Unlock instant, AI-driven research and patent intelligence for your innovation.

Household power load prediction method and system

A technology of electric load and prediction method, applied in the field of household electric load prediction method and system, can solve the problems of low accuracy, large fluctuation of household-level load, deviation, etc., and achieve the effect of improving accuracy

Inactive Publication Date: 2020-04-28
BEIJING GUODIANTONG NETWORK TECH CO LTD +1
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, due to large load fluctuations at the household level, the future household power load of the time series analysis method often produces large deviations, and the accuracy is low

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
  • Household power load prediction method and system
  • Household power load prediction method and system
  • Household power load prediction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0062] As an implementation manner, the basic household electric load data includes single household load data in a certain area, daily maximum temperature and daily minimum temperature in this area, and holiday data.

[0063] The inventors have found in practice that both weather conditions and holidays will have a certain impact on household power loads, and including the above data in the basic data can improve the prediction accuracy.

[0064] As an implementation manner, before dividing the household electric load basic data into a training set, a verification set and a test set, it also includes:

[0065] Preprocessing the basic household electric load data, including but not limited to: normalizing the basic household electric load data; performing mean interpolation for missing values ​​in the basic household electric load data; clearing redundant data; The household electric load basic data is formed into an input vector sequence in chronological order.

[0066] Sinc...

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 household power load prediction method and system. Household power load basic data is obtained; and performing pretreatment, constructing data sets, constructing an adaptiveconvolutional neural network model; dividing the data set into a training set, a verification set and a test set, repeatedly training through a training set and finely adjusting a verification set anda test set; according to the method, the finally determined adaptive convolutional neural network model is obtained, and the home power load in the future unit time at any moment is predicted by inputting the home load basic data into the finally determined adaptive convolutional neural network model, so that the home load prediction precision can be effectively improved.

Description

technical field [0001] The present invention relates to the field, in particular to a household power load forecasting method and system. Background technique [0002] With the popularity of smart meters, a large amount of fine-grained electricity consumption data is collected, which makes load forecasting at the household level possible. Compared with the total load of the country and region, the household user load forecast has non-stationarity and randomness. In response to this problem, various new electric load forecasting techniques have been proposed in the past few years. Due to the uncertainty of user behavior and the nonlinearity of external factors, household-level load forecasting has become one of the most challenging tasks faced by power market entities; [0003] Researchers have proposed different short-term load forecasting methods, using historical load data and weather data as input to predict the overall system load, usually using time series analysis me...

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): G06Q50/06G06Q10/04G06N3/04G06N3/08
CPCG06Q50/06G06Q10/04G06N3/08G06N3/045
Inventor 唐新忠刘兰方李天杰王艳如刘海峰刘宗李迪吴晓江孙胜宇刘冲
Owner BEIJING GUODIANTONG NETWORK TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com