CN107274100A - Economic alarming analysis method based on electric power big data - Google Patents
Economic alarming analysis method based on electric power big data Download PDFInfo
- Publication number
- CN107274100A CN107274100A CN201710486353.0A CN201710486353A CN107274100A CN 107274100 A CN107274100 A CN 107274100A CN 201710486353 A CN201710486353 A CN 201710486353A CN 107274100 A CN107274100 A CN 107274100A
- Authority
- CN
- China
- Prior art keywords
- data
- economic
- electric power
- big data
- method based
- 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
-
- 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
- G06F16/26—Visual data mining; Browsing structured data
-
- 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
- G06Q10/067—Enterprise or organisation modelling
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/82—Energy audits or management systems therefor
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a kind of economic alarming analysis method based on electric power big data, analysis mining is carried out it establishes an economic alarming model, and by electric power data, methods described includes, and sets up operational data storehouse, and the data of collection are arranged；Carry out data cleansing；Data are carried out merger classification；Data are changed the excavation of rule；Estimation prediction is carried out according to data；Also it is that the result estimated is tested and fed back, the mode of inspection is that predicted value and existing big data are compared, the output data if coincideing misfits, changed by model optimization；Finally set up raw data for users to use.It can be realized by the present invention using electric power big data and the economic characteristics of multiclass enterprise or economic zone are analyzed, enterprise and regional government just can carry out decision-making according to data results, the a series of production schedule and counter-measure are formulated, so as to preferably promote socio-economic development.
Description
Technical field
The present invention relates to the utilization of electric power data, it particularly relates to a kind of economic alarming based on electric power big data
Analysis method.
Background technology
Economic alarming model plays very important effect in entire society develops.If can accomplish that prediction is economical,
National government can just be given special assistance to according to economy trend and move towards preferable industry；Economic problems can also be found early, put into effect
Policy is intervened, reduction industry loss.For enterprise, according to industry development trend, the production schedule, control just can be suitably adjusted
Production capacity, the measures such as market are widened, cater to market.Must deposit for a long time conversely, not recognizing to carry out the economic preparation of prediction
Living.Either country or enterprise, think little of economic development trend, without prevention awareness, cannot consolidate and develop.Cause
This, develop the economy, it is necessary to have perspective.
It is well known that electric energy is the important basic energy resource of China, the proportion accounted in AND ENERGY RESOURCES CONSUMPTION IN CHINA is maximum.Electric power quilt
Be widely used in weaving, communicate, broadcast, the every field such as chemistry, be the major impetus of China's economic development, at the same with state's people's livelihood
Work is closely bound up.It is reported that the power consumption rate of China is only second to the U.S., it is number two in the whole world.Other are replaced using electric energy
The energy, is the inevitable requirement of energy-conserving and environment-protective, meets continuable development principle.In future, usage amount, the utilization rate of electric energy can all be entered
One step increases, and therefore, sets up an economic alarming model, and it is than convenient to carry out analysis mining by electric power data.
Economic alarming model is by collecting enterprise's load of enterprise and regional government, company information, special varying capacity, public becoming negative
These big datas are carried out screening rejecting with many algorithms, sort out the processing such as merging, and excavate them by the electric power datas such as lotus
Consistent changing rule, leading changing rule, the delayed rule of development etc., so as to draw every Economic Function index (such as fluctuation
Cycle, average potential, annual rate of increase etc.).And by analyzing the economic characteristics of multiclass enterprise or economic zone, enterprise and
Regional government just can carry out decision-making according to data results, a series of production schedule and counter-measure be formulated, so that more
Promote socio-economic development well.
The content of the invention
For the above-mentioned reasons, inventor is made that the present invention, that is, proposes a kind of economic alarming based on electric power big data
Analysis method, it comprises the following steps：
Operational data storehouse is set up, and the data of collection are arranged；
Carry out data cleansing；
Data are carried out merger classification；
Data are changed the excavation of rule；
Estimation prediction is carried out according to data；
Also it is that the result estimated is tested and fed back, the mode of inspection is by predicted value and existing big data
It is compared, the output data if coincideing misfits, changed by model optimization；
Raw data is finally set up, for users to use.
Further, the operational data storehouse step of setting up includes the electric power data of collection enterprise and government and is used to
Set up the operational data storehouse.
Further, the data cleansing step includes screening the electric power data of collection, invalid or mistake
Data reject, correct data error.
Further, the changing rule of described data includes：The uniformity of Data Data change, the elder generation of data variation
The hysteresis quality of row and data variation.
Further, wherein according to data carry out estimation prediction include according to data prediction region industry consumer confidence index and
Region consumer confidence index.
Brief description of the drawings
Fig. 1 is the model algorithm level schematic diagram of the present invention.
The model algorithm that Fig. 2 is the present invention constitutes schematic diagram.
Fig. 3 is the data flow block diagram of the present invention.
Fig. 4 is the model framework schematic diagram of the present invention.
Fig. 5 is that the big data that the present invention is used excavates directive function cell schematics.
Specific embodiment
Below in conjunction with accompanying drawing 1-5, the present invention is described further.
1. model orientation
Economic alarming model based on electric power big data, service object is broadly divided into two major classes：Enterprise and governments at all levels.Mould
Type is mainly by the data analysis to electric load, and the economic trend to every profession and trade and various economic regions domain is predicted.Enterprise determines
Plan person can make intuitively analysis according to model and judge that government is then according to mould to its production schedule, annual summary, development trend
Increase and decrease of the economic situation of enterprise to Public Enterprise Construction carries out decision-making in the region that type is shown., first can be with using this model
The economic forecasting index for being difficult to quantify is realized, the cumbersome and difficulty that manpower collects data secondly can also be reduced, realizes that the personnel reduction increases
Effect.Model uses multistage operations, it is possible to reduce the error of HR accounting, realizes data input to the automation of data output
Journey, and as the performance of the storage cumulative model of data can be improved further.
Submodel is positioned：
Economic alarming model based on Power system load data.The support of data source class is provided for national decision-making.It is divided into：
Region industry middle or short term consumer confidence index early warning submodel based on enterprise's electric load.
Regional economy middle or short term early warning submodel based on public power load.
2. big data condition
Constitute two big electric power data conditions of this model：
1) basic data：Totally ten
A, enterprise's ammeter and correlation basic data five, enterprise's load and company information are necessary datas.
B, public ammeter and correlation basic data five, public varying duty and ammeter information are necessary datas.
2), inspection data：Tested for region Industrial Cycle intensity of variation and regional economy change degree
A, classify using trade information as necessity, make necessary quantify to region industry consumer confidence index.
B, expansible quantization is done to regional economy.
The detailed contents such as inspection frequency, necessity, the quality that each data needs see the table below：
I) basic data：
II) inspection data：
A) region industry middle or short term prosperity degree statistics.
B) regional economy middle or short term statistics.
3. model algorithm level
The foundation of economic alarming model based on electric power big data, it is necessary first to collect data, then using mathematical algorithm,
Excavated again by software analysis, predicted the outcome finally by the inspection checking of model, just can determine that the correctness of model.Due to mould
Data qualification needed for type is more and content is numerous and diverse, and model employs the analytic operation that three layers of algorithm support data, and first layer is calculated
Method takes the parser being the theme with mathematics, and this layer of algorithm is mainly counted by the change to Various types of data, is next layer of calculation
Method carries out preliminary data screening；Second layer algorithm is pre-processed to data, the changing rule of mining data, by becoming to data
The excavation of law, sets up performance data；Third layer algorithm is achievement checking algorithm, and second layer algorithm performance data is filtered out
The economic indicator needed, such as turning point index, annual rate of increase, period of waves, predicted value, the Base day of growth rate cyclic swing
Phase etc., used and investigated for user.
4. model algorithm is constituted
Economic alarming model algorithm based on electric power big data can be decomposed into seven parts of following table, and they cause model
More efficiently carry out big data intellectual analysis computing.It is to set up operational data storehouse first, the data of collection is arranged；Then
Data to collection are screened, and invalid, mistake data are rejected, and correct data error；Then data are split, fitted
Aggregation of data is classified in locality, and sorting technique refers to ten basic datas of big data condition；Data are carried out various changes afterwards
The uniformity of the excavation of law, such as data variation, pioneer, the hysteresis quality of data variation of data variation；Furthermore it is pair
Data carry out estimation prediction, major prognostic region industry consumer confidence index and region consumer confidence index；Also it is the result to estimating
Test and feed back, the mode of inspection is that predicted value and existing big data are compared, the output data if coincideing,
Misfit, changed by model optimization；It is finally to set up raw data, for users to use
5. data flow block diagram
In walking upwards for high amount of traffic, it is to carry out tentative calculation with emulation data first, emulation data is examined by algorithm model
Validity, model is modified, the analysis that degree of agreement is carried out to revised data and existing big data is contrasted, and is connect
, model is further corrected, revised data are accumulated as performance data with existing data, finally
Run up to a certain amount (required in basic data for example special varying capacity of some data data volume be 3 years), model can for
Family comparative analysis.
6. model framework
Accompanying drawing gives the economic alarming model support composition based on electric power big data.The place of data in model is illustrated in figure
Details is managed, seven links are divided into, it is indispensable.
1. load data interface：Most basic link.The electric power data of enterprise of all categories and government is collected extensively, it is defeated
Enter and set up complete database：
A) step 1.1：Collect transformer station's ammeter load datas at different levels and relevant information data, i.e., basic data listed by table one
D1, D2, D3, D4, D5, D6, D7, D8, D9, D10.
B) step 1.2：D1~D10 is stored in database data table TAB1.
C) algorithm：TAB1 [i]=Get (D [i]), i=0 ..., 9
2. data cleansing
The link has specifically " cleaning parameterses ", and the data to most original are rejected, and rejects invalid and wrong data：
A) step 2.1：Set cleaning parameterses table:Upper bound TCtop, lower bound TClow, error code TCerr
B) step 2.2：All abnormal datas in TAB1 are marked, are stored in TAB2
C) algorithm：
if(TAB1[i]>TCtop [i]) TAB2 [i]=Mark (i)；
if(TAB1[i]>TClow [i]) TAB2 [i]=Mark (i)；
If (TAB1 [i] ∈ TCerr [i]) TAB2 [i]=Mark (i)；
3. data are split
Enterprise is classified according to " clustering parameter ", is such as divided into manufacturing industry, financial circles, textile industry, aquaculture：
A) step 3.1：Set clustering parameter table：Poly- heart TCc, class is away from TCd
B) step 3.2：The point centered on N number of poly- heart, all data are gathered for N classes, are stored in TAB3
C) algorithm：TAB3 [i]=Custer (TAB1 [i], TAB2 [i], TCc, TCd)
4. data mining
Data are excavated with the change of fault-tolerant rule according to parameter is constituted, the basic changing rule of data is drawn：One
As changing rule, leading changing rule, retardation change rule：
A) step 4.1：Setting constitutes parameter list：TS
B) step 4.2：Changing rule index is calculated using cluster data and composition parameter：Basic index Inor, refers in advance
Number Ilead, lagging index Ilag
C) algorithm：I=0 ..., N classes
Inor [i]=IndexNor (TAB1, TAB3, TS)；
Ilead [i]=IndexLead (TAB1, TAB3, TS)；
Ilag [i]=IndexLag (TAB1, TAB3, TS)；
5. law forecasting
According to precompensation parameter business and government data are carried out with the law forecasting of economic situation：
A) step 5.1：Set precompensation parameter table：TE
B) step 5.2：Predicted value E is calculated using changing rule index and precompensation parameter, including：General forecast value
Enor, leading predicted value Elead, delay prediction value Elag
C) algorithm：I=0 ..., N classes
Enor=HMMestimate (Inor [i], TE)；
Elead=HMMestimate (Ilead [i], TE)；
Elag=HMMestimate (Ilag [i], TE)；
6. fitting is examined
The predicted value that economic alarming model is drawn all is had to by examining.Can not can be for repairing by the data of inspection
Holotype shape parameter so that it is more and more accurate to predict the outcome：
A) step 6.1：Using inspection data by 5. calculating inspection predicted value：CE
B) step 6.2：Comparison prediction value is with examining predicted value, to Optimized model parameter
C) algorithm：if(|E-CE|>D)Adjust(TC,TS,TE)；
7. warning data interface
Failing to the inspection by link 6., then continue to optimize；If passing through, the data with regard to that can export early warning are created as
Complete economic alarming model：
A) step 7.1：Export economic alarming result
B) step 7.2：Early warning result is stored in result database table：TAB7
C) algorithm：TAB7 [t]=E [t]；
8. cleaning parameterses：According to the result of data cleansing, cleaning parameterses can be suitably adjusted according to data
Parameter is described：Upper bound TCtop, lower bound TClow, error code TCerr
9. clustering parameter：By model data partition test, effective enterprise classifying is retained, invalid rejecting can root
According to data point reuse parameter
Parameter is described：Poly- heart TCc, class is away from TCd
10. parameter is constituted：The rule Components matrix selected during rule, including the daily fluctuation characteristic of every profession and trade are excavated,
Average potential etc., constitutes daily index
Parameter is described：Rule Components TS
Precompensation parameter：Time series HMM prediction algorithm coefficient matrixes.Model can be carried out excellent according to assay
Change, adjust parameters.
Parameter is described：HMM predictive coefficients TE：
It is not fitted by examining, then carries out model optimization
A) step 8.1：If upchecked, retain original parameter；Otherwise corrected parameter
B) algorithm：if(|E-CE|>D)Adjust(TC,TS,TE)；
7. big data excavates directive function unit
For the excavation of big data, there are 12 specific targets units, including time series index, turning point index, year
Growth rate, period of waves, Study on Trend index, predicted value, the base period of growth rate cyclic swing, length spy piece, amplitude are special
Levy, be averaged potential, deviation ratio, Collaboration agent.Such as time series index, using the time as sequence, each enterprise is changed over time
Specific power consumption intuitively show；And for example period of waves, user is allowed to predict production peak period and the production of oneself
The low ebb phase, can avoid decision-making of loss etc. to the production low ebb phase in advance.Have these functional parameters, enterprise plan and
Government, which sets up decision-making, to carry out related preparation before huge risk arrives to chance, preferably promote social and economic construction.
8. software analysis method
In economic alarming model based on electric power big data, the content drawn by analyzing electric power big data is divided into six big
Class.
The first kind is the Economic Climate index early warning based on electric power big data, this part by electric load, capacity,
The mathematical modeling of the data such as maintenance can just allow enterprise or government to make a prediction profit and loss economic in a short time, successfully to carry out
The decision-making of next step development makes change to the developing direction of enterprise.
Equations of The Second Kind is the economic index time series feature mining analysis based on electric power big data, and this part is using the time as sequence
Row, allow user in units of the moon/season/year, analyze economic rising or falling, and phase specific aim is fallen after rise in rising next year
Make the precautionary measures in ground.
3rd class is that, based on the analysis of turning point feature mining, this part can allow customer analysis economy to rise and fall after rise turnover
The reason for and feature, find out key factor and improve its production schedule.
4th class is the excavation based on feature period of waves, and this part can allow customer analysis to go out economic rising falling or produce
In product sales volume many and few specific periods, so that targeted surveys are made in market in period to this, traveller is met to improve its product
And dominate the market.
5th class is to be based on economic index situation signature analysis, and this part can be analyzed in a region in the regular period
Mutually enterprise's status of profit and loss of the same trade, so that government or relevant enterprise are preferably regulated and control the market.
6th class is to be based on economic index Collaboration agent signature analysis, and this part can be analyzed in one period an of region
The enterprise of different industries be how profit and loss, such as auto manufacturing's economic growth within a period is rapid, automobile accessories industry
Economy whether increase with the growth of automobile industry economy, whether the replacement industrial economy of opposite automobile with automobile industry economy
Growth and decline.
1) the Economic Climate index early warning based on electric power big data
Function：
A) electric load, capacity, the mathematical modeling of failure/mantenance data and analysis
B) modeling of Economic Climate index and analysis
C) in the region industry based on enterprise's electric load, short-term consumer confidence index prediction is calculated and early warning
D in the regional economy) based on public power load, short-term consumer confidence index prediction calculate and early warning
2) the economic index time series feature mining analysis based on electric power big data
Function：
A) electric load, capacity, the time series signature analysis of failure/mantenance data
B) the time series feature association analysis of Economic Climate index
C) the electric power big data motion based on time series linked character, change and progress rule are excavated
D) the Economic Climate exponential forecasting based on time series linked character is calculated and early warning
3) the economic index turning point feature mining analysis based on electric power big data
Function：
A) electric load, capacity, the turning point signature analysis of failure/mantenance data
B) the turning point character association analysis of Economic Climate index
C) the electric power big data motion based on turning point linked character, change and progress rule are excavated
D) the Economic Climate exponential forecasting based on turning point linked character is calculated and early warning
4) the economic index feature mining period of waves analysis based on electric power big data
Function：
A) electric load, capacity, signature analysis period of waves of failure/mantenance data
B) feature association analysis period of waves of Economic Climate index
C) the electric power big data motion based on linked character period of waves, change and progress rule are excavated
D) the Economic Climate exponential forecasting based on linked character period of waves is calculated and early warning
5) the economic index situation feature mining analysis based on electric power big data
Function：
A) electric load, capacity, the situation signature analysis of failure/mantenance data
B) the situation feature association analysis of Economic Climate index
C) the electric power big data motion based on situation association feature, change and progress rule are excavated
D) the Economic Climate exponential forecasting based on situation association feature is calculated and early warning
6) the economic index Collaboration agent feature mining analysis based on electric power big data
Function：
A) electric load, capacity, the Collaboration agent signature analysis of failure/mantenance data
B) the Collaboration agent feature association analysis of Economic Climate index
C) the electric power big data motion based on Collaboration agent linked character, change and progress rule are excavated
D) the Economic Climate exponential forecasting based on Collaboration agent linked character is calculated and early warning.
Claims (5)
1. a kind of economic alarming analysis method based on electric power big data, it is characterised in that the described method comprises the following steps：
Operational data storehouse is set up, and the data of collection are arranged；
Carry out data cleansing；
Data are carried out merger classification；
Data are changed the excavation of rule；
Estimation prediction is carried out according to data；
Also it is that the result estimated is tested and fed back, the mode of inspection is by predicted value and the progress of existing big data
Compare, the output data if coincideing misfits, changed by model optimization；
Raw data is finally set up, for users to use.
2. a kind of economic alarming analysis method based on electric power big data as claimed in claim 1, it is characterised in that described to build
Vertical operational data storehouse step is including collecting the electric power data of enterprise and government and to set up the operational data storehouse.
3. a kind of economic alarming analysis method based on electric power big data as claimed in claim 2, it is characterised in that the number
Include screening the electric power data of collection according to cleaning step, invalid or wrong data are rejected, data error is corrected.
4. a kind of economic alarming analysis method based on electric power big data as claimed in claim 3, it is characterised in that described
The changing rule of data includes：Uniformity, pioneer and data variation the hysteresis quality of data variation of Data Data change.
5. a kind of economic alarming analysis method based on electric power big data as claimed in claim 4, it is characterised in that wherein root
Carrying out estimation prediction according to data is included according to data prediction region industry consumer confidence index and region consumer confidence index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710486353.0A CN107274100A (en) | 2017-06-23 | 2017-06-23 | Economic alarming analysis method based on electric power big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710486353.0A CN107274100A (en) | 2017-06-23 | 2017-06-23 | Economic alarming analysis method based on electric power big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107274100A true CN107274100A (en) | 2017-10-20 |
Family
ID=60068188
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710486353.0A Pending CN107274100A (en) | 2017-06-23 | 2017-06-23 | Economic alarming analysis method based on electric power big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107274100A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111832805A (en) * | 2020-06-06 | 2020-10-27 | 国网河北省电力有限公司衡水供电分公司 | Economic early warning analysis system and method based on electric power big data |
| CN114331308A (en) * | 2021-08-12 | 2022-04-12 | 国网安徽省电力有限公司蚌埠供电公司 | Self-trade district development analysis system based on electric big data and construction method thereof |
| CN116304931A (en) * | 2023-05-12 | 2023-06-23 | 山东英伟电子技术有限公司 | Electric power data mining method based on big data |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102214338A (en) * | 2010-04-06 | 2011-10-12 | 上海驭策信息技术有限公司 | Sales forecasting system and method |
| CN106485367A (en) * | 2016-10-26 | 2017-03-08 | 贵州电网有限责任公司电力科学研究院 | A kind of economic analysis platform based on the coupling of multiple enterprises electricity consumption data and Forecasting Methodology |
-
2017
- 2017-06-23 CN CN201710486353.0A patent/CN107274100A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102214338A (en) * | 2010-04-06 | 2011-10-12 | 上海驭策信息技术有限公司 | Sales forecasting system and method |
| CN106485367A (en) * | 2016-10-26 | 2017-03-08 | 贵州电网有限责任公司电力科学研究院 | A kind of economic analysis platform based on the coupling of multiple enterprises electricity consumption data and Forecasting Methodology |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111832805A (en) * | 2020-06-06 | 2020-10-27 | 国网河北省电力有限公司衡水供电分公司 | Economic early warning analysis system and method based on electric power big data |
| CN114331308A (en) * | 2021-08-12 | 2022-04-12 | 国网安徽省电力有限公司蚌埠供电公司 | Self-trade district development analysis system based on electric big data and construction method thereof |
| CN116304931A (en) * | 2023-05-12 | 2023-06-23 | 山东英伟电子技术有限公司 | Electric power data mining method based on big data |
| CN116304931B (en) * | 2023-05-12 | 2023-08-04 | 山东英伟电子技术有限公司 | Electric power data mining method based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106845717B (en) | Energy efficiency evaluation method based on multi-model fusion strategy | |
| CN102567807B (en) | Method for predicating gas card customer churn | |
| CN104123600B (en) | A kind of electric power manager's exponential trend Forecasting Methodology towards representative row sparetime university data | |
| CN111324642A (en) | Model algorithm type selection and evaluation method for power grid big data analysis | |
| CN111738462B (en) | Fault first-aid repair active service early warning method for electric power metering device | |
| CN106909933A (en) | A kind of stealing classification Forecasting Methodology of three stages various visual angles Fusion Features | |
| CN103310388B (en) | Based on the composite index of grid operation method of calculation of information source entropy | |
| CN103473619A (en) | Analysis method based on network architecture and application thereof | |
| CN103632203A (en) | Distribution network power supply area division method based on comprehensive evaluation | |
| CN108170769A (en) | A kind of assembling manufacturing qualitative data processing method based on decision Tree algorithms | |
| CN107301604A (en) | Multi-model fusion estimation system | |
| CN107274100A (en) | Economic alarming analysis method based on electric power big data | |
| CN103440539A (en) | Method for processing electricity consumption data of consumers | |
| CN113344449A (en) | Method for predicting monthly-scale industrial water demand | |
| CN115641162A (en) | Prediction data analysis system and method based on construction project cost | |
| CN117273414A (en) | System and method for analyzing and identifying big data of smart city | |
| CN111950910A (en) | Airport guarantee vehicle task scheduling method based on DBSCAN-GA | |
| CN111652403A (en) | Feedback correction-based work platform task workload prediction method | |
| CN113962477A (en) | Industrial electric quantity association aggregation prediction method, device, equipment and storage medium | |
| CN104217296A (en) | Listed company performance comprehensive evaluation method | |
| CN109377436A (en) | A kind of accurate monitoring and managing method of environment and device, terminal device and storage medium | |
| Yu et al. | A new two-stage stochastic model for reverse logistics network design under government subsidy and low-carbon emission requirement | |
| CN111581882A (en) | Rescheduling triggering judgment method under uncertain conditions of production units | |
| CN109190204B (en) | Complex mechanical product module division method based on complex network | |
| Deng et al. | Comprehensive evaluation method of urban water resources utilization based on dynamic reduct |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190319 Address after: 510000 Building 604, Building B1, 162 Science Avenue, Huangpu District, Guangzhou City, Guangdong Province Applicant after: Guangzhou Huaying Electric Technology Co., Ltd. Address before: Room A210-1, Research Building A, Nefo High-tech Think Tank Center, Nanhai Software Science Park, Shishan Town, Nanhai District, Guangdong Province Applicant before: Guangdong informed Robot Technology Co., Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171020 |