Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Partition maximum load prediction method based on MapReduce framework

A mapreduce framework and maximum load technology, applied in forecasting, instrumentation, data processing applications, etc., can solve problems such as stagnant distribution network data, achieve good scalability, fast and accurate real-time calculations, and improve work efficiency

Active Publication Date: 2018-03-23
STATE GRID JIANGSU ELECTRIC POWER CO LTD NANTONG POWER SUPPLY BRANCH
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] It is not uncommon to apply big data technology to distribution network data analysis at home and abroad, but the current use of this framework is only limited to the clustering prediction of distribution network data, and there is no analysis of distribution network data according to the power supply unit. Carry out classified planning and statistics, and provide a precedent for the display service of station area load statistics and analysis indicators that are directly related to users

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Partition maximum load prediction method based on MapReduce framework
  • Partition maximum load prediction method based on MapReduce framework
  • Partition maximum load prediction method based on MapReduce framework

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention will be described in detail below in conjunction with the accompanying drawings.

[0042] 1, the present invention takes figure 1 The layered structure builds a distributed system development platform, stores the data including load data, date, distribution variable name, and distribution variable coordinates in the distributed file system, and constructs an external table for the original data of the electric load through the Hive component of Hadoop. For the access and query of the distributed computing layer. The distributed computing layer uses Apache Spark for parallel computing.

[0043] 2. Before the data table is built, process the empty data, repeated data, and out-of-limit data in the used data: the main processing method for the empty data is to use the map method to cut the data set in the Spark platform, and the condition Determine whether the data field is empty. If a field is empty, delete the row of data; the main processing meth...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a partition maximum load prediction method based on the MapReduce framework. The method mainly comprises steps of big data platform establishment, original data cleaning, load data partition, historical maximum load calculation and linear regression prediction. The big data real-time processing platform mainly comprises a distributed storage layer and a distributed calculation layer, wherein the distributed storage layer employs a Hadoop distributed file system (HDFS), data table construction employs a Hadoop Hive assembly, the distributed calculation layer employs Apache Spark to convert and operate the data in the form of distributed elastic data sets. The method is advantaged in that the historical maximum region load from the data can be calculated rapidly and accurately, maximum load prediction is carried out on the data basis, data support is provided for power distribution network management and planning, and the method is of great importance to safe and economical operation of the power distribution network.

Description

technical field [0001] The present invention relates to the use of computer technology to process the big data of the distribution network, aiming to extract the maximum load value of the distribution network that has practical value for the planning and management of the distribution network from the massive distribution network data, and use it as the data Based on load forecasting, it belongs to the field of distribution network big data mining and analysis. Background technique [0002] With the State Grid Corporation's strategic goal of building a strong power grid, the number of smart power consumption terminals and collection terminals is increasing day by day, which makes various types of power automation data grow geometrically, showing "large volume" and "multiple types". , "low density" and "fast growth" typical big data characteristics. In the process of distribution network management and planning, a series of data such as power load statistical indicators and ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06Q10/04G06Q50/06
CPCG06Q10/04G06Q50/06
Inventor 周嘉
Owner STATE GRID JIANGSU ELECTRIC POWER CO LTD NANTONG POWER SUPPLY BRANCH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com