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

A Method of Monthly Power Load Computer Forecasting Based on Wavelet Analysis

A technology of electric load and wavelet analysis, applied in forecasting, calculation, instrumentation, etc., can solve the problems that cannot reflect the growth trend of the load curve well

Active Publication Date: 2016-08-24
STATE GRID FUJIAN ELECTRIC POWER CO LTD +3
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the method of using regression model and artificial neural network can reflect the seasonal fluctuation characteristics of the load curve, but it cannot reflect the year-by-year growth trend of the load curve.

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 Method of Monthly Power Load Computer Forecasting Based on Wavelet Analysis
  • A Method of Monthly Power Load Computer Forecasting Based on Wavelet Analysis
  • A Method of Monthly Power Load Computer Forecasting Based on Wavelet Analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] refer to figure 1 with figure 2 , the monthly power load forecasting method based on wavelet analysis of the present invention, comprises input module 1, wavelet transformation module 2, first type prediction module 3,4,5,6, second type prediction module 7, wavelet reconstruction module 8, Output module 9. Input module 1 receives historical load data c 0 , and the historical data c 0 Send to wavelet transform module 2; wavelet transform module 2 decomposes the historical data, and decomposes into d 1 、d 2 、d 3 、d 4 、c 4 five components, where d 1 -d 4 Characterized by annual cyclical changes, c 4 With a growing trend of change; the first type of forecasting modules 3, 4, 5, 6 for d 1 -d 4 These four components are predicted; the second type of prediction module 7 pairs c 4 The component is predicted; the wavelet reconstruction module 8 performs wavelet reconstruction on each component after prediction, and obtains the predicted load c 0 '; Finally, the pr...

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 electrical load computer forecasting method based on wavelet analysis. The monthly electrical load computer forecasting method comprises an input module, a wavelet conversion module, a first kind forecasting module, a second kind forecasting module, a wavelet reconstruction module and an output module, wherein the input module receives historical load data c0, and transmits the historical data c0 to the wavelet conversion module, the wavelet conversion module conducts decomposition for the historical data, the historical data is sequentially decomposed to five components including d1, d2, d3, d4 and d5, the d1, the d2, the d3 and the d4 have annual cyclical change characteristics, c4 has ever-increasing variation tendency, the first class forecasting module forecasts four components of the d1, the d2, the d3 and the d4, and the second class forecasting module forecasts a c4 component. The wavelet conversion module conducts wavelet reconstruction for the components after forecasted, forecasting load c0'is obtained, and finally, the forecasting load is displayed through the output module.

Description

technical field [0001] The invention relates to a power load forecasting method, in particular to a monthly power load computer forecasting method based on wavelet analysis. Background technique [0002] Load forecasting is the basis for power system development planning, fuel planning, and power generation planning. The monthly forecast takes the month as the forecast period and the monthly power consumption as the forecast content. Through the monthly load forecasting technology, the medium-term operation plan of the power system can be reasonably arranged, the operation cost can be reduced, and the reliability of power supply can be improved. [0003] The change law of monthly load in each year has annual periodicity. When forecasting monthly load, it is necessary to take into account the annual periodicity of monthly load, make full use of the latest monthly data, and use the latest change law to forecast the future. The predicted impact is clearly reflected. Since th...

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): G06Q10/04G06Q50/06
Inventor 易弢林扬宇陈彬高丙团包宇庆
Owner STATE GRID FUJIAN ELECTRIC POWER CO LTD
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