CN112116205A - Portrayal method, device and storage medium for power utilization characteristics of transformer area - Google Patents
Portrayal method, device and storage medium for power utilization characteristics of transformer area Download PDFInfo
- Publication number
- CN112116205A CN112116205A CN202010849417.0A CN202010849417A CN112116205A CN 112116205 A CN112116205 A CN 112116205A CN 202010849417 A CN202010849417 A CN 202010849417A CN 112116205 A CN112116205 A CN 112116205A
- Authority
- CN
- China
- Prior art keywords
- data
- power
- utilization
- area
- label
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000003860 storage Methods 0.000 title claims description 16
- 238000009826 distribution Methods 0.000 claims abstract description 77
- 230000005611 electricity Effects 0.000 claims abstract description 65
- 238000012544 monitoring process Methods 0.000 claims abstract description 27
- 230000008014 freezing Effects 0.000 claims description 79
- 238000007710 freezing Methods 0.000 claims description 79
- 239000013598 vector Substances 0.000 claims description 55
- 230000035945 sensitivity Effects 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 238000004140 cleaning Methods 0.000 claims description 7
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 230000000737 periodic effect Effects 0.000 claims description 4
- 238000003384 imaging method Methods 0.000 claims 7
- 238000007405 data analysis Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 12
- 238000004458 analytical method Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013075 data extraction Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000003442 weekly effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- 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
-
- 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
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- 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
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Fuzzy Systems (AREA)
- Evolutionary Biology (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides an image method for power utilization characteristics of a transformer area, and belongs to the field of power utilization big data. The portrait method aiming at the power utilization characteristics of the transformer area comprises the following steps: acquiring power utilization data related to power utilization conditions of each transformer area within preset time; configuring a plurality of electricity utilization feature tags for reflecting electricity utilization features of corresponding distribution areas in a multi-dimensional mode according to the acquired electricity utilization data, and extracting feature tag data corresponding to each electricity utilization feature tag from the electricity utilization data; and clustering the characteristic label data corresponding to all the distribution areas within the preset power grid monitoring range to obtain the power utilization characteristic image corresponding to the optimal distribution area classification. According to the technical scheme, the embodiment of the invention provides a complete power utilization characteristic portrait method aiming at the power utilization of the transformer area, so that the labeled power utilization characteristics of the transformer area can be quickly obtained and mastered, and the investment of data analysis in mass data is reduced.
Description
Technical Field
The invention relates to the field of power consumption big data, in particular to an image method, device and storage medium for power consumption characteristics of a transformer area.
Background
With the remarkable improvement of the demand of the modern society on the power supply quantity and the power supply quality and the popularization of the smart electric meters, classifying and constructing the power utilization images of the transformer area aiming at the power utilization modes of the transformer area become one of the key points concerned by power grid managers. The transformer area is a basic unit for operation management of a power grid and refers to a power supply range or area of a transformer. The power utilization characteristic analysis is the basis for carrying out power grid load prediction, overload prediction and other multiple power grid service scenes, and is also an important component of an intelligent power grid energy management system. According to different research objects, the power utilization characteristic analysis can be divided into user power utilization characteristic analysis, platform area power utilization characteristic analysis and larger-range area power utilization characteristic analysis. The user electricity load characteristic analysis cannot well represent the overall characteristics of electricity consumption in a certain area due to individual differences of users and different sensitivities of external environments. Therefore, the more representative characteristic analysis of the power utilization characteristics of the transformer area has more important significance for the power department to perform work such as power utilization management of the transformer area, planning of a new transformer area, power dispatching and the like.
The disadvantages of the prior art for power utilization portrait technology aiming at power utilization characteristics are shown in the following aspects: 1) the existing portrait technology in the power system mostly researches the construction of the electric portrait for users, but the construction of the electric portrait for the platform area is almost blank; 2) the problems of transformer area line loss, transformer area identification, health assessment and the like are mostly researched by the existing characteristic analysis technology about transformer area power utilization, and a relatively complete transformer area power utilization tag system and an image system do not exist.
Disclosure of Invention
The embodiment of the invention aims to provide an image method, an image device and a storage medium for power utilization characteristics of a transformer area, so as to provide a complete image of the power utilization characteristics of the transformer area.
In order to achieve the above object, an embodiment of the present invention provides an image method for power consumption characteristics of a platform area, including: acquiring power utilization data related to power utilization conditions of each transformer area within preset time; configuring a plurality of electricity utilization feature tags for reflecting electricity utilization features of corresponding distribution areas in a multi-dimensional mode according to the acquired electricity utilization data, and extracting feature tag data corresponding to each electricity utilization feature tag from the electricity utilization data; and clustering the characteristic label data corresponding to all the distribution areas within the preset power grid monitoring range to obtain the power utilization characteristic image corresponding to the optimal distribution area classification.
Preferably, after the acquiring of the power consumption data about the power consumption of each distribution area within the preset time, the method for representing the power consumption characteristics of the distribution area further includes: performing data cleaning on the electricity utilization data; and carrying out standardization processing on the electricity utilization data after data cleaning.
Preferably, the electricity consumption data includes: daily frozen quantity data and 96-point power data.
Preferably, the power usage feature tag includes: one or more of an electricity utilization stability label, an electricity utilization fluctuation rate label, a comfort sensitivity label and a daily freezing amount curve label configured according to the daily freezing amount data, wherein the electricity utilization stability label is used for reflecting the degree of predictability of the electricity utilization characteristics of the station area, the electricity utilization fluctuation rate label is used for reflecting the fluctuation amplitude of the daily freezing amount data of the station area, the comfort sensitivity label is used for reflecting the relation between the electricity utilization characteristics of the station area and weather factors, and the daily freezing amount curve label is used for reflecting the category of the daily freezing amount mode of the station area; and/or one or more of an average load rate label, a power average label and a load rate curve label configured according to the 96-point power data, wherein the average load rate label is used for reflecting the load fluctuation degree of the power utilization of the station area, the power average label is used for reflecting the power size of the power utilization of the station area, and the load rate curve label is used for reflecting the category of the power utilization mode of the station area.
Preferably, the extracting, from the power consumption data, feature tag data corresponding to the power consumption stability tag includes: carrying out finite Fourier decomposition on the daily freezing quantity data in a preset time period, and recombining different decomposed frequency components to form daily freezing quantity frequency curve data; decomposing daily freezing quantity frequency curve data into a cycle component, a low-frequency component and a high-frequency component according to the periodic difference of the frequency components of different daily freezing quantity data; and obtaining an upper limit and a lower limit of the power utilization stability according to the decomposed circumferential component, the low-frequency component and the high-frequency component.
Preferably, the extracting of the feature tag data corresponding to the daily freezing amount curve tag and/or the load factor curve tag from the power consumption data includes: converting the daily freezing amount data or the 96-point power data of each station area in the preset time into respective corresponding data vectors; the data vectors of all the distribution areas in the preset power grid monitoring range are clustered independently, respectively corresponding optimal distribution area classifications are obtained, and respectively corresponding mode numbers representing the classifications are obtained; and corresponding the obtained mode numbers to characteristic label data corresponding to the daily freezing amount curve label or the load rate curve label.
Preferably, the clustering process is performed on the feature tag data corresponding to all the distribution areas within the preset power grid monitoring range to obtain the electricity consumption feature portrait of each distribution area corresponding to the optimal distribution area classification, and the clustering process includes: forming a distribution area characteristic vector corresponding to the distribution area by taking each characteristic label data of the distribution area as a one-dimensional parameter; clustering the station area characteristic vectors corresponding to all station areas in a preset power grid monitoring range, taking the station area classification corresponding to the maximum absolute value of the contour coefficient as an optimal station area classification, and obtaining the optimal cluster number; and establishing a power utilization characteristic image rule of the distribution area according to the obtained optimal distribution area classification, and performing characteristic image on various distribution areas.
Preferably, after the station area classification corresponding to the maximum absolute value of the profile coefficient is the optimal station area classification and the optimal cluster number is obtained, the method for profiling the power consumption characteristics of the station area further includes: randomly selecting one of the distribution area feature vectors as a first clustering center; calculating the distance between the other district characteristic vectors in the preset power grid monitoring range and the first clustering center according to a preset distance calculation method to obtain a district characteristic vector farthest from the first clustering center, and adding the clustering center according to the district characteristic vector; calculating the distance between other station area characteristic vectors in the preset range and the nearest clustering center according to the preset distance calculation method to obtain the station area characteristic vector corresponding to the maximum distance, and adding the clustering center by using the station area characteristic vector; and when the number of the clustering centers is equal to the optimal clustering cluster number, clustering the station area characteristic vectors corresponding to all station areas in the preset power grid monitoring range to obtain an optimized optimal station area classification.
The embodiment of the invention also provides an image device for the power utilization characteristics of the transformer area, which comprises: the power utilization system comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the method for representing the power utilization characteristics of the transformer area.
The invention provides a machine-readable storage medium, which stores instructions for enabling a machine to execute any one of the above-mentioned methods for representing power utilization characteristics of a distribution area.
Through the technical scheme, the embodiment of the invention provides a complete power utilization characteristic portrait method aiming at power utilization of the transformer area, so that the labeled power utilization characteristics of the transformer area can be quickly obtained and mastered, and the investment of data analysis in mass data is reduced.
Additional features and advantages of embodiments of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the embodiments of the invention without limiting the embodiments of the invention. In the drawings:
FIG. 1 is a flow chart illustrating a method for representing power consumption characteristics of a distribution room according to an embodiment of the present invention;
FIG. 2 is a frequency chart corresponding to daily freezing data in power consumption data of a distribution room;
fig. 3(a), fig. 3(b), and fig. 3(c) are schematic diagrams of the cycle component, the high frequency classification, and the low frequency component obtained by performing the frequency extraction with respect to fig. 2 according to the embodiment of the present invention;
FIG. 4 is a graph of daily freeze volume data for a distribution room versus a comfort index;
FIG. 5 is a schematic flow chart of an example of an embodiment of the present invention;
fig. 6(a), 6(b), and 6(c) are schematic diagrams of the clustering result after the example clustering of fig. 5.
Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating embodiments of the invention, are given by way of illustration and explanation only, not limitation.
Referring to fig. 1, an image method for power utilization characteristics of a distribution room according to an embodiment of the present invention may include the following steps:
step S100: and acquiring power utilization data related to the power utilization condition of each distribution area in preset time.
Preferably, the electricity consumption data includes: daily freezing amount data and daily 96-point power data in a preset time. The daily freezing quantity data is the daily electricity consumption of the transformer area; the 96-point power data is power data collected by the station area according to the frequency of 96 points in a day, namely data collected according to 15-minute intervals.
After the acquiring of the power consumption data about the power consumption condition of each distribution area within the preset time, the method for representing the power consumption characteristics of the distribution area may further include: performing data cleaning on the electricity utilization data; and carrying out standardization processing on the electricity utilization data after data cleaning.
For example, the daily freezing amount data and the 96-point power data of each station area are respectively cleaned, that is, the daily freezing amount data and the 96-point power data are subjected to missing value and abnormal value processing, such as missing value supplement and abnormal value deletion. After the data is cleaned, the data is unified, that is, the data is normalized, and for example, for the daily frozen amount data, the normalized daily frozen amount data can be obtained by subtracting the daily frozen amount mean value from each daily frozen amount data value and dividing the daily frozen amount mean value by the daily frozen amount standard deviation.
Step S200: and configuring a plurality of electricity utilization feature tags for reflecting electricity utilization features of corresponding distribution areas in a multi-dimensional mode according to the acquired electricity utilization data, and extracting feature tag data corresponding to each electricity utilization feature tag from the electricity utilization data.
Wherein, taking electricity data as daily freezing quantity data and 96-point power data as an example, the electricity utilization characteristics of the multi-dimensional reflection platform area are represented as follows: one or more of a power utilization stability label, a power utilization fluctuation rate label, a comfort sensitivity label and a daily freezing amount curve label configured according to the daily freezing amount data; and/or one or more of an average load rate label, a power mean label, and a load rate curve label configured from the 96-point power data. Wherein the tags are defined as follows:
1) the power utilization stability label is used for reflecting the predictable degree of the power utilization characteristics of the distribution room;
2) the power consumption fluctuation rate label is used for reflecting the fluctuation amplitude of the daily freezing amount data of the transformer area;
3) the comfort sensitivity label is used for reflecting the relation between the power utilization characteristics of the transformer area and weather factors;
4) the daily freezing amount curve label is used for reflecting the category of the daily freezing amount mode of the transformer area;
5) the average load rate label is used for reflecting the load fluctuation degree of the power utilization of the transformer area;
6) the power average label is used for reflecting the power of the power utilization of the transformer area;
7) and the load rate curve label is used for reflecting the type of the power utilization mode of the transformer area.
It should be noted that the embodiment of the present invention also includes other feature tags for reflecting the power utilization features of the distribution area, which is not exemplified here.
Furthermore, the characteristic data corresponding to the characteristic tag can be extracted from the power utilization data of the transformer area by means of direct acquisition, statistical analysis, data mining and the like. The following describes a method for extracting feature data of a part of feature tags.
First, daily freezing amount curve label and/or load rate curve label.
In a preferred embodiment, extracting feature tag data corresponding to the daily freezing amount curve tag and/or the load factor curve tag from the electricity consumption data may include: converting the daily freezing amount data or the 96-point power data of each station area in the preset time into respective corresponding data vectors; the data vectors of all the distribution areas in the preset power grid monitoring range are clustered independently, respectively corresponding optimal distribution area classifications are obtained, and respectively corresponding mode numbers representing the classifications are obtained; and corresponding the obtained mode numbers to characteristic label data corresponding to the daily freezing amount curve label or the load rate curve label.
The load rate curve is an important characteristic for describing the power utilization modes of the transformer area, the forms of the load rate curves corresponding to the transformer areas with different power utilization modes are obviously different, and the corresponding label data is extracted by comprehensively considering the characteristic information of the load rate curve in the monitoring time period and classifying the power utilization modes of the transformer areas. The preferred clustering method in the embodiment of the invention performs corresponding data extraction on the platform load rate curve label, which is specifically represented by the following steps that load rate curve data can be extracted through steps S111-S113:
step S111: and converting the 96-point power data of each station area in the preset time into corresponding 96-point power data vectors.
For example, the 96-point power data of the station region in the monitoring time is converted into the following vector:
Si＝[si1,si2…sin] (1)
wherein S isiThe number n of sampling points is preferably the number of all effective 96-point power data in the monitoring time.
Step S112: and clustering the 96-point power data vectors of all the distribution areas within the preset power grid monitoring range to obtain the distribution area classification corresponding to the optimal 96-point power data, and obtaining the corresponding pattern number representing the classification.
For example, K-means clustering can be performed on the load rate curve vectors of all the transformer areas. In the embodiment of the present invention, the following euclidean distances are preferably used as the measurement of the distance between the load rate curve vectors of each station:
wherein, dist (S)i,Sj) The distance between the load factor curve vectors of the ith station area and the jth station area is shown, and p represents the p-th element in each vector.
Further, selecting a profile coefficient to evaluate the clustering effect of the load rate curve vectors of each station area, obtaining the station area classification corresponding to the optimal load rate curve vector by using the maximum absolute value of the profile coefficient as the optimal clustering result, wherein the optimal classification cluster number is K, namely, all the station areas in the preset power grid monitoring range are classified into K types, selecting a sorting mode to mark the K types of load rate curve vectors to obtain the corresponding mode number, for example, sorting by using the average load rate value of the clustering center of the K types of load rate curve vectors to obtain the mode number of 1-K.
Step S113: and taking the mode number as load rate curve data corresponding to the load rate curve label.
Accordingly, steps S111 to S113 realize the extraction of the load factor curve data. It should be noted that, since the daily freezing amount curve label is used to reflect the category of the station area daily freezing amount pattern, the manner of extracting the corresponding daily freezing amount curve data can also be implemented by steps S111 to S113 similar to the load factor curve data, with the difference that: for the daily freezing amount curve label, converting the daily freezing amount data of each station area into corresponding vectors, and in the formula (1), SiAnd n turns to represent the number of sampling points of daily frozen quantity data. Therefore, the process of extracting the daily freezing amount curve data corresponding to the daily freezing amount curve label is not repeated.
It should be noted that the feature tag data obtained by extracting the feature tag in the above manner cannot visually obtain the feature information thereof, and only the category thereof can be obtained, and then the feature form thereof is deduced by the category thereof, so that the feature tags such as the daily freezing amount curve tag and the load rate curve tag are type feature tags, and the correspondingly extracted feature tag data is type tag data. The feature tags different from the feature data extraction mode can visually acquire feature information of the feature tags and are continuous feature tags, and correspondingly extracted feature tag data are continuous tag data.
Second, an average load rate tag and/or a power mean tag.
For the average load rate label, the average load rate data can be extracted by:
wherein, PavgRepresenting the mean value of the load, P, over the predetermined time spanmaxRepresenting the maximum load within the preset time span. It can be known through calculation that the higher the average load rate data is, the higher the ratio of the average load level of the station area to the load peak value is, and the fluctuation of the load rate curve is smaller.
It should be noted that the power mean label may pass through PavgAnd extracting corresponding characteristic data.
Thirdly, power utilization stability label.
The daily freezing data corresponding to each station region for a period of time is time series data with strong periodicity, wherein the periodic data component can be accurately predicted by a proper method, and the high-frequency data component belongs to a noise component and cannot be predicted.
For example, the electricity stability label may be extracted from the daily freezing amount data according to the following steps S121 to S123.
Step S121: and carrying out finite Fourier decomposition on the daily freezing quantity data in a preset time period, and recombining different decomposed frequency components to form daily freezing quantity frequency curve data.
The embodiment of the invention can carry out finite Fourier decomposition on the time sequence corresponding to the daily freezing quantity data corresponding to each station area in the preset time period, and recombine different decomposed frequency components to form daily freezing quantity frequency curve data. For example, referring to fig. 2, the daily freezing amount frequency curve data corresponding to the time series of the daily freezing amount data in 350 days of a certain area is shown, wherein the abscissa represents the preset number of days and the ordinate represents the daily freezing amount data.
Step S122: and decomposing the daily freezing amount data in a preset time period into a week component, a low-frequency component and a high-frequency component according to the periodic difference of the frequency components of different daily freezing amount data.
For example, referring to fig. 3(a), 3(b) and 3(c) for the 3 components of the weekly component, the high frequency component and the low frequency component obtained by decomposing the daily freezing quantity frequency curve of fig. 2, it can be seen that the weekly component in the obtained 3 frequency components has obvious periodicity and belongs to a predictable component; the high-frequency component changes violently and has no regularity and belongs to an unpredictable component; the low frequency components are long-term changing components whose predictability is determined by the prediction model and the data span used.
Step S123: and obtaining an upper limit and a lower limit of the power utilization stability according to the decomposed circumferential component, the low-frequency component and the high-frequency component.
The upper limit of the electricity stability prediction accuracy is a component that can be accurately predicted except for the high-frequency component, and therefore the upper limit of the electricity stability can be extracted by the following equation:
wherein S (i) represents the daily freezing amount data in the preset time period, h (i) represents the high-frequency component separated from S (i) in step S121, and N represents the preset time period.
Meanwhile, the lower limit of the electricity stability prediction accuracy is a component other than the high-frequency component and the low-frequency component, and thus the electricity stability lower limit can be extracted by the following equation:
where l (i) represents the low-frequency component separated from S (i) in step S121.
And fourthly, using a fluctuation rate label.
For the power consumption signature, the power consumption data can be extracted by:
wherein S isavgPresentation instrumentAverage value of daily freezing amount in the preset time period, SmaxRepresents the maximum value of the daily freezing amount in the preset time period. If the preset time period is K weeks, the average power consumption fluctuation rate data in the preset time period can be extracted by the following formula:
wherein r isiThe data of the used fluctuation rate of the i-th week. The fluctuation range of daily freezing amount curve data in the monitoring time is reflected by the power consumption fluctuation rate label, and the lower the power consumption fluctuation rate data is, the larger the peak-to-valley difference of power consumption in the monitoring time is, and the larger the fluctuation range of the daily freezing amount curve data is.
And fifthly, a comfort sensitivity label.
For example, for a comfort sensitivity label, comfort sensitivity data may be extracted by the following steps S131-S132:
step S131: a comfort index associated with the power usage characteristics of the platform and weather factors is determined.
The power utilization behavior of users in the platform area is closely related to external weather factors, particularly temperature and humidity, so that the effect of the comprehensive effect of the power utilization behavior and the external weather factors is reflected by the composite index comfort level index. The following temperature-humidity index is preferred as the comfort index in the embodiment of the present invention:
C＝T-0.55(1-U)(T-14.5) (8)
wherein T is the daily average temperature and U is the relative humidity. Because the influence of temperature and humidity is comprehensively considered, the comfort index can more comprehensively depict the relation between the daily freezing quantity data of the platform area and external weather factors.
Step S132: and extracting high-temperature comfort sensitivity data and low-temperature comfort sensitivity data according to the relation between the comfort index and the daily freezing amount data.
For example, a relationship between the daily freezing amount data and the comfort index of one of the distribution rooms is selected to obtain a relationship diagram, please refer to fig. 4, where the abscissa is the data degree index and the ordinate is the daily freezing amount data (KWh), a fitting curve of the daily freezing amount data and the comfort index of the distribution room is a piecewise linear function of approximately 3 segments, and absolute slope values of the fitting curve of the high-temperature region and the low-temperature region are extracted to obtain high-temperature comfort sensitivity data and low-temperature comfort sensitivity data.
The comfort sensitivity label delineates the change of the daily freezing amount of the transformer area caused by the change of the comfort degree caused by the weather change, and the higher the comfort sensitivity data is, the more sensitive the daily freezing amount data of the transformer area to the change of the comfort degree is.
Step S300: and clustering the characteristic label data corresponding to all the distribution areas within the preset power grid monitoring range to obtain the power utilization characteristic image corresponding to the optimal distribution area classification.
In step S300, based on the feature tag data corresponding to the multidimensional feature tag for reflecting the power consumption characteristics of the distribution room obtained in step S200, optimal clustering is performed, and a complete distribution room power consumption feature image is created. The station area electricity consumption feature image is an identifier including a category of each electricity consumption feature of the station area. For example, the characteristic image of the ith station area is as follows:
preferably, the electricity consumption feature image of each type of platform area corresponding to the optimal platform area classification can be obtained through the following steps S311 to S313:
step S311: and forming a distribution area characteristic vector corresponding to the distribution area by taking each characteristic label data of the distribution area as a one-dimensional parameter.
For example, one or more of power consumption stability data, power consumption fluctuation rate data, comfort sensitivity data, daily freezing amount curve data, average load rate data, power average value data, and load rate curve data are selected, and are respectively one-dimensional parameters of vectors, so as to form a station area feature vector corresponding to each station area:
Xi＝[xi1,xi2…xin] (9)
step S312: and clustering the station area characteristic vectors corresponding to all station areas in the preset power grid monitoring range, taking the station area classification corresponding to the maximum absolute value of the contour coefficient as the optimal station area classification, and obtaining the optimal cluster number.
Similar to the step S112, the euclidean distance in the formula (2) is used as the measurement of the distance between the feature vectors of each station area, a K-means algorithm is selected for clustering all the station areas in the monitoring range, the station area classification corresponding to the maximum absolute value of the contour coefficient is used as the optimal station area classification, and the optimal cluster number K is obtained.
Step S313: and establishing a power utilization characteristic image rule of the distribution area according to the obtained optimal distribution area classification, and performing characteristic image on various distribution areas.
For example, K-class station area classifications are obtained, each feature label data of each class of station area is compared with a preset rule to obtain an identifier capable of visually reflecting each power utilization feature of the station area, and a corresponding station area power utilization feature image rule is established. The table area electrical characteristic representation rule may also be obtained by, for example, averaging feature tag data in each type of table area, and then comparing and sorting the average values, and the rule is not limited in the embodiment of the present invention.
The selection of the initial clustering center has great influence on the clustering result of the K-means algorithm, and the random initialization of the clustering center sometimes cannot obtain a good clustering result, so the embodiment of the invention also provides an improved clustering method K-means + + algorithm to avoid the problems. More preferably, after the station area classification corresponding to the maximum absolute value of the contour coefficient is the optimal station area classification and the optimal cluster number is obtained, the method for representing the station area power consumption characteristics further includes the following steps S321 to S324:
step S321: and randomly selecting one of the platform region feature vectors as a first clustering center.
For example, with the feature vector as X0C of (A)0The platform area serves as a first clustering center.
Step S322: and calculating the distance between the other station area characteristic vectors in the preset power grid monitoring range and the first clustering center according to a preset distance calculation method to obtain the station area characteristic vector farthest from the first clustering center, and adding the clustering center by using the station area characteristic vector.
For example, according to a preset distance calculation method, for example, the distance calculation method of formula (2), other distribution areas C in the power grid monitoring range are calculatediFeature vector X ofiAnd X0And calculating CiProbability P (x) of selecting as new cluster center, wherein the larger D (x) is, the larger P (x) is, and the maximum P (x) or D (x) is corresponding to CiIs a newly added clustering center.
Step S323: and calculating the distance between the other station area characteristic vectors in the preset range and the nearest clustering center according to the preset distance calculation method to obtain the station area characteristic vector corresponding to the maximum distance, and adding the clustering center by using the station area characteristic vector.
When there are multiple cluster centers, adding new cluster centers according to the distance calculation method of step S322. For example, the distance D (x) between the feature vector of other region and the nearest cluster center is calculated, and C corresponding to the maximum P (x) or D (x)iIs a newly added clustering center.
Step S324: and when the number of the clustering centers is equal to the optimal clustering cluster number, clustering the station area characteristic vectors corresponding to all the station areas in the preset power grid monitoring range to obtain an optimized optimal station area classification.
And when the number of the clustering centers is equal to the optimal clustering cluster number K, clustering by using a K-means algorithm by taking the current K clustering centers as initial clustering centers to obtain an optimal distribution area classification and obtain an electricity utilization characteristic image corresponding to the optimal distribution area classification.
In summary, the embodiments of the present invention configure tags capable of depicting electricity consumption characteristics of the distribution room in the massive electricity consumption data of the distribution room, and provide a method for extracting feature tag data corresponding to each distribution room feature tag, thereby forming a relatively complete distribution room feature tag system. Meanwhile, the power utilization label data with different dimensions for reflecting the power utilization characteristics of the transformer area are clustered to obtain the power utilization portrait of the transformer area, so that the labeled power utilization characteristics of the transformer area can be obtained and mastered quickly, and the investment for data analysis in mass data is reduced.
Further, please refer to fig. 5, an implementation process of the above-mentioned portrait method is explained as an example. Selecting 181 transformer areas in a certain Shanghai area and corresponding electricity utilization data for testing, wherein the process is as follows:
step S11: daily freezing data and 96-point power data of 181 station areas within 365 days of a year are acquired, and data cleaning is carried out.
Step S12: and correspondingly extracting feature tag data from the configured electricity utilization feature tags by methods of direct extraction, statistical analysis, data mining and the like. According to the example, the electricity utilization stability data, the electricity utilization fluctuation rate data, the comfort sensitivity data and the daily freezing amount curve data are extracted according to the daily freezing amount data; average load rate data, power mean data and load rate curve data were extracted from the 96-point power data.
Step S13: and establishing a station area characteristic vector of each station area according to the data, and clustering to obtain the optimal station area classification. The optimal cluster number K obtained in this example is 5, and as a result of clustering, refer to fig. 6(a), fig. 6(b), and fig. 6 (c).
Wherein, the abscissa of fig. 6(a) is each continuous electricity utilization feature label; the ordinate is standardized feature tag data of various power utilization feature tags of the distribution room obtained after clustering of the feature tag data, the step S313 is referred to for the obtaining mode of the feature tag data, and the numerical value is a relative value for easy viewing; the column diagrams are respectively a type 1 distribution area and a type 2 distribution area … … type 5 distribution area from left to right. The size of a certain electricity utilization characteristic label value of a certain type of distribution room can be directly obtained through the graph, and the distribution room electricity utilization image rule is established according to the size, wherein a comfortable sensitivity label is taken as an example, the value is low when the value is below 0.8, the value is medium when the value is 0.8-0.9, and the data is high when the value is above 0.9.
As can be seen from the extraction of the daily freezing amount curve data and the extraction of the load rate curve data in step S200, the daily freezing amount curve label and the load rate curve label are type feature labels, which are corresponding data extracted in a clustering manner, so that the data clustered by the two labels cannot be viewed visually, and in order to better show the actual features of the daily freezing amount curve data and the extracted load rate curve data, the clustering results of the daily freezing amount curve label and the load rate curve label are shown in fig. 6(b) and fig. 6 (c).
Step S14: the power utilization characteristic image corresponding to the optimal distribution area classification is obtained in the example as follows:
the embodiment of the invention also provides an image device for the power utilization characteristics of the transformer area, which comprises: the device comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the portrayal method for the power utilization characteristics of the platform area.
The embodiment of the invention also provides a machine-readable storage medium, wherein the machine-readable storage medium is stored with instructions, and the instructions enable a machine to execute the above-mentioned method for representing the power utilization characteristics of the transformer area.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method 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 invention 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.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
The above are merely examples of the present invention, and are not intended to limit the present invention. Various modifications and alterations to this invention will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (10)
1. An image method for power utilization characteristics of a transformer area is characterized by comprising the following steps:
acquiring power utilization data related to power utilization conditions of each transformer area within preset time;
configuring a plurality of electricity utilization feature tags for reflecting electricity utilization features of corresponding distribution areas in a multi-dimensional mode according to the acquired electricity utilization data, and extracting feature tag data corresponding to each electricity utilization feature tag from the electricity utilization data; and
and clustering the characteristic label data corresponding to all the distribution areas within the preset power grid monitoring range to obtain the power utilization characteristic image corresponding to the optimal distribution area classification.
2. The method for imaging the power utilization characteristics of the transformer district as claimed in claim 1, wherein after the acquiring of the power utilization data about the power utilization condition of each transformer district within the preset time, the method for imaging the power utilization characteristics of the transformer district further comprises:
performing data cleaning on the electricity utilization data; and
and carrying out standardization processing on the electricity utilization data after data cleaning.
3. The imaging method for the power utilization feature of the platform area according to claim 1, wherein the power utilization data comprises:
daily frozen quantity data and 96-point power data.
4. The method for imaging the power utilization feature of the platform according to claim 3, wherein the power utilization feature tag comprises:
one or more of an electricity utilization stability label, an electricity utilization fluctuation rate label, a comfort sensitivity label and a daily freezing amount curve label configured according to the daily freezing amount data, wherein the electricity utilization stability label is used for reflecting the degree of predictability of the electricity utilization characteristics of the station area, the electricity utilization fluctuation rate label is used for reflecting the fluctuation amplitude of the daily freezing amount data of the station area, the comfort sensitivity label is used for reflecting the relation between the electricity utilization characteristics of the station area and weather factors, and the daily freezing amount curve label is used for reflecting the category of the daily freezing amount mode of the station area; and/or
One or more of an average load rate label, a power average label and a load rate curve label configured according to the 96-point power data, wherein the average load rate label is used for reflecting the load fluctuation degree of the power utilization of the station area, the power average label is used for reflecting the power consumption of the station area, and the load rate curve label is used for reflecting the category of the power utilization mode of the station area.
5. The imaging method for the power utilization feature of the platform area according to claim 4, wherein extracting feature tag data corresponding to the power utilization stability tag from the power utilization data comprises:
carrying out finite Fourier decomposition on the daily freezing quantity data in a preset time period, and recombining different decomposed frequency components to form daily freezing quantity frequency curve data;
decomposing daily freezing quantity frequency curve data into a cycle component, a low-frequency component and a high-frequency component according to the periodic difference of the frequency components of different daily freezing quantity data; and
and obtaining an upper limit and a lower limit of the power utilization stability according to the decomposed circumferential component, the low-frequency component and the high-frequency component.
6. The method for imaging the power consumption feature of the platform according to claim 4, wherein extracting feature tag data corresponding to the daily freezing amount curve tag and/or the load factor curve tag from the power consumption data includes:
converting the daily freezing amount data or the 96-point power data of each station area in the preset time into respective corresponding data vectors;
the data vectors of all the distribution areas in the preset power grid monitoring range are clustered independently, respectively corresponding optimal distribution area classifications are obtained, and respectively corresponding mode numbers representing the classifications are obtained; and
and correspondingly taking the obtained mode numbers as the characteristic label data corresponding to the daily freezing amount curve label or the load rate curve label.
7. The method for imaging the power utilization characteristics of the distribution room according to claim 1, wherein the clustering process is performed on the characteristic tag data corresponding to all distribution rooms within a preset power grid monitoring range to obtain the power utilization characteristic image of each type of distribution room corresponding to the optimal distribution room classification, and the method comprises the following steps:
forming a distribution area characteristic vector corresponding to the distribution area by taking each characteristic label data of the distribution area as a one-dimensional parameter;
clustering the station area characteristic vectors corresponding to all station areas in a preset power grid monitoring range, taking the station area classification corresponding to the maximum absolute value of the contour coefficient as an optimal station area classification, and obtaining the optimal cluster number; and
and establishing a power utilization characteristic image rule of the distribution area according to the obtained optimal distribution area classification, and performing characteristic image on various distribution areas.
8. The method as claimed in claim 7, wherein after the station area classification corresponding to the maximum absolute value of the contour coefficient is the optimal station area classification and the optimal cluster number is obtained, the method further comprises:
randomly selecting one of the distribution area feature vectors as a first clustering center;
calculating the distance between the other district characteristic vectors in the preset power grid monitoring range and the first clustering center according to a preset distance calculation method to obtain a district characteristic vector farthest from the first clustering center, and adding the clustering center according to the district characteristic vector;
calculating the distance between other station area characteristic vectors in the preset range and the nearest clustering center according to the preset distance calculation method to obtain the station area characteristic vector corresponding to the maximum distance, and adding the clustering center by using the station area characteristic vector; and
and when the number of the clustering centers is equal to the optimal clustering cluster number, clustering the station area characteristic vectors corresponding to all the station areas in the preset power grid monitoring range to obtain an optimized optimal station area classification.
9. An image device for power consumption characteristics of a platform area, the image device comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the computer program to implement the portrayal method for the power usage characteristics of a table area according to any one of claims 1 to 8.
10. A machine-readable storage medium having stored thereon instructions for causing a machine to execute the method for profiling power usage characteristics of a platform according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010849417.0A CN112116205B (en) | 2020-08-21 | 2020-08-21 | Image method, device and storage medium for power utilization characteristics of platform area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010849417.0A CN112116205B (en) | 2020-08-21 | 2020-08-21 | Image method, device and storage medium for power utilization characteristics of platform area |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112116205A true CN112116205A (en) | 2020-12-22 |
| CN112116205B CN112116205B (en) | 2024-03-12 |
Family
ID=73805263
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010849417.0A Active CN112116205B (en) | 2020-08-21 | 2020-08-21 | Image method, device and storage medium for power utilization characteristics of platform area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112116205B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112734212A (en) * | 2020-12-31 | 2021-04-30 | 北京一起教育科技有限责任公司 | Student homework behavior portrait method and device and electronic equipment |
| CN114881429A (en) * | 2022-04-19 | 2022-08-09 | 国网江苏省电力有限公司南通供电分公司 | Data-driven transformer area line loss quantification method and system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107977737A (en) * | 2017-11-19 | 2018-05-01 | 国网浙江省电力公司信息通信分公司 | Distribution transformer load Forecasting Methodology based on mxnet frame depth neutral nets |
| CN109685581A (en) * | 2019-01-03 | 2019-04-26 | 江苏方天电力技术有限公司 | A kind of large power customers electricity consumption behavior analysis method based on label clustering technology |
| CN109903082A (en) * | 2019-01-24 | 2019-06-18 | 平安科技（深圳）有限公司 | Clustering method, electronic device and storage medium based on user's portrait |
| CN109977177A (en) * | 2019-03-27 | 2019-07-05 | 新奥数能科技有限公司 | Generate the method and device of user's portrait |
| CN110991530A (en) * | 2019-12-02 | 2020-04-10 | 天津开心生活科技有限公司 | Missing data processing method and device, electronic equipment and storage medium |
| CN111384726A (en) * | 2020-01-21 | 2020-07-07 | 国网安徽省电力有限公司六安供电公司 | High-permeability photovoltaic power distribution network partition voltage regulation method |
| CN111415049A (en) * | 2020-04-27 | 2020-07-14 | 国网河北能源技术服务有限公司 | Power failure sensitivity analysis method based on neural network and clustering |
| CN111415107A (en) * | 2020-04-30 | 2020-07-14 | 南方电网数字电网研究院有限公司 | Power distribution network platform region portrait generation method and device, computer equipment and storage medium |
| CN111461761A (en) * | 2020-02-29 | 2020-07-28 | 国网江苏省电力有限公司苏州供电分公司 | Resident user portrait method based on multi-dimensional fine-grained behavior data |
-
2020
- 2020-08-21 CN CN202010849417.0A patent/CN112116205B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107977737A (en) * | 2017-11-19 | 2018-05-01 | 国网浙江省电力公司信息通信分公司 | Distribution transformer load Forecasting Methodology based on mxnet frame depth neutral nets |
| CN109685581A (en) * | 2019-01-03 | 2019-04-26 | 江苏方天电力技术有限公司 | A kind of large power customers electricity consumption behavior analysis method based on label clustering technology |
| CN109903082A (en) * | 2019-01-24 | 2019-06-18 | 平安科技（深圳）有限公司 | Clustering method, electronic device and storage medium based on user's portrait |
| CN109977177A (en) * | 2019-03-27 | 2019-07-05 | 新奥数能科技有限公司 | Generate the method and device of user's portrait |
| CN110991530A (en) * | 2019-12-02 | 2020-04-10 | 天津开心生活科技有限公司 | Missing data processing method and device, electronic equipment and storage medium |
| CN111384726A (en) * | 2020-01-21 | 2020-07-07 | 国网安徽省电力有限公司六安供电公司 | High-permeability photovoltaic power distribution network partition voltage regulation method |
| CN111461761A (en) * | 2020-02-29 | 2020-07-28 | 国网江苏省电力有限公司苏州供电分公司 | Resident user portrait method based on multi-dimensional fine-grained behavior data |
| CN111415049A (en) * | 2020-04-27 | 2020-07-14 | 国网河北能源技术服务有限公司 | Power failure sensitivity analysis method based on neural network and clustering |
| CN111415107A (en) * | 2020-04-30 | 2020-07-14 | 南方电网数字电网研究院有限公司 | Power distribution network platform region portrait generation method and device, computer equipment and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112734212A (en) * | 2020-12-31 | 2021-04-30 | 北京一起教育科技有限责任公司 | Student homework behavior portrait method and device and electronic equipment |
| CN114881429A (en) * | 2022-04-19 | 2022-08-09 | 国网江苏省电力有限公司南通供电分公司 | Data-driven transformer area line loss quantification method and system |
| CN114881429B (en) * | 2022-04-19 | 2024-04-02 | 国网江苏省电力有限公司南通供电分公司 | Data-driven-based method and system for quantifying line loss of transformer area |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112116205B (en) | 2024-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110231528B (en) | Transformer household variation common knowledge identification method and device based on load characteristic model library | |
| CN110097297B (en) | Multi-dimensional electricity stealing situation intelligent sensing method, system, equipment and medium | |
| CN110082579B (en) | Intelligent platform area anti-electricity-stealing monitoring method, system, equipment and medium | |
| Chicco et al. | Emergent electricity customer classification | |
| JP7319757B2 (en) | Data processing system and data processing method | |
| US10664931B2 (en) | Data analyzing system and method | |
| Alahakoon et al. | Advanced analytics for harnessing the power of smart meter big data | |
| CN110223196A (en) | Analysis method of opposing electricity-stealing based on typical industry feature database and sample database of opposing electricity-stealing | |
| JP2018092439A5 (en) | ||
| CN101872441A (en) | Discrete resource management | |
| WO2019049546A1 (en) | Prediction system and method | |
| CN114676883A (en) | Power grid operation management method, device and equipment based on big data and storage medium | |
| CN110414768B (en) | Big data analysis method based on instrument current data | |
| CN112116205B (en) | Image method, device and storage medium for power utilization characteristics of platform area | |
| US20200144816A1 (en) | Submodular Load Clustering with Robust Principal Component Analysis | |
| Shamim et al. | Multi-domain feature extraction for improved clustering of smart meter data | |
| Dong et al. | Forecasting smart meter energy usage using distributed systems and machine learning | |
| Dinesh et al. | Residential power forecasting based on affinity aggregation spectral clustering | |
| CN112288172A (en) | Prediction method and device for line loss rate of transformer area | |
| CN116777124B (en) | Power stealing monitoring method based on user power consumption behavior | |
| CN108154259B (en) | Load prediction method and device for heat pump, storage medium, and processor | |
| Chicco et al. | A review of concepts and techniques for emergent customer categorisation | |
| CN112215482A (en) | Method and device for identifying user variable relationship | |
| Wang et al. | Application of clustering technique to electricity customer classification for load forecasting | |
| CN116226293A (en) | Method and system for generating and managing power customer portrait |
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 |