A Monthly Power Consumption Prediction Method Using Temperature Data Abnormal Point Compensation

A technology of data anomalies and prediction methods, applied in data processing applications, prediction, kernel methods, etc., can solve problems such as low precision, achieve the effect of overcoming low precision and improving the overall prediction accuracy

Active Publication Date: 2022-04-15
STATE GRID SHAANXI ELECTRIC POWER RES INST +3
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a monthly power consumption prediction method using temperature data abnormal point compensation to solve the technical problem that the current traditional monthly power consumption prediction method is not accurate

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
  • A Monthly Power Consumption Prediction Method Using Temperature Data Abnormal Point Compensation
  • A Monthly Power Consumption Prediction Method Using Temperature Data Abnormal Point Compensation
  • A Monthly Power Consumption Prediction Method Using Temperature Data Abnormal Point Compensation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0081] see Figure 1 to Figure 6 , a monthly power consumption prediction method using temperature data abnormal point compensation according to an embodiment of the present invention, comprising the following steps:

[0082] Step 1: Analysis of daily electricity consumption and daily average temperature.

[0083] Based on the robust least squares method, with daily average temperature as the independent variable and daily electricity consumption as the dependent variable, a polynomial regression model is established to explore the relationship between temperature and electricity.

[0084] Select the polynomial regression order p to establish a regression model, the expression is:

[0085]

[0086] Estimation of regression coefficient a by robust least squares method i , the fitting value l′ of daily electricity consumption can be obtained.

[0087] Step 2: Calculate the threshold temperature for temperature data abnormal point compensation.

[0088] The order of the po...

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 monthly power consumption prediction method using temperature data abnormal point compensation, which includes: collecting and obtaining the original time series data of daily power consumption and daily average temperature of the place to be predicted; obtaining daily average temperature-daily power consumption A robust polynomial regression is used for the daily average temperature-daily power consumption series; the temperature corresponding to the lowest daily power consumption is selected as the threshold temperature T for distinguishing high temperature from low temperature * ;according to the threshold temperature T * , calculate the monthly heating coefficient MHDD and monthly cooling coefficient MCDD of each month; carry out the seasonal decomposition of the additive model on the daily electricity consumption, and decompose it into three parts: long-term trend and cycle component, seasonal component and irregular component; among them, the irregular component adopts MHDD and MCDD parameters to compensate the abnormal points of temperature data to predict the irregular components in the power consumption time series. The invention can solve the technical problem that the accuracy of the current traditional monthly power consumption prediction method is not high.

Description

technical field [0001] The invention belongs to the technical field of power system load forecasting, in particular to a monthly electricity consumption forecasting method using temperature data abnormal point compensation. Background technique [0002] Power system load forecasting has an important impact on power system planning and design, power system operation, power market and other aspects, and is an important research direction in modern power systems. In terms of power system planning, if the load forecast result is too high, the installed capacity of the system will be too large, and many devices cannot fully play their roles in actual operation, resulting in economic losses and investment waste; if the load forecast result is too low, In actual operation, the installed capacity of the system and insufficient power backup will affect the safe and reliable operation of the power system. For power system dispatching and operation, the results of load forecasting can...

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 Patents(China)
IPC IPC(8): G06Q10/04G06Q50/06G06N20/10G06N7/00
CPCG06Q10/04G06Q50/06G06N20/10G06N7/01
Inventor 王楷彭书涛邓俊张艳丽万青贺瀚青张青蕾李俊臣刘俊赵宏炎刘嘉诚潘良军李英奇仇继扬王芝麟
Owner STATE GRID SHAANXI ELECTRIC POWER RES INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap