CN112348074B - Power distribution network power failure event accurate diagnosis method, device and system based on data driving - Google Patents
Power distribution network power failure event accurate diagnosis method, device and system based on data driving Download PDFInfo
- Publication number
- CN112348074B CN112348074B CN202011202332.XA CN202011202332A CN112348074B CN 112348074 B CN112348074 B CN 112348074B CN 202011202332 A CN202011202332 A CN 202011202332A CN 112348074 B CN112348074 B CN 112348074B
- Authority
- CN
- China
- Prior art keywords
- power failure
- electric quantity
- distribution transformer
- distribution
- check index
- 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.)
- Active
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 252
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000003745 diagnosis Methods 0.000 title claims description 22
- 239000012634 fragment Substances 0.000 claims abstract description 178
- 238000004364 calculation method Methods 0.000 claims abstract description 29
- 238000005259 measurement Methods 0.000 claims abstract description 28
- 230000008859 change Effects 0.000 claims abstract description 15
- 238000013145 classification model Methods 0.000 claims abstract description 7
- 230000005611 electricity Effects 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 13
- 238000007477 logistic regression Methods 0.000 claims description 12
- 238000013467 fragmentation Methods 0.000 claims description 5
- 238000006062 fragmentation reaction Methods 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 4
- 208000003443 Unconsciousness Diseases 0.000 description 16
- 238000010586 diagram Methods 0.000 description 16
- 238000004590 computer program Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 8
- 238000012545 processing Methods 0.000 description 8
- 238000007726 management method Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008014 freezing Effects 0.000 description 1
- 238000007710 freezing Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy 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
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Analysis (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Mathematics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Water Supply & Treatment (AREA)
- Algebra (AREA)
- Public Health (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
Abstract
The invention discloses a method, a device and a system for accurately diagnosing a power distribution network power failure event based on data driving, wherein the method comprises the steps of generating a primary power failure fragment set of a distribution transformer based on acquired measurement data of the distribution transformer; calculating an integral electric quantity check index of the primary power failure fragment of the distribution transformer, removing partial unreal power failure fragments in the primary power failure fragment set, and generating a middle-level power failure fragment set of the distribution transformer; inputting the variation amplitude of the bottom of the distribution transformer corresponding to the middle-stage power failure fragment of each distribution transformer into a frozen electric quantity checking index calculation formula to obtain a frozen electric quantity checking index set; inputting the frozen electric quantity check index set and the time length of the medium-level power failure fragment of each distribution transformer into the classification model, and eliminating all unreal power failure fragments in the medium-level power failure fragment set to generate a high-level power failure fragment set of the distribution transformer. The method learns the operation data change characteristics of the distribution transformer in a data driving mode, judges whether the real power failure occurs to the distribution transformer, and realizes accurate collection of power failure events.
Description
Technical Field
The invention belongs to the field of medium-voltage power distribution network power failure event diagnosis, and particularly relates to a power distribution network power failure event accurate diagnosis method, device and system based on data driving.
Background
The power distribution network is used as a link at the tail end of power transmission and is the most intuitive object for power grid service experience of users, but the power distribution network is complex in structure and numerous in equipment, and faces the dilemma of low operation and maintenance level and poor reliability. In the traditional distribution network power failure management work, the collection accuracy is often depended on the device, the management mode is relatively extensive, the working efficiency is low, and the phenomenon of missing report is relatively common. The incompleteness of the power failure information of the distribution network fault influences the decision making of reliability analysis, inspection tour, network frame upgrading and the like of the distribution network.
Through the measured data change characteristics of the distribution transformer and the feeder line, the real power failure event is identified from the data driving angle, the power-assisted power supply accurately holds the power failure information of the distribution network, the accurate input and the accurate output of the enterprise are promoted, and the reliability of the distribution network is improved in an auxiliary mode. Therefore, the accurate diagnosis method for the power failure events of the medium-voltage distribution network is an important research subject, and research results can help operators to find the power failure events in time and identify the weak risk points of the network frame.
Disclosure of Invention
Aiming at the problem that the traditional distribution network reliability management depends on the acquisition accuracy of a device and the blackout information is difficult to master comprehensively at present, the invention provides the accurate diagnosis method, the device and the system for the blackout event of the power distribution network based on data driving, which can be used for identifying the blackout event of the medium-voltage power distribution network with any scale, have simple calculation and clear principle, and can help distribution network operators to find the real blackout event in time.
In order to achieve the technical purpose and achieve the technical effects, the invention is realized by the following technical scheme:
in a first aspect, the invention provides a power distribution network power failure event precision diagnosis method based on data driving, which includes:
generating a primary power failure fragment set of the distribution transformer based on the obtained measurement data of the distribution transformer;
calculating integral electric quantity check indexes of primary power failure fragments of each distribution transformer, removing partial unreal power failure fragments in the primary power failure fragment set based on the integral electric quantity check indexes, and generating a middle-level power failure fragment set of the distribution transformer;
respectively inputting the variation amplitude of the surface bottom of each distribution transformer corresponding to the middle-stage power failure fragment of each distribution transformer into a frozen electric quantity check index calculation formula to obtain a frozen electric quantity check index set;
inputting the frozen electric quantity check index set and the time length of the medium-level power failure fragment of each distribution transformer into a preset classification model, classifying the medium-level power failure fragment set of the distribution transformer, removing all unreal power failure fragments in the medium-level power failure fragment set, generating a high-level power failure fragment set of the distribution transformer, and completing the accurate diagnosis of the power failure event of the distribution network based on data driving.
Optionally, the distribution transformer primary blackout fragment set includes a plurality of distribution transformer primary blackout fragments, and the generation method of the distribution transformer primary blackout fragments includes the following sub-steps:
obtaining distribution transformer T k Active power measurement data P k ＝[p k,1 ,p k,2 ,...,p k,i ,...,p k,n ]；
If distribution transformer T k Active power measurement data P k In successive data sections p k,i ,...,p k,j ]0 or null, based on the distribution transformer T k Data section [ i, j ] of (1)]Creating a primary blackout fragment.
Optionally, a distribution transformer T k The generation method of the distribution transformer medium-level power failure fragments comprises the following substeps:
acquiring an integral electric quantity check index calculation formula:
wherein, W k JF For distribution transformers T k Integrated electric quantity of (A) k For distribution transformers T k Checking indexes of the integrated electric quantity;
calculating an integral electric quantity check index corresponding to the primary power failure fragment of each distribution transformer based on the integral electric quantity check index calculation formula to obtain an integral electric quantity check index set;
acquiring an integral electric quantity check index threshold;
comparing each integral electric quantity check index in the integral electric quantity check index set with the integral electric quantity check index threshold value;
and if the integral electric quantity check index is higher than the integral electric quantity check index threshold, judging that the primary power failure fragment of the distribution transformer corresponding to the integral electric quantity check index is the middle-level power failure fragment of the distribution transformer.
Optionally, the method for calculating the integrated electric quantity check index threshold includes:
calculating normal distribution of the integral electric quantity check index data set based on the integral electric quantity check index data set by using a probability distribution estimation method based on a Bayesian information quantity criterion;
and calculating the check index threshold value of the integral electric quantity by using the 3Sigma principle of normal distribution.
Optionally, the calculation formula of the check indicator of the frozen electric quantity is:
wherein m is k,j For table bottom data at the end of power failure fragmentation, m k,i Table bottom data when power failure fragment begins, i is power failure fragment beginning time, j is power failure fragment ending time, and Z k In order to freeze the electric quantity change index on the same day,
the same data section [ i, …, j ] at the bottom of the previous daily electricity meter]The frozen power change index.
Optionally, the method for generating the distribution transformer advanced outage debris set includes:
obtaining a logistic regression model;
and taking the frozen electric quantity check index set and the time length of the medium-level power failure fragment of each distribution transformer as input data, classifying the medium-level power failure fragments of each distribution transformer by using the logistic regression model, and judging the medium-level power failure fragment corresponding to the distribution transformer to be the high-level power failure fragment if the medium-level power failure fragment of the distribution transformer is classified as the real power failure class.
In a second aspect, the present invention provides a data-driven power distribution network outage event precision diagnosis apparatus, including:
the first generation unit is used for generating a primary power failure fragment set of the distribution transformer based on the acquired measurement data of the distribution transformer;
the second generation unit is used for calculating an integral electric quantity check index of each primary power failure fragment of the distribution transformer, eliminating partial unreal power failure fragments in the primary power failure fragment set based on the integral electric quantity check index and generating a middle-level power failure fragment set of the distribution transformer;
the calculation unit is used for respectively inputting the variation amplitude of the bottom of the distribution transformer corresponding to the medium-level power failure fragment of each distribution transformer into a frozen electric quantity check index calculation formula to obtain a frozen electric quantity check index set;
and the third generation unit is used for inputting the frozen electric quantity check index set and the time length of the medium-level power failure fragment of each distribution transformer into a preset classification model, classifying the medium-level power failure fragment set of the distribution transformer, removing all unreal power failure fragments in the medium-level power failure fragment set, generating a high-level power failure fragment set of the distribution transformer, and completing the accurate diagnosis of the power failure event of the distribution network based on data driving.
Optionally, the distribution transformer primary blackout fragment set includes a plurality of distribution transformer primary blackout fragments, and the generation method of the distribution transformer primary blackout fragments includes the following sub-steps:
obtaining distribution transformer T k Active power measurement data P k ＝[p k,1 ,p k,2 ,...,p k,i ,...,p k,n ]；
If distribution transformer T k Active power measurement data P k In successive data sections p k,i ,...,p k,j ]0 or null, based on the distribution transformer T k Data section [ i,... j ] of]Creating a primary blackout fragment.
Optionally, a distribution transformer T k The generation method of the distribution transformer medium-level power failure fragments comprises the following substeps:
acquiring an integral electric quantity check index calculation formula:
wherein, W k JF For distribution transformers T k Integral electric quantity of A k For distribution transformers T k Checking indexes of the integrated electric quantity;
calculating an integral electric quantity check index corresponding to the primary power failure fragment of each distribution transformer based on the integral electric quantity check index calculation formula to obtain an integral electric quantity check index set;
acquiring an integral electric quantity check index threshold;
comparing each integral electric quantity check index in the integral electric quantity check index set with the integral electric quantity check index threshold value;
and if the integral electric quantity check index is higher than the integral electric quantity check index threshold value, judging that the primary power failure fragment of the distribution transformer corresponding to the integral electric quantity check index is the middle-level power failure fragment of the distribution transformer.
Optionally, the method for calculating the integrated electric quantity check index threshold includes:
calculating normal distribution of the integral electric quantity check index data set by utilizing a probability distribution estimation method based on a Bayesian information quantity criterion and based on the integral electric quantity check index data set;
and calculating the check index threshold value of the integral electric quantity by using the 3Sigma principle of normal distribution.
Optionally, the calculation formula of the check indicator of the frozen electric quantity is:
wherein m is k,j For table bottom data at the end of power failure fragmentation, m k,i The table bottom data when the power failure fragment begins, i is the power failure fragment starting time, j is the power failure fragment ending time, and Z k In order to freeze the electricity quantity change index on the same day,
the same data section [ i, …, j ] at the bottom of the previous daily electricity meter]The frozen power change index.
Optionally, the method for generating the distribution transformer advanced power outage fragment set includes:
obtaining a logistic regression model;
and taking the frozen electric quantity check index set and the time length of the middle-level power failure fragment of each distribution transformer as input data, classifying the middle-level power failure fragments of each distribution transformer by using the logistic regression model, and judging the middle-level power failure fragment corresponding to the distribution transformer as the high-level power failure fragment if the middle-level power failure fragments of the distribution transformer are classified as the real power failure class.
In a third aspect, the invention provides a power distribution network power failure event precision diagnosis system based on data driving, which comprises a storage medium and a processor;
the storage medium is to store instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to any one of the first aspects.
Compared with the prior art, the invention has the beneficial effects that:
(1) the invention comprehensively considers various data characteristics of the distribution transformer such as integral electric quantity, frozen electric quantity, power failure duration and the like, gradually eliminates false power failure fragments, and has high accuracy.
(2) The invention learns the change trend of historical mass data in a data driving mode, calculates the threshold value of the integral check index for judging whether the power failure event is real or not, and avoids artificial designation.
(3) The method is simple in calculation and clear in principle, can help distribution network operators to find real power failure events in time, and has a good application prospect.
Drawings
In order that the present disclosure may be more readily and clearly understood, reference is now made to the following detailed description of the present disclosure taken in conjunction with the accompanying drawings, in which:
fig. 1 is a flowchart of a power distribution network blackout event diagnosis method according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the scope of the invention.
The following detailed description of the principles of the invention is provided in connection with the accompanying drawings.
Example 1
The embodiment of the invention provides a power distribution network power failure event precision diagnosis method based on data driving, which can be suitable for a medium-voltage power distribution network and comprises the following steps as shown in figure 1:
the method comprises the following steps of (1) acquiring measurement data of a distribution transformer in a power distribution network;
in a specific implementation manner of the embodiment of the present invention, the specific implementation process of the step (1) is as follows:
selecting a medium voltage distribution network to be processed in an energy management system (the system is a system existing in the prior art), reading a line-to-line relation of 'bus-distribution transformer load' stored in the prior system, deriving active power and electricity meter bottom data of distribution transformer sampled once every 15min in an electricity utilization information acquisition system, and obtaining frozen electricity quantity data sampled once every 15min by the distribution transformer, wherein the sampling frequency sampled once every 15min can be modified according to actual conditions.
Step (2) generating a primary power failure fragment set of the distribution transformer based on the obtained measurement data of the distribution transformer;
in a specific implementation manner of the embodiment of the present invention, the specific implementation process of the step (2) is as follows:
considering that the real power failure may occur when the active power measurement data of the distribution transformer is 0 or empty, and the real power failure may also occur due to false power failure caused by signal transmission, data storage and the like, the real power failure and the false power failure need to be effectively and reasonably distinguished through a data analysis method. Suppose a distribution transformer T k Connected to line f, distribution transformer T k The active power measurement data is P k ＝[p k,1 ,p k,2 ,…,p k,i ,…,p k,n ]Distribution transformer T k The frozen electric quantity data of is W k DJ The active power measurement data of the line f is P f ＝[p f,1 ,p f,2 ,…,p f,i ,…,p f,n ]N represents the number of sampling points of the active power measurement data of the distribution transformer and the line; the distribution transformer primary power failure fragment set comprises a plurality of distribution transformer primary power failure fragments, and the generation method of the distribution transformer primary power failure fragment set comprises the following steps: if distribution transformer T k Active power measurement data P k In successive data sections p k,i ,…,p k,j ]0 or null, a distribution transformer T is generated k Data section [ i, …, j ] of (1)]Is a primary blackout fragment.
Calculating integral electric quantity check indexes of primary power failure fragments of each distribution transformer, removing partial unreal power failure fragments in the primary power failure fragment set based on the integral electric quantity check indexes, and generating a middle-stage power failure fragment set of the distribution transformer;
in a specific implementation manner of the embodiment of the present invention, the step (3) specifically includes the following sub-steps:
(3.1) acquiring an integral electric quantity check index calculation formula, wherein the integral electric quantity check index calculation formula is as follows:
wherein, W k JF For distribution transformers T k Integral electric quantity of A k For distribution transformers T k Checking indexes of the integrated electric quantity;
(3.2) calculating integral electric quantity check indexes of the distribution transformers aiming at the primary power failure fragments of the distribution transformers to form an integral electric quantity check index data set;
and (3.3) calculating an integral electric quantity check index threshold value. Calculating normal distribution of the integral electric quantity check index data set based on the integral electric quantity check index data set by using a probability distribution estimation method based on a Bayesian information quantity criterion;
(3.4) according to the 3Sigma principle of normal distribution, the probability of a numerical distribution in (mu-3 Sigma, mu +3 Sigma) is 0.9974, i.e., there is an important inflection point in the normal distribution at mu-3 Sigma. Setting mu-3 sigma as an integral electric quantity check index threshold value based on the normal distribution of the data set D calculated in the step (3.3);
(3.5) comparing the integral electric quantity check index of each distribution transformer with the integral electric quantity check index threshold, and if the integral electric quantity check index of the distribution transformer is higher than the integral electric quantity check index threshold, judging that the primary power failure fragment of the distribution transformer is the medium-level power failure fragment of the distribution transformer.
Step (4) the variation amplitude of the bottom of the distribution transformer corresponding to the middle-stage power failure fragment of each distribution transformer is respectively input into a frozen electric quantity check index calculation formula to obtain a frozen electric quantity check index set;
in a specific implementation manner of the embodiment of the present invention, the step (4) specifically includes the following sub-steps:
(4.1) obtaining the electricity meter bottom data of the distribution transformer corresponding to the medium-level power failure fragment as M k ＝[m k,1 ,m k,2 ,…,m k,i ,…,m k,n ]For blackout fragment data segment [ i, …, j ]]The table bottom data is m when the power failure fragment begins k,i The table bottom data at the end of power failure fragment is m k,j ；
And (4.2) calculating a frozen electric quantity change index.
(4.3) calculating the same data section [ i, …, j ] at the bottom of the previous daily electricity meter]Freezing electric quantity change index Z k * And calculating a check index of the frozen electric quantity.
And (4.4) repeating the steps, and calculating the frozen electric quantity check indexes of each distribution transformer aiming at the medium-level power failure fragments of each distribution transformer to form a frozen electric quantity check index data set.
And (5) inputting the frozen electric quantity checking index set and the time length of the medium-level power failure fragment of each distribution transformer into a preset classification model, classifying the medium-level power failure fragment set of the distribution transformer, eliminating all unreal power failure fragments in the medium-level power failure fragment set, generating a high-level power failure fragment set of the distribution transformer, and completing the accurate diagnosis of the power failure event of the distribution network based on data driving.
In a specific implementation manner of the embodiment of the present invention, the step (E) specifically includes the following sub-steps:
and (5.1) selecting the frozen electric quantity check index and the power failure fragment length j-i as input, and establishing a logistic regression model.
(5.3) set the samples as 0.5: the training set and the test set are divided into 0.5 form, and the F1 value of the training set is evaluated by using the trained model.
And (5.3) classifying the medium-level power failure fragments of the distribution transformers by using a logistic regression model, and if the medium-level power failure fragments of the distribution transformers are classified as real power failure classes, judging the medium-level power failure fragments corresponding to the distribution transformers to be high-level power failure fragments.
Example 2
The embodiment of the invention provides a power distribution network power failure event precision diagnosis device based on data driving, which comprises:
the acquisition unit is used for acquiring measurement data of a distribution transformer in the power distribution network;
the first generation unit is used for generating a primary power failure fragment set of the distribution transformer based on the acquired measurement data of the distribution transformer;
the second generation unit is used for calculating an integral electric quantity check index of each primary power failure fragment of the distribution transformer, eliminating partial unreal power failure fragments in the primary power failure fragment set based on the integral electric quantity check index and generating a middle-level power failure fragment set of the distribution transformer;
the calculating unit is used for respectively inputting the variation amplitude of the bottom of the distribution transformer corresponding to the middle-stage power failure fragment of each distribution transformer into a frozen electric quantity checking index calculating formula to obtain a frozen electric quantity checking index set;
and the third generation unit is used for inputting the frozen electric quantity check index set and the time length of the medium-level power failure fragment of each distribution transformer into a preset classification model, classifying the medium-level power failure fragment set of the distribution transformer, removing all unreal power failure fragments in the medium-level power failure fragment set, generating a high-level power failure fragment set of the distribution transformer, and completing the accurate diagnosis of the power failure event of the distribution network based on data driving.
In a specific implementation manner of the embodiment of the present invention, the distribution transformer primary power outage fragment set includes a plurality of distribution transformer primary power outage fragments, and the generation method of the distribution transformer primary power outage fragments includes the following sub-steps:
obtaining distribution transformer T k Active power measurement data P k ＝[p k,1 ,p k,2 ,...,p k,i ,...,p k,n ]；
If distribution transformer T k Active power measurement data P k In successive data sections p k,i ,...,p k,j ]0 or null, based on the distribution transformer T k Data section [ i, j ] of (1)]Creating a primary blackout fragment.
In a specific implementation of an embodiment of the invention, the distribution transformer T k The generation method of the distribution transformer medium-level power failure fragments comprises the following substeps:
acquiring an integral electric quantity check index calculation formula:
wherein, W k JF For distribution transformers T k Integral electric quantity of A k For distribution transformers T k Checking indexes of the integrated electric quantity;
calculating an integral electric quantity check index corresponding to the primary power failure fragment of each distribution transformer based on the integral electric quantity check index calculation formula to obtain an integral electric quantity check index set;
acquiring an integral electric quantity check index threshold;
comparing each integral electric quantity check index in the integral electric quantity check index set with the integral electric quantity check index threshold value;
and if the integral electric quantity check index is higher than the integral electric quantity check index threshold value, judging that the primary power failure fragment of the distribution transformer corresponding to the integral electric quantity check index is the middle-level power failure fragment of the distribution transformer.
In a specific implementation manner of the embodiment of the present invention, the method for calculating the integrated electric quantity check index threshold includes:
calculating normal distribution of the integral electric quantity check index data set based on the integral electric quantity check index data set by using a probability distribution estimation method based on a Bayesian information quantity criterion;
and calculating the check index threshold value of the integral electric quantity by using the 3Sigma principle of normal distribution.
In a specific implementation manner of the embodiment of the present invention, the frozen power check indicator calculation formula is:
wherein m is k,j For table bottom data at the end of power failure fragmentation, m k,i The table bottom data when the power failure fragment begins, i is the power failure fragment starting time, j is the power failure fragment ending time, and Z k In order to freeze the electricity quantity change index on the same day,
the same data section [ i, …, j ] at the bottom of the previous daily electricity meter]The frozen power change index.
In a specific implementation manner of the embodiment of the present invention, the method for generating the high-level power outage fragment set of the distribution transformer includes:
obtaining a logistic regression model;
and taking the frozen electric quantity check index set and the time length of the medium-level power failure fragment of each distribution transformer as input data, classifying the medium-level power failure fragments of each distribution transformer by using the logistic regression model, and judging the medium-level power failure fragment corresponding to the distribution transformer to be the high-level power failure fragment if the medium-level power failure fragment of the distribution transformer is classified as the real power failure class.
Example 3
Based on the same inventive concept as embodiment 1, the embodiment of the invention provides a power distribution network power failure event accurate diagnosis system based on data driving, which comprises a storage medium and a processor, wherein the storage medium is used for storing a plurality of data;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to any of embodiment 1.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application 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 application. 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.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application 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 application. 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.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (7)
1. A power distribution network power failure event accurate diagnosis method based on data driving is characterized by comprising the following steps:
generating a primary power failure fragment set of the distribution transformer based on the obtained measurement data of the distribution transformer;
calculating integral electric quantity check indexes of primary power failure fragments of each distribution transformer, removing partial unreal power failure fragments in the primary power failure fragment set based on the integral electric quantity check indexes, and generating a middle-level power failure fragment set of the distribution transformer;
respectively inputting the variation amplitude of the surface bottom of each distribution transformer corresponding to the middle-stage power failure fragment of each distribution transformer into a frozen electric quantity check index calculation formula to obtain a frozen electric quantity check index set;
inputting the frozen electric quantity check index set and the time length of the medium-level power failure fragment of each distribution transformer into a preset classification model, classifying the medium-level power failure fragment set of the distribution transformer, eliminating all unreal power failure fragments in the medium-level power failure fragment set, generating a high-level power failure fragment set of the distribution transformer, and completing the accurate diagnosis of the power failure event of the distribution network based on data driving;
the distribution transformer primary power failure fragment set comprises a plurality of distribution transformer primary power failure fragments, and the generation method of the distribution transformer primary power failure fragments comprises the following sub-steps:
obtaining distribution transformer T k Active power measurement data P k ＝[p k,1 ,p k,2 ,...,p k,i ,...,p k,n ]；
If distribution transformer T k Active power measurement data P k In successive data sections p k,i ,...,p k,j ]0 or null, based on the distribution transformer T k Data section [ i, j ] of (1)]Forming primary power failure fragments;
distribution transformer T k The generation method of the distribution transformer medium-level power failure fragments comprises the following substeps:
acquiring an integral electric quantity check index calculation formula:
wherein, W k JF For distribution transformers T k Integrated electric quantity of (A) k For distribution transformers T k Checking indexes of the integrated electric quantity;
calculating an integral electric quantity check index corresponding to the primary power failure fragment of each distribution transformer based on the integral electric quantity check index calculation formula to obtain an integral electric quantity check index set; p is a radical of k,i The ith active power measurement data is represented, and n represents the number of sampling points of the distribution transformer and the line active power measurement data;
for distribution transformers T k Frozen power data of (a);
acquiring an integral electric quantity check index threshold;
comparing each integral electric quantity check index in the integral electric quantity check index set with the integral electric quantity check index threshold value;
if the integral electric quantity check index is higher than the integral electric quantity check index threshold, judging that the primary power failure fragment of the distribution transformer corresponding to the integral electric quantity check index is a middle-level power failure fragment of the distribution transformer;
the generation method of the advanced power failure fragment set of the distribution transformer comprises the following steps:
obtaining a logistic regression model;
and taking the frozen electric quantity check index set and the time length of the medium-level power failure fragment of each distribution transformer as input data, classifying the medium-level power failure fragments of each distribution transformer by using the logistic regression model, and judging the medium-level power failure fragment corresponding to the distribution transformer to be the high-level power failure fragment if the medium-level power failure fragment of the distribution transformer is classified as the real power failure class.
2. The method for accurately diagnosing the power failure event of the power distribution network based on data driving as claimed in claim 1, wherein the method comprises the following steps: the calculation method of the integrated electric quantity check index threshold comprises the following steps:
calculating normal distribution of the integral electric quantity check index data set by utilizing a probability distribution estimation method based on a Bayesian information quantity criterion and based on the integral electric quantity check index data set;
and calculating the threshold value of the check index of the integral electric quantity by using the 3Sigma principle of normal distribution.
3. The method for accurately diagnosing the power failure event of the power distribution network based on data driving as claimed in claim 1, wherein the method comprises the following steps: the calculation formula of the frozen electric quantity check index is as follows:
wherein m is k,j For table bottom data at the end of power failure fragmentation, m k,i The table bottom data when the power failure fragment begins, i is the power failure fragment starting time, j is the power failure fragment ending time, and Z k In order to freeze the electricity quantity change index on the same day,
the same data section [ i, …, j ] at the bottom of the previous daily electricity meter]The frozen electric quantity change index.
4. The utility model provides a distribution network power failure incident accurate diagnostic device based on data drive which characterized in that includes:
the first generation unit is used for generating a primary power failure fragment set of the distribution transformer based on the acquired measurement data of the distribution transformer;
the distribution transformer primary power failure fragment set comprises a plurality of distribution transformer primary power failure fragments, and the generation method of the distribution transformer primary power failure fragments comprises the following sub-steps:
obtaining distribution transformer T k Active power measurement data P k ＝[p k,1 ,p k,2 ,...,p k,i ,...,p k,n ]；
If distribution transformer T k Active power measurement data P k In successive data sections p k,i ,...,p k,j ]0 or null, based on the distribution transformer T k Data section [ i,... j ] of]Forming primary power failure fragments;
the second generation unit is used for calculating an integral electric quantity check index of the primary power failure fragment of each distribution transformer, eliminating part of unreal power failure fragments in the primary power failure fragment set based on the integral electric quantity check index and generating a middle-level power failure fragment set of the distribution transformer;
distribution transformer T k The generation method of the distribution transformer medium-level power failure fragments comprises the following substeps:
acquiring an integral electric quantity check index calculation formula:
wherein, W k JF For distribution transformers T k Integral electric quantity of A k For distribution transformers T k Checking indexes of the integrated electric quantity;
calculating an integral electric quantity check index corresponding to the primary power failure fragment of each distribution transformer based on the integral electric quantity check index calculation formula to obtain an integral electric quantity check index set; p is a radical of formula k,i The ith active power measurement data is represented, and n represents the number of sampling points of the distribution transformer and the line active power measurement data;
for distribution transformers T k Frozen electrical quantity data of;
acquiring an integral electric quantity check index threshold;
comparing each integral electric quantity check index in the integral electric quantity check index set with the integral electric quantity check index threshold value;
if the integral electric quantity check index is higher than the integral electric quantity check index threshold, judging that the primary power failure fragment of the distribution transformer corresponding to the integral electric quantity check index is a middle-level power failure fragment of the distribution transformer;
the calculation unit is used for respectively inputting the variation amplitude of the bottom of the distribution transformer corresponding to the medium-level power failure fragment of each distribution transformer into a frozen electric quantity check index calculation formula to obtain a frozen electric quantity check index set;
the third generation unit is used for inputting the frozen electric quantity check index sets and the time lengths of the medium-level power failure fragments of the distribution transformers into a preset classification model, classifying the medium-level power failure fragment sets of the distribution transformers, eliminating all unreal power failure fragments in the medium-level power failure fragment sets, generating high-level power failure fragment sets of the distribution transformers, and completing the accurate diagnosis of power failure events of the distribution network based on data driving;
the generation method of the distribution transformer advanced power failure fragment set comprises the following steps:
obtaining a logistic regression model;
and taking the frozen electric quantity check index set and the time length of the medium-level power failure fragment of each distribution transformer as input data, classifying the medium-level power failure fragments of each distribution transformer by using the logistic regression model, and judging the medium-level power failure fragment corresponding to the distribution transformer to be the high-level power failure fragment if the medium-level power failure fragment of the distribution transformer is classified as the real power failure class.
5. The power distribution network power failure event precision diagnosis device based on data driving according to claim 4, characterized in that: the calculation method of the integrated electric quantity check index threshold comprises the following steps:
calculating normal distribution of the integral electric quantity check index data set by utilizing a probability distribution estimation method based on a Bayesian information quantity criterion and based on the integral electric quantity check index data set;
and calculating the check index threshold value of the integral electric quantity by using the 3Sigma principle of normal distribution.
6. The power distribution network power failure event precision diagnosis device based on data driving according to claim 4, characterized in that: the calculation formula of the frozen electric quantity check index is as follows:
wherein m is k,j For table bottom data at the end of power failure fragmentation, m k,i Table bottom data when power failure fragment begins, i is power failure fragment beginning time, j is power failure fragment ending time, and Z k In order to freeze the electricity quantity change index on the same day,
the same data section [ i, …, j ] at the bottom of the previous daily electricity meter]The frozen power change index.
7. The utility model provides a distribution network power failure incident accurate diagnostic system based on data drive which characterized in that: comprising a storage medium and a processor;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011202332.XA CN112348074B (en) | 2020-11-02 | 2020-11-02 | Power distribution network power failure event accurate diagnosis method, device and system based on data driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011202332.XA CN112348074B (en) | 2020-11-02 | 2020-11-02 | Power distribution network power failure event accurate diagnosis method, device and system based on data driving |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112348074A CN112348074A (en) | 2021-02-09 |
| CN112348074B true CN112348074B (en) | 2022-08-30 |
Family
ID=74355838
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011202332.XA Active CN112348074B (en) | 2020-11-02 | 2020-11-02 | Power distribution network power failure event accurate diagnosis method, device and system based on data driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112348074B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111400295A (en) * | 2020-03-13 | 2020-07-10 | 国电南瑞科技股份有限公司 | Power distribution network power failure event analysis method and device and storage medium |
-
2020
- 2020-11-02 CN CN202011202332.XA patent/CN112348074B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111400295A (en) * | 2020-03-13 | 2020-07-10 | 国电南瑞科技股份有限公司 | Power distribution network power failure event analysis method and device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| "基于数据驱动的中压配电网负损诊断系统设计与研发";陈锦铭等;《电力信息与通信技术》;20200925(第09期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112348074A (en) | 2021-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106779505B (en) | Power transmission line fault early warning method and system based on big data driving | |
| CN111459700B (en) | Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium | |
| CN108376982B (en) | Load phase sequence identification method and device | |
| CN113011481B (en) | Electric energy meter function abnormality assessment method and system based on decision tree algorithm | |
| CN115170000A (en) | Remote monitoring method and system based on electric energy meter communication module | |
| CN111458661A (en) | Power distribution network line variation relation diagnosis method, device and system | |
| CN109239456B (en) | Harmonic tracing method based on dynamic programming time series similarity algorithm | |
| CN110968703B (en) | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm | |
| CN113641959A (en) | High-voltage cable joint temperature trend prediction method | |
| CN115758151A (en) | Combined diagnosis model establishing method and photovoltaic module fault diagnosis method | |
| CN112345972B (en) | Power distribution network line transformation relation abnormity diagnosis method, device and system based on power failure event | |
| CN112348074B (en) | Power distribution network power failure event accurate diagnosis method, device and system based on data driving | |
| CN116166655B (en) | Big data cleaning system | |
| CN116452054A (en) | Method and device for managing material spot check of electric power system | |
| CN113540526B (en) | Fuel cell fault diagnosis method and system based on historical data analysis | |
| CN115659620A (en) | FMECA (failure mode-feedback analysis) method and system based on relative importance of data | |
| CN112347655B (en) | Wind power plant theoretical power calculation method based on unit operation performance evaluation | |
| CN114168662A (en) | Power distribution network problem combing and analyzing method and system based on multiple data sources | |
| CN113872200B (en) | Medium-voltage distribution network power failure event diagnosis and identification method, system and storage medium | |
| Hao et al. | Transmission line fault diagnosis based on machine learning | |
| CN117833824B (en) | Performance analysis method, device and equipment of photovoltaic inverter and storage medium | |
| CN117493857B (en) | Electric energy metering abnormality judging method, system, equipment and medium | |
| CN115828165B (en) | New energy intelligent micro-grid data processing method and system | |
| CN118050600B (en) | Distribution network fault positioning system based on distributed traveling wave measurement | |
| Raj et al. | Investigation of Partial Discharge Characteristics as Electric Treeing Prognostic Markers |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |