CN106447206A - Power utilization analysis method based on acquisition data of power utilization information - Google Patents
Power utilization analysis method based on acquisition data of power utilization information Download PDFInfo
- Publication number
- CN106447206A CN106447206A CN201610880295.5A CN201610880295A CN106447206A CN 106447206 A CN106447206 A CN 106447206A CN 201610880295 A CN201610880295 A CN 201610880295A CN 106447206 A CN106447206 A CN 106447206A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- load
- industry
- curve
- 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
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a power utilization analysis method based on acquisition data of power utilization information, and relates to a power utilization analysis method. At present, power utilization is difficult to be analyzed and monitored, and the accuracy is low. The power utilization analysis method comprises the steps of 1) acquiring daily time-sharing load statistic data details of users; 2) grouping the detail data according to users and industries; 3) performing normalization processing; 4) performing k-means clustering calculation to acquire characteristic load curves of each industry and each user; 5) adjusting the number of the generated curves, acquiring obviously characterized curves, labeling the acquired curves, and corresponding each industry and each user to the respective characteristic load curves; and 6) extracting characteristic users according to the characteristic load curves, and performing comparative analysis on the characteristic load curves. The technical scheme provided by the invention improves the accuracy of a power utilization information acquisition system, and provides basic guarantee for supporting execution of tiered pricing for electricity, reinforcing lean management, improving the high-quality service level, extending the power market and innovating the transaction platform.
Description
Technical field
The present invention relates to a kind of electrical energy consumption analysis method, the especially electrical energy consumption analysis method based on power information gathered data.
Background technology
Power information acquisition system construction is pushed forward comprehensively from 2010.By in July, 2014,27 units of state's net are complete
Portion has carried out power information acquisition system construction, and unified user realizes collection and covers 2.3 hundred million families, and collection coverage rate reaches
66.98%, the electricity of collection accounts for total electricity sales amount ratio and reaches 93.49%.Power information acquisition system is by system main website, transmission letter
Road, acquisition terminal and intelligent electric meter composition.
System main website be responsible for whole system power information collection, storage, analysis, process and apply, by communication subsystem,
Database, service application, Application of Interface etc. form.Most of net provincial company adopts the deployment way construction of provincial concentration.
Transmission channel is divided into local between telecommunication channel between system main website and terminal, terminal and intelligent electric meter
Communication channel.In current firm-wide acquisition system telecommunication channel mainly adopt GPRS/CDMA wireless public network system,
230MHz wireless private network channel, phone PSTN, fiber optic communication channel etc..Local communi-cation channel mainly adopts RS485, low-voltage power
Line carrier wave（Arrowband, broadband）, micropower is wireless etc..Power user power consumption information acquisition system is the power information to power consumer
Be acquired, process and monitor in real time system, realize power information automatic data collection, metering exception monitoring, the quality of power supply prison
Survey, electrical energy consumption analysis and the function such as management, relevant information issue, distributed energy monitoring, information exchange of intelligent power equipment.
But due to becoming more meticulous, lean management require, these real time datas are all that discrete type information, accuracy be not high, and
And there is difference of injection time in the information of separate sources.Analysis, monitoring be difficult and accuracy is low it is difficult to basis as decision-making.
Content of the invention
The technical problem to be solved in the present invention and the technical assignment proposing are prior art to be improved and is improved,
Electrical energy consumption analysis method based on power information gathered data is provided, facilitates analysis monitoring purpose to reach.For this reason, the present invention takes
Technical scheme below.
Electrical energy consumption analysis method based on power information gathered data is it is characterised in that comprise the following steps：
1）Obtain the daily timesharing load statistics of user detailed；
2）Detailed data is grouped by user, industry respectively, is obtained customer charge statistics and industry load statistical number
According to；
3）Customer charge statistics and industry load statistics are normalized；Each index is made to be in same quantity
Level, eliminates the dimension impact between index；
4）K-means cluster calculation is carried out to the data of normalized, obtains the feature load of each industry and each user
Curve；
5）The curve quantity that adjustment generates, obtains each and characterizes obvious curve being labeled, simultaneously by industry-by-industry and
Each user is corresponding with respective feature load curve；
6）According to feature load curve, extraction feature user, the feature load of the feature load curve to user and corresponding industry
Curve is analyzed to carry out problem identification and/aid decision.
The technical program be based on big data technological achievement, in power domain pass through apply big data relational storage technique,
Computing technique lifts power information acquisition system, for supporting step price execution, strengthens lean management, improves good service water
Flat, extend electricity market, innovation transaction platform provides basic guarantee.
As improving further and supplementing to technique scheme, present invention additionally comprises following additional technical feature.
In step 6）In, similarity meter is carried out to the feature load curve and the feature load curve of corresponding industry of user
Calculate, when the feature load curve similarity of the industry that feature load curve and its are located of this user is less than setting value, continue to look into
Ask every daily power consumption situation of this user and every daily load peak valley, be inferred to this user and whether there is load unusual fluctuation, remind in time
User adjusts power program.
In step 6）In, Similarity Measure is cosine similarity algorithm.
In step 1）In, 24 points of statistical number of load of all users are obtained by accessing power information acquisition system database
According to this and user profile table data genaration itemized bill, including User Profile information table and load data detail list, extracted
Field information includes：Power supply unit, family number, name in an account book, user's classification, SIC code, be subject to capacitance, 0-23 point load.
After obtaining itemized bill, the itemized bill obtaining is screened and is pre-processed：
Cleaning shortage of data, data redundancy, inaccurate, the nonstandard user data of data, wherein each field any data disappearance
For shortage of data, when districts and cities' unit, district unit, power supply station's unit, family number, name in an account book, user's classification, SIC code, it is subject to electric capacity
Amount or 0-23 point load data think shortage of data for space-time；Detailed entry repeats as data redundancy, when such as districts and cities' unit,
District unit, power supply station's unit, family number, name in an account book, user's classification, SIC code, be subject to capacitance, the data of 0-23 point load data
Shortage of data is thought during repetition；Business datum occur obvious common-sense mistake be data inaccurate, when power supply unit, family number,
Think when name in an account book is not inconsistent with general knowledge that data is inaccurate；Each field any data form lack of standardization for lack of standardization, when by capacitance, 0-
23 point load data, data time form think lack of standardization when lack of standardization；
After cleaning finishes, merge User Profile information table and load data detail list by family number, form user profile load data
Table, using the data basis analyzing and processing as postorder.
In step 3）In, when being normalized, linear transformation to initial data, end value is mapped to [0-
1] between.Expression formula is as follows：Y=(x-MinValue)/(MaxValue-MinValue), wherein：X, y respectively change forward and backward
Value, MaxValue, MinValue are respectively the maximum of sample and minimum of a value.
Beneficial effect：
1st, pass through the foundation of customer charge feature database, the electricity consumption situation to all users accomplished carries out historical trending analysis, more
Plus accurately position possible stealing user.Effectively lift stealing or the accurate investigation of promise breaking electricity consumption behavior, reduce power supply enterprise
Loss.
2nd, a set of suggestion of the optimization electricity consumption for this user can be calculated according to the load characteristic of user and its industry
Scheme, and carry out the accurate push of scheme.Moved using householder and select saving, economic power mode, progressively excavate to active and " move
Peak load " benefit direction changes.With price signal for guiding, change to the person of being actively engaged in from passive customer identification.
3rd, the technical program can be guided and calculate and used by the load characteristic of the sector to the customer charge in the mutually same industry
The electricity consumption trend at family, provides another kind to have the basic data of reference value for shot and long term load prediction.For reasonable arrangement electrical network
Power supply, ensures that user power utilization reliability and security provides certain data supporting.
4th, customers are finely divided, help electric power enterprise more precisely to grasp the business of Electricity customers differentiated service
Demand, assists to provide correspond to actual needs to take the initiative in offering a hand, and final acquirement lifts customer electricity experience satisfaction and reduce electric power
The effect of enterprises service cost.
Brief description
Fig. 1 is flow chart of the present invention.
Fig. 2 is customer charge indicatrix.
Fig. 3 is industry load characteristic curve.
Fig. 4 is user's industry correlation curve.
Specific embodiment
Below in conjunction with Figure of description, technical scheme is described in further detail.
As shown in figure 1, the present invention comprises the following steps：
1）Obtain the daily timesharing load statistics of user detailed；
2）Detailed data is grouped by user, industry respectively, is obtained customer charge statistics and industry load statistical number
According to；
3）Customer charge statistics and industry load statistics are normalized；Each index is made to be in same quantity
Level, eliminates the dimension impact between index；
4）K-means cluster calculation is carried out to the data of normalized, obtains the feature load of each industry and each user
Curve；
5）The curve quantity that adjustment generates, obtains each and characterizes obvious curve being labeled, simultaneously by industry-by-industry and
Each user is corresponding with respective feature load curve；
6）According to feature load curve, extraction feature user, the feature load of the feature load curve to user and corresponding industry
Curve is analyzed to carry out problem identification and/aid decision.
Above above-mentioned steps are illustrated：
First, specific algorithm
The load data obtaining from power information acquisition system is analyzed, following algorithm is met by utilization and carries out data
Process and calculate.
（1）Algorithm one：Data normalization, for step 3）.
【Arthmetic statement】It is an element task of data mining that data normalization is processed, and different evaluation index often has
Different dimensions and dimensional unit, such situation influences whether the result of data analysis, in order to eliminate the dimension between index
Impact, needs to carry out data normalization process, to solve the comparativity between data target.Initial data is through data normalization
After process, each index is in the same order of magnitude, is appropriate to Comprehensive Correlation evaluation.
【Computing formula】Min-max standardization be the linear transformation to initial data, make end value be mapped to [0-1] it
Between.Expression formula is as follows：
y=(x-MinValue)/(MaxValue-MinValue)
Explanation：X, y respectively change forward and backward value, and MaxValue, MinValue are respectively maximum and the minimum of a value of sample.
（2）Algorithm two：K-means clustering algorithm, for step 4）.
【Arthmetic statement】K-means algorithm is the very typical clustering algorithm based on distance, using distance as similitude
Evaluation index, that is, think that the distance of two objects is nearer, its similarity is bigger.This algorithm thinks that cluster is by apart from close
Object composition, therefore using obtaining compact and independent cluster as final goal.
【Computing formula】
Wherein, k represents the number of cluster, x and u represents the data value of any two points, and si represents the distance of every bit and left point
Value
Handling process
（1）Arbitrarily select k object from n data object as initial cluster center；
（2）Average according to each clustering object（Center object）, calculate the distance of each object and these center object；And root
Again corresponding object is divided according to minimum range；
（3）Recalculate each（Change）The average of cluster（Center object）
（4）Circulation（2）Arrive（3）Till each cluster no longer changes
（3）Algorithm two：Cosine similarity algorithm, for step 6）The feature load curve of user and the feature load of corresponding industry
Curve is contrasted.
【Arthmetic statement】Cosine similarity algorithm is based on vectorial, and it utilizes the remaining of two vector angles in vector space
String value, as the size weighing two interindividual variations, focuses on difference on direction for two vectors, interior cosine value is got in [0,1]
Greatly, illustrate that two vector similarities are bigger.
【Computing formula】
Wherein, a and b represents the two values needing to be compared respectively
2nd, data and pretreatment, for step 1）.
（1）Data acquiring mode
Obtain power information acquisition system database-access rights, write respective queries sentence, access power information acquisition system
Database obtains 24 points of statistics of load of all users, and user profile table data, and the field information being extracted includes：
Power supply unit（Comprise districts and cities, district level, power supply station）, family number, name in an account book, user's classification, SIC code, by capacitance, 0 point bear
Lotus, 1 point load, 2 point loads, 3 point loads...23 point loads etc., itemized bill is derived and is formed《User Profile information table》With《Negative
Lotus data list》.
Tables of data 1：User Profile information table
Tables of data 2：Load data detail list
（2）Data cleansing and pretreatment
Extracted data is that business is detailed, according to following data cleansing rule, the not extracted data in the range of class statistic is entered
Row cleaning：
L cleaning rule one：Each field any data disappearance is defined as shortage of data.As districts and cities' unit, district unit, power supply
Institute's unit, family number, name in an account book, user's classification, SIC code, by capacitance, 0-23 point load data etc. be sky.
Cleaning rule two：Detailed entry repeats to be defined as data redundancy.As districts and cities' unit, district unit, power supply
Institute's unit, family number, name in an account book, user's classification, SIC code, be subject to the Data duplication such as capacitance, 0-23 point load data.
Cleaning rule three：Obvious common-sense mistake in business datum, that is, be defined as data inaccurate.As power supply unit
（Comprise districts and cities, district level, power supply station）, family number, name in an account book etc. be not inconsistent with general knowledge.
Cleaning rule four：Each field any data form is lack of standardization be defined as lack of standardization.As born by capacitance, 0-23 point
Lotus data, data time form are lack of standardization.
After cleaning finishes, merge by family number《User Profile information table》With《Load data detail list》, formed《User profile
Loading data sheet》The data basis excavated as this Perspective Analysis, this literary name section is as follows：
Table 3：User profile loading data sheet
【Data basis】《User profile loading data sheet》.
3rd, step 4）Characteristi c curve of formation.
（1）Show one：The indicatrix being clustered by user and industry respectively
After the normalization to user profile loading data sheet and cluster calculation, according to the number of clusters of input, show phase
Answer the load characteristic curve of quantity（See Fig. 1 Fig. 2）.
（2）Show two：User's industrial characteristic curve comparison
User characteristics curve belonging to certain user and its affiliated industrial characteristic curve are overlapped contrast show（See figure
4）.
4th, step 6）Compare the indicatrix of user and industry.
Table 3：The contrast of user's industry load curve deviates table
| Sequence number | Contrast object | Cosine value | A reference value |
| 1 | User's curve 1- industry curve 1 | 0.9622560503163505 | 0.95 |
| 2 | User's curve 2- industry curve 2 | 0.969670473957427 | 0.95 |
| 3 | User's curve 3- industry curve 3 | 0.9459665643298746 | 0.95 |
In upper table, cosine value, closer to 1, represents that two curve similarities are bigger
As can be seen from the above table, the power load pattern of this user and industry that it is located generally has very big area with power mode
Not.Continue to inquire about every daily power consumption situation of this user and every daily load peak valley, it can be inferred that this user whether there is stealing etc.
Load unusual fluctuation, timely prompting user's adjustment power program, and then ensure user power utilization, caused because ordered electric executes with minimizing
Electric quantity loss and user's loss.
Five. application mode
（1）Analytical cycle
Larger in view of load data amount of calculation ratio, need certain calculating time it is proposed that day degree is pressed at this visual angle carries out rolling point
Analysis.
（2）Analysis level
The level of this Perspective Analysis is three-level, is prefecture-level company, province respectively（Municipality directly under the Central Government）Company and Guo Wang general headquarters.
Prefecture-level company can carry out the user's industry load characteristics clustering analysis in our unit and the compass of competency of company of affiliated county, can
Review inquiry customer charge detailed data.
Save（City）Company can carry out statistics, analysis based on the whole province's data, can collect display, inquiry subordinate districts and cities analysis knot
Really.
General headquarters can collect display, penetrate all provinces of inquiry（Municipality directly under the Central Government）Cluster analysis data.
Shown in figure 1 above is the specific embodiment of the present invention based on the electrical energy consumption analysis method of power information gathered data,
Embody substantive distinguishing features of the present invention and progress, under the enlightenment of the present invention, it can have been entered according to actual use needs
The equivalent modifications of the aspects such as row shape, structure, all in the row of the protection domain of this programme.
Claims (6)
1. the electrical energy consumption analysis method based on power information gathered data is it is characterised in that comprise the following steps：
A) obtain the daily timesharing load statistics of user detailed；
B) detailed data is grouped by user, industry respectively, is obtained customer charge statistics and industry load statistical number
According to；
C) customer charge statistics and industry load statistics are normalized；Each index is made to be in same quantity
Level, eliminates the dimension impact between index；
D) k-means cluster calculation is carried out to the data of normalized, obtain the feature load of each industry and each user
Curve；
E) the curve quantity that adjustment generates, obtains each and characterizes obvious curve being labeled, simultaneously by industry-by-industry and
Each user is corresponding with respective feature load curve；
F) according to feature load curve, extraction feature user, the feature load of the feature load curve to user and corresponding industry
Curve is analyzed to carry out problem identification and/aid decision.
2. the electrical energy consumption analysis method based on power information gathered data according to claim 1 it is characterised in that：In step
6）In, Similarity Measure is carried out to the feature load curve and the feature load curve of corresponding industry of user, as the spy of this user
When levying the feature load curve similarity of load curve and industry that it is located and being less than setting value, continue to inquire about the often daily of this user
Charge condition and every daily load peak valley, are inferred to this user and whether there is load unusual fluctuation, remind user's adjustment power program in time.
3. the electrical energy consumption analysis method based on power information gathered data according to claim 2 it is characterised in that：In step
6）In, Similarity Measure is cosine similarity algorithm.
4. the electrical energy consumption analysis method based on power information gathered data according to claim 1 it is characterised in that：In step
1）In, 24 points of statistics of load and the files on each of customers of all users is obtained by accessing power information acquisition system database
Table data genaration itemized bill, including User Profile information table and load data detail list, the field information being extracted includes：For
Electric unit, family number, name in an account book, user's classification, SIC code, be subject to capacitance, 0-23 point load.
5. the electrical energy consumption analysis method based on power information gathered data according to claim 4 it is characterised in that：Obtain bright
After thin inventory, the itemized bill obtaining is screened and is pre-processed：Cleaning shortage of data, data redundancy, data are inaccurate, no
The user data of specification, wherein each field any data lacks as shortage of data, when districts and cities' unit, district unit, power supply station are single
Position, family number, name in an account book, user's classification, SIC code, thought shortage of data by capacitance or 0-23 point load data for space-time；Bright
Slice mesh repeats as data redundancy, when such as districts and cities' unit, district unit, power supply station's unit, family number, name in an account book, user's classification,
SIC code, by capacitance, the Data duplication of 0-23 point load data when think shortage of data；Business datum occurs significantly normal
The property known mistake is that data is inaccurate, thinks that data is inaccurate when power supply unit, family number, name in an account book and general knowledge are not inconsistent；Each field is appointed
One data form lack of standardization for lack of standardization, when being thought not when lack of standardization by capacitance, 0-23 point load data, data time form
Specification；
After cleaning finishes, merge User Profile information table and load data detail list by family number, form user profile load data
Table, using the data basis analyzing and processing as postorder.
6. the electrical energy consumption analysis method based on power information gathered data according to claim 1 it is characterised in that：In step
3）In, when being normalized, linear transformation to initial data, end value is mapped between [0-1].Expression formula is such as
Under：Y=(x-MinValue)/(MaxValue-MinValue), wherein：X, y respectively change forward and backward value, MaxValue,
MinValue is respectively maximum and the minimum of a value of sample.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610880295.5A CN106447206A (en) | 2016-10-09 | 2016-10-09 | Power utilization analysis method based on acquisition data of power utilization information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610880295.5A CN106447206A (en) | 2016-10-09 | 2016-10-09 | Power utilization analysis method based on acquisition data of power utilization information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106447206A true CN106447206A (en) | 2017-02-22 |
Family
ID=58172091
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610880295.5A Pending CN106447206A (en) | 2016-10-09 | 2016-10-09 | Power utilization analysis method based on acquisition data of power utilization information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106447206A (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709822A (en) * | 2017-03-14 | 2017-05-24 | 国家电网公司 | Industry power consumption data correlation mining method and device |
| CN108596416A (en) * | 2017-12-29 | 2018-09-28 | 中国南方电网有限责任公司电网技术研究中心 | Obtain the method and system of power load datum quantity |
| CN109117872A (en) * | 2018-07-24 | 2019-01-01 | 贵州电网有限责任公司信息中心 | A kind of user power utilization behavior analysis method based on automatic Optimal Clustering |
| CN109190916A (en) * | 2018-08-09 | 2019-01-11 | 国网浙江桐庐县供电有限公司 | Method of opposing electricity-stealing based on big data analysis |
| CN109614997A (en) * | 2018-11-29 | 2019-04-12 | 武汉大学 | A kind of stealing Risk Forecast Method and device based on deep learning |
| CN109767108A (en) * | 2018-12-31 | 2019-05-17 | 国网安徽省电力有限公司 | A kind of accurate analysis method of electric power dispatching system line status |
| CN109784606A (en) * | 2018-11-23 | 2019-05-21 | 国网江苏省电力有限公司电力科学研究院 | A kind of overdue methods of risk assessment of business electrical |
| CN109948909A (en) * | 2019-02-26 | 2019-06-28 | 国网山东省电力公司莒县供电公司 | A kind of electric network data capturing analysis method and system |
| CN110298056A (en) * | 2019-03-27 | 2019-10-01 | 国网浙江海盐县供电有限公司 | A kind of power distribution network contact efficiency assessment method |
| CN110334912A (en) * | 2019-06-10 | 2019-10-15 | 国网浙江省电力有限公司嘉兴供电公司 | A kind of distributed generation resource networking contact efficiency assessment method |
| CN110572813A (en) * | 2018-05-19 | 2019-12-13 | 北京融信数联科技有限公司 | mobile phone user behavior similarity analysis method based on mobile big data |
| CN110689185A (en) * | 2019-09-23 | 2020-01-14 | 国网青海省电力公司海西供电公司 | Power utilization processing method and device, storage medium and processor |
| CN110807012A (en) * | 2018-07-20 | 2020-02-18 | 国网山东省电力公司枣庄供电公司 | Big data supporting platform of all-round power supply station |
| CN111027741A (en) * | 2019-10-28 | 2020-04-17 | 国网天津市电力公司电力科学研究院 | Method for constructing space-time dimension-oriented generalized load model analysis library |
| CN111209595A (en) * | 2020-04-21 | 2020-05-29 | 国网四川省电力公司电力科学研究院 | Power utilization information matching and data processing method for pollution-related enterprises |
| CN111612228A (en) * | 2020-05-12 | 2020-09-01 | 国网河北省电力有限公司电力科学研究院 | User electricity consumption behavior analysis method based on electricity consumption information |
| CN111626543A (en) * | 2020-04-03 | 2020-09-04 | 国网浙江杭州市富阳区供电有限公司 | Method and device for processing power related data |
| CN111680074A (en) * | 2019-12-31 | 2020-09-18 | 国网浙江省电力有限公司 | Clustering algorithm-based electric power collection load leakage point feature mining method |
| CN111738364A (en) * | 2020-08-05 | 2020-10-02 | 国网江西省电力有限公司供电服务管理中心 | Electricity stealing detection method based on combination of user load and electricity consumption parameter |
| CN112258052A (en) * | 2020-10-26 | 2021-01-22 | 国网青海省电力公司海西供电公司 | Power load prediction method and device |
| CN112560934A (en) * | 2020-12-10 | 2021-03-26 | 国家电网有限公司 | Multi-scale power consumption behavior analysis method |
| US11847619B2 (en) | 2018-09-20 | 2023-12-19 | Siemens Ltd., China | System-state monitoring method and device and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140067327A1 (en) * | 2011-05-03 | 2014-03-06 | China Real-Time Technology Co., Ltd. | Similarity curve-based equipment fault early detection and operation optimization methodology and system |
| CN104933630A (en) * | 2015-05-21 | 2015-09-23 | 国家电网公司 | Load characteristic analysis method and system |
| CN105678314A (en) * | 2015-10-15 | 2016-06-15 | 东南大学 | Typical demand-side user screening method based on fuzzy C clustering |
-
2016
- 2016-10-09 CN CN201610880295.5A patent/CN106447206A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140067327A1 (en) * | 2011-05-03 | 2014-03-06 | China Real-Time Technology Co., Ltd. | Similarity curve-based equipment fault early detection and operation optimization methodology and system |
| CN104933630A (en) * | 2015-05-21 | 2015-09-23 | 国家电网公司 | Load characteristic analysis method and system |
| CN105678314A (en) * | 2015-10-15 | 2016-06-15 | 东南大学 | Typical demand-side user screening method based on fuzzy C clustering |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709822A (en) * | 2017-03-14 | 2017-05-24 | 国家电网公司 | Industry power consumption data correlation mining method and device |
| CN108596416A (en) * | 2017-12-29 | 2018-09-28 | 中国南方电网有限责任公司电网技术研究中心 | Obtain the method and system of power load datum quantity |
| CN110572813A (en) * | 2018-05-19 | 2019-12-13 | 北京融信数联科技有限公司 | mobile phone user behavior similarity analysis method based on mobile big data |
| CN110807012B (en) * | 2018-07-20 | 2023-06-09 | 国网山东省电力公司枣庄供电公司 | All-round power substation big data supporting platform |
| CN110807012A (en) * | 2018-07-20 | 2020-02-18 | 国网山东省电力公司枣庄供电公司 | Big data supporting platform of all-round power supply station |
| CN109117872A (en) * | 2018-07-24 | 2019-01-01 | 贵州电网有限责任公司信息中心 | A kind of user power utilization behavior analysis method based on automatic Optimal Clustering |
| CN109190916A (en) * | 2018-08-09 | 2019-01-11 | 国网浙江桐庐县供电有限公司 | Method of opposing electricity-stealing based on big data analysis |
| US11847619B2 (en) | 2018-09-20 | 2023-12-19 | Siemens Ltd., China | System-state monitoring method and device and storage medium |
| CN109784606A (en) * | 2018-11-23 | 2019-05-21 | 国网江苏省电力有限公司电力科学研究院 | A kind of overdue methods of risk assessment of business electrical |
| CN109614997A (en) * | 2018-11-29 | 2019-04-12 | 武汉大学 | A kind of stealing Risk Forecast Method and device based on deep learning |
| CN109767108A (en) * | 2018-12-31 | 2019-05-17 | 国网安徽省电力有限公司 | A kind of accurate analysis method of electric power dispatching system line status |
| CN109948909A (en) * | 2019-02-26 | 2019-06-28 | 国网山东省电力公司莒县供电公司 | A kind of electric network data capturing analysis method and system |
| CN110298056A (en) * | 2019-03-27 | 2019-10-01 | 国网浙江海盐县供电有限公司 | A kind of power distribution network contact efficiency assessment method |
| CN110334912A (en) * | 2019-06-10 | 2019-10-15 | 国网浙江省电力有限公司嘉兴供电公司 | A kind of distributed generation resource networking contact efficiency assessment method |
| CN110689185A (en) * | 2019-09-23 | 2020-01-14 | 国网青海省电力公司海西供电公司 | Power utilization processing method and device, storage medium and processor |
| CN111027741A (en) * | 2019-10-28 | 2020-04-17 | 国网天津市电力公司电力科学研究院 | Method for constructing space-time dimension-oriented generalized load model analysis library |
| CN111680074A (en) * | 2019-12-31 | 2020-09-18 | 国网浙江省电力有限公司 | Clustering algorithm-based electric power collection load leakage point feature mining method |
| CN111680074B (en) * | 2019-12-31 | 2023-07-04 | 国网浙江省电力有限公司 | Clustering algorithm-based power acquisition load leakage point feature mining method |
| CN111626543A (en) * | 2020-04-03 | 2020-09-04 | 国网浙江杭州市富阳区供电有限公司 | Method and device for processing power related data |
| CN111209595B (en) * | 2020-04-21 | 2020-08-11 | 国网四川省电力公司电力科学研究院 | Power utilization information matching and data processing method for pollution-related enterprises |
| CN111209595A (en) * | 2020-04-21 | 2020-05-29 | 国网四川省电力公司电力科学研究院 | Power utilization information matching and data processing method for pollution-related enterprises |
| CN111612228A (en) * | 2020-05-12 | 2020-09-01 | 国网河北省电力有限公司电力科学研究院 | User electricity consumption behavior analysis method based on electricity consumption information |
| CN111738364A (en) * | 2020-08-05 | 2020-10-02 | 国网江西省电力有限公司供电服务管理中心 | Electricity stealing detection method based on combination of user load and electricity consumption parameter |
| CN112258052A (en) * | 2020-10-26 | 2021-01-22 | 国网青海省电力公司海西供电公司 | Power load prediction method and device |
| CN112560934A (en) * | 2020-12-10 | 2021-03-26 | 国家电网有限公司 | Multi-scale power consumption behavior analysis method |
| CN112560934B (en) * | 2020-12-10 | 2024-03-01 | 国家电网有限公司 | Multi-scale power consumption behavior analysis method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106447206A (en) | Power utilization analysis method based on acquisition data of power utilization information | |
| US11043808B2 (en) | Method for identifying pattern of load cycle | |
| CN103714139B (en) | Parallel data mining method for identifying a mass of mobile client bases | |
| CN103135009B (en) | Electric appliance detection method and system based on user feedback information | |
| CN110223196A (en) | Analysis method of opposing electricity-stealing based on typical industry feature database and sample database of opposing electricity-stealing | |
| CN106485262A (en) | A kind of bus load Forecasting Methodology | |
| CN105117810A (en) | Residential electricity consumption mid-term load prediction method under multistep electricity price mechanism | |
| CN107392479A (en) | The power customer power failure susceptibility scorecard implementation of logic-based regression model | |
| CN107507038A (en) | A kind of electricity charge sensitive users analysis method based on stacking and bagging algorithms | |
| CN108280541A (en) | Customer service strategies formulating method, device based on random forest and decision tree | |
| CN108959424A (en) | A kind of operating method of the city electricity consumption map for power system load monitoring | |
| CN111080101A (en) | AHP-based multi-dimensional evaluation method for service efficiency of power supply channel | |
| CN101398919A (en) | Electric power requirement analytic system for utilizing mode analysis and method thereof | |
| CN107248086A (en) | Advertisement putting aided analysis method based on user power utilization behavioural analysis | |
| CN110119948A (en) | Based on when variable weight dynamic combined power consumer credit assessment method and system | |
| CN104537433A (en) | Sold electricity quantity prediction method based on inventory capacities and business expansion characteristics | |
| CN108388974A (en) | Top-tier customer Optimum Identification Method and device based on random forest and decision tree | |
| CN108428055B (en) | Load clustering method considering load longitudinal characteristics | |
| CN110717619A (en) | Multi-scale space-time load prediction method and system for bottom-up power distribution network | |
| Panapakidis et al. | Implementation of modified versions of the K-means algorithm in power load curves profiling | |
| CN107578277A (en) | Rental housing client's localization method for power marketing | |
| CN108154311A (en) | Top-tier customer recognition methods and device based on random forest and decision tree | |
| CN112614004A (en) | Method and device for processing power utilization information | |
| CN104239722A (en) | Forecasting method based on recognition of correlational relationship between factors | |
| CN112200209A (en) | Poor user identification method based on day-to-day power consumption |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170222 |