micro-distribution system;

[0037] is the reference voltage of the digital-to-analog converter, D is the number of bits of the digital-to-analog converter, , For distribution transformers The voltage divider ratio, For distribution transformers The split ratio, For distribution transformers The resistance value;

[0038] is the power factor of the micro distribution system at time t;

[0039] The micro current unbalance parameter, voltage unbalance parameter and power factor of the micro distribution system at time t are used as the operating state parameters of the micro distribution system at time t. .

[0040] Optionally, in step S2, the operating status parameters calculated in real time are sent to the server through a message queue for storage, including:

[0041] The data calculator creates a Socket interface with the proxy server, and uses the Socket interface to send the calculated running status parameters to the queue of the proxy server. The server side monitors the number of Socket interfaces in the proxy server queue, and obtains the ready Socket interfaces in the proxy server queue, calls the Socket interface from the ready Socket interface in the queue according to the first-in-first-out rule, and extracts the running status parameters from the Hash table of the called Socket interface for storage. After the storage is completed, the Socket connection is disconnected.

[0042] Optionally, in step S2, forming a time series of operating status parameters of the micro power distribution system on the server side includes:

[0043] The server side stores the operating status parameters of the micro-distribution system in chronological order. The stored operating status parameters are in the form of:

[0044] ;

[0045] in:

[0046] T represents the time series of operating status parameters of the micro-distribution system;

[0047] For the micro distribution system at the initial moment The operating status parameters of

[0048] For micro-distribution systems at this moment The operating status parameters of the

[0049] Optionally, in step S3, constructing an operation status parameter time series anomaly detection model using a generative adversarial network includes:

[0050] Based on the generative adversarial network, an operation state parameter time series anomaly detection model is constructed. The operation state parameter time series anomaly detection model includes an operation state parameter data generation sub-model and anomaly detection sub-model. The input of the operation state parameter data generation sub-model is the normal operation state parameter time series, and the output is the operation state parameter time series generated by the model. The input of the anomaly detection sub-model is the operation state parameter time series, and the output is the detection difference. If the difference is greater than the threshold , then the operating status parameter time series is marked as abnormal 1, otherwise it is marked as normal 0;

[0051] The operating state parameter data generation sub-model includes an encoder and decoder , by using the encoder Encode the operating state parameter time series, and decode the encoding result by using a decoder to obtain a reconstructed operating state parameter time series as a generation result of the model;

[0052] The anomaly detection sub-model includes a discriminator ,The discriminator compares whether the data generated by the running status parameter data ,generation sub-model is similar to the original data in distribution, and compares whether the real-time running status ,parameter time series is similar to the normal running parameter time series, and outputs the detection ,difference degree according to the degree of distribution similarity.

[0053] Optionally, in step S4, optimizing and solving the model parameters of the constructed operation status parameter time series anomaly detection model includes:

[0054] Collect the time series data of the operating status parameters of the micro-distribution system under normal power distribution as training data, and construct the encoder in the operating status parameter data generation sub-model and decoder The objective function of training is:

[0055] ;

[0056] in:

[0057] It is the time series data of the operating status parameters of the micro-distribution system under normal power distribution. for Distribution of

[0058] represents expected value calculation;

[0059] For encoder Parameters, For decoder Parameters;

[0060] The operating state parameter time series generated by the operating state parameter data generation sub-model;

[0061] The operating state parameter time series generated by the operating state parameter data generation sub-model is used as the training data of the anomaly detection sub-model for adversarial training. The objective function of the anomaly detection sub-model training is:

[0062] ;

[0063] in:

[0064] c is the operating status parameter time series generated by the operating status parameter data generation sub-model, is the distribution of c;

[0065] For c and The sum of the differences in each dimension in the time neighborhood, including the micro-current unbalance parameter, the voltage unbalance parameter and the power factor, is As the detection difference of c;

[0066] The time series data of the operating status parameters of the micro-distribution system with normal distribution with Gaussian noise added;

[0067] are the parameters of the anomaly detection sub-model;

[0068] The updating and optimization process of the sub-model parameters is as follows:

[0069] ;

[0070] ;

[0071] in:

[0072] The parameters of the submodel At the kth iteration, the parameters of the sub-model include the encoder , Decoder And the discriminator Parameters;

[0073] is the learning rate, set it to 0.6;

[0074] is a hyperparameter, set it to 0.2;

[0075] For parameters The training objective function of

[0076] is the state parameter of the kth iteration;

[0077] Repeat the updating and optimization of the sub-model parameters until the sub-model parameters remain unchanged, and use the sub-model parameters finally optimized as the parameters of the sub-model to obtain the optimized operating status parameter data generation sub-model and the anomaly detection sub-model.

[0078] Optionally, in the step S5, the time series of the operating state parameters collected in real time is input into the optimized and solved abnormality detection sub-model, and the output result is the detection difference. If the detection difference exceeds a threshold, it indicates that there is a distribution abnormality in the micro-distribution system, including:

[0079] The real-time operating state parameter time series T of the micro-distribution system is input into the optimized anomaly detection sub-model. The anomaly detection sub-model outputs the detection difference degree of T. ,in is the anomaly detection sub-model, is the normal operation state parameter time series with Gaussian noise added. If the output detection difference is greater than the threshold , it means that there is an abnormality in the power distribution of the micro-distribution system at the current moment, otherwise it means that the power distribution of the micro-distribution system is normal.

[0080] In order to solve the above problems, the present invention further provides an intelligent power distribution monitoring system, characterized in that the system comprises:

[0081] The data acquisition and processing module includes a data collector and a data calculator, which are used to acquire the power distribution information of the distribution transformer in the micro-distribution system, calculate the operating status parameters of the micro-distribution system according to the acquired power distribution information, and send the real-time calculated operating status parameters to the server through a message queue;

[0082] The server side is used to store the operating status parameters and form a time series of the operating status parameters of the micro-distribution system;

[0083] A power distribution monitoring device is used to use a generative adversarial network to construct an operation status parameter time series anomaly detection model, optimize and solve the model parameters of the constructed operation status parameter time series anomaly detection model, input the collected operation status parameter time series into the optimized and solved anomaly detection sub-model, and output the detection difference. If the detection difference exceeds a threshold, it means that there is a power distribution anomaly in the micro-distribution system.

[0084] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0085] a memory storing at least one instruction; and

[0086] The processor executes the instructions stored in the memory to implement the above-mentioned intelligent power distribution monitoring method.

[0087] In order to solve the above problem, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned intelligent power distribution monitoring method.

[0088] Compared with the prior art, the present invention proposes an intelligent power distribution monitoring method, which has the following advantages:

[0089] First, this scheme proposes a method for quantifying the operating status of a micro-distribution system. By deploying a data collector at the location of the distribution transformer, the distribution information of the distribution transformer in the micro-distribution system is collected, and the data calculator calculates the operating status parameters of the micro-distribution system. The calculation process of the operating status parameters is as follows:

[0090] ;

[0091] ;

[0092] ;

[0093] ;

[0094] ;

[0095] ;

[0096] in: represents the micro-current unbalance parameter of the micro-distribution system at time t; Indicates distribution transformer The three-phase voltages of ABC at time t; Indicates distribution transformer The ABC three-phase micro current at time t; Indicates distribution transformer The average phase current at time t is Indicates distribution transformer The average phase voltage at time t; represents the set of distribution transformers in the micro-distribution system, N is the total number of distribution transformers in the micro-distribution system; represents the voltage unbalance parameter of the micro-distribution system at time t; is the active power of the micro-distribution system; is the reference voltage of the digital-to-analog converter, D is the number of bits of the digital-to-analog converter, , For distribution transformers The voltage divider ratio, For distribution transformers The split ratio, For distribution transformers The resistance value; is the power factor of the micro-distribution system at time t; the micro-current unbalance parameter, voltage unbalance parameter and power factor of the micro-distribution system at time t are used as the operating state parameters of the micro-distribution system at time t . The data calculator creates a Socket interface with the proxy server, and uses the Socket interface to send the calculated operating status parameters to the queue of the proxy server. The server monitors the number of Socket interfaces in the proxy server queue, obtains the ready Socket interfaces in the proxy server queue, calls the Socket interface from the ready Socket interface in the queue according to the first-in-first-out rule, and extracts the operating status parameters from the Hash table of the called Socket interface for storage. After the storage is completed, the Socket connection is disconnected. Since the proxy server queue sends the operating status parameter message to the server according to the first-in-first-out rule, the operating status parameters stored on the server are arranged in a chronological order. Compared with traditional technologies, this scheme deploys data collectors based on the network topology of the micro-distribution system. The deployed collectors are located in the distribution transformer of the distribution system, where the distribution transformer is an important power-consuming equipment in the distribution system. By obtaining the distribution information of the distribution transformer, the operating status of the distribution system is quantified, and the time series data of the operating status is formed. The real-time calculated operating status is added to the historical time series data, and the updated time series data is input into the detection model. If the detection is abnormal, it means that there is a distribution problem in the current distribution system.

[0097] At the same time, this scheme proposes a distribution monitoring method based on a generative adversarial network, by constructing an operation state parameter time series anomaly detection model based on the generative adversarial network, the operation state parameter time series anomaly detection model includes an operation state parameter data generation sub-model and an anomaly detection sub-model, the operation state parameter data generation sub-model includes an encoder and decoder , by using the encoder The operating state parameter time series is encoded, and the encoded result is decoded by a decoder to obtain a reconstructed operating state parameter time series as the generation result of the model; the anomaly detection submodel includes a discriminator The discriminator compares whether the data generated by the running state parameter data generation sub-model is similar to the original data in distribution, and compares whether the real-time running state parameter time series is similar to the normal running parameter time series in distribution, and outputs the detection difference according to the degree of distribution similarity. The training objective functions of the running state parameter data generation sub-model and the anomaly detection sub-model are constructed respectively, and the sub-model parameters are updated and optimized. The update and optimization process of the sub-model parameters is as follows:

[0098] ;

[0099] ;

[0100] in: The parameters of the submodel At the kth iteration, the parameters of the sub-model include the encoder , Decoder And the discriminator Parameters; is the learning rate, set it to 0.6; is a hyperparameter, set it to 0.2; For parameters The training objective function of is the state parameter of the kth iteration; repeat the update optimization of the sub-model parameters until the sub-model parameters remain unchanged, and use the sub-model parameters finally optimized as the sub-model parameters to obtain the optimized operating state parameter data generation sub-model and the anomaly detection sub-model. Input the real-time operating state parameter time series T of the micro-distribution system into the anomaly detection sub-model after optimization, and the detection difference degree of the anomaly detection sub-model output T is ,in is the anomaly detection sub-model, is the normal operation state parameter time series with Gaussian noise added. If the output detection difference is greater than the threshold , it means that there is a power distribution anomaly in the micro-distribution system at the current moment, otherwise it means that the power distribution of the micro-distribution system is normal. Compared with the traditional scheme, this scheme uses the generative adversarial network method to construct an operation status parameter time series anomaly detection model, and uses the adversarial training method to train the anomaly monitoring sub-model, that is, the input of the generated sub-model is used as the input of the anomaly monitoring sub-model, and the parameters of the anomaly monitoring sub-model are optimized. The parameters of the generated sub-model are optimized according to the input of the anomaly monitoring sub-model, and the real-time collected operation status parameter time series is input into the optimized and solved anomaly detection sub-model. The output result is the detection difference. If the detection difference exceeds the threshold, it means that there is a power distribution anomaly in the micro-distribution system, and the real-time monitoring of the micro-distribution system is realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0101] Figure 1 A schematic diagram of a flow chart of an intelligent power distribution monitoring method provided by an embodiment of the present invention;

[0102] Figure 2 A functional module diagram of an intelligent power distribution monitoring system provided by an embodiment of the present invention;

[0103] Figure 3 A schematic diagram of the structure of an electronic device for implementing an intelligent power distribution monitoring method provided by an embodiment of the present invention.

[0104] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0105] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0106] The embodiment of the present application provides an intelligent power distribution monitoring method. The execution subject of the intelligent power distribution monitoring method includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the intelligent power distribution monitoring method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0107] Embodiment 1:

[0108] S1: deploy a data collector in the network topology of the micro-distribution system, collect the distribution information of the distribution transformer in the micro-distribution system, and calculate the operating status parameters of the micro-distribution system based on the collected distribution information, wherein the distribution information includes current information and voltage information.

[0109] In the step S1, a data collector is deployed in the network topology of the micro-distribution system to collect distribution information of the distribution transformer in the micro-distribution system, including:

[0110] The network topology of the micro-distribution system includes a server side, a distribution transformer and electrical equipment, wherein the server side is used to visualize the distribution process, including calculating and viewing the distribution information and the operating status parameters of the micro-distribution system, and the distribution transformer is used to transform the electric energy generated by the generator and distribute the transformed electric energy to the electrical equipment;

[0111] In the embodiment of the present invention, the current emitted by the distribution transformer is a microcurrent, the current unit of the microcurrent is microampere, and the range of the microcurrent is between 100 microamperes and 15000 microamperes. The electrical equipment includes microcurrent beauty instruments and microcurrent medical equipment, etc. Different equipment requires different microcurrents, and the distribution transformer is used to adjust and control the size of the microcurrent;

[0112] A data collector is deployed at the distribution transformer location to collect the distribution information of the distribution transformer in the micro-distribution system, wherein the data collector is used to collect the three-phase micro-current value and the three-phase voltage value in the distribution transformer. The signal representation of the distribution information is:

[0113] ;

[0114] in:

[0115] Indicates distribution transformer Three-phase micro-current signal at time t;

[0116] Indicates distribution transformer Three-phase voltage signal at time t;

[0117] Indicates distribution transformer Power distribution information signal at time t.

[0118] In an embodiment of the present invention, the data collector includes two distribution transformer interfaces, an analog-to-digital converter, an amplifier and a DMA (Direct Memory Access) controller. The distribution transformer interface is used to access the control chip of the distribution transformer, and sample the sampled current signal and the sampled voltage signal of the distribution transformer respectively. Since the signal in the distribution transformer of the micro-distribution system is too small, the amplifier is used to amplify the sampled signal, wherein the amplifier uses negative feedback to reduce the input impedance to implement the method of sampling the signal; the amplified sampled signal is converted into a digital signal by using the analog-to-digital converter, and the converted digital signal is the distribution information. The converted digital signal is directly transferred to the data calculator through the DMA controller, and 128 sample signal points are sampled in each sampling cycle, with 10 sampling cycles as a round; the voltage divider circuit of the distribution transformer performs level raising processing so that the sampled voltage signals are all above 0 volts, and the shunt circuit converts the current into a segmented current for sampling.

[0119] In step S1, the operation status parameters of the micro power distribution system are calculated based on the collected power distribution information, including:

[0120] The data calculator receives the power distribution information of the distribution transformer in the micro power distribution system, and calculates the operating state parameters of the micro power distribution system. The calculation process of the operating state parameters is as follows:

[0121] ;

[0122] ;

[0123] ;

[0124] ;

[0125] ;

[0126] ;

[0127] in:

[0128] represents the micro-current unbalance parameter of the micro-distribution system at time t;

[0129] Indicates distribution transformer The three-phase voltages of ABC at time t;

[0130] Indicates distribution transformer The ABC three-phase micro current at time t;

[0131] Indicates distribution transformer The average phase current at time t is Indicates distribution transformer The average phase voltage at time t;

[0132] represents the set of distribution transformers in the micro-distribution system, N is the total number of distribution transformers in the micro-distribution system;

[0133] represents the voltage unbalance parameter of the micro-distribution system at time t;

[0134] is the active power of the micro-distribution system;

[0135] is the reference voltage of the digital-to-analog converter, D is the number of bits of the digital-to-analog converter, , For distribution transformers The voltage divider ratio, For distribution transformers The split ratio, For distribution transformers The resistance value;

[0136] is the power factor of the micro distribution system at time t;

[0137] The micro current unbalance parameter, voltage unbalance parameter and power factor of the micro distribution system at time t are used as the operating state parameters of the micro distribution system at time t. .

[0138] S2: The operating status parameters calculated in real time are sent to the server through the message queue for storage, forming a time series of the operating status parameters of the micro distribution system.

[0139] In the step S2, the operating status parameters calculated in real time are sent to the server through a message queue for storage, including:

[0140] The data calculator creates a Socket interface with the proxy server, and uses the Socket interface to send the calculated running status parameters to the queue of the proxy server. The server side monitors the number of Socket interfaces in the proxy server queue, and obtains the ready Socket interfaces in the proxy server queue, calls the Socket interface from the ready Socket interface in the queue according to the first-in-first-out rule, and extracts the running status parameters from the Hash table of the called Socket interface for storage. After the storage is completed, the Socket connection is disconnected.

[0141] In the step S2, the operating state parameter time series of the micro-distribution system is formed on the server side, including:

[0142] It should be explained that, since the proxy server queue sends the operation status parameter message to the server side according to the first-in-first-out rule, the operation status parameters stored in the server side are arranged in chronological order;

[0143] The server side stores the operating status parameters of the micro-distribution system in chronological order. The stored operating status parameters are in the form of:

[0144] ;

[0145] in:

[0146] T represents the time series of operating status parameters of the micro-distribution system;

[0147] For the micro distribution system at the initial moment The operating status parameters of

[0148] For micro-distribution systems at this moment The operating status parameters of the

[0149] S3: Use a generative adversarial network to construct an operation status parameter time series anomaly detection model, wherein the anomaly detection model includes an operation status parameter data generation sub-model and an anomaly detection sub-model.

[0150] In the step S3, a generative adversarial network is used to construct an operation status parameter time series anomaly detection model, including:

[0151] Based on the generative adversarial network, an operation state parameter time series anomaly detection model is constructed. The operation state parameter time series anomaly detection model includes an operation state parameter data generation sub-model and anomaly detection sub-model. The input of the operation state parameter data generation sub-model is the normal operation state parameter time series, and the output is the operation state parameter time series generated by the model. The input of the anomaly detection sub-model is the operation state parameter time series, and the output is the detection difference. If the difference is greater than the threshold , then the operating status parameter time series is marked as abnormal 1, otherwise it is marked as normal 0;

[0152] The operating state parameter data generation sub-model includes an encoder and decoder , by using the encoder Encode the operating state parameter time series, and decode the encoding result by using a decoder to obtain a reconstructed operating state parameter time series as a generation result of the model;

[0153] The anomaly detection sub-model includes a discriminator ,The discriminator compares whether the data generated by the running status parameter data ,generation sub-model is similar to the original data in distribution, and compares whether the real-time running status ,parameter time series is similar to the normal running parameter time series, and outputs the detection ,difference degree according to the degree of distribution similarity.

[0154] S4: Optimizing and solving the model parameters of the constructed operation status parameter time series anomaly detection model to obtain an anomaly detection sub-model after optimization and solution.

[0155] In the step S4, the model parameters of the constructed operation status parameter time series anomaly detection model are optimized and solved, including:

[0156] Collect the time series data of the operating status parameters of the micro-distribution system under normal power distribution as training data, and construct the encoder in the operating status parameter data generation sub-model and decoder The objective function of training is:

[0157] ;

[0158] in:

[0159] It is the time series data of the operating status parameters of the micro-distribution system under normal power distribution. for Distribution of

[0160] represents expected value calculation;

[0161] For encoder Parameters, For decoder Parameters;

[0162] The operating state parameter time series generated by the operating state parameter data generation sub-model;

[0163] The operating state parameter time series generated by the operating state parameter data generation sub-model is used as the training data of the anomaly detection sub-model for adversarial training. The objective function of the anomaly detection sub-model training is:

[0164] ;

[0165] in:

[0166] c is the operating status parameter time series generated by the operating status parameter data generation sub-model, is the distribution of c;

[0167] For c and The sum of the differences in each dimension in the time neighborhood, including the micro-current unbalance parameter, the voltage unbalance parameter and the power factor, is As the detection difference of c;

[0168] The time series data of the operating status parameters of the micro-distribution system with normal distribution with Gaussian noise added;

[0169] are the parameters of the anomaly detection sub-model;

[0170] The updating and optimization process of the sub-model parameters is as follows:

[0171] ;

[0172] ;

[0173] in:

[0174] The parameters of the submodel At the kth iteration, the parameters of the sub-model include the encoder , Decoder And the discriminator Parameters;

[0175] is the learning rate, set it to 0.6;

[0176] is a hyperparameter, set it to 0.2;

[0177] For parameters The training objective function of

[0178] is the state parameter of the kth iteration;

[0179] Repeat the updating and optimization of the sub-model parameters until the sub-model parameters remain unchanged, and use the sub-model parameters finally optimized as the parameters of the sub-model to obtain the optimized operating status parameter data generation sub-model and the anomaly detection sub-model.

[0180] It should be explained that the initial values ​​of the sub-model parameters are randomly generated, and the model parameter training method of the operating status parameter data generation sub-model and the anomaly detection sub-model is asynchronous training.

[0181] S5: Input the real-time collected operating status parameter time series into the optimized and solved anomaly detection sub-model, and the output result is the detection difference. If the detection difference exceeds the threshold, it means that there is a distribution anomaly in the micro-distribution system, otherwise it is normal.

[0182] In the step S5, the real-time collected operating state parameter time series is input into the optimized and solved abnormality detection sub-model, and the output result is the detection difference. If the detection difference exceeds the threshold, it means that there is a distribution abnormality in the micro-distribution system, including:

[0183] The real-time operating state parameter time series T of the micro-distribution system is input into the optimized anomaly detection sub-model. The anomaly detection sub-model outputs the detection difference degree of T. ,in is the anomaly detection sub-model, is the normal operation state parameter time series with Gaussian noise added. If the output detection difference is greater than the threshold , it means that there is an abnormality in the power distribution of the micro-distribution system at the current moment, otherwise it means that the power distribution of the micro-distribution system is normal.

[0184] Embodiment 2:

[0185] like Figure 2 , which is a functional module diagram of an intelligent power distribution monitoring system provided in one embodiment of the present invention, which can implement the power distribution monitoring method in Example 1.

[0186] The intelligent power distribution monitoring system 100 of the present invention can be installed in an electronic device. According to the functions to be implemented, the intelligent power distribution monitoring system can include a data acquisition and processing module 101, a server 102 and a power distribution monitoring device 103. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0187] The data acquisition and processing module 101 includes a data collector and a data calculator, which are used to acquire the power distribution information of the distribution transformer in the micro-distribution system, calculate the operating status parameters of the micro-distribution system according to the acquired power distribution information, and send the real-time calculated operating status parameters to the server through a message queue;

[0188] The server 102 is used to store the operating status parameters to form a time series of the operating status parameters of the micro-distribution system;

[0189] The power distribution monitoring device 103 is used to construct an operation status parameter time series anomaly detection model using a generative adversarial network, optimize and solve the model parameters of the constructed operation status parameter time series anomaly detection model, input the collected operation status parameter time series into the optimized and solved anomaly detection sub-model, and output the detection difference. If the detection difference exceeds a threshold, it indicates that there is a power distribution anomaly in the micro-distribution system.

[0190] In detail, each module in the intelligent power distribution monitoring system 100 in the embodiment of the present invention is used in the same manner as described above. Figure 1 The intelligent power distribution monitoring method described in the present invention has the same technical means and can produce the same technical effects, so it will not be repeated here.

[0191] Embodiment 3:

[0192] like Figure 3 FIG. 1 is a schematic diagram of the structure of an electronic device for implementing an intelligent power distribution monitoring method provided by an embodiment of the present invention.

[0193] The electronic device 1 may include a processor 10 , a memory 11 and a bus, and may also include a computer program stored in the memory 11 and executable on the processor 10 , such as an intelligent power distribution monitoring program 12 .

[0194] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the intelligent power distribution monitoring program 12, etc., but also be used to temporarily store data that has been output or is to be output.

[0195] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes various functions and processes data of the electronic device 1 by running or executing programs or modules (such as intelligent power distribution monitoring programs) stored in the memory 11, and calling data stored in the memory 11.

[0196] The bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0197] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0198] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0199] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0200] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0201] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0202] The intelligent power distribution monitoring program 12 stored in the memory 11 in the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve:

[0203] Deploy a data collector in the network topology of the micro-distribution system to collect distribution information of the distribution transformer in the micro-distribution system, and calculate the operating status parameters of the micro-distribution system based on the collected distribution information;

[0204] The operating status parameters calculated in real time are sent to the server through the message queue for storage, forming a time series of operating status parameters of the micro-distribution system;

[0205] Use generative adversarial networks to build an anomaly detection model for time series of operating status parameters;

[0206] Optimizing and solving the model parameters of the constructed operation status parameter time series anomaly detection model to obtain an optimized anomaly detection sub-model;

[0207] The time series of operating status parameters collected in real time is input into the optimized anomaly detection sub-model, and the output result is the detection difference. If the detection difference exceeds the threshold, it means that there is a distribution anomaly in the micro-distribution system, otherwise it is normal.

[0208] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0209] It should be noted that the serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. And the terms "including", "comprising" or any other variants thereof in this article are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "including a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0210] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0211] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An intelligent power distribution monitoring method, characterized in that: The method comprises: S1: deploying a data collector in the network topology of the micro-distribution system, collecting distribution information of the distribution transformer in the micro-distribution system, and calculating the operating state parameters of the micro-distribution system according to the collected distribution information, wherein the distribution information includes current information and voltage information; S2: The operating status parameters calculated in real time are sent to the server through the message queue for storage, forming a time series of operating status parameters of the micro-distribution system; S3: constructing an operation status parameter time series anomaly detection model using a generative adversarial network, wherein the anomaly detection model includes an operation status parameter data generation sub-model and an anomaly detection sub-model; S4: Optimizing and solving the model parameters of the constructed operation status parameter time series anomaly detection model to obtain an optimized anomaly detection sub-model; S5: Input the real-time collected operation status parameter time series into the optimized and solved anomaly detection sub-model, and the output result is the detection difference. If the detection difference exceeds the threshold, it means that the micro-distribution system has a power distribution anomaly, otherwise it is normal; In the step S3, a generative adversarial network is used to construct an operation status parameter time series anomaly detection model, including: Based on the generative adversarial network, an operation state parameter time series anomaly detection model is constructed. The operation state parameter time series anomaly detection model includes an operation state parameter data generation sub-model and anomaly detection sub-model. The input of the operation state parameter data generation sub-model is the normal operation state parameter time series, and the output is the operation state parameter time series generated by the model. The input of the anomaly detection sub-model is the operation state parameter time series, and the output is the detection difference. If the difference is greater than the threshold , then the operating status parameter time series is marked as abnormal 1, otherwise it is marked as normal 0; The operating state parameter data generation sub-model includes an encoder and decoder , by using the encoder Encode the operating state parameter time series, and decode the encoding result by using a decoder to obtain a reconstructed operating state parameter time series as a generation result of the model; The anomaly detection sub-model includes a discriminator ,The discriminator compares whether the data generated by the running state parameter data generation sub-model is similar to the original data in distribution, and compares whether the real-time running state parameter time series is similar to the normal running parameter time series, and outputs the detection difference degree according to the degree of distribution similarity; In the step S4, the model parameters of the constructed operation status parameter time series anomaly detection model are optimized and solved, including: Collect the time series data of the operating status parameters of the micro-distribution system under normal power distribution as training data, and construct the encoder in the operating status parameter data generation sub-model and decoder The objective function of training is: ； in: It is the time series data of the operating status parameters of the micro-distribution system under normal power distribution. for Distribution of represents expected value calculation; For encoder Parameters, For decoder Parameters; The operating state parameter time series generated by the operating state parameter data generation sub-model; The operating state parameter time series generated by the operating state parameter data generation sub-model is used as the training data of the anomaly detection sub-model for adversarial training. The objective function of the anomaly detection sub-model training is: ； in: c is the operating status parameter time series generated by the operating status parameter data generation sub-model, is the distribution of c; For c and The sum of the differences in each dimension in the time neighborhood, including the micro-current unbalance parameter, the voltage unbalance parameter and the power factor, is As the detection difference of c; The time series data of the operating status parameters of the micro-distribution system with normal distribution with Gaussian noise added; are the parameters of the anomaly detection sub-model; The updating and optimization process of the sub-model parameters is as follows: ； in: The parameters of the submodel At the kth iteration, the parameters of the sub-model include the encoder , Decoder And the discriminator Parameters; is the learning rate, set it to 0.6; is a hyperparameter, set it to 0.2; For parameters The training objective function of is the state parameter of the kth iteration; Repeat the updating and optimization of the sub-model parameters until the sub-model parameters remain unchanged, and use the sub-model parameters finally optimized as the parameters of the sub-model to obtain the optimized operating status parameter data generation sub-model and the anomaly detection sub-model.

2. The intelligent power distribution monitoring method according to claim 1, characterized in that: In the step S1, a data collector is deployed in the network topology of the micro-distribution system to collect distribution information of the distribution transformer in the micro-distribution system, including: The network topology of the micro-distribution system includes a server, a distribution transformer and power-consuming equipment, wherein the server is used to visualize the distribution process, including calculating and viewing the distribution information and the operating status parameters of the micro-distribution system, and the distribution transformer is used to transform the electric energy generated by the generator and distribute the transformed electric energy to the power-consuming equipment. A data collector is deployed at the distribution transformer location to collect the distribution information of the distribution transformer in the micro-distribution system, wherein the data collector is used to collect the three-phase micro-current value and the three-phase voltage value in the distribution transformer. The signal representation of the distribution information is: ; in: Indicates distribution transformer Three-phase micro-current signal at time t; Indicates distribution transformer Three-phase voltage signal at time t; Indicates distribution transformer Power distribution information signal at time t.

3. The intelligent power distribution monitoring method according to claim 2, characterized in that: In step S1, the operation status parameters of the micro power distribution system are calculated based on the collected power distribution information, including: The data calculator receives the power distribution information of the distribution transformer in the micro power distribution system, and calculates the operating state parameters of the micro power distribution system. The calculation process of the operating state parameters is as follows: ; in: represents the micro-current unbalance parameter of the micro-distribution system at time t; Indicates distribution transformer The three-phase voltages of ABC at time t; Indicates distribution transformer The ABC three-phase micro current at time t; Indicates distribution transformer The average phase current at time t is Indicates distribution transformer The average phase voltage at time t; represents the set of distribution transformers in the micro-distribution system, N is the total number of distribution transformers in the micro-distribution system; represents the voltage unbalance parameter of the micro-distribution system at time t; is the active power of the micro-distribution system; is the reference voltage of the digital-to-analog converter, D is the number of bits of the digital-to-analog converter, , For distribution transformers The voltage divider ratio, For distribution transformers The split ratio, For distribution transformers The resistance value; is the power factor of the micro distribution system at time t; The micro current unbalance parameter, voltage unbalance parameter and power factor of the micro distribution system at time t are used as the operating state parameters of the micro distribution system at time t. .

4. The intelligent power distribution monitoring method according to claim 1, characterized in that: In the step S2, the operating status parameters calculated in real time are sent to the server through a message queue for storage, including: The data calculator creates a Socket interface with the proxy server, and uses the Socket interface to send the calculated running status parameters to the queue of the proxy server. The server side monitors the number of Socket interfaces in the proxy server queue, and obtains the ready Socket interfaces in the proxy server queue, calls the Socket interface from the ready Socket interface in the queue according to the first-in-first-out rule, and extracts the running status parameters from the Hash table of the called Socket interface for storage. After the storage is completed, the Socket connection is disconnected.

5. The intelligent power distribution monitoring method according to claim 4, characterized in that: In the step S2, the operating state parameter time series of the micro-distribution system is formed on the server side, including: The server side stores the operating status parameters of the micro-distribution system in chronological order. The stored operating status parameters are in the form of: ; in: T represents the time series of operating status parameters of the micro-distribution system; For the micro distribution system at the initial moment The operating status parameters of For micro-distribution systems at this moment The operating status parameters of the 6. The intelligent power distribution monitoring method according to claim 5, characterized in that: In the step S5, the real-time collected operating state parameter time series is input into the optimized and solved abnormality detection sub-model, and the output result is the detection difference. If the detection difference exceeds the threshold, it means that there is a distribution abnormality in the micro-distribution system, including: The real-time operating state parameter time series T of the micro-distribution system is input into the optimized anomaly detection sub-model. The anomaly detection sub-model outputs the detection difference degree of T. , where D is the anomaly detection sub-model, is the normal operation state parameter time series with Gaussian noise added. If the output detection difference is greater than the threshold , it means that there is an abnormality in the power distribution of the micro-distribution system at the current moment, otherwise it means that the power distribution of the micro-distribution system is normal.

7. An intelligent power distribution monitoring system, characterized in that: The system comprises: The data acquisition and processing module includes a data collector and a data calculator, which are used to acquire the power distribution information of the distribution transformer in the micro-distribution system, calculate the operating status parameters of the micro-distribution system according to the acquired power distribution information, and send the real-time calculated operating status parameters to the server through a message queue; The server side is used to store the operating status parameters and form a time series of the operating status parameters of the micro-distribution system; A power distribution monitoring device is used to use a generative adversarial network to construct an operation status parameter time series anomaly detection model, optimize and solve the model parameters of the constructed operation status parameter time series anomaly detection model, input the collected operation status parameter time series into the optimized and solved anomaly detection sub-model, and output the detection difference. If the detection difference exceeds a threshold, it indicates that there is a power distribution anomaly in the micro-distribution system, so as to realize an intelligent power distribution monitoring method as described in any one of claims 1 to 6.

Images