CN109242132A - Subregion peak load prediction technique based on MapReduce frame - Google Patents
Subregion peak load prediction technique based on MapReduce frame Download PDFInfo
- Publication number
- CN109242132A CN109242132A CN201810567569.4A CN201810567569A CN109242132A CN 109242132 A CN109242132 A CN 109242132A CN 201810567569 A CN201810567569 A CN 201810567569A CN 109242132 A CN109242132 A CN 109242132A
- Authority
- CN
- China
- Prior art keywords
- data
- area
- peak load
- platform
- bianyutai
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000012417 linear regression Methods 0.000 claims abstract description 18
- 238000007405 data analysis Methods 0.000 claims abstract description 11
- 238000002405 diagnostic procedure Methods 0.000 claims abstract description 11
- 230000001131 transforming effect Effects 0.000 claims description 24
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000013439 planning Methods 0.000 abstract description 6
- 238000007726 management method Methods 0.000 abstract description 5
- 230000008859 change Effects 0.000 description 8
- 238000012545 processing Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 1
- 240000002853 Nelumbo nucifera Species 0.000 description 1
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000007619 statistical method Methods 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
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (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 subregion peak load prediction technique based on MapReduce frame that the present invention relates to a kind of, comprising the following steps: step a: build big data analysis platform；Step b: data prediction is carried out to initial data；Step c: distribution region is judged using crosspoint diagnostic method；Step d: it seeks the area Gong Bianyutai of platform area and specially becomes the peak load in 1 year；Step e: being predicted respectively using the peak load that linear regression model (LRM) specially becomes the area Gong Bianyutai of platform area, and platform area peak load is the sum of two predicted values.The present invention is predicted respectively using the peak load that linear regression model (LRM) specially becomes the area Gong Bianhetai of platform area, and peak load prediction is carried out as data basis, data are provided and are supported for power distribution network management, planning, are of great significance to power distribution network the safe and economic operation.
Description
Technical field
The present invention relates to handling using computer technology for power distribution network big data, belong to power distribution network big data
Excavation and analysis field.
Background technique
With the proposition of State Grid Corporation of China's construction sturdy power grid strategic objective, intelligent power terminal and acquisition terminal quantity
It is growing, so that the growth of geometry grade occur in various types of power automation data, shows " scale of construction is big ", " type
It is more ", the typical big data feature of " density is low " and " speedup is fast ".In the management and planning process of power distribution network, electric load system
Meter index, the volume of data such as voltage analysis statistical indicator can be provided for power distribution network Fa Ce department Power System Planning, design,
Scheduling provides the foundation of decision.The construction of the existing conventional electric power system information platform in the country mostly uses greatly expensive large-scale clothes
Business device, storage use disk array, and database uses relational database system, and service application is soft using the suit of close-coupled
Part, leads to that set expandability is poor, higher cost, it is difficult to adapt to smart grid to Condition Monitoring Data reliability and real-time
Requirements at the higher level.Hadoop Distributed Computing Platform publication in 2006,2009, Berkeley University proposed and has developed Spark meter
Calculate platform, on the basis of Hadoop distributed computing, introduce memory calculating, make data calculating speed obtain 10 times or even
100 times of promotion.Hadoop big data processing frame can be very good to solve data volume sharp increase bring bottleneck, and have good
Reliability and scalability, data processing amount it is big, real-time is high, the advantages such as low in cost.HDFS(Hadoop
Distribute File System) it is distributed file system on Hadoop.HDFS has the characteristics of high fault tolerance, adopts
Master/slave structure, and be used to design to be deployed on cheap hardware.It provides high-throughput to access data, is suitble to
The application program of those mass data.
Big data Technology application is not uncommon in the example that distribution network data is analyzed both at home and abroad, but is not had according to power supply
Unit carries out classification planning statistics to distribution network data, provides the platform area load statistical analysis index exhibition for having direct correlation with user
Show the precedent of service.
Summary of the invention
The technical problem to be solved by the present invention is proposing a kind of subregion peak load prediction based on MapReduce frame
Method provides load warning service for power supply company.
The technical solution adopted by the present invention to solve the technical problems is: a kind of subregion based on MapReduce frame is most
Big load forecasting method, comprising the following steps:
Step a: big data analysis platform is built；
Step b: data prediction is carried out to initial data；
Step c: distribution region is judged using crosspoint diagnostic method；
Step d: it seeks the area Gong Bianyutai of platform area and specially becomes the peak load in 1 year；
Step e: it is predicted respectively using the peak load that linear regression model (LRM) specially becomes the area Gong Bianyutai of platform area, platform area
Peak load is the sum of two predicted values.
Big data analysis platform building in step a is specific as follows:
1) using Linux Ubuntu as operating system；
2) initial data is stored in the distributed file system HDFS that Hadoop platform provides, realizes the discrete of data set
Change storage and inquiry；
3) data build the Hive component that table uses Hadoop to provide；
4) using Apache Hadoop as developing instrument, calculating task is scheduled, is completed on HQL sentence and cluster
The conversion of MapReduce operation；
5) distributed computing layer uses Apache Spark, data is carried out in the form of elasticity distribution formula data set parallel
Change operation.
In step b includes: to data prediction
1) empty data use Lagrange interpolation formula completion；
2) it is Key with distribution transforming ID and date, duplicate removal is carried out to data；
3) abnormal data in initial data and rejecting are found using 3 σ theorems in statistics.
In step c using crosspoint diagnostic method judge distribution transforming region the step of include:
1) map projection is carried out to distribution transforming coordinate and region apex coordinate；
2) straight line is done with the ordinate of distribution transforming to be measured, obtains each intersection point of the straight line and polygon；
3) number for calculating tested point both sides straight line and intersection point determines if tested point both sides number of hits is odd number
The distribution transforming is in for radio area；If it is not, determining the distribution transforming outside for radio area.
In step d to seek the peak load that the area Gong Bianyutai of platform area specially became in 1 year specific as follows:
1) area Gong Bianyutai of all areas of platform area is specially become and is summed by key value of sampled point, obtained comprising this area
The area Gong Bianyutai of current year any point-in-time platform area specially becomes the RDD of total load；
2) building Map function seeks the maximum value that 96, each day area Gong Bianyutai of the area sampled point Zhong Tai specially becomes total load, with
This first row as 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 the area Gong Bianyutai of platform area and specially becomes peak load.
The beneficial effects of the present invention are: the advantage that present invention utilizes Spark in terms of iterative calculation, with close with user
On the basis of the line of demarcation in relevant area, judgement is iterated according to crosspoint diagnostic method to the longitude and latitude of distribution transforming, is thus completed
To the region division of initial data.Data analysis task resolves into multiple lightweight tasks respectively in distribution by Map method
On each computer of system, the electric power index in region summarizes acquisition by result of the Reduce method to each computer.Using
The peak load that linear regression model (LRM) specially becomes the area Gong Bianhetai of platform area is predicted respectively.The present invention can quickly accurately from
History area peak load is calculated in data, and carries out peak load prediction as data basis, is power distribution network management, rule
It draws and data support is provided, be of great significance to power distribution network the safe and economic operation.
Detailed description of the invention
The following further describes the present invention with reference to the drawings.
Fig. 1 is the whole schematic diagram of the subregion peak load prediction technique of the invention based on MapReduce frame；
Fig. 2 is the architecture diagram of big data analysis platform of the invention；
Fig. 3 is that RDD operator parallelization handles to obtain the procedure chart of region load statistical indicator；
The calculation flow chart of the area Tu4Shi Tai peak load predicted value.
Specific embodiment
Presently in connection with attached drawing, the present invention is further illustrated.These attached drawings are simplified schematic diagram only with signal side
Formula illustrates basic structure of the invention, therefore it only shows the composition relevant to the invention.
As shown in Figure 1, a kind of subregion peak load prediction technique based on MapReduce frame, comprising the following steps:
Step a: big data analysis platform is built；
Step b: data prediction is carried out to initial data；
Step c: distribution region is judged using crosspoint diagnostic method；
Step d: it seeks the area Gong Bianyutai of platform area and specially becomes the peak load in 1 year；
Step e: it is predicted respectively using the peak load that linear regression model (LRM) specially becomes the area Gong Bianyutai of platform area, platform area
Peak load is the sum of two predicted values.
As shown in Fig. 2, the big data analysis platform building in step a is specific as follows:
1) using Linux Ubuntu as operating system；
2) initial data is stored in the distributed file system HDFS that Hadoop platform provides, realizes the discrete of data set
Change storage and inquiry；
3) data build the Hive component that table uses Hadoop to provide；
Such as: using EXTERNAL as keyword, data are carried out according to following format to load data and build table:
4) using Apache Hadoop as developing instrument, calculating task is scheduled, is completed on HQL sentence and cluster
The conversion of MapReduce operation；
5) distributed computing layer uses Apache Spark, data is carried out in the form of elasticity distribution formula data set parallel
Change operation.
It will include that load data, date, distribution transforming name, the data of distribution transforming coordinate are deposited in distributed file system, lead to
The Hive component for crossing Hadoop constructs external table to electric load initial data, access, inquiry for distributed computing layer.Point
Cloth computation layer carries out parallelization calculating using Apache Spark.
In step b includes: to data prediction
1) empty data use Lagrange interpolation formula completion；
2) it is Key with distribution transforming ID and date, duplicate removal is carried out to data；
3) abnormal data in initial data and rejecting are found using 3 σ theorems in statistics.
To with adopt sky data, repeated data existing for data, out-of-limit data are handled: to the main processing side of empty data
Formula is to be cut with map mode to data set in Spark platform, and condition judges whether data field is sky, if certain field
For sky, then the row data are deleted.Main processing ways to repeated data are to identify ID and criterion characterized by the date by distribution transforming,
Data with identical key-value are merged, statistical result is not 1, then deletes in original data set and repeat to go.It is right
The main processing ways of out-of-limit data remove abnormal data, the i.e. residual error of calculated load data, standard deviation using 3 σ criterion, reject
Residual error is greater than the data of 3 times of single measurement standard deviations.
It, can be according to after carrying out pretreatment cleaning to data: serial number: bigint, data guiding system: string, route:
String, mark: string, position: string, address: string, the date: string, total hits: int, sampled point 0:
The structure of double ... ..., sampled point 95:double carry out data to load data and build table.
In step c using crosspoint diagnostic method judge distribution transforming region the step of include:
1) map projection is carried out to distribution transforming coordinate and region apex coordinate；
2) straight line is done with the ordinate of distribution transforming to be measured, obtains each intersection point of the straight line and polygon；
3) number for calculating tested point both sides straight line and intersection point determines if tested point both sides number of hits is odd number
The distribution transforming is in for radio area；If it is not, determining the distribution transforming outside for radio area.
In step d to seek the peak load that the area Gong Bianyutai of platform area specially became in 1 year specific as follows:
1) area Gong Bianyutai of all areas of platform area is specially become and is summed by key value of sampled point, obtained comprising this area
The area Gong Bianyutai of current year any point-in-time platform area specially becomes the RDD of total load；
2) building Map function seeks the maximum value that 96, each day area Gong Bianyutai of the area sampled point Zhong Tai specially becomes total load, with
This first row as 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 the area Gong Bianyutai of platform area and specially becomes peak load.
As shown in figure 3, the external table of foundation, which is read in Spark platform, becomes distributed elastic data set (RDD), bullet
Property data set owner will by convert and operate two ways processing: conversion mainly by original RDD by centainly operation formed one
A new RDD is counted on the basis of the boundary Tai Qu according to intersection according to the distribution transforming longitude and latitude for including in Power system load data RDD
Diagnostic method carries out filter division to each distribution transforming；Operation mainly counts the structure of element or RDD itself in RDD
It calculates, obtains a determining data, pass through agg method to according to for the good public change of radio station Division, special parameter evidence with collection point
Public affairs change, special parameter are become under available each section for radio area public affairs, the special varying duty in platform area according to read group total is carried out for key value
The sum of RDD.Building Map function seeks the maximum value that 96, each day sampled point Zhong Tai area's public affairs become/specially become total load, in this, as
The first row of new RDD.The Reduce function of building is to compare to be maximized two-by-two, is iterated for the first row to new RDD,
Platform area peak load is obtained with this.
As shown in figure 4, the step of being predicted using linear regression model (LRM) for radio area peak load is as follows:
1) the history peak load of this area public affairs change is found out；
2) it is worth characterized by the time, linear regression is carried out according to the following formula to history peak load:
loadmax(y)=α0+α1y
3) same processing mode is used to the history peak load that platform area specially becomes, platform area peak load predicted value is public affairs
Become predicted value and specially become the sum of predicted value:
loadmax_pre=loadcommon_pre+loadSpecial_pre
The subregion peak load prediction technique based on MapReduce frame that the invention proposes a kind of, mainly there is big data
Analysis platform is built, initial data pre-processes, load data subregion, history peak load are sought, linear regression prediction.Big data
Analysis platform is mainly made of distributed storage layer and distributed computing layer.Distributed storage layer is literary using the distribution of Hadoop
Part system HDFS, data build the Hive component that table uses Hadoop；Distributed computing layer use Apache Spark, by data with
Form conversion, the operation of distributed elastic data set RDD.It is excellent in terms of iterative calculation that Spark is cleverly utilized in the present invention
Gesture changes to the longitude and latitude of distribution transforming according to crosspoint diagnostic method on the basis of the line of demarcation in the platform area closely related with user
Generation judgement, thus completes the region division to initial data.The calculating core of history peak load is MapReduce, data point
Analysis task resolves into multiple lightweight tasks respectively on each computer of distributed system by Map method, the electricity in region
Power index summarizes acquisition by result of the Reduce method to each computer.Using linear regression model (LRM) to the area Gong Bianhetai of platform area
The peak load specially become is predicted respectively.It is negative that the present invention can quickly accurately calculate history area maximum from data
Lotus, and peak load prediction is carried out as data basis, data are provided and are supported for power distribution network management, planning, power distribution network is pacified
Full economical operation is of great significance.
For the present invention as unit of the platform area of power distribution network least significant end, peak load prediction result is directly related with user.This hair
It is bright that memory is made full use of to calculate the fast advantage of iteration speed, the method for the region division of elasticity distribution formula data set is used and is intersected
Point diagnostic method, is iterated the longitude and latitude in each data, can quickly obtain the division result of switching data.The present invention
The distributed storage Computational frame scalability built is fine, i.e., the calculated performance of system can be kept with the increase of number of nodes
Close to linear growth, when the electric load real time data source of acquisition increases, it can guarantee big data by increasing node
Calculating speed and response efficiency.
The advantage in terms of Spark iteration is cleverly utilized in the present invention, carries out platform Division to Power system load data.Using
The conversion of Spark and operating method carry out parallelization calculating to data, have many advantages, such as that calculating speed is fast, and data accuracy is high,
The big data for being power distribution network from now on as unit of power supply zone processing, analysis provide technology path.
Magnanimity Power system load data can be carried out fast and accurately calculating in real time using the present invention.It is calculated by big data
Data mechanism MapReduce huge to power grid carry out parallelization calculating, finally extract the platform area being directly linked with user and refer to
Mark, and predicted as data basis, the data basis of science is provided for management, the planning of power distribution network.The distribution of use
Formula file system has good scalability, it is ensured that when data volume increases, the arithmetic speed of system will not change.This hair
The bright raising to power grid hair plan department efficiency is of great significance.
Claims (5)
1. a kind of subregion peak load prediction technique based on MapReduce frame, which comprises the following steps:
Step a: big data analysis platform is built；
Step b: data prediction is carried out to initial data；
Step c: distribution region is judged using crosspoint diagnostic method；
Step d: it seeks the area Gong Bianyutai of platform area and specially becomes the peak load in 1 year；
Step e: being predicted respectively using the peak load that linear regression model (LRM) specially becomes the area Gong Bianyutai of platform area, and platform area is maximum
Load is the sum of two predicted values.
2. the subregion peak load prediction technique according to claim 1 based on MapReduce frame, which is characterized in that
Big data analysis platform building in step a is specific as follows:
1) using Linux Ubuntu as operating system；
2) initial data is stored in the distributed file system HDFS that Hadoop platform provides, realizes that the discretization of data set is deposited
Storage and inquiry；
3) data build the Hive component that table uses Hadoop to provide；
4) using Apache Hadoop as developing instrument, calculating task is scheduled, is completed on HQL sentence and cluster
The conversion of MapReduce operation；
5) distributed computing layer uses Apache Spark, and data are carried out parallelization behaviour in the form of elasticity distribution formula data set
Make.
3. the subregion peak load prediction technique according to claim 1 based on MapReduce frame, which is characterized in that
In step b includes: to data prediction
1) empty data use Lagrange interpolation formula completion；
2) it is Key with distribution transforming ID and date, duplicate removal is carried out to data；
3) abnormal data in initial data and rejecting are found using 3 σ theorems in statistics.
4. the subregion peak load prediction technique according to claim 1 based on MapReduce frame, which is characterized in that
In step c using crosspoint diagnostic method judge distribution transforming region the step of include:
1) map projection is carried out to distribution transforming coordinate and region apex coordinate；
2) straight line is done with the ordinate of distribution transforming to be measured, obtains each intersection point of the straight line and polygon；
3) number for calculating tested point both sides straight line and intersection point determines that this is matched if tested point both sides number of hits is odd number
Become in for radio area；If it is not, determining the distribution transforming outside for radio area.
5. the subregion peak load prediction technique according to claim 1 based on MapReduce frame, which is characterized in that
In step d to seek the peak load that the area Gong Bianyutai of platform area specially became in 1 year specific as follows:
1) area Gong Bianyutai of all areas of platform area is specially become and is summed by key value of sampled point, obtained comprising this area current year
The area Gong Bianyutai of any point-in-time platform area specially becomes the RDD of total load；
2) building Map function seeks the maximum value that 96, each day area Gong Bianyutai of the area sampled point Zhong Tai specially becomes total load, is made with this
For 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, is obtained with this
The area Gong Bianyutai of platform area specially becomes peak load.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810567569.4A CN109242132A (en) | 2018-06-05 | 2018-06-05 | Subregion peak load prediction technique based on MapReduce frame |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810567569.4A CN109242132A (en) | 2018-06-05 | 2018-06-05 | Subregion peak load prediction technique based on MapReduce frame |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109242132A true CN109242132A (en) | 2019-01-18 |
Family
ID=65083787
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810567569.4A Withdrawn CN109242132A (en) | 2018-06-05 | 2018-06-05 | Subregion peak load prediction technique based on MapReduce frame |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109242132A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111949940A (en) * | 2020-06-28 | 2020-11-17 | 佰聆数据股份有限公司 | Transformer overload prediction method, system and storage medium for transformer area based on regression model |
| 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 (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104751255A (en) * | 2015-04-23 | 2015-07-01 | 国家电网公司 | Distribution unit-area maximum load forecasting method |
| 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
- 2018-06-05 CN CN201810567569.4A patent/CN109242132A/en not_active Withdrawn
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104751255A (en) * | 2015-04-23 | 2015-07-01 | 国家电网公司 | Distribution unit-area maximum load forecasting method |
| 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 (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111949940A (en) * | 2020-06-28 | 2020-11-17 | 佰聆数据股份有限公司 | Transformer overload prediction method, system and storage medium for transformer area based on regression model |
| CN111949940B (en) * | 2020-06-28 | 2021-08-13 | 佰聆数据股份有限公司 | Transformer overload prediction method, system and storage medium for transformer area based on regression model |
| 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 |
|---|---|---|
| Wang et al. | Time-dependent graphs: Definitions, applications, and algorithms | |
| CN105069703B (en) | A kind of electrical network mass data management method | |
| CN107402976B (en) | Power grid multi-source data fusion method and system based on multi-element heterogeneous model | |
| CN107832876A (en) | Subregion peak load Forecasting Methodology based on MapReduce frameworks | |
| CN108446293A (en) | A method of based on urban multi-source isomeric data structure city portrait | |
| CN109286188B (en) | 10kV power distribution network theoretical line loss calculation method based on multi-source data set | |
| CN105678398A (en) | Power load forecasting method based on big data technology, and research and application system based on method | |
| CN109376924A (en) | A kind of method, apparatus, equipment and the readable storage medium storing program for executing of material requirements prediction | |
| Liu et al. | Real-time complex event processing and analytics for smart grid | |
| AU2022204116A1 (en) | Verification method for electrical grid measurement data | |
| CN108876019A (en) | A kind of electro-load forecast method and system based on big data | |
| CN107590749A (en) | A kind of processing method and system with electricity consumption data | |
| CN115423429A (en) | Multimode integrated distribution network operation system based on image and sound information | |
| CN107807961A (en) | A kind of power distribution network big data multidomain treat-ment method based on Spark computing engines | |
| CN109977125A (en) | A kind of big data safety analysis plateform system based on network security | |
| Dong et al. | Forecasting smart meter energy usage using distributed systems and machine learning | |
| CN114327964A (en) | Method, device, equipment and storage medium for processing fault reasons of service system | |
| CN114969263A (en) | Construction method, construction device and application of urban traffic knowledge map | |
| Ho et al. | Amic: An adaptive information theoretic method to identify multi-scale temporal correlations in big time series data | |
| CN107862459B (en) | Metering equipment state evaluation method and system based on big data | |
| CN109242132A (en) | Subregion peak load prediction technique based on MapReduce frame | |
| Lee et al. | A big data management system for energy consumption prediction models | |
| CN117453937B (en) | Automatic generation method and device for power grid graph data model | |
| CN113326343A (en) | Road network data storage method and system based on multi-level grids and file indexes | |
| CN118473086A (en) | Automatic low-voltage power distribution fault monitoring method and system based on Internet of things |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190118 |