CN114840591A - Method and device for determining sectional switch power data - Google Patents

Method and device for determining sectional switch power data Download PDF

Info

Publication number
CN114840591A
CN114840591A CN202210451966.1A CN202210451966A CN114840591A CN 114840591 A CN114840591 A CN 114840591A CN 202210451966 A CN202210451966 A CN 202210451966A CN 114840591 A CN114840591 A CN 114840591A
Authority
CN
China
Prior art keywords
data
section switch
power data
samples
specific section
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210451966.1A
Other languages
Chinese (zh)
Inventor
叶迪卓然
陈锦铭
陈烨
赵新冬
郭雅娟
袁栋
蔡云峰
程力涵
焦昊
李岩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Jiangsu Electric Power Co Ltd
Electric Power Research Institute of State Grid Jiangsu Electric Power Co Ltd
Original Assignee
State Grid Jiangsu Electric Power Co Ltd
Electric Power Research Institute of State Grid Jiangsu Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by State Grid Jiangsu Electric Power Co Ltd, Electric Power Research Institute of State Grid Jiangsu Electric Power Co Ltd filed Critical State Grid Jiangsu Electric Power Co Ltd
Priority to CN202210451966.1A priority Critical patent/CN114840591A/en
Publication of CN114840591A publication Critical patent/CN114840591A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/25—Integrating or interfacing systems involving database management systems
    • G06F16/258—Data format conversion from or to a database
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28—Databases characterised by their database models, e.g. relational or object models
    • G06F16/284—Relational databases
    • G06F16/285—Clustering or classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Abstract

The method comprises the steps of firstly obtaining multiple groups of specific section switch data, dividing the specific section switch data into practice samples and test samples, then standardizing all the samples, establishing and training a BP neural network according to the standardized practice samples, constructing an initial power data determination model, further comparing and verifying the initial power data determination model and the test samples, determining a final power data model, and finally determining the power data of a section switch to be tested through the final power data model. According to the invention, the BP neural network is trained by using the current and power data of the section switch and the voltage data of the surrounding distribution transformer, so that the power data fitting of the section switch only with the current and the surrounding distribution transformer voltage data is realized, the problem of power data loss in the line loss calculation process is solved, and the efficiency of line loss management is improved.

Description

Method and device for determining sectional switch power data
Technical Field
The application relates to the technical field of line loss calculation of a power distribution network, in particular to a method and a device for determining sectional switch power data.
Background
In the current economic indexes of power distribution network operation, the line loss rate is one of important assessment indexes for measuring the power distribution network planning design, production operation, operation management and enterprise economic benefit level. The accurate and simple line loss calculation and analysis method is beneficial to drawing reasonable measures for reducing the line loss and investigating the actual effect of the measures, and is also convenient to draw proper line loss assessment indexes and plans, thereby playing a role in guiding and promoting line loss management work.
Under the background, obtaining more real and complete measurement data of the power system becomes more and more important, because only a reliable line loss calculation result can a corresponding loss reduction strategy be better formulated, and further the operation efficiency of a power grid and the comprehensive management level of line loss are improved. However, in the process of calculating the line loss of the power distribution network, the problem of power data loss on the section switch can occur, and the efficiency of line loss comprehensive management is seriously influenced.
Disclosure of Invention
The application discloses a method and a device for determining sectional switch power data, which are used for solving the technical problems that power data on a sectional switch are lost in the process of calculating the line loss of a power distribution network at present, and the efficiency of line loss comprehensive management is seriously influenced.
The application discloses in a first aspect a method for determining segmented switching power data, comprising:
acquiring multiple groups of specific section switch data, wherein the specific section switches are section switches with power data, and any group of specific section switch data comprises specific section switch current data, specific section switch power data and distribution voltage data around the specific section switches;
formatting the multiple groups of specific section switch data into a matrix form, and dividing the matrix form into practice samples and test samples;
normalizing the practice sample and the test sample;
by utilizing a BP neural network, standardized specific section switch current data and standardized distribution voltage data around a specific section switch in a standardized practice sample are used as the input of the BP neural network, corresponding specific section switch power data are used as the expected output of the BP neural network, the neural network is established and trained, and an initial power data determination model is established;
comparing and verifying the initial power data determination model with a standardized test sample, analyzing the data fitting effect, and determining a final power data model if the fitting effect meets the preset requirement;
and acquiring current data of the section switch to be tested and distribution voltage data around the section switch to be tested, and determining power data of the section switch to be tested according to the final power data model, the current data of the section switch to be tested and the distribution voltage data around the section switch to be tested.
Optionally, the specific sectional switch current data is specific sectional switch single-phase current data or specific sectional switch three-phase current data.
Optionally, the normalizing the practice sample and the test sample includes:
the practice and test specimens were normalized using the mean square error method, and the data sizes of the practice and test specimens were changed to [0,1 ].
Optionally, the normalizing the practice sample and the test sample by using a mean-square error method includes:
the practice and test samples were normalized by the following formula:
Figure BDA0003618992270000021
wherein x is k Representing practice and test samples, x min Represents the minimum value, x, of data in the practice and test samples max Represents the maximum of the data in the practice and test samples.
Optionally, the comparing and verifying the initial power data determination model and the standardized test sample, and analyzing the data fitting effect, further includes:
and if the fitting effect does not meet the preset requirement, re-determining the initial power data determination model.
Optionally, the establishing and training of the neural network includes:
and in the practical samples, 70% of samples are used as training data, 15% of samples are used as verification data, and 15% of samples are used as test data, and the neural network is established and trained.
Optionally, in the BP neural network, the number of hidden neurons is set to 10.
Optionally, the training algorithm of the BP neural network is a Levenberg-Marquardt algorithm, a Bayesian Regularization algorithm, or a Scaled constraint Gradient algorithm.
Optionally, the fitting effect is determined by mean square error and goodness of fit.
The second aspect of the present application discloses a device for determining segmented switching power data, which is applied to the method for determining segmented switching power data disclosed in the first aspect of the present application, and the device for determining segmented switching power data includes:
the specific data acquisition module is used for acquiring a plurality of groups of specific section switch data, the specific section switches are section switches with power data, and any group of specific section switch data comprises specific section switch current data, specific section switch power data and distribution transformer voltage data around the specific section switches;
the preprocessing module is used for formatting the multiple groups of specific section switch data into a matrix form and dividing the matrix form into practice samples and test samples;
a standardization processing module for standardizing the practice sample and the test sample;
the initial model building module is used for utilizing the BP neural network, taking standardized specific section switch current data and standardized distribution voltage data around a specific section switch in a standardized practical sample as the input of the BP neural network, taking corresponding specific section switch power data as the expected output of the BP neural network, building and training the neural network, and building an initial power data determining model;
the final model construction module is used for comparing and verifying the initial power data determination model and a standardized test sample, analyzing the data fitting effect, and determining a final power data model if the fitting effect meets the preset requirement;
and the application module is used for acquiring current data of the section switch to be tested and distribution voltage data around the section switch to be tested, and determining power data of the section switch to be tested according to the final power data model, the current data of the section switch to be tested and the distribution voltage data around the section switch to be tested.
Optionally, the specific sectional switch current data is specific sectional switch single-phase current data or specific sectional switch three-phase current data.
Optionally, the normalization processing module is configured to: the practice and test specimens were normalized using the mean square error method, and the data sizes of the practice and test specimens were changed to [0,1 ].
Optionally, the normalization processing module is configured to: the practice and test samples were normalized by the following formula:
Figure BDA0003618992270000031
wherein x is k Representing practice and test samples, x min Represents the minimum value, x, of data in the practice and test samples max Represents the maximum of the data in the practice and test samples.
Optionally, the final model building module is further configured to: and if the fitting effect does not meet the preset requirement, re-determining the initial power data determination model.
Optionally, the initial model building module is configured to: and in the practical samples, 70% of samples are used as training data, 15% of samples are used as verification data, and 15% of samples are used as test data, and the neural network is established and trained.
Optionally, in the BP neural network, the number of hidden neurons is set to 10.
Optionally, the training algorithm of the BP neural network is a Levenberg-Marquardt algorithm, a Bayesian Regularization algorithm, or a Scaled constraint Gradient algorithm.
Optionally, the fitting effect is determined by mean square error and goodness of fit.
The application discloses a method and a device for determining sectional switch power data. According to the method, a plurality of groups of specific section switch data are obtained, the specific section switch data are divided into practice samples and test samples after being formatted in a matrix form, then the practice samples and the test samples are standardized, a BP neural network is utilized, the neural network is built and trained according to the standardized practice samples, an initial power data determination model is built, the initial power data determination model is further compared with the standardized test samples for verification, a final power data model is determined, and finally the power data of the section switch to be tested are determined through the final power data model. According to the invention, the BP neural network is trained by using the current and power data of the section switch and the voltage data of the surrounding distribution transformer, so that the power data fitting of the section switch only with the current and the surrounding distribution transformer voltage data is realized, the problem of power data loss in the line loss calculation process is solved, and the efficiency of line loss management is improved.
Drawings
In order to more clearly explain the technical solution of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious to those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic workflow diagram of a method for determining segmented switching power data according to an embodiment of the present disclosure;
FIG. 2 is a graph illustrating a variation of a sample mean square error according to an exemplary embodiment of the disclosure;
FIG. 3 is a graph of goodness of fit of an exemplary next-test sample as disclosed in an embodiment of the present application;
FIG. 4 is a graph illustrating a variation of mean square error of samples according to an exemplary embodiment of the present disclosure;
FIG. 5 is a graph of goodness of fit of test samples under example two disclosed in embodiments of the present application;
fig. 6 is a schematic structural diagram of an apparatus for determining segmented switching power data according to an embodiment of the present application.
Detailed Description
In order to solve the technical problems that power data on a section switch are lost and the efficiency of line loss comprehensive management is seriously affected in the process of calculating the line loss of a power distribution network at present, the application discloses a method and a device for determining the power data of the section switch through the following embodiments.
A first embodiment of the present application discloses a method for determining piecewise switching power data, which, with reference to a work flow diagram shown in fig. 1, includes:
and step S1, acquiring multiple groups of specific section switch data, wherein the specific section switches are section switches with power data, and any group of specific section switch data comprises specific section switch current data, specific section switch power data and distribution voltage data around the specific section switches.
Further, the specific sectional switch current data is specific sectional switch single-phase current data or specific sectional switch three-phase current data.
Specifically, a specific section switch on a specific area line with power data is selected, and single-phase or three-phase current data, power data and surrounding distribution transformation voltage data of the section switch are collected.
And step S2, formatting the multiple groups of specific section switch data into a matrix form, and dividing the matrix form into practice samples and test samples.
Specifically, to match the programmed computation of Matlab, it is formatted in a matrix form and groups of specific piecewise switch data are divided into practice samples and test samples.
Step S3, standardizing the practice sample and the test sample.
Further, the normalizing the practice sample and the test sample includes:
the practice and test specimens were normalized using the mean square error method, and the data sizes of the practice and test specimens were changed to [0,1 ].
Further, the normalizing the practice sample and the test sample by using a mean variance method comprises:
the normalization process can ensure that the data sizes are relatively close, avoid calculating some data with less sample number due to large size difference, and improve the data processing precision. After normalization, the data size for all samples becomes [0,1 ]. Currently, the mean variance method is mainly used for normalization, and the practice sample and the test sample are specifically normalized by the following formula:
Figure BDA0003618992270000051
wherein x is k Representing practice and test samples, x min Represents the minimum value, x, of data in the practice and test samples max Represents the maximum of the data in the practice and test samples.
Specifically, since the data sizes of different samples are usually different, direct input without processing will affect convergence and processing speed. Therefore, the data samples were normalized by the mean variance method.
And step S4, using the BP neural network, taking the standardized specific section switch current data and the standardized distribution voltage data around the specific section switch in the standardized practice sample as the input of the BP neural network, taking the corresponding specific section switch power data as the expected output of the BP neural network, establishing and training the neural network, and establishing an initial power data determination model.
In some embodiments of the present application, the establishing and training of the neural network includes:
and in the practical samples, 70% of samples are used as training data, 15% of samples are used as verification data, and 15% of samples are used as test data, and the neural network is established and trained.
In some embodiments of the present application, in the BP neural network, the number of hidden neurons is set to 10, and the specific number may be adjusted according to practical situations.
In some embodiments of the present application, the training algorithm of the BP neural network is Levenberg-Marquardt algorithm, Bayesian Regularization algorithm, or Scaled connection Gradient algorithm.
Specifically, the neural network is built and trained by calling the BP neural network toolbox in Matlab.
And step S5, comparing and verifying the initial power data determination model and the standardized test sample, analyzing the data fitting effect, and determining the final power data model if the fitting effect meets the preset requirement. The preset requirement is predetermined according to an actual application scene.
Further, the comparing and verifying the initial power data determination model and the standardized test sample, and analyzing the data fitting effect, further includes:
and if the fitting effect does not meet the preset requirement, re-determining the initial power data determination model.
In some embodiments of the present application, the fitting effect is determined by mean square error and goodness of fit.
Specifically, the trained neural network is compared with a test sample for verification, and the data fitting effect is analyzed, so that the training effect is conveniently verified.
The BP neural network analysis is carried out by calling a BP neural network tool box in Matlab, and the method comprises the following specific steps: selecting a Neural Net Fitting tool APP; according to the data type of the section switch, normalized three-phase current data and normalized three-phase voltage data or single-phase current data and normalized three-phase voltage data are selectively led in as input data, and normalized power data are led in as expected output data; selecting the proportion of the sample size occupied by three types of data, wherein the three types of data are training data, verification data and test data respectively, the proportion can be adjusted according to specific conditions, and the default is to randomly select 70% of samples as training data, 15% of samples as verification data and 15% of samples as test data; determining the number of hidden neurons, selecting 10 normally, and then adjusting the specific number according to the practical situation; selecting a training algorithm, wherein the training algorithm is generally divided into Levenberg-Marquardt, Bayesian Regularization and Scaled relationship Gradient, and a default Levenberg-Marquardt algorithm is generally selected; according to the obtained result, generally, the smaller the value of Mean Square Error (MSE), the closer the value of goodness of fit (R) is to 1, and the better the training effect is; and if the obtained model cannot meet the preset requirement, repeating the steps until the desired fitting precision is obtained.
And step S6, acquiring current data of the section switch to be tested and distribution voltage data around the section switch to be tested, and determining power data of the section switch to be tested according to the final power data model, the current data of the section switch to be tested and the distribution voltage data around the section switch to be tested.
The method for determining the sectional switch power data disclosed in the embodiment of the application includes the steps of firstly obtaining a plurality of groups of specific sectional switch data, formatting the specific sectional switch data into a matrix form, dividing the specific sectional switch data into practice samples and test samples, then standardizing the practice samples and the test samples, establishing and training a neural network according to the standardized practice samples by using a BP (back propagation) neural network, establishing an initial power data determination model, further comparing and verifying the initial power data determination model and the standardized test samples, determining a final power data model, and finally determining the power data of the sectional switch to be tested through the final power data model. According to the invention, the BP neural network is trained by using the current and power data of the section switch and the voltage data of the surrounding distribution transformer, so that the power data fitting of the section switch only with the current and the surrounding distribution transformer voltage data is realized, the problem of power data loss in the line loss calculation process is solved, and the efficiency of line loss management is improved.
It should be understood that, although the steps in the flowchart of fig. 1 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 1 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
The following is further illustrated with reference to specific examples:
example one: given three-phase current data of the section switch and three-phase voltage data of the peripheral distribution transformer, the power value of the corresponding section switch needs to be determined. According to the method for determining the sectional switching power data disclosed by the embodiment, the specific steps are as follows:
130 groups of data of the section switch in a certain 10kV line are selected, and each group of data comprises a three-phase current value, a power value and a three-phase voltage value of the distribution transformer around the section switch.
The 130 groups of data were normalized according to the formula of mean square error method.
According to the network structure design of the BP neural network, 6 input neural units (three-phase voltage and three-phase current data) and 1 output neural unit (sectionalized switch active power data) are selected, and the network iteration number is 1000. 70% were selected as training data (90 groups), 15% as validation data (20 groups) and 15% as test data (20 groups). The results after training are shown in table 1, and the mean square error MSE results for the validation data are 4.4876 e-5.
TABLE 1
Number of samples Mean square error MSE Goodness of fit R
Training data 90 2.15135e-5 9.99829e-1
Verification data
20 4.48756e-5 9.99815e-1
Test data
20 7.03161e-5 9.99702e-1
Figure 2 details the variation in mean error for three sets of sample data during online training. It can be seen that in the repeated online training process, the average error of the sample is gradually reduced, and the average error of the confirmation sample of the test sample is gradually reduced, but the improvement of the generalization capability is the main purpose of online training. The goodness of fit R of the sample data is quite close to 1, and expected requirements are met.
Then, the sampling data of a certain time period of another section switch of the line is selected as a test sample of the trained model, the output result of the comparison model is compared with the actual power value, the result is shown in fig. 3, the goodness of fit R between the model fitting value and the target value is 0.96214, and the effect is good.
Example two: the known single-phase current data of the sectional switch and the surrounding distribution and transformation three-phase voltage data need to determine the power value of the corresponding sectional switch. According to the method for determining the sectional switch power data disclosed by the embodiment, the specific steps are as follows:
130 groups of data of the section switch in the 10kV line are selected, and each group of data comprises the single-phase current value and the power value of the section switch and the three-phase voltage value of the peripheral distribution transformer.
The 130 groups of data were normalized according to the formula of mean square error method.
According to the network structure design of the BP neural network, 4 input neural units (three-phase voltage and single-phase current data) and 1 output neural unit (sectionalized switch active power data) are selected, and the network iteration number is 1000. 70% were selected as training data (90 groups), 15% as validation data (20 groups) and 15% as test data (20 groups). The results after training are shown in table 2, and the mean square error MSE result of the verification data is 5.42717e-4, which is larger than that in case 1.
TABLE 2
Number of samples Mean square error MSE Goodness of fit R
Training data 90 2.57490e-4 9.98061e-1
Verification data
20 5.42717e-4 9.96858e-1
Test data
20 6.60963e-4 9.96564e-1
Fig. 4 shows in detail the variation of the mean error of three sets of sample data during online training.
Then, sampling data of a certain time period of another section switch of the line is selected as a test sample of the trained model, the output result of the comparison model is compared with the actual power value, the result is shown in fig. 5, the goodness of fit R between the model fitting value and the target value is 0.81166, the effect is inferior to that under the scenario 1, but the overall effect is within the error allowable range.
The following are embodiments of the apparatus of the present application that may be used to perform embodiments of the method of the present application. For details which are not disclosed in the embodiments of the apparatus of the present application, reference is made to the embodiments of the method of the present application.
The second embodiment of the present application discloses a device for determining segmented switching power data, which is applied to the method for determining segmented switching power data disclosed in the first embodiment of the present application, and referring to the schematic structural diagram shown in fig. 6, the device for determining segmented switching power data includes:
the specific data acquisition module 10 is configured to acquire a plurality of sets of specific section switch data, where the specific section switches are section switches with power data, and any set of specific section switch data includes specific section switch current data, specific section switch power data, and distribution voltage data around the specific section switches.
And the preprocessing module 20 is used for formatting the multiple groups of specific section switch data into a matrix form and dividing the matrix form into practice samples and test samples.
A normalization processing module 30 for normalizing the practice sample and the test sample.
And the initial model building module 40 is configured to utilize the BP neural network, take the normalized specific section switch current data and the normalized distribution voltage data around the specific section switch in the standardized practice sample as inputs of the BP neural network, take the corresponding specific section switch power data as expected outputs of the BP neural network, build and train the BP neural network, and build an initial power data determination model.
And the final model building module 50 is used for comparing and verifying the initial power data determination model and the standardized test sample, analyzing the data fitting effect, and determining a final power data model if the fitting effect meets the preset requirement.
And the application module 60 is configured to obtain current data of the to-be-tested section switch and distribution voltage data around the to-be-tested section switch, and determine power data of the to-be-tested section switch according to the final power data model, the current data of the to-be-tested section switch and the distribution voltage data around the to-be-tested section switch.
Further, the specific sectional switch current data is specific sectional switch single-phase current data or specific sectional switch three-phase current data.
Further, the normalization processing module is configured to: the practice and test specimens were normalized using the mean square error method, and the data sizes of the practice and test specimens were changed to [0,1 ].
Further, the normalization processing module is configured to: the practice and test samples were normalized by the following formula:
Figure BDA0003618992270000081
wherein x is k Representing practice and test samples, x min Represents the minimum value, x, of data in the practice and test samples max Represents the maximum of the data in the practice and test samples.
Further, the final model building module is further configured to: and if the fitting effect does not meet the preset requirement, re-determining the initial power data determination model.
Further, the initial model building module is configured to: and in the practical samples, 70% of samples are used as training data, 15% of samples are used as verification data, and 15% of samples are used as test data, and the neural network is established and trained.
Further, in the BP neural network, the number of hidden neurons is set to 10.
Further, the training algorithm of the BP neural network is a Levenberg-Marquardt algorithm, a Bayesian Regularization algorithm or a Scaled connection Gradient algorithm.
Further, the fitting effect is determined by mean square error and goodness of fit.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting the protection scope thereof, and although the present invention has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that after reading the present invention, they can make various changes, modifications or equivalents to the specific embodiments of the present invention, but these changes, modifications or equivalents are within the protection scope of the appended claims.

Claims (10)

1. A method for determining segmented switching power data, comprising:
acquiring multiple groups of specific section switch data, wherein the specific section switches are section switches with power data, and any group of specific section switch data comprises specific section switch current data, specific section switch power data and distribution voltage data around the specific section switches;
formatting the multiple groups of specific section switch data into a matrix form, and dividing the matrix form into practice samples and test samples;
standardizing the practice sample and the test sample;
by utilizing a BP neural network, standardized specific section switch current data and standardized distribution voltage data around a specific section switch in a standardized practice sample are used as the input of the BP neural network, corresponding specific section switch power data are used as the expected output of the BP neural network, the neural network is established and trained, and an initial power data determination model is established;
comparing and verifying the initial power data determination model with a standardized test sample, analyzing the data fitting effect, and determining a final power data model if the fitting effect meets the preset requirement;
and acquiring current data of the section switch to be tested and distribution voltage data around the section switch to be tested, and determining power data of the section switch to be tested according to the final power data model, the current data of the section switch to be tested and the distribution voltage data around the section switch to be tested.
2. The method of claim 1, wherein the sectionalizing switch current data is sectionalizing switch single-phase current data or sectionalizing switch three-phase current data.
3. The method of claim 1, wherein the normalizing the practice sample and the test sample comprises:
the practice and test specimens were normalized using the mean square error method, and the data sizes of the practice and test specimens were changed to [0,1 ].
4. The method of claim 3, wherein the normalizing the practice samples and the test samples using mean-square error comprises:
the practice and test samples were normalized by the following formula:
Figure FDA0003618992260000011
wherein x is k Representing practice and test samples, x min Represents the minimum value, x, of data in the practice and test samples max Represents the maximum value of data in the practical sample and the test sample.
5. The method for determining sectionalized switch power data according to claim 1, wherein the comparing the initial power data determination model with the standardized test sample for verifying and analyzing data fitting effects further comprises:
and if the fitting effect does not meet the preset requirement, re-determining the initial power data determination model.
6. The method of claim 1, wherein the establishing and training of the neural network comprises:
and in the practical samples, 70% of samples are used as training data, 15% of samples are used as verification data, and 15% of samples are used as test data, and the neural network is established and trained.
7. The method of claim 1, wherein the number of hidden neurons in the BP neural network is set to 10.
8. The method of claim 1, wherein the training algorithm of the BP neural network is a Levenberg-Marquardt algorithm, a Bayesian Regularization algorithm, or a Scaled connection Gradient algorithm.
9. The method of claim 1, wherein the fitting is determined by mean square error and goodness-of-fit.
10. A device for determining sectionalized switching power data, wherein the device for determining sectionalized switching power data is applied to the method for determining sectionalized switching power data according to any one of claims 1-9, and the device for determining sectionalized switching power data comprises:
the specific data acquisition module is used for acquiring a plurality of groups of specific section switch data, the specific section switches are section switches with power data, and any group of specific section switch data comprises specific section switch current data, specific section switch power data and distribution transformer voltage data around the specific section switches;
the preprocessing module is used for formatting the multiple groups of specific section switch data into a matrix form and dividing the matrix form into practice samples and test samples;
a standardization processing module for standardizing the practice sample and the test sample;
the initial model building module is used for utilizing the BP neural network, taking standardized specific section switch current data and standardized distribution voltage data around the specific section switch in a standardized practice sample as the input of the BP neural network, taking corresponding specific section switch power data as the expected output of the BP neural network, building and training the neural network, and building an initial power data determination model;
the final model construction module is used for comparing and verifying the initial power data determination model and a standardized test sample, analyzing the data fitting effect, and determining a final power data model if the fitting effect meets the preset requirement;
and the application module is used for acquiring current data of the section switch to be tested and distribution voltage data around the section switch to be tested, and determining power data of the section switch to be tested according to the final power data model, the current data of the section switch to be tested and the distribution voltage data around the section switch to be tested.
CN202210451966.1A 2022-04-24 2022-04-24 Method and device for determining sectional switch power data Pending CN114840591A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210451966.1A CN114840591A (en) 2022-04-24 2022-04-24 Method and device for determining sectional switch power data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210451966.1A CN114840591A (en) 2022-04-24 2022-04-24 Method and device for determining sectional switch power data

Publications (1)

Publication Number Publication Date
CN114840591A true CN114840591A (en) 2022-08-02

Family

ID=82568666

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210451966.1A Pending CN114840591A (en) 2022-04-24 2022-04-24 Method and device for determining sectional switch power data

Country Status (1)

Country Link
CN (1) CN114840591A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115808589A (en) * 2023-02-06 2023-03-17 国网江苏省电力有限公司电力科学研究院 Power distribution network time-sharing segmentation line loss abnormity diagnosis method and device

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115808589A (en) * 2023-02-06 2023-03-17 国网江苏省电力有限公司电力科学研究院 Power distribution network time-sharing segmentation line loss abnormity diagnosis method and device

Similar Documents

Publication Publication Date Title
CN112488395B (en) Method and system for predicting line loss of power distribution network
CN107340492A (en) Electric power meter failure analysis methods with scene anticipation are excavated based on big data
CN116125361B (en) Voltage transformer error evaluation method, system, electronic equipment and storage medium
CN112016755A (en) Construction method of universal design cost standardization technology module of power transmission and transformation project construction drawing
CN114840591A (en) Method and device for determining sectional switch power data
CN106779436A (en) A kind of Electric Power Network Planning stage construction harmony comprehensive estimation method
CN109583086A (en) Distribution transformer heavy-overload prediction technique and terminal device
CN111612149A (en) Main network line state detection method, system and medium based on decision tree
CN105956755A (en) Method and system for establishing quantitative relationship of general power line loss rate influencing factors
CN110991741A (en) Section constraint probability early warning method and system based on deep learning
CN106327009A (en) Main constituent analysis method for determining cell load maximum value in space load prediction
CN111080089A (en) Method and device for determining critical factors of line loss rate based on random matrix theory
CN112528762B (en) Harmonic source identification method based on data correlation analysis
CN112732773B (en) Method and system for checking uniqueness of relay protection defect data
CN114139408A (en) Power transformer health state assessment method
CN116136580A (en) Line loss grading detection method and device based on sensing equipment
CN113836125A (en) Distribution transformer data cleaning and repairing method and system for distribution internet of things edge side
CN112365024A (en) High-voltage direct-current converter station energy efficiency prediction method and system based on deep learning
CN109871998A (en) A kind of Line Loss of Distribution Network System rate prediction technique and device based on expert sample bank
CN110287272A (en) A kind of configurable real-time feature extraction method, apparatus and system
CN111222673A (en) Section out-of-limit positioning method and system in electric quantity transaction plan
CN109614635B (en) Nuclear power plant cable secondary bridge capacity pre-judging method
CN110968638B (en) Retrospective analysis method and retrospective analysis device for power system
CN113837815A (en) Quotation prediction model construction method, prediction method, system, device and medium
CN113159394A (en) Intelligent power distribution network partition cold and hot load prediction method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination