CN109102106A - One kind being based on electric power big data load density optimized calculation method - Google Patents
One kind being based on electric power big data load density optimized calculation method Download PDFInfo
- Publication number
- CN109102106A CN109102106A CN201810729043.1A CN201810729043A CN109102106A CN 109102106 A CN109102106 A CN 109102106A CN 201810729043 A CN201810729043 A CN 201810729043A CN 109102106 A CN109102106 A CN 109102106A
- Authority
- CN
- China
- Prior art keywords
- data
- load
- area
- rdd
- radio area
- 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
- 238000004364 calculation method Methods 0.000 title claims abstract description 19
- 230000001788 irregular Effects 0.000 claims abstract description 5
- 230000006870 function Effects 0.000 claims description 25
- 230000001131 transforming effect Effects 0.000 claims description 19
- 238000007619 statistical method Methods 0.000 claims description 6
- 238000013500 data storage Methods 0.000 claims description 5
- 238000007726 management method Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000002354 daily effect Effects 0.000 claims description 3
- 230000008676 import Effects 0.000 claims description 3
- 238000013316 zoning Methods 0.000 claims description 3
- 230000003203 everyday effect Effects 0.000 claims description 2
- 238000010248 power generation Methods 0.000 abstract description 6
- 238000006243 chemical reaction Methods 0.000 abstract description 2
- 238000000034 method Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 4
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 3
- 240000002853 Nelumbo nucifera Species 0.000 description 3
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000013439 planning Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The calculating field of network transformer load data of the present invention.More particularly to it is a kind of based on electric power big data load density optimized calculation method.The present invention cleverly utilizes plane conversion to convert the latitude and longitude coordinates on any irregular area vertex, converts region area computational problem to the calculating of area of a polygon.Areal concentration calculating can be carried out to the region that any frame selects using the present invention, power generation data when power supply company being made quickly to grasp the peak of power consumption of load hot zones are of great significance to the safe operation of regional power grid.
Description
Technical field
The calculating field of network transformer load data of the present invention.More particularly to it is a kind of negative based on electric power big data
Lotus density optimized calculation method.
Background technique
With intelligent, the information-based development of power distribution network, the data volume that power distribution network generates daily is increasing, traditional number
Power supply company is early had been unable to meet according to processing mode for the demand of distribution network planning management.Data structure multiplicity, data relationship
Complexity, the difficult point that real-time property requires high always power distribution network effective information to extract.Big data technology is applied to electric power row
Industry can efficiently solve power distribution network mass data processing and calculate bring problem, can also carry out region to load data
Change, industry-specific statistic of classification, big data technology, which is applied to power distribution network, can make the tie more intelligence between power supply unit and user
Energyization, it is information-based thus receive extensive use.
According to the difference of the source situation of data information, the big data in intelligent distribution network can be divided into electric system hair
The data of electric data, the data of Operation of Electric Systems and the electric system external world.Electric system power generation data mainly include that public become is used
Data, distribution transforming are adopted with adopting data and power distribution network topological data.Distributed computing architecture is applied to the normal fortune of electric system
Row work, electricity consumption strategy marketing work, information valence in big data is excavated in and the data management direction of social internet information
Value, can reduce the cost of power system management, be of great significance to the economic benefit for promoting electric power enterprise, at the same time also
The integrated service that electric system can be effectively improved is horizontal.
Traditional Hadoop big data processing platform can apply at batch data using HDFS and MapReduce as core
Reason, but it is not suitable for interactive data inquiry, real time data stream process.2009, UCBerkeley was proposed completely new big number
According to processing frame: Spark, the frame calculating speed is fast, performance is brilliant, offer batch data is handled, interactive data is inquired,
Real time data stream process, the big data process demand of machine learning these different scenes.Currently, the computing platform has become use
Highest is spent, most active big data processing platform is developed.
Load density is the quantization parameter for characterizing power load distributing concentration, it is every square kilometre of average electric power
Numerical value, with MW/km2Metering.The method of traditional calculations region load density is only in the plot for determining boundary, with each substation
And each route maximum load is divided by the area in the plot.The numerical procedure needs a large amount of data supporting and can not be suitable for real-time
The load data of frame choosing, therefore power distribution network power generation data are urgently made full use of, to region load using a kind of new calculation method
Density efficiently, accurately calculate.
Summary of the invention
The purpose of the invention is, provides a kind of utilization big data principle, simple and fast by distribution netting index
The load density calculation method in region is obtained according to parallel computation is carried out.
To achieve the above object, the invention adopts the following technical scheme that.
One kind being based on electric power big data load density optimized calculation method, including
Step 1: establish distributed storage computing platform, including at least establishing distributed computing layer and data storage layer；
Establishing distributed computing layer includes establishing by the upper layer computing platform of Spark and based on the lower layer of Hadoop
Platform is calculated, upper layer computing platform is calculated for constructing RDD operator and Mllib algorithms library, completing memory, and lower layer's computing platform is used for
Creation and distribution task, complete cluster management and parallel computation at building MapReduce；Using parallel computation as load number
According to calculating structure, computational problem is resolved into multiple tasks, each task can on different CPU simultaneously be counted
It calculates, saves time and the cost of the calculating of large-scale area load density.
Establishing data Layer reservoir includes establishing the distributed file system based on HDFS and the statistical analysis based on Hive
System, distributed file system establish distributed storage data according to source data, and statistical analysis system is according to distributed storage number
According to database table is established, it is completed at the same time data query and data reconstruction function；Using Hadoop distributed file system
(HDFS) frame as the storage of distribution network load data, data-storage system have low cost, high fault tolerance, high-throughput
And enhanced scalability.
Step 2: being pre-processed to initial data；Including collecting user power utilization load data, using Lagrange's interpolation
Theorem completion sky data；It is Key with distribution transforming ID and date, duplicate removal is carried out to data；Abnormal data in initial data is used
3 σ theorems in statistics are rejected；
Step 3: being divided so that radio area is unit to load data；It specifically refers to the ordinate of distribution transforming to be measured
Straight line is done, each intersection point of the straight line and polygon is obtained；The number for calculating tested point both sides straight line and intersection point, if tested point
Both sides number of hits is odd number, then determines the distribution transforming in for radio area；If it is not, determining the distribution transforming outside for radio area；
Step 4: building Map function and Reduce function parallelization calculate region peak load；Including
1) it sums, obtains comprising this for radio area by key value of sampled point to for all public changes in radio area/special become
Current year any point-in-time public affairs become/specially become the RDD of total load；
2) building Map function seeks the maximum value for becoming/specially becoming total load in each day sampled point for radio area public affairs, in this, as
The first row of new RDD；
3) the Reduce function constructed is to compare to be maximized two-by-two, is iterated for the first row to new RDD, with this
It obtains for radio area peak load；
Step 5: converting two-dimensional coordinate for region vertex, distribution transforming longitude and latitude by map projection；Including
1) the geographic coordinate system GCS of frame favored area is judged, selects suitable map projection's mode；
2) the vertex longitude and latitude of frame favored area is subjected to Mercator projection, obtains region vertex in the seat of projected coordinate system
Mark；
3) distribution transforming longitude and latitude is equally obtained by Mercator projection；
Step 6: using area of a polygon calculation formula zoning area；
1) it will obscure for radio area and be divided into multiple for irregular polygon using the certain point of polygon as vertex
Triangle；
2) area of triangle is calculated using the multiplication cross of vector；
3) these triangle areas are summed to obtain for radio area area；
Step 7: calculating for radio area load density, numerical value is for radio area peak load divided by for the total face in radio area
Product.
It is further optimized for, further includes following steps: being based on source data foundation in data Layer reservoir and data are locally stored,
Api interface is established in distributed computing layer.
It is further optimized for, distributed storage computing platform is established in linux system, and source data is with external tables of data
Form of the form as data query and reconstruct completes access to external tables of data using Hive, by HOL language by data
The form import system of table data set in a distributed manner.
It is further optimized for, Map function is constructed in step 4 and Reduce function parallelization calculates region maximum and bears
Lotus；Further include:
It is screened using frame favored area coordinate pair transformer load, obtains the RDD for the transformer information for belonging to the region；
To RDD according to when discontinuity surface sum, obtain new RDD, the every a line of RDD includes the sum of various time points region load in the same day,
Different column have the different dates；A Map function is defined, the peak load section of every day is found out by iteration, is obtained
RDD store Daily treatment cost；A Reduce function is defined, size is compared by column to this RDD two-by-two, selects two numbers
Between biggish number, constitute new list, same Reduce operation carried out to this new list, continuous iteration obtains year most
Big load.
The beneficial effect is that: the present invention obtains region in a manner of carrying out parallel computation to power distribution network power generation data and bears
Lotus density.The Map function and Reduce function of building can be focused to find out region load maximum value from data rapidly.The present invention is skilful
Wonderful is converted the latitude and longitude coordinates on any irregular area vertex using plane conversion, converts region area computational problem to
The calculating of area of a polygon.Areal concentration calculating can be carried out to the region that any frame selects using the present invention, keep power supply company fast
Speed grasps the power generation data when peak of power consumption of load hot zones, is of great significance to the safe operation of regional power grid.This
Invention calculates the region load density of any one location with big data computing technique, has data fault-tolerant rate high, and calculating speed is fast, meter
Calculate the simple feature of program.The region load that the load hot zones of frame choosing can fast and accurately be calculated using this method is close
Degree is conducive to the working efficiency for improving local distribution network Power System Planning personnel, and the lateral comparison for area power generation data mentions
For standard.
Detailed description of the invention
Fig. 1 is the general frame of big data storage computing platform of the invention；
Fig. 2 is technical solution of the present invention flow chart；
Fig. 3 is the present invention to Power system load data specific operation process figure.
Specific embodiment
It elaborates below in conjunction with specific embodiment to the invention.
One kind being based on electric power big data load density optimized calculation method, including
Step 1: as shown in Figure 1, establishing distributed storage computing platform in linux system, source data is with external tables of data
Form of the form as data query and reconstruct, complete the access to external tables of data using Hive, will be counted by HOL language
According to the form import system of table data set in a distributed manner.
Distributed storage computing platform, including at least establishing distributed computing layer and data storage layer；
Include the upper layer computing platform established based on Spark and be based on as shown in Fig. 2, establishing distributed computing layer
Lower layer's computing platform of Hadoop, upper layer computing platform are calculated for constructing RDD operator and Mllib algorithms library, completing memory, under
Layer computing platform is for creating and distributing task, building MapReduce, complete cluster management and parallel computation；Establish data
Layer reservoir includes establishing the distributed file system based on HDFS and the statistical analysis system based on Hive, distributed field system
System establishes distributed storage data according to source data, and statistical analysis system establishes database table according to distributed storage data, together
When complete data query and data reconstruction function；
Initial data is stored in the distributed file system (HDFS) that Hadoop platform provides, realizes the discrete of data set
Change storage and inquiry；Initial data is stored in the distributed file system (HDFS) that Hadoop platform provides, realizes data set
Discretization storage and inquiry；Its data format such as table 1:
Table 1
Further include being based on source data foundation in data Layer reservoir data are locally stored, establishes API in distributed computing layer and connect
Mouthful.
Step 2: being pre-processed to initial data, the integrality and accuracy of data are audited, including collects and uses
Family power load data, using Lagrange interpolation formula completion sky data；It is Key with distribution transforming ID and date, data is carried out
Duplicate removal；Abnormal data in initial data is rejected using 3 σ theorems in statistics；
Step 3: being divided so that radio area is unit to load data；It specifically refers to the ordinate of distribution transforming to be measured
Straight line is done, each intersection point of the straight line and polygon is obtained；The number for calculating tested point both sides straight line and intersection point, if tested point
Both sides number of hits is odd number, then determines the distribution transforming in for radio area；If it is not, determining the distribution transforming outside for radio area；
Step 4: as shown in figure 3, building Map function and Reduce function parallelization calculate region peak load；Including
1) it sums, obtains comprising this for radio area by key value of sampled point to for all public changes in radio area/special become
Current year any point-in-time public affairs become/specially become the RDD of total load；
2) building Map function seeks the maximum value for becoming/specially becoming total load in each day sampled point for radio area public affairs, in this, as
The first row of new RDD；By to RDD according to when discontinuity surface sum, obtain a new RDD, the every a line of this RDD includes the same day
The sum of middle various time points region load, different column have the different dates
3) the Reduce function constructed is to compare to be maximized two-by-two, is iterated for the first row to new RDD, with this
It obtains for radio area peak load；
Step 5: converting two-dimensional coordinate for region vertex, distribution transforming longitude and latitude by map projection；Including
1) the geographic coordinate system GCS of frame favored area is judged, selects suitable map projection's mode；
2) the vertex longitude and latitude of frame favored area is subjected to Mercator projection, obtains region vertex in the seat of projected coordinate system
Mark；
3) distribution transforming longitude and latitude is equally obtained by Mercator projection；
Step 6: using area of a polygon calculation formula zoning area；Due to each vertex in region be it is fixed,
Therefore subregion approximation being found out to, polygon, region area are calculated using arbitrary polygon areal calculation formula.First
Corresponding region is selected, is planarized the longitude and latitude on each vertex using map projection transformation.Frame favored area after planarization can
To regard the polygon containing multiple vertex as.It selects one of point as vertex, calculates it in any other two vertex structures
At triangle area arbitrary polygon areal calculation formula it is as follows:
Its specific steps includes:
1) it will obscure for radio area and be divided into multiple for irregular polygon using the certain point of polygon as vertex
Triangle；
2) area of triangle is calculated using the multiplication cross of vector；
3) these triangle areas are summed to obtain for radio area area；
Step 7: calculating for radio area load density, numerical value is for radio area peak load divided by for the total face in radio area
Product.
Finally it should be noted that above embodiments are only to illustrate the technical solution of the invention, rather than to this hair
The bright limitation for creating protection scope, those skilled in the art should understand that, it can be to the technical solution of the invention
It is modified or replaced equivalently, without departing from the spirit and scope of the invention technical solution.
Claims (4)
1. one kind is based on electric power big data load density optimized calculation method characterized by comprising
Step 1: establish distributed storage computing platform, including at least establishing distributed computing layer and data storage layer；
Establish distributed computing layer include establish upper layer computing platform based on Spark and the lower layer based on Hadoop calculate it is flat
Platform, the upper layer computing platform are calculated for constructing RDD operator and Mllib algorithms library, completing memory, lower layer's computing platform
For creating and distributing task, building MapReduce, complete cluster management and parallel computation；
Establishing data Layer reservoir includes establishing the distributed file system based on HDFS and the statistical analysis system based on Hive,
The distributed file system establishes distributed storage data according to source data, and the statistical analysis system is according to distributed storage
Data establish database table, are completed at the same time data query and data reconstruction function；
Step 2: being pre-processed to initial data；Including collecting user power utilization load data, using Lagrange interpolation formula
Completion sky data；It is Key with distribution transforming ID and date, duplicate removal is carried out to data；By the abnormal data in initial data using statistics
3 σ theorems in are rejected；
Step 3: being divided so that radio area is unit to load data；It specifically refers to do with the ordinate of distribution transforming to be measured directly
Line obtains each intersection point of the straight line and polygon；The number for calculating tested point both sides straight line and intersection point, if tested point both sides
Number of hits is odd number, then determines the distribution transforming in for radio area；If it is not, determining the distribution transforming outside for radio area；
Step 4: building Map function and Reduce function parallelization calculate region peak load；Including
1) it sums, obtains comprising this for radio area current year by key value of sampled point to for all public changes in radio area/special become
Any point-in-time public affairs become/specially become the RDD of total load；
2) building Map function seeks the maximum value for becoming/specially becoming total load in each day sampled point for radio area public affairs, in this, as new
The first row of RDD；
3) the Reduce function constructed is to compare to be maximized two-by-two, is iterated for the first row to new RDD, is obtained with this
For radio area peak load；
Step 5: converting two-dimensional coordinate for region vertex, distribution transforming longitude and latitude by map projection；Including
1) the geographic coordinate system GCS of frame favored area is judged, selects suitable map projection's mode；
2) the vertex longitude and latitude of frame favored area is subjected to Mercator projection, obtains region vertex in the coordinate of projected coordinate system；
3) distribution transforming longitude and latitude is equally obtained by Mercator projection；
Step 6: using area of a polygon calculation formula zoning area；
1) it will be obscured for radio area and be divided into multiple triangles using the certain point of polygon as vertex for irregular polygon
Shape；
2) area of triangle is calculated using the multiplication cross of vector；
3) these triangle areas are summed to obtain for radio area area；
Step 7: calculating for radio area load density, numerical value is for radio area peak load divided by for the radio area gross area.
2. a kind of according to claim 1 be based on electric power big data load density optimized calculation method, which is characterized in that also wrap
It includes following steps: being based on source data foundation in data Layer reservoir and data are locally stored, establish api interface in distributed computing layer.
3. a kind of according to claim 1 be based on electric power big data load density optimized calculation method, which is characterized in that described
Distributed storage computing platform establish in linux system, the source data in the form of external tables of data as data query with
The form of reconstruct completes access to external tables of data using Hive, by HOL language by tables of data data set in a distributed manner
Form import system.
4. a kind of according to claim 1 be based on electric power big data load density optimized calculation method, which is characterized in that described
Map function is constructed in step 4 and Reduce function parallelization calculates region peak load；Further include:
It is screened using frame favored area coordinate pair transformer load, obtains the RDD for the transformer information for belonging to the region；It is right
RDD according to when discontinuity surface sum, obtain new RDD, described every a line of RDD include in the same day various time points region load it
With different column have the different dates；A Map function is defined, the peak load section of every day is found out by iteration, is obtained
To RDD store Daily treatment cost；A Reduce function is defined, size is compared by column to this RDD two-by-two, selects two
Biggish number between number, constitutes new list, carries out same Reduce operation to this new list, continuous iteration obtains year
Peak load.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810729043.1A CN109102106A (en) | 2018-07-05 | 2018-07-05 | One kind being based on electric power big data load density optimized calculation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810729043.1A CN109102106A (en) | 2018-07-05 | 2018-07-05 | One kind being based on electric power big data load density optimized calculation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109102106A true CN109102106A (en) | 2018-12-28 |
Family
ID=64845725
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810729043.1A Pending CN109102106A (en) | 2018-07-05 | 2018-07-05 | One kind being based on electric power big data load density optimized calculation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109102106A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109712453A (en) * | 2019-02-28 | 2019-05-03 | 安徽腾策网络科技有限公司 | A kind of software Training Management Information System based on big data |
| CN111859488A (en) * | 2020-07-27 | 2020-10-30 | 深圳市纵维立方科技有限公司 | Support structure generation method and device, electronic equipment and storage medium |
| CN112330483A (en) * | 2020-10-26 | 2021-02-05 | 南京南瑞继保工程技术有限公司 | Power grid multi-period future mode section generation method based on MapReduce framework |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107807961A (en) * | 2017-10-10 | 2018-03-16 | 国网浙江省电力公司丽水供电公司 | A kind of power distribution network big data multidomain treat-ment method based on Spark computing engines |
| CN107832876A (en) * | 2017-10-27 | 2018-03-23 | 国网江苏省电力公司南通供电公司 | Subregion peak load Forecasting Methodology based on MapReduce frameworks |
-
2018
- 2018-07-05 CN CN201810729043.1A patent/CN109102106A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107807961A (en) * | 2017-10-10 | 2018-03-16 | 国网浙江省电力公司丽水供电公司 | A kind of power distribution network big data multidomain treat-ment method based on Spark computing engines |
| CN107832876A (en) * | 2017-10-27 | 2018-03-23 | 国网江苏省电力公司南通供电公司 | Subregion peak load Forecasting Methodology based on MapReduce frameworks |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109712453A (en) * | 2019-02-28 | 2019-05-03 | 安徽腾策网络科技有限公司 | A kind of software Training Management Information System based on big data |
| CN111859488A (en) * | 2020-07-27 | 2020-10-30 | 深圳市纵维立方科技有限公司 | Support structure generation method and device, electronic equipment and storage medium |
| CN111859488B (en) * | 2020-07-27 | 2024-03-29 | 深圳市纵维立方科技有限公司 | Support structure generation method and device, electronic equipment and storage medium |
| CN112330483A (en) * | 2020-10-26 | 2021-02-05 | 南京南瑞继保工程技术有限公司 | Power grid multi-period future mode section generation method based on MapReduce framework |
| CN112330483B (en) * | 2020-10-26 | 2022-08-26 | 南京南瑞继保工程技术有限公司 | Power grid multi-period future mode section generation method based on MapReduce framework |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103488736B (en) | Method and system for establishing multisource geospatial information correlation model | |
| CN109102106A (en) | One kind being based on electric power big data load density optimized calculation method | |
| CN105631764A (en) | Smart power grid big data application system orienting smart city | |
| CN108694244A (en) | A kind of electric network synthetic application platform based on three-dimensional data | |
| CN107330056A (en) | Wind power plant SCADA system and its operation method based on big data cloud computing platform | |
| CN107832876A (en) | Subregion peak load Forecasting Methodology based on MapReduce frameworks | |
| CN107807961B (en) | Spark calculation engine-based power distribution network big data partition processing method | |
| Zhu et al. | GIScience can facilitate the development of solar cities for energy transition | |
| CN105303292A (en) | Distribution data storage method and device | |
| Kong et al. | The method and application of big data mining for mobile trajectory of taxi based on MapReduce | |
| CN116911055B (en) | Digital twinning-based intelligent city planning management system | |
| CN108648099A (en) | The intelligent aided design system of distribution planning | |
| Melo et al. | Data issues in spatial electric load forecasting | |
| CN109241216B (en) | Method for realizing gridding management by using power grid level storage database architecture | |
| Wu et al. | Study of GIS-oriented graphical management system for power grid planning based on cloud service | |
| Bakalov et al. | A network model for the utility domain | |
| CN115730711A (en) | Space division method, device and storage medium | |
| CN109472862A (en) | Three-dimensional modeling system of transformer substation | |
| CN108053125A (en) | A kind of energy based on macro-management shows method and system | |
| CN107436945A (en) | A kind of information collecting method and system based on electronic map | |
| CN112650792A (en) | Method and system for automatically identifying and storing element water flow in urban water flow simulation | |
| CN111882457A (en) | Transformer substation site selection method and device | |
| Graser | Tessellating urban space based on street intersections and barriers to movement | |
| Zhao et al. | Forecasting regional short-term freight volume using QPSO-LSTM algorithm from the perspective of the importance of spatial information | |
| CN113590727B (en) | Spatial data structural analysis method |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Long Yu Inventor after: Huang He Inventor after: Qi Hui Inventor after: Jiang Wei Inventor after: Weng Beibei Inventor after: Yang Le Inventor after: Duan Xiaofeng Inventor after: Wu Qian Inventor after: Mei Xin Inventor before: Wu Qian Inventor before: Weng Beibei Inventor before: Mei Xin Inventor before: Duan Xiaofeng |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181228 |