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

Short-term power consumption prediction method based on Spark

A forecasting method and power technology, applied in forecasting, electrical digital data processing, special data processing applications, etc., can solve problems such as inability to achieve efficient training, lack of computing resources, etc., to improve forecasting accuracy, reduce cross-influence, and increase mass The effect of data capabilities

Active Publication Date: 2019-07-12
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Under the massive data, the stand-alone environment cannot achieve efficient training due to the lack of computing resources. Therefore, it is necessary to realize the processing of large-scale training data through computer clusters.

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
  • Short-term power consumption prediction method based on Spark
  • Short-term power consumption prediction method based on Spark
  • Short-term power consumption prediction method based on Spark

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The technical scheme of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0022] like figure 1 As shown, it is the flow chart of the training and prediction stage of the present invention, in which, except for the high efficiency of STL time series decomposition and no parallelization, the rest of the steps are all parallelized through the Spark distributed computing framework.

[0023] In the model training phase, historical power consumption data and weather data are used

[0024] The first step: power consumption data preprocessing and feature engineering processing, wherein the preprocessing includes a) missing data processing, which is completed by the adjacent number average method; b) outlier processing, which is judged by the standard deviation method, and then the same The way of missing data processing; c) noise reduction, which is done by moving average method. The feature engineering processing of feat...

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 discloses a short-term power consumption prediction method based on Spark. The method is mainly characterized by comprising the following steps: according to historical power energy consumption data and weather information, the STL time sequence decomposition and the support vector regression are used for predicting the power energy consumption use condition in the future short term;a Spark distributed computing framework is used for accelerating model training under mass power consumption data, so that the mass data processing capacity of the model is improved, meanwhile, due to the fact that an STL time sequence decomposition algorithm is used, the cross influence among components is reduced, and the prediction precision of the model is improved.

Description

technical field [0001] The invention relates to a short-term power consumption forecasting method based on Spark. Background technique [0002] At present, energy saving and emission reduction has become an important measure to achieve sustainable development in my country. However, as the main carrier of the application of energy saving and emission reduction technologies, some universities and parks have extensive statistics on energy consumption data. There is no scientific energy consumption supervision and prediction, and they cannot rely on history. Energy consumption data assist management, improve the system and formulate corresponding energy-saving strategies. The reason is the lack of effective supervision of energy consumption data, and theoretically, the lack of research on energy consumption models. The analysis and prediction of power consumption can effectively help tap the energy-saving potential and promote the optimization of energy use in the park. [000...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/50G06Q10/04G06Q50/06
CPCG06Q10/04G06Q50/06G06F30/20
Inventor 姜书艳赵云鹏左志宏
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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