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

Ultra-short-term load prediction method and system considering data loss and feature redundancy

A load forecasting and data missing technology, applied in forecasting, data processing applications, character and pattern recognition, etc., can solve problems affecting the accuracy of ultra-short-term load forecasting, achieve fairness and breadth, avoid input sequences and output sequences Length limitation, the effect of fast convergence speed

Active Publication Date: 2021-02-09
STATE GRID SICHUAN ECONOMIC RES INST
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is that the existing research on ultra-short-term load forecasting seldom considers data loss and feature redundancy of multivariate time-series data, which directly affects the accuracy of ultra-short-term load forecasting. The purpose is to provide a method that considers data loss and The ultra-short-term load forecasting method and system with feature redundancy solves the problem of how to improve the accuracy of ultra-short-term load forecasting

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
  • Ultra-short-term load prediction method and system considering data loss and feature redundancy
  • Ultra-short-term load prediction method and system considering data loss and feature redundancy
  • Ultra-short-term load prediction method and system considering data loss and feature redundancy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025]This embodiment 1 provides an ultra-short-term load forecasting method that considers the lack of time series data and feature redundancy for the lack of data and feature redundancy of multivariate time series data, as well as the low accuracy of existing deep learning load forecasting models. , firstly, by improving the K-Nearest Neighbor (KNN) missing data completion algorithm to process the data sets with missing data; secondly, through the package feature selection method based on the maximum information coefficient (MIC) to obtain super The optimal feature set for short-term load forecasting reduces the feature redundancy of multivariate time-series data; finally, the sequence-to-sequence time-series data processing model improves the model's ability to process time-series information, thereby improving the accuracy of ultra-short-term load forecasting.

[0026] Such as figure 1 As shown, firstly, the data set with missing data problem is processed by improving the ...

Embodiment 2

[0065] In this embodiment 2, on the basis of the embodiment 1, relevant experiments are carried out on the "Individual household electric power consumption Data Set" data set in the UCI database. This data set is a multi-feature time series data set, which describes the electricity consumption information collected by a user from December 2006 to November 2010. The sampling frequency is 1min / time, and the data missing ratio is 1.25%. The present invention The experiment selects the electricity consumption information of 48 collection points every day, and the data contains a total of eight characteristic variables, which are:

[0066] global_active_power: the total active power consumption of the household (kWh);

[0067] global_reactive_power: total household reactive power consumption (kWh);

[0068] voltage: voltage strength (volts);

[0069] global_intensity: current intensity (ampere);

[0070] sub_metering_1: Active energy consumption of the kitchen (Wh);

[0071] su...

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 an ultra-short-term load prediction method and system considering data missing and feature redundancy, and the method comprises the steps of carrying out the processing of a data set with a data missing problem through a missing data completion algorithm based on an improved KNN; obtaining an optimal feature set of ultra-short-term load prediction through a package type feature selection method based on a maximum information coefficient MIC, and reducing the feature redundancy of multivariable time series data; adopting an S2SGRU ultra-short-term load prediction model,performing load prediction from sequence to sequence, improving the processing capacity of time sequence information, and therefore the precision of ultra-short-term load prediction is improved. According to the invention, the morphological similarity of the load data is considered, the optimal feature set can be effectively screened out, and the precision of ultra-short-term load prediction is improved. An S2SGRU ultra-short-term load prediction model is adopted to perform load prediction through sequences, so that the prediction capability of the algorithm on a long-time sequence model is further improved, and the limitation of the lengths of an input sequence and an output sequence in a traditional load prediction task is avoided.

Description

technical field [0001] The invention relates to the field of power data processing, in particular to an ultra-short-term load forecasting method and system considering data loss and feature redundancy. Background technique [0002] Accurate ultra-short-term load forecasting is an important basis for real-time power market operation and refined development of auxiliary services. With the advancement of electric power informatization and the development of smart meters and advanced measurement technology systems, electricity consumption information is characterized by massive quantities and diversification. At present, in addition to power load data, electricity consumption information also includes multiple heterogeneous data such as voltage, current, and energy consumption of various electrical appliances. In the context of more complex power big data, it is of great significance to effectively use multiple heterogeneous power consumption information for accurate ultra-shor...

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): G06N3/04G06K9/62G06Q10/04G06Q50/06
CPCG06N3/049G06Q10/04G06Q50/06G06N3/044G06F18/24143G06F18/214Y04S10/50
Inventor 任志超叶强马瑞光程超王海燕胥威汀汪伟徐浩
Owner STATE GRID SICHUAN ECONOMIC RES INST
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