A power distribution network whole-process data monitoring method

Abstract

The application relates to a power distribution network whole-process data monitoring method, which comprises the following steps: obtaining a power distribution network data monitoring model according to the topological relationship between nodes of the power distribution network and by collecting the operation state characteristics of the nodes through sensors; obtaining a monitoring data set according to the power distribution network data monitoring model, and determining the types and quantities of the operation state characteristics; inputting the monitoring data set and monitoring target parameters of different categories into a machine learning model to obtain associated characteristics of each monitoring target parameter; dividing the monitoring data set into multiple monitoring sub-data sets based on the associated characteristics of each monitoring target parameter; initiating a monitoring request for any monitoring target parameter, obtaining a sub-data set of the corresponding monitoring target parameter, and obtaining multiple monitoring target time sequence data sets based on a monitoring time interval and the associated characteristics; and inputting the multiple monitoring target time sequence data sets into an anomaly detection model to identify whether the monitoring parameters are abnormal.

Description

TECHNICAL FIELD

[0001] The application relates to a power distribution network whole-process data monitoring method and belongs to the technical field of power distribution network data monitoring. BACKGROUND

[0002] With the rapid development of smart grids, the accuracy and real-time performance of power distribution network data monitoring are increasingly required. However, in practical applications, there are many defects in power distribution network data monitoring, which affect the stable operation of the power system and the power supply quality.

[0003] Firstly, the imperfection of power distribution network data monitoring equipment is one of the main reasons for defects. The monitoring equipment of the power distribution network in some areas is outdated and has single functions, which cannot meet the current demand of the power system. These devices can only monitor limited power parameters and cannot fully reflect the operation status of the power distribution network. At the same time, due to equipment aging, improper maintenance and other reasons, the accuracy and reliability of the monitoring data are greatly reduced.

[0004] Secondly, the lack of real-time performance of data monitoring is also a major defect of power distribution network data monitoring. In the power system, the operation status of the power distribution network is real-time changing, and real-time monitoring and processing of data are crucial. However, the existing data monitoring system often has problems such as data transmission delay and slow processing speed, which leads to the fact that the monitoring data cannot timely reflect the actual status of the power distribution network. This may lead to untimely fault discovery, increasing the safety risk of the power system.

[0005] In addition, the low degree of intelligence of power distribution network data monitoring is also a major problem. With the continuous development of artificial intelligence technology, power distribution network data monitoring should gradually realize intelligence to improve the efficiency and accuracy of data processing and analysis. However, most of the current power distribution network data monitoring systems still remain in the stage of simple data collection and display, lacking intelligent analysis and prediction functions. This makes it difficult for operation and maintenance personnel to extract valuable information from massive data, affecting the optimized operation of the power system. SUMMARY

[0006] In order to solve the problems existing in the prior art, the application provides a power distribution network whole-process data monitoring method.

[0007] The technical scheme of the application is as follows:

[0008] On the one hand, the application provides a power distribution network whole-process data monitoring method, which comprises the following steps:

[0009] According to the topological relationship between each node of the power distribution network, and by collecting the operation state characteristics of each node through sensors, a power distribution network data monitoring model is obtained;

[0010] According to the power distribution network data monitoring model, a monitoring data set is obtained, and the types and quantities of the operating state features are determined;

[0011] The monitoring data set and the monitoring target parameters of different categories are input into the machine learning model to obtain the associated features of each monitoring target parameter, the associated features being operating state features having relevance to the monitoring target parameters;

[0012] The monitoring data set is divided into a plurality of monitoring sub-data sets based on the associated features of each monitoring target parameter, each sub-data set corresponding to a monitoring target parameter and the corresponding associated features;

[0013] A monitoring request for any monitoring target parameter is initiated, a sub-data set corresponding to the monitoring target parameter is obtained, a plurality of monitoring target time series data sets are obtained based on the monitoring time interval and the associated features, and the plurality of monitoring target time series data sets are input into the anomaly detection model to identify whether the monitoring parameters are abnormal.

[0014] As a preferred embodiment, the step of obtaining the power distribution network data monitoring model according to the topological relationship between each node of the power distribution network and collecting the operating state features of each node by the sensor is specifically as follows:

[0015] Establish a state model:

[0016] F(QN)=P(Q1)·P(Q2 / Q1)·P(Q3 / Q2)·……·P(Qn / Qn-1);

[0017] Wherein, F(QN) represents the state model of the node set of the power distribution network, Qn represents the state of the nth node in the power distribution network, and P(Qn / Qn-1) represents the conditional probability distribution between the (n-1)th node and the nth node in the power distribution network.

[0018] And the state Qn of the nth node in the power distribution network and the state Qn-1 of the (n-1)th node satisfy:

[0019] Qn=Qn-1+s;

[0020] Wherein, s is state noise conforming to Gaussian distribution;

[0021] Therefore, P(Qn / Qn-1)=G(Qn-1,σ 2 ); G(·,σ 2 ) represents Gaussian distribution;

[0022] Establish a sampling model:

[0023] F(xn / Qn)=G(J(xn),σ 2 );

[0024] Wherein, F(xn / Qn) is a probability distribution of the sampling value of the node of the power distribution network in the state Qn, xn is the sensor sampling value of the nth node, and J(xn) is a sampling function;

[0025] And J(xn) = xn + τ;

[0026] Wherein, τ is sampling noise conforming to a Gaussian distribution;

[0027] The power distribution network data monitoring model is obtained by combining the state model and the sampling model:

[0028] Y(QN, xN) = P(Q1)F(x1 / Q1)·P(Q2 / Q1)F(x2 / Q2)·P(Q3 / Q2)F(x3 / Q3)·……·P(Qn / Qn-1)F(xn / Qn).

[0029] As a preferred embodiment, the step of inputting the monitoring data set and the monitoring target parameters of different categories into the machine learning model to obtain the associated features of each monitoring target parameter specifically comprises:

[0030] The monitoring data set is preprocessed, and the preprocessing includes data cleaning and normalization processing;

[0031] Based on the preprocessed monitoring data set, a training sample set is established, and each training sample in the training sample set contains an operating state feature and a corresponding monitoring target parameter label;

[0032] A machine learning model based on a neural network is constructed; the machine learning model is iteratively trained by using the training sample set to obtain a trained associated feature classification model;

[0033] The monitoring data set and the monitoring target parameters of different categories are input into the trained associated feature classification model, and the associated features corresponding to each input monitoring target parameter are output.

[0034] As a preferred embodiment, the operating state features include voltage, current, power factor, load rate, temperature, and humidity.

[0035] In another aspect, the present application also provides a power distribution network full-process data monitoring system, comprising:

[0036] A monitoring model establishment module is configured to obtain a power distribution network data monitoring model according to the topological relationship between nodes of the power distribution network and by collecting operating state features of the nodes through sensors;

[0037] A feature classification module is configured to obtain a monitoring data set and determine the types and quantities of operating state features according to the power distribution network data monitoring model;

[0038] The association feature acquisition module is configured to input the monitoring data set and the monitoring target parameters of different categories into the machine learning model, and acquire an association feature of each monitoring target parameter, the association feature being an operation state feature having an association with the monitoring target parameter;

[0039] The data set division module is configured to divide the monitoring data set into a plurality of monitoring sub-data sets based on the association feature of each monitoring target parameter, each sub-data set corresponding to a monitoring target parameter and a corresponding association feature;

[0040] The anomaly diagnosis module is configured to initiate a monitoring request for any monitoring target parameter, acquire a sub-data set of the corresponding monitoring target parameter, acquire a plurality of monitoring target time sequence data sets based on a monitoring time interval and each association feature, and input the plurality of monitoring target time sequence data sets into the anomaly detection model to identify whether the monitoring parameter is abnormal.

[0041] As a preferred embodiment, the step of obtaining the power distribution network data monitoring model according to the topological relationship between each node of the power distribution network and by collecting the operation state features of each node by the sensor is specifically as follows:

[0042] Establish a state model:

[0043] F(QN)=P(Q1)·P(Q2 / Q1)·P(Q3 / Q2)·……·P(Qn / Qn-1);

[0044] wherein, F(QN) represents the state model of the node set of the power distribution network, Qn represents the state of the nth node in the power distribution network, and P(Qn / Qn-1) represents the conditional probability distribution between the (n-1)th node and the nth node in the power distribution network.

[0045] and the state Qn of the nth node in the power distribution network and the state Qn-1 of the (n-1)th node satisfy:

[0046] Qn=Qn-1+s;

[0047] wherein, s is state noise conforming to a Gaussian distribution;

[0048] P(Qn / Qn-1)=G(Qn-1,σ 2 ); G(·,σ 2 ) represents a Gaussian distribution.

[0049] Establish a sampling model:

[0050] F(xn / Qn)=G(J(xn),σ 2 );

[0051] Wherein, F(xn / Qn) is a probability distribution of a sampling value of a node of a power distribution network in a state Qn, xn is a sensor sampling value of an nth node, and J(xn) is a sampling function;

[0052] And J(xn) = xn + τ;

[0053] Wherein, τ is sampling noise conforming to a Gaussian distribution;

[0054] The state model and the sampling model are combined to obtain a power distribution network data monitoring model:

[0055] Y(QN, xN) = P(Q1)F(x1 / Q1)·P(Q2 / Q1)F(x2 / Q2)·P(Q3 / Q2)F(x3 / Q3)·……·P(Qn / Qn-1)F(xn / Qn).

[0056] As a preferred embodiment, the step of inputting the monitoring data set and the monitoring target parameters of different categories into the machine learning model to obtain the associated features of each monitoring target parameter specifically comprises:

[0057] The monitoring data set is preprocessed, and the preprocessing includes data cleaning and normalization processing;

[0058] Based on the preprocessed monitoring data set, a training sample set is established, and each training sample in the training sample set contains an operating state feature and a corresponding monitoring target parameter label;

[0059] A machine learning model based on a neural network is constructed; the machine learning model is iteratively trained by using the training sample set to obtain a trained associated feature classification model;

[0060] The monitoring data set and the monitoring target parameters of different categories are input into the trained associated feature classification model, and the associated features corresponding to each input monitoring target parameter are output.

[0061] As a preferred embodiment, the operating state features include voltage, current, power factor, load rate, temperature and humidity.

[0062] In another aspect, the present application also provides an electronic device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the power distribution network whole-process data monitoring method according to any one of the embodiments of the present application when executing the program.

[0063] In another aspect, the present application also provides a computer readable storage medium, which stores a computer program, and the program is executable on a processor to implement the power distribution network whole-process data monitoring method according to any one of the embodiments of the present application.

[0064] The present application has the following advantages:

[0065] The application discloses a power distribution network full-process data monitoring method, which comprises the following steps: establishing a power distribution network data monitoring model through topological relations and sensor collected data; constructing a monitoring data set through the power distribution network data monitoring model, and classifying collected features; acquiring associated features of monitoring target parameters by using a machine learning model, so as to divide a sub-data set of each monitoring target parameter; and finally, identifying an abnormal condition by using an anomaly detection model and the sub-data set of each monitoring target parameter, thereby improving reliability and safety of the power distribution network. BRIEF DESCRIPTION OF DRAWINGS

[0066] Figure 1 It is a method flowchart of the embodiment one of the application. DETAILED DESCRIPTION

[0067] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative work are within the protection scope of the application.

[0068] It should be understood that the step numbers used herein are only for the convenience of description, and are not limited to the execution sequence of the steps.

[0069] It should be understood that the terms used in the specification of the application are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in the specification and the appended claims of the application, unless otherwise clear from the context, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0070] The terms "comprise" and "include" indicate the presence of described features, integers, steps, operations, elements, and / or components, but do not exclude one or more other features, integers, steps, operations, elements, components, and / or sets thereof.

[0071] The term "and / or" means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0072] Embodiment one:

[0073] Reference Figure 1In the power system, as the key link of power transmission and distribution, the stable operation of the distribution network is crucial to ensure the reliability of the entire power supply. In order to realize the comprehensive monitoring and accurate management of the operation state of the distribution network, the embodiment provides a distribution network whole-process data monitoring method based on topology relationship and machine learning technology, which specifically includes the following steps:

[0074] S100, according to the topology relationship between each node of the distribution network, the structure and connection mode of the whole process of the distribution network are clearly understood, and the running state characteristics of each node are collected in real time through sensors, including voltage, current, power factor and other key indicators. Comprehensive node topology relationship and running state characteristics, establish a distribution network data monitoring model.

[0075] S200, according to the distribution network data monitoring model, obtain the monitoring data set, and determine the type and number of running state characteristics; it can understand the running state of the distribution network, and provide basic data resources for subsequent machine learning model training.

[0076] S300, input the monitoring data set and different categories of monitoring target parameters into the machine learning model to obtain the associated characteristics of each monitoring target parameter, the associated characteristics are the running state characteristics associated with the monitoring target parameters;

[0077] S400, based on the associated characteristics of each monitoring target parameter, the monitoring data set is divided into multiple monitoring sub-data sets, each sub-data set corresponds to a monitoring target parameter and the corresponding associated characteristics;

[0078] S500, initiate a monitoring request for any monitoring target parameter, and quickly obtain the sub-data set of the corresponding monitoring target parameter. Then, according to the set monitoring time interval and the associated characteristics, we can construct multiple monitoring target time series data sets. These time series data sets can intuitively show the change of the monitoring target parameter with time; input multiple monitoring target time series data sets into the anomaly detection model to identify whether the monitoring parameter is abnormal.

[0079] Based on the above embodiment, the method provided by the embodiment can realize whole-process monitoring of the running state of the distribution network through topology relationship and machine learning technology. By deeply analyzing the running state characteristics, constructing the monitoring sub-data set and using the anomaly detection model, abnormal faults can be found and solved in time, and the reliability and safety of the distribution network are improved.

[0080] As a preferred embodiment of the present embodiment, the step of obtaining the distribution network data monitoring model according to the topology relationship between each node of the distribution network and collecting the running state characteristics of each node through the sensor is specifically:

[0081] Establish a state model:

[0082] F(QN)=P(Q1)·P(Q2 / Q1)·P(Q3 / Q2)·……·P(Qn / Qn-1);

[0083] Wherein, F(QN) represents the state model of each node set of the power distribution network, Qn represents the state of the nth node in the power distribution network; P(Qn / Qn-1) represents the conditional probability distribution between the (n-1) th node and the nth node in the power distribution network;

[0084] And the state Qn of the nth node in the power distribution network and the state Qn-1 of the (n-1) th node exist:

[0085] Qn=Qn-1+s;

[0086] Wherein, s is the state noise conforming to the Gaussian distribution;

[0087] Then P(Qn / Qn-1)=G(Qn-1,σ 2 ); G(·,σ 2 ) represents the Gaussian distribution;

[0088] Establish a sampling model:

[0089] F(xn / Qn)=G(J(xn),σ 2 );

[0090] Wherein, F(xn / Qn) is the probability distribution of the sampling value of the power distribution network node under the state Qn, xn is the sensor sampling value of the nth node, and J(xn) is the sampling function;

[0091] And J(xn)=xn+τ;

[0092] Wherein, τ is the sampling noise conforming to the Gaussian distribution;

[0093] The state model and the sampling model are combined to obtain the power distribution network data monitoring model:

[0094] Y(QN,xN)=P(Q1)F(x1 / Q1)·P(Q2 / Q1)F(x2 / Q2)·P(Q3 / Q2)F(x3 / Q3)·……·P(Qn / Qn-1)F(xn / Qn).

[0095] As a preferred embodiment of the present embodiment, the step of inputting the monitoring data set and the monitoring target parameters of different categories into the machine learning model to obtain the associated features of each monitoring target parameter specifically comprises:

[0096] The monitoring data set is preprocessed, and the preprocessing includes data cleaning and normalization processing; the purpose is to eliminate noise, errors and redundant information in the original data, and to enable data of different dimensions to be compared and calculated on the same scale.

[0097] Data cleaning involves checking for missing values, outliers, duplicate values and other issues in the data, and performing appropriate processing. For missing values, interpolation, mean filling, median filling and other methods can be used to fill in; for outliers, it is necessary to judge according to the distribution of the data and the business background to decide whether to exclude or correct; for duplicate values, direct de-duplication processing is performed.

[0098] Because data of different features may have different dimensions and units, if used directly for training of a machine learning model, it may cause the model to fail to correctly learn the internal rules and relationships of the data. Therefore, the data is normalized to scale the data of each feature to the same range, such as [0, 1] or [-1, 1], thereby eliminating the influence of dimensions and units on model training.

[0099] Based on the preprocessed monitoring data set, a training sample set is established, each training sample in the training sample set includes an operating state feature and a corresponding monitoring target parameter label; the monitoring target parameter label is obtained by feature extraction and label annotation on the monitoring data set.

[0100] A machine learning model based on a neural network is constructed; the training sample set is used to iteratively train the machine learning model, and the parameters and structure of the model are continuously adjusted to minimize the prediction error and improve the generalization ability of the model, to obtain a trained correlation feature classification model;

[0101] The monitoring data set and monitoring target parameters of different categories are input into the trained correlation feature classification model, and the correlation feature corresponding to each monitoring target parameter input is output.

[0102] As a preferred embodiment of the present embodiment, the operating state feature includes voltage, current, power factor, load rate, temperature and humidity, and voltage and current are important indicators of the operating state of power equipment in the node. The stability of voltage is directly related to whether the equipment can work normally. If the voltage is too high or too low, it may cause damage to the equipment, and even cause a fault. The size and change of current can reflect the load condition of the equipment and reveal the power consumption condition of the equipment.

[0103] The higher the power factor, the higher the power utilization rate of the equipment, and vice versa, indicating that there is a large amount of reactive power loss. Therefore, by monitoring the power factor, the energy efficiency operating state of the equipment can be discovered in a timely manner.

[0104] The load rate represents the proportional relationship between the actual load borne by the equipment and the rated load. The high or low load rate directly reflects the utilization of the equipment, and both high and low load rates can adversely affect the equipment.

[0105] Temperature and humidity are important environmental factors that affect the running state of equipment. Equipment generates heat during operation, and if heat dissipation is poor or the environmental temperature is too high, it may cause the equipment temperature to rise, thereby affecting its normal operation. At the same time, too high humidity may cause condensation or corrosion problems inside the equipment.

[0106] Embodiment two:

[0107] The embodiment provides a power distribution network full-process data monitoring system, comprising:

[0108] The monitoring model establishment module is configured to obtain a power distribution network data monitoring model according to the topological relationship between nodes of the power distribution network and by collecting the running state characteristics of the nodes through sensors; the module is configured to realize the function of step S100 in embodiment one, and details are not repeated here;

[0109] The feature classification module is configured to obtain a monitoring data set and determine the types and quantities of the running state characteristics according to the power distribution network data monitoring model; the module is configured to realize the function of step S200 in embodiment one, and details are not repeated here;

[0110] The associated feature acquisition module is configured to input the monitoring data set and different types of monitoring target parameters into a machine learning model to obtain associated features of each monitoring target parameter, the associated features being running state characteristics having relevance to the monitoring target parameters; the module is configured to realize the function of step S300 in embodiment one, and details are not repeated here;

[0111] The data set division module is configured to divide the monitoring data set into a plurality of monitoring sub-data sets based on the associated features of each monitoring target parameter, each sub-data set corresponding to a monitoring target parameter and corresponding associated features; the module is configured to realize the function of step S400 in embodiment one, and details are not repeated here;

[0112] The anomaly diagnosis module is configured to initiate a monitoring request for any monitoring target parameter, obtain a sub-data set of the corresponding monitoring target parameter, obtain a plurality of monitoring target time series data sets based on a monitoring time interval and the associated features, input the plurality of monitoring target time series data sets into an anomaly detection model to identify whether the monitoring parameters are abnormal; the module is configured to realize the function of step S500 in embodiment one, and details are not repeated here.

[0113] As a preferred embodiment of the present embodiment, the step of obtaining the power distribution network data monitoring model according to the topological relationship between each node of the power distribution network and by collecting the operating state characteristics of each node through the sensor is specifically as follows:

[0114] Establish a state model:

[0115] F(QN)=P(Q1)·P(Q2 / Q1)·P(Q3 / Q2)·……·P(Qn / Qn-1);

[0116] wherein F(QN) represents the state model of each node set of the power distribution network, Qn represents the state of the nth node in the power distribution network; P(Qn / Qn-1) represents the conditional probability distribution between the (n-1)th node and the nth node in the power distribution network;

[0117] and there is a relationship between the state Qn of the nth node and the state Qn-1 of the (n-1)th node in the power distribution network:

[0118] Qn=Qn-1+s;

[0119] wherein s is state noise conforming to a Gaussian distribution;

[0120] P(Qn / Qn-1)=G(Qn-1,σ 2 ); G(·,σ 2 ) represents a Gaussian distribution;

[0121] Establish a sampling model:

[0122] F(xn / Qn)=G(J(xn),σ 2 );

[0123] wherein F(xn / Qn) is the probability distribution of the sampling value of the power distribution network node under the state Qn, xn is the sensor sampling value of the nth node, and J(xn) is a sampling function;

[0124] and J(xn)=xn+τ;

[0125] wherein τ is sampling noise conforming to a Gaussian distribution;

[0126] The power distribution network data monitoring model is obtained by combining the state model and the sampling model:

[0127] Y(QN,xN)=P(Q1)F(x1 / Q1)·P(Q2 / Q1)F(x2 / Q2)·P(Q3 / Q2)F(x3 / Q3)·……·P(Qn / Qn-1)F(xn / Qn).

[0128] As a preferred embodiment of the present embodiment, the step of inputting the monitoring data set and the monitoring target parameters of different categories into the machine learning model to obtain the associated features of each monitoring target parameter specifically comprises:

[0129] The monitoring data set is preprocessed, and the preprocessing includes data cleaning and normalization processing.

[0130] Based on the preprocessed monitoring data set, a training sample set is established, and each training sample in the training sample set contains an operating state feature and a corresponding monitoring target parameter label.

[0131] A machine learning model based on a neural network is constructed, and the machine learning model is iteratively trained using the training sample set to obtain a trained associated feature classification model.

[0132] The monitoring data set and the monitoring target parameters of different categories are input into the trained associated feature classification model, and the associated features corresponding to each input monitoring target parameter are output.

[0133] As a preferred embodiment of the present embodiment, the operating state features include voltage, current, power factor, load rate, temperature, and humidity.

[0134] Embodiment three:

[0135] The present embodiment proposes an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the power distribution network full-process data monitoring method according to any embodiment of the present application when executing the program.

[0136] Embodiment four:

[0137] The present embodiment proposes a computer-readable storage medium having a computer program stored thereon, and the program is executed by a processor to implement the power distribution network full-process data monitoring method according to any embodiment of the present application.

[0138] In the embodiments of the present application, "at least one" means one or more, and "multiple" means two or more. The "and / or" describes the association relationship between the associated objects, which means that there can be three relationships, for example, A and / or B, which means that A exists alone, A and B exist together, and B exists alone. Wherein A and B can be singular or plural. The character " / " generally represents an "or" relationship between the front and rear associated objects. "At least one of the following" and similar expressions mean any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, and c can mean a, b, c, a and b, a and c, b and c, or a and b and c, wherein a, b, and c can be single or multiple.

[0139] Those skilled in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented using a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0140] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0141] In the several embodiments provided in this application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of this application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), magnetic disk or optical disk, and other media that can store program code.

[0142] The above descriptions are merely 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's description 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. A method for monitoring data of the entire distribution network, characterized in that: The following steps are involved: Based on the topological relationship between the nodes in the distribution network and the operation status characteristics of each node collected by sensors, a distribution network data monitoring model is obtained; According to the distribution network data monitoring model, obtain the monitoring data set and determine the type and quantity of operating status characteristics; Inputting the monitoring data set and different categories of monitoring target parameters into the machine learning model to obtain the associated features with each monitoring target parameter, wherein the associated features are operating status features associated with the monitoring target parameters; Based on the correlation characteristics of each monitoring target parameter, the monitoring data set is divided into multiple monitoring sub-data sets, each sub-data set corresponds to a monitoring target parameter and the corresponding correlation characteristics; Initiate a monitoring request for any monitoring target parameter, obtain the sub-dataset of the corresponding monitoring target parameter, and obtain multiple monitoring target time series data sets based on the monitoring time interval and various associated features; input the multiple monitoring target time series data sets into the anomaly detection model to identify whether there are anomalies in the monitoring parameters; The steps of obtaining the distribution network data monitoring model based on the topological relationship between the nodes of the distribution network and collecting the operating status characteristics of each node through sensors are specifically as follows: Build a state model: F(QN)=P(Q1)·P(Q2 / Q1)·P(Q3 / Q2)·…·P(Qn / Qn-1); Where F(QN) represents the state model of the set of nodes in the distribution network, Qn represents the state of the nth node in the distribution network; P(Qn / Qn-1) represents the conditional probability distribution between the n-1th node in the distribution network and the nth node in the distribution network; And there exists between the state Qn of the nth node and the state Qn-1 of the n-1th node in the distribution network: Qn=Qn-1+s; Where s is the state noise that conforms to the Gaussian distribution; Then P(Qn / Qn-1)=G(Qn-1,σ 2 ); G(·,σ 2 ) represents Gaussian distribution; Build a sampling model: F(xn / Qn)=G(J(xn),σ 2 ); Where F(xn / Qn) is the probability distribution of the sampling value of the distribution network node in state Qn, xn is the sensor sampling value of the nth node, and J(xn) is the sampling function; And J(xn)=xn+τ; Among them, τ is the sampling noise that conforms to the Gaussian distribution; The distribution network data monitoring model is obtained by combining the state model and the sampling model: Y(QN,xN)=P(Q1)F(x1 / Q1)·P(Q2 / Q1)F(x2 / Q2)·P(Q3 / Q2)F(x3 / Q3)·…·P(Qn / Qn-1)F(xn / Qn); The step of inputting the monitoring data set and different types of monitoring target parameters into the machine learning model to obtain the associated features with each monitoring target parameter specifically includes: Preprocess the monitoring data set, including data cleaning and normalization; Based on the preprocessed monitoring data set, a training sample set is established, where each training sample in the training sample set contains an operating state feature and a corresponding monitoring target parameter label; Construct a machine learning model based on a neural network; iteratively train the machine learning model using a training sample set to obtain a trained correlation feature classification model; The monitoring data set and different categories of monitoring target parameters are input into the trained association feature classification model, and the association features corresponding to each input monitoring target parameter are output.

2. A method for monitoring the entire process of distribution network data according to claim 1, characterized in that: The operating status characteristics include voltage, current, power factor, load rate, temperature and humidity.

3. A distribution network full-process data monitoring system, characterized in that: include: The monitoring model establishment module is used to obtain the distribution network data monitoring model based on the topological relationship between the nodes of the distribution network and the operating status characteristics of each node collected by sensors; A feature classification module is used to obtain monitoring data sets and determine the types and quantities of operating status features based on the distribution network data monitoring model; An associated feature acquisition module is used to input the monitoring data set and different categories of monitoring target parameters into the machine learning model to obtain associated features with each monitoring target parameter, wherein the associated features are operating status features associated with the monitoring target parameters; A data set division module divides the monitoring data set into multiple monitoring sub-data sets based on the associated features of each monitoring target parameter, each sub-data set corresponding to a monitoring target parameter and the corresponding associated features; The anomaly diagnosis module is used to initiate a monitoring request for any monitoring target parameter, obtain a sub-dataset of the corresponding monitoring target parameter, and obtain multiple monitoring target time series data sets based on the monitoring time interval and various associated features; input the multiple monitoring target time series data sets into the anomaly detection model to identify whether there are anomalies in the monitoring parameters; The steps of obtaining the distribution network data monitoring model based on the topological relationship between the nodes of the distribution network and collecting the operating status characteristics of each node through sensors are specifically as follows: Build a state model: F(QN)=P(Q1)·P(Q2 / Q1)·P(Q3 / Q2)·…·P(Qn / Qn-1); Where F(QN) represents the state model of the set of nodes in the distribution network, Qn represents the state of the nth node in the distribution network; P(Qn / Qn-1) represents the conditional probability distribution between the n-1th node in the distribution network and the nth node in the distribution network; And there exists between the state Qn of the nth node and the state Qn-1 of the n-1th node in the distribution network: Qn=Qn-1+s; Where s is the state noise that conforms to the Gaussian distribution; Then P(Qn / Qn-1)=G(Qn-1,σ 2 ); G(·,σ 2 ) represents Gaussian distribution; Build a sampling model: F(xn / Qn)=G(J(xn),σ 2 ); Where F(xn / Qn) is the probability distribution of the sampling value of the distribution network node in state Qn, xn is the sensor sampling value of the nth node, and J(xn) is the sampling function; And J(xn)=xn+τ; Among them, τ is the sampling noise that conforms to the Gaussian distribution; The distribution network data monitoring model is obtained by combining the state model and the sampling model: Y(QN,xN)=P(Q1)F(x1 / Q1)·P(Q2 / Q1)F(x2 / Q2)·P(Q3 / Q2)F(x3 / Q3)·…·P(Qn / Qn-1)F(xn / Qn); The step of inputting the monitoring data set and different types of monitoring target parameters into the machine learning model to obtain the associated features with each monitoring target parameter specifically includes: Preprocess the monitoring data set, including data cleaning and normalization; Based on the preprocessed monitoring data set, a training sample set is established, where each training sample in the training sample set contains an operating state feature and a corresponding monitoring target parameter label; Construct a machine learning model based on a neural network; iteratively train the machine learning model using a training sample set to obtain a trained correlation feature classification model; The monitoring data set and different categories of monitoring target parameters are input into the trained association feature classification model, and the association features corresponding to each input monitoring target parameter are output.

4. A distribution network full-process data monitoring system according to claim 3, characterized in that: The operating status characteristics include voltage, current, power factor, load rate, temperature and humidity.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the distribution network full-process data monitoring method as described in any one of claims 1 to 2 is implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for monitoring the full-process data of a distribution network as described in any one of claims 1 to 2 is implemented.

Images