CN109598535A - It is a kind of based on big data to the method and system of distributed photovoltaic client segmentation - Google Patents
It is a kind of based on big data to the method and system of distributed photovoltaic client segmentation Download PDFInfo
- Publication number
- CN109598535A CN109598535A CN201811308003.6A CN201811308003A CN109598535A CN 109598535 A CN109598535 A CN 109598535A CN 201811308003 A CN201811308003 A CN 201811308003A CN 109598535 A CN109598535 A CN 109598535A
- Authority
- CN
- China
- Prior art keywords
- photovoltaic
- client
- index
- default
- photovoltaic client
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- Y04S50/00—Market activities related to the operation of systems integrating technologies related to power network operation or related to communication or information technologies
- Y04S50/14—Marketing, i.e. market research and analysis, surveying, promotions, advertising, buyer profiling, customer management or rewards
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of based on big data to the method for distributed photovoltaic client segmentation, division customers are carried out only according to region, affiliated industry to solve to analyze photovoltaic client in the prior art, the problem of accurate customers can not be grasped, this method includes: S1: by preset data acquisition mode, acquiring the preset data information of photovoltaic client；S2: by preset data Collator Mode, the default characteristic index value of photovoltaic client is obtained；S3: excavating the default characteristic index value of class software and acquisition in conjunction with preset data, and photovoltaic client is carried out Cluster Classification；S4: it according to the result and default performance indicator calculation method classified to photovoltaic Customer clustering, determines in Cluster Classification and presets high-quality class photovoltaic client.Using this method, top-tier customer can be filtered out, specific aim is promoted, and is improved marketing success rate and be may be implemented to use for the photovoltaic of different groups, enterprise, specifies corresponding service strategy.
Description
Technical field
The present invention relates to data analysis technique fields, more particularly to a kind of big data that is based on is to distributed photovoltaic client segmentation
Method and system.
Background technique
With the development of society, the energy is the important material base of survival and development of mankind, increasingly with global warming
Serious and fossil energy, increasingly in the case of exhaustion, renewable energy becomes most competitive and development in numerous energy
The energy of prospect.
In recent years, photovoltaic power generation application market in China's gradually expands, and photovoltaic generator capacity is every year with speed at double
Increase, under the background of photovoltaic power generation market persistently overheating, photovoltaic products manufacturing industry production capacity is also gradually expanded at present.Photovoltaic power generation
The market competition in field is also more and more fierce, therefore, in existing photovoltaic client, according to the data information of photovoltaic client,
To photovoltaic power generation, client is finely divided, and is then accurately marketed and is very important.
Utilities Electric Co. has the historical failure information of the photovoltaic client of accumulation magnanimity in the prior art, however at present to these
The processing of fault message is based only on surface analysis, such as is individually divided from region or affiliated industry, however these
Preliminary data processing can not specifically use these data informations, accumulate to form " data disaster " and " money instead with data
Source waste ".
Therefore it needs to design one kind intuitively, there is the targetedly data processing of high-quality photovoltaic client statistics and analysis side
Method, to solve the above problems.
Summary of the invention
To solve the above-mentioned problems, the present invention provides a kind of methods using cluster, in photovoltaic customer database
Data information carries out the method and system based on big data to distributed photovoltaic client segmentation of the preferred top-tier customer of analysis classification.
In order to achieve the above object, using following technical scheme:
A method of based on big data to distributed photovoltaic client segmentation, comprising steps of
S1: by preset data acquisition mode, the preset data information of photovoltaic client is acquired；
S2: by preset data Collator Mode, the default characteristic index value in photovoltaic client preset data information is obtained；
S3: excavating the default characteristic index value of class software and acquisition in conjunction with preset data, and photovoltaic client is carried out cluster point
Class；
S4: according to the result and default performance indicator calculation method classified to photovoltaic Customer clustering, Cluster Classification is determined
In preset high-quality class photovoltaic client.
Further, step S1 includes:
S11: receiving default acquisition keyword, in presetting database in retrieved；
S12: in the preset database, the corresponding photovoltaic customer information of each keyword is extracted；
S13: acquisition keyword photovoltaic customer information corresponding with the keyword is saved and is exported according to preset list.
Further, step S2 includes:
S21: in photovoltaic client's preset data information of acquisition, according to default daily load Index Formula, photovoltaic visitor is obtained
The photovoltaic electricity consumption daily load index at family；
S22: in photovoltaic client's preset data information of acquisition, according to default electricity index formula, photovoltaic client is obtained
Photovoltaic electricity service index；
S23: in photovoltaic client's preset data information of acquisition, according to default daily load factor Index Formula, photovoltaic is obtained
The photovoltaic daily load factor index of client.
Further, step S3 includes:
S31: the multiple index value combination preset datas of the photovoltaic client that will acquire excavate software, establish photovoltaic client segmentation mould
Type；
S32: being pre-set categories by photovoltaic client segmentation according to the photovoltaic Customer Classifying Model of foundation.
Further, step S4 includes:
S41: multiple index values of every a kind of photovoltaic client after photovoltaic client segmentation are determined；
S42: in conjunction with default performance indicator calculation method, high-quality class photovoltaic client after Cluster Classification is determined.
It is a kind of based on big data to the system of distributed photovoltaic client segmentation, comprising:
Data acquisition module, for acquiring the preset data information of photovoltaic client by preset data acquisition mode；
Characteristic module is obtained, for obtaining pre- in photovoltaic client preset data information by preset data Collator Mode
If characteristic index value；
Cluster Classification module, for combining preset data to excavate the default characteristic index value of class software and acquisition, by photovoltaic
Client carries out Cluster Classification；
Cluster Analysis module, for according to the result and default performance indicator calculating side classified to photovoltaic Customer clustering
Method determines in Cluster Classification and presets high-quality class photovoltaic client.
Further, data acquisition module includes:
Receive retrieval unit, for receiving default acquisition keyword, in presetting database in retrieved；
Information unit is extracted, according in the preset database, extracting the corresponding photovoltaic customer information of each keyword；
Data lead-out unit, for keyword photovoltaic customer information corresponding with the keyword will to be acquired according to preset list
It saves and exports.
Further, obtaining characteristic module includes:
Daily load index unit is obtained, for being born in photovoltaic client's preset data information of acquisition according to default day
Lotus Index Formula obtains the photovoltaic electricity consumption daily load index of photovoltaic client；
Electricity service index unit is obtained, in photovoltaic client's preset data information of acquisition, according to default electricity
Index Formula obtains the photovoltaic electricity service index of photovoltaic client；
Daily load factor index unit is obtained, for being born in photovoltaic client's preset data information of acquisition according to default day
Load rate Index Formula obtains the photovoltaic daily load factor index of photovoltaic client.
Further, Cluster Classification module includes:
Clustering Model unit, the multiple index value combination preset datas of photovoltaic client for will acquire are excavated software, are established
Photovoltaic Customer Classifying Model；
Photovoltaic client segmentation is pre-set categories for the photovoltaic Customer Classifying Model according to foundation by Cluster Classification unit.
Further, cluster analysis unit includes:
Index unit is determined, for determining multiple index values of every a kind of photovoltaic client after photovoltaic client segmentation；
It determines top-tier customer unit, for combining default performance indicator calculation method, determines high-quality class light after Cluster Classification
Lie prostrate client.
The invention has the benefit that
(1) by the feature extraction to photovoltaic client, carrying out Cluster Classification to photovoltaic client is pre-set categories, is established new
Client group can select corresponding marketing mode according to every class client group.
(2) installation and after sale for targetedly promoting distributed photovoltaic can be carried out, photovoltaic is improved with screening high-quality client
The marketing success rate of product.
(3) it can be directed to different groups, enterprise, targetedly service strategy is executed, improve the clothes after sale of photovoltaic products
Business accuracy rate, also improves the usage experience of photovoltaic client.
Detailed description of the invention
Fig. 1 is based on big data to the method flow diagram one of distributed photovoltaic client segmentation；
Fig. 2 is based on big data to the method flow diagram two of distributed photovoltaic client segmentation；
Fig. 3 is based on big data to the clustering disaggregated model figure of distributed photovoltaic client segmentation；
Fig. 4 is based on big data to Cluster Classification photovoltaic client's pie chart of distributed photovoltaic client segmentation；
Fig. 5 is based on big data to the Cluster Classification variable importance ordering chart of distributed photovoltaic client segmentation；
Fig. 6 is based on big data to the Cluster Classification index value list of distributed photovoltaic client segmentation；
Fig. 7 is based on big data to the system construction drawing one of distributed photovoltaic client segmentation；
Fig. 8 is based on big data to the system construction drawing two of distributed photovoltaic client segmentation.
Specific embodiment
Following is a specific embodiment of the present invention in conjunction with the accompanying drawings, technical scheme of the present invention will be further described,
However, the present invention is not limited to these examples.
Embodiment one
A kind of method based on big data to distributed photovoltaic client segmentation is present embodiments provided, such as Fig. 1 to Fig. 6 institute
Show, this method includes:
S1: by preset data acquisition mode, the preset data information of photovoltaic client is acquired；
S2: by preset data Collator Mode, the default characteristic index value in photovoltaic client preset data information is obtained；
S3: excavating the default characteristic index value of class software and acquisition in conjunction with preset data, and photovoltaic client is carried out cluster point
Class；
S4: according to the result and default performance indicator calculation method classified to photovoltaic Customer clustering, Cluster Classification is determined
In preset high-quality class photovoltaic client.
It is further preferred that it is provided in this embodiment based on big data to the method for distributed photovoltaic client segmentation, mainly
For firstly, collection to photovoltaic customer data, followed by the data of the photovoltaic client of collection are arranged, including to photovoltaic visitor
The acquisition of characteristic index value is preset at family, presets characteristic index value then in conjunction with the photovoltaic client of acquisition and preset data excavation class is soft
Part carries out photovoltaic customer data information to carry out Cluster Classification according to characteristic index value, then for each after Cluster Classification
Class photovoltaic customer information carries out characteristic index value and default performance indicator calculation method, calculates high-quality photovoltaic client classification.
It is SPSS Modeler data mining software that preset data, which excavates software, in the present embodiment, by the photovoltaic client of acquisition
Data information and photovoltaic client characteristics index value combine in input SPSS Modeler software, it will to photovoltaic, client gathers
Class classification.
Further, step S1 includes:
S11: receiving default acquisition keyword, in presetting database in retrieved；
S12: in the preset database, the corresponding photovoltaic customer information of each keyword is extracted；
S13: acquisition keyword photovoltaic customer information corresponding with the keyword is saved and is exported according to preset list.
The wherein acquisition of data is the method provided in this embodiment based on big data to distributed photovoltaic client segmentation
Basis, selected photovoltaic customer data information, it will determine the Cluster Classification of photovoltaic customer data information.
The presetting database wherein provided in the present embodiment includes that default marketing system database and default power information are adopted
Collecting system database, wherein marketing system database and default power information acquisition system database, can completely obtain photovoltaic
The data information of user, wherein receiving default acquisition keyword, it is therefore an objective to by default marketing system database and default telecommunications
Photovoltaic customer data information in breath acquisition system database is integrated, and is then divided according to default acquisition keyword
Class.
It is further preferred that the keyword provided in the present embodiment are as follows: power supply unit (includes districts and cities, district grade, power supply
Institute), power generation family number, name in an account book, electricity consumption address, grid entry point voltage class, power generation capacity, generation mode, generated energy dissolve mode, machine
Group information, generating equipment title, generating equipment type, device model, daily generation, moon generated energy, annual electricity generating capacity etc..Wherein unite
It is as shown in the table to count inventory:
, can be by the various information in different classes of photovoltaic customer information using method of data capture, including be lower than, send out
Electric mode, power generation type generating equipment, day, the moon, annual electricity generating capacity, electricity volume moon etc. information, photovoltaic customer data can be believed
Breath is targetedly analyzed and is counted.
Further, step S2 includes:
S21: in photovoltaic client's preset data information of acquisition, according to default daily load Index Formula, photovoltaic visitor is obtained
The photovoltaic electricity consumption daily load index at family；
S22: in photovoltaic client's preset data information of acquisition, according to default electricity index formula, photovoltaic client is obtained
Photovoltaic electricity service index；
S23: in photovoltaic client's preset data information of acquisition, according to default daily load factor Index Formula, photovoltaic is obtained
The photovoltaic daily load factor index of client.
Since the data type in photovoltaic customer data information has very much, wherein therefore to believe the data in photovoltaic client
Breath carries out characteristic index and is obtained, the characteristic index data packets in photovoltaic customer data information provided in the present embodiment
It includes: daily load index field, electricity service index field and daily load factor index field.
Wherein obtain daily load index field, in order to the voltage of preset interval time is obtained using data, wherein
It is the utilization voltage information in the photovoltaic customer data information that export saves to each photovoltaic client, analysis is learnt, photovoltaic visitor
Family in photovoltaic power generation use process, one, electricity consumption daytime be higher than night, photovoltaic power generation can utilize directly, be not necessarily to energy storage or online；
Two, it with electrical stability height, if wherein stability is higher, fluctuates the smaller the better.Therefore enterprise will be extracted every 15 minutes
Voltage uses data, then indicates the visitor using the average voltage that the voltage got in one day at interval of 15 minutes uses
The service condition of family voltage indicates fluctuation situation with standard deviation difference, integrates these two aspects, it is further preferred that passing through:
Daily load Index Formula=(average value of remaining time of 8 points to ten six points of average value -)/daily every 15 minutes
The standard deviation of the voltage of clock acquisition；
Thus formula has obtained the daily load index field of client.Wherein daily load index expression photovoltaic client photovoltaic on daytime
The usage amount of power generation illustrates that 8 points to ten six points of electricity uses and is greater than other times, illumination if daily load index is greater than 1
Time usage amount is big.
Obtain electricity service index field
The purpose of acquisition electricity service index is whether the electricity consumption of acquisition photovoltaic client is stable, is wherein mentioned in the present embodiment
The method of confession are as follows: from export client's in January, 2017 to every month between in April, 2018 in the photovoltaic customer data information with acquisition
Electricity consumption can judge that it is whether stable that photovoltaic client's electricity uses by standard deviation that electricity uses, but due to each light
It is inconsistent to lie prostrate the power generation of client, electricity consumption scale, also needs the standardization by variance, and from obtain electricity index=monthly average value/
Standard deviation, the index are to measure user power utilization stability indicator.
Obtain daily load factor index field
The purpose of obtaining daily load factor index is to judge its power benefit, therefore lead from the photovoltaic customer data information of acquisition
The electricity consumption and corresponding working capacity of photovoltaic client in January, 2017 to every month between in April, 2018 out, from power supply company at
This angle considers that when company's electricity consumption and traffic capacity ratio are bigger, then for power supply company, the benefit of photovoltaic power generation is most
It is good, therefore provided in the present embodiment: daily load factor=average monthly electricity consumption/(working capacity * 10*30).
The extraction of the photovoltaic client characteristics index provided in the present embodiment can be realized and determine photovoltaic customer data information
Property analysis, targetedly to photovoltaic client carry out data analysis.It further, is the Cluster Classification of photovoltaic customer data information
Carry out characteristic index preparation.
Further, step S3 includes:
S31: the multiple index value combination preset datas of the photovoltaic client that will acquire excavate software, establish photovoltaic client segmentation mould
Type；
S32: being pre-set categories by photovoltaic client segmentation according to the photovoltaic Customer Classifying Model of foundation.
SPSS Modeler data mining software is utilized in the present embodiment, photovoltaic Customer Classifying Model is established, such as Fig. 3 institute
Show, in the present embodiment, photovoltaic client has been divided into 4 classes, classification results, as shown in Figure 4；It wherein can also be to the feature of acquisition
Index carries out variable importance prediction, as shown in figure 5, wherein determining that the most important factor of photovoltaic Customer clustering refers to for daily load
Mark, followed by load factor, are finally electricity index.
Further, step S4 includes:
S41: multiple index values of every a kind of photovoltaic client after photovoltaic client segmentation are determined；
S42: in conjunction with default performance indicator calculation method, high-quality class photovoltaic client after Cluster Classification is determined.
Wherein the characteristic index in every class photovoltaic client has display, as shown in Figure 6:
Wherein load factor is 0.29 in cluster 1, daily load index is 1.18, electricity index 2.98；
Wherein load factor is 0.92 in cluster 2, daily load index is 1.09, electricity index 3.86；
Wherein load factor is 0.83 in cluster 3, daily load index is -0.23, electricity index 3.47；
Wherein load factor is 0.27 in cluster 4, daily load index is -0.28, electricity index 2.75；
Wherein load factor, electricity index and daily load are that Utilities Electric Co. uses brought performance indicator after photovoltaic power generation,
So being the bigger the better；Therefore by judgement, wherein cluster 2 can be used as main marketing target, it, will because its load factor is 0.92
Closely reach 1, illustrates that the transformer of installation substantially completely uses；Daily load index is 1.09, illustrates that user's electricity service condition is
8 points of morning is far longer than remaining time to 16 points of electricity use in afternoon, and light application time is big using electricity, is adapted to fit photovoltaic hair
Electricity；Electricity index are 3.86, illustrate that electricity stability in use is high, fluctuate small.It see the table below, cluster the poly- of the photovoltaic client of 2 classifications
Class list:
It can thus be seen that the photovoltaic client of 2 classifications of cluster also will be to bring the enterprise of best benefit to company, therefore select
High-quality photovoltaic customer class is selected out, the photovoltaic client for including in 2 is exactly clustered, therefore can choose the photovoltaic client in cluster 2 and make
For main marketing target.Further, wherein clustering the cluster list of the photovoltaic client of 4 classifications:
It can thus be seen that cluster 4 is the client for being least adapted to fit photovoltaic.
In conclusion a kind of method based on big data to distributed photovoltaic client segmentation provided in the present embodiment, energy
Enough extractions that accurate feature is carried out to photovoltaic client, so as to pass through the extraction and mining data class in the prior art of feature
The Cluster Classification of software further can find a kind of photovoltaic client for being most suitable for marketing, can adequately utilize existing marketing
The data information of photovoltaic client in system and electricity consumption data acquisition system realizes the abundant benefit to photovoltaic customer data information
With.
It is provided in this embodiment based on big data to the method for distributed photovoltaic client segmentation, can pass through and excavate photovoltaic visitor
Between family Different Individual industry and with electrical characteristics rule, to photovoltaic client carry out clustering, obtain high-quality photovoltaic customer class, reach
To the purpose of precision marketing.
Embodiment two
A kind of system based on big data to distributed photovoltaic client segmentation is present embodiments provided, such as Fig. 7 to Fig. 8 institute
Show, this system includes:
Data acquisition module, for acquiring the preset data information of photovoltaic client by preset data acquisition mode；
Characteristic module is obtained, for obtaining pre- in photovoltaic client preset data information by preset data Collator Mode
If characteristic index value；
Cluster Classification module, for combining preset data to excavate the default characteristic index value of class software and acquisition, by photovoltaic
Client carries out Cluster Classification；
Cluster Analysis module, for according to the result and default performance indicator calculating side classified to photovoltaic Customer clustering
Method determines in Cluster Classification and presets high-quality class photovoltaic client.
Wherein data acquisition module, be retrieved and acquired in the preset database using default gopher, wherein
Presetting database includes default marketing system database and default power information acquisition system database.
Further, data acquisition module includes:
Receive retrieval unit, for receiving default acquisition keyword, in presetting database in retrieved；
Information unit is extracted, according in the preset database, extracting the corresponding photovoltaic customer information of each keyword；
Data lead-out unit, for keyword photovoltaic customer information corresponding with the keyword will to be acquired according to preset list
It saves and exports.
Further, obtaining characteristic module includes:
Daily load index unit is obtained, for being born in photovoltaic client's preset data information of acquisition according to default day
Lotus Index Formula obtains the photovoltaic electricity consumption daily load index of photovoltaic client；
Electricity service index unit is obtained, in photovoltaic client's preset data information of acquisition, according to default electricity
Index Formula obtains the photovoltaic electricity service index of photovoltaic client；
Daily load factor index unit is obtained, for being born in photovoltaic client's preset data information of acquisition according to default day
Load rate Index Formula obtains the photovoltaic daily load factor index of photovoltaic client.
Further, Cluster Classification module includes:
Clustering Model unit, the multiple index value combination preset datas of photovoltaic client for will acquire are excavated software, are established
Photovoltaic Customer Classifying Model；
Photovoltaic client segmentation is pre-set categories for the photovoltaic Customer Classifying Model according to foundation by Cluster Classification unit.
Further, cluster analysis unit includes:
Index unit is determined, for determining multiple index values of every a kind of photovoltaic client after photovoltaic client segmentation；
It determines top-tier customer unit, for combining default performance indicator calculation method, determines high-quality class light after Cluster Classification
Lie prostrate client.
Using it is provided in this embodiment based on big data to the system of distributed photovoltaic client segmentation, can be by photovoltaic
The feature extraction of client, carrying out Cluster Classification to photovoltaic client is pre-set categories, establishes new client group, can be according to every class
Client group selects corresponding marketing mode.And it can carry out targetedly promoting distributed photovoltaic with screening high-quality client
Installation improves the marketing success rate of photovoltaic products with after sale.
Further, it can be directed to different groups, enterprise, targetedly service strategy is executed, improve photovoltaic products
After-sale service accuracy rate also improves the usage experience of photovoltaic client.
Specific embodiment described herein is only an example for the spirit of the invention.The neck of technology belonging to the present invention
The technical staff in domain can make various modifications or additions to the described embodiments or replace by a similar method
In generation, however, it does not deviate from the spirit of the invention or beyond the scope of the appended claims.
Claims (10)
1. it is a kind of based on big data to the method for distributed photovoltaic client segmentation, which is characterized in that comprising steps of
S1: by preset data acquisition mode, the preset data information of photovoltaic client is acquired；
S2: by preset data Collator Mode, the default characteristic index value in photovoltaic client preset data information is obtained；
S3: excavating the default characteristic index value of class software and acquisition in conjunction with preset data, and photovoltaic client is carried out Cluster Classification；
S4: it according to the result and default performance indicator calculation method classified to photovoltaic Customer clustering, determines in Cluster Classification
Preset high-quality class photovoltaic client.
2. it is according to claim 1 it is a kind of based on big data to the method for distributed photovoltaic client segmentation, which is characterized in that
Step S1 includes:
S11: receiving default acquisition keyword, in presetting database in retrieved；
S12: in the preset database, the corresponding photovoltaic customer information of each keyword is extracted；
S13: acquisition keyword photovoltaic customer information corresponding with the keyword is saved and is exported according to preset list.
3. it is according to claim 1 it is a kind of based on big data to the method for distributed photovoltaic client segmentation, which is characterized in that
Step S2 includes:
S21: in photovoltaic client's preset data information of acquisition, according to default daily load Index Formula, obtain photovoltaic client's
Photovoltaic electricity consumption daily load index；
S22: in photovoltaic client's preset data information of acquisition, according to default electricity index formula, the light of photovoltaic client is obtained
Lie prostrate electricity service index；
S23: in photovoltaic client's preset data information of acquisition, according to default daily load factor Index Formula, photovoltaic client is obtained
Photovoltaic daily load factor index.
4. it is according to claim 1 it is a kind of based on big data to the method for distributed photovoltaic client segmentation, which is characterized in that
Step S3 includes:
S31: the multiple index value combination preset datas of the photovoltaic client that will acquire excavate software, establish photovoltaic Customer Classifying Model；
S32: being pre-set categories by photovoltaic client segmentation according to the photovoltaic Customer Classifying Model of foundation.
5. it is according to claim 1 it is a kind of based on big data to the method for distributed photovoltaic client segmentation, which is characterized in that
Step S4 includes:
S41: multiple index values of every a kind of photovoltaic client after photovoltaic client segmentation are determined；
S42: in conjunction with default performance indicator calculation method, high-quality class photovoltaic client after Cluster Classification is determined.
6. it is a kind of based on big data to the system of distributed photovoltaic client segmentation characterized by comprising
Data acquisition module, for acquiring the preset data information of photovoltaic client by preset data acquisition mode；
Characteristic module is obtained, for obtaining the default spy in photovoltaic client preset data information by preset data Collator Mode
Levy index value；
Cluster Classification module, for combining preset data to excavate the default characteristic index value of class software and acquisition, by photovoltaic client
Carry out Cluster Classification；
Cluster Analysis module, for basis to the result and default performance indicator calculation method of the classification of photovoltaic Customer clustering, really
Determine to preset high-quality class photovoltaic client in Cluster Classification.
7. it is according to claim 6 it is a kind of based on big data to the system of distributed photovoltaic client segmentation, which is characterized in that
Data acquisition module includes:
Receive retrieval unit, for receiving default acquisition keyword, in presetting database in retrieved；
Information unit is extracted, according in the preset database, extracting the corresponding photovoltaic customer information of each keyword；
Data lead-out unit is saved for that will acquire keyword photovoltaic customer information corresponding with the keyword according to preset list
And it exports.
8. it is according to claim 6 it is a kind of based on big data to the system of distributed photovoltaic client segmentation, which is characterized in that
Obtaining characteristic module includes:
Daily load index unit is obtained, for referring in photovoltaic client's preset data information of acquisition according to default daily load
Formula is marked, the photovoltaic electricity consumption daily load index of photovoltaic client is obtained；
Electricity service index unit is obtained, in photovoltaic client's preset data information of acquisition, according to default electricity index
Formula obtains the photovoltaic electricity service index of photovoltaic client；
Daily load factor index unit is obtained, in photovoltaic client's preset data information of acquisition, according to default daily load factor
Index Formula obtains the photovoltaic daily load factor index of photovoltaic client.
9. it is according to claim 6 it is a kind of based on big data to the system of distributed photovoltaic client segmentation, which is characterized in that
Cluster Classification module includes:
Clustering Model unit, the multiple index value combination preset datas of photovoltaic client for will acquire excavate software, establish photovoltaic
Customer Classifying Model；
Photovoltaic client segmentation is pre-set categories for the photovoltaic Customer Classifying Model according to foundation by Cluster Classification unit.
10. it is according to claim 6 it is a kind of based on big data to the system of distributed photovoltaic client segmentation, feature exists
In cluster analysis unit includes:
Index unit is determined, for determining multiple index values of every a kind of photovoltaic client after photovoltaic client segmentation；
It determines top-tier customer unit, for combining default performance indicator calculation method, determines high-quality class photovoltaic visitor after Cluster Classification
Family.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811308003.6A CN109598535A (en) | 2018-11-05 | 2018-11-05 | It is a kind of based on big data to the method and system of distributed photovoltaic client segmentation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811308003.6A CN109598535A (en) | 2018-11-05 | 2018-11-05 | It is a kind of based on big data to the method and system of distributed photovoltaic client segmentation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109598535A true CN109598535A (en) | 2019-04-09 |
Family
ID=65957501
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811308003.6A Pending CN109598535A (en) | 2018-11-05 | 2018-11-05 | It is a kind of based on big data to the method and system of distributed photovoltaic client segmentation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109598535A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110163279A (en) * | 2019-05-17 | 2019-08-23 | 国网天津市电力公司 | A kind of energy client segmentation method, apparatus and calculate equipment |
| CN112950359A (en) * | 2021-03-30 | 2021-06-11 | 建信金融科技有限责任公司 | User identification method and device |
| CN114971700A (en) * | 2022-05-16 | 2022-08-30 | 河南鑫安利职业健康科技有限公司 | Big data based new-in high-quality client capturing system and summarizing method thereof |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102999791A (en) * | 2012-11-23 | 2013-03-27 | 广东电网公司电力科学研究院 | Power load forecasting method based on customer segmentation in power industry |
| CN104268804A (en) * | 2014-10-29 | 2015-01-07 | 国家电网公司 | High-quality electric power customer data mining method based on hierarchical data envelopment analysis |
| CN107292513A (en) * | 2017-06-21 | 2017-10-24 | 国网辽宁省电力有限公司 | A kind of method that power customer management is realized based on svm classifier algorithm |
| CN108205761A (en) * | 2016-12-16 | 2018-06-26 | 国家电网公司 | A kind of multi-layer power sales data analysis monitors system |
-
2018
- 2018-11-05 CN CN201811308003.6A patent/CN109598535A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102999791A (en) * | 2012-11-23 | 2013-03-27 | 广东电网公司电力科学研究院 | Power load forecasting method based on customer segmentation in power industry |
| CN104268804A (en) * | 2014-10-29 | 2015-01-07 | 国家电网公司 | High-quality electric power customer data mining method based on hierarchical data envelopment analysis |
| CN108205761A (en) * | 2016-12-16 | 2018-06-26 | 国家电网公司 | A kind of multi-layer power sales data analysis monitors system |
| CN107292513A (en) * | 2017-06-21 | 2017-10-24 | 国网辽宁省电力有限公司 | A kind of method that power customer management is realized based on svm classifier algorithm |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110163279A (en) * | 2019-05-17 | 2019-08-23 | 国网天津市电力公司 | A kind of energy client segmentation method, apparatus and calculate equipment |
| CN112950359A (en) * | 2021-03-30 | 2021-06-11 | 建信金融科技有限责任公司 | User identification method and device |
| CN114971700A (en) * | 2022-05-16 | 2022-08-30 | 河南鑫安利职业健康科技有限公司 | Big data based new-in high-quality client capturing system and summarizing method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106154209B (en) | Electrical energy meter fault prediction technique based on decision Tree algorithms | |
| CN109325545A (en) | Low-voltage network topological structure method of calibration, device, equipment and storage medium | |
| Nizar et al. | Load profiling and data mining techniques in electricity deregulated market | |
| CN109598535A (en) | It is a kind of based on big data to the method and system of distributed photovoltaic client segmentation | |
| US20160018835A1 (en) | System and method for virtual energy assessment of facilities | |
| CN108776939A (en) | The analysis method and system of user power utilization behavior | |
| CN108022043A (en) | Abnormal electricity consumption behavior identification method and device and central server | |
| CN107133652A (en) | Electricity customers Valuation Method and system based on K means clustering algorithms | |
| EP3968040A1 (en) | Abnormal electricity use recognition method and device, and computer readable storage medium | |
| CN107578277B (en) | Rental house client positioning method for electric power marketing | |
| CN102567412A (en) | Method for processing computer-assisted network load analysis information | |
| CN106384015B (en) | A kind of distributed photovoltaic system energy efficiency Pre-Evaluation method based on energy consumption data acquisition | |
| Williams et al. | Electricity consumption and load profile segmentation analysis for rural micro grid customers in Tanzania | |
| CN113469486A (en) | Line negative loss and high loss analysis method | |
| CN107945050A (en) | Method and device for identifying and identifying type of electricity customer and central server | |
| Cardell-Oliver | Discovering water use activities for smart metering | |
| CN111461521A (en) | Residential housing vacancy rate analysis method based on electric power big data | |
| CN105809573A (en) | Big data analysis based load nature authentication method | |
| Prakash et al. | A comprehensive analytical exploration and customer behaviour analysis of smart home energy consumption data with a practical case study | |
| CN111428745A (en) | Clustering analysis-based low-voltage user electricity utilization feature extraction method | |
| CN103140763A (en) | Systems, methods, and devices for analyzing utility usage with load duration curves | |
| Selvam et al. | Fuzzy based clustering of smart meter data using real power and THD patterns | |
| CN112988717B (en) | Design and construction method of resident intelligent energy consumption service specimen library | |
| KR20160074325A (en) | Electricity Demand Index (EDI) Forecasting System with respect to Weather Condition Change | |
| Ferreira et al. | A data-mining-based methodology for transmission expansion planning |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190409 |
|
| RJ01 | Rejection of invention patent application after publication |