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

Improved wavelet-analysis-based short-term power load prediction method

A technology of short-term power load and forecasting method, applied in forecasting, instrumentation, data processing applications, etc., can solve the problem of inability to accurately predict short-term power load, etc., to improve the level of load forecasting technology, save fuel and power generation costs, and improve economic benefits. and social benefits

Inactive Publication Date: 2017-03-15
STATE GRID CORP OF CHINA +2
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention proposes an improved short-term power load forecasting method based on wavelet analysis in order to solve the problem that the prior art cannot accurately predict the short-term power load

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
  • Improved wavelet-analysis-based short-term power load prediction method
  • Improved wavelet-analysis-based short-term power load prediction method
  • Improved wavelet-analysis-based short-term power load prediction method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0020] Specific implementation mode one: as figure 1 As shown, a short-term power load forecasting method based on wavelet analysis includes the following steps:

[0021] Step 1: Preprocessing the sample data;

[0022] Step 2: Select sample data;

[0023] Step 3: Normalize the sample data selected in Step 2;

[0024] Step 4: Establishing a wavelet regression analysis prediction model;

[0025] Step 5: Analysis and correction of forecast results.

specific Embodiment approach 2

[0026] Embodiment 2: The difference between this embodiment and Embodiment 1 is that the specific process of preprocessing the sample data in Step 1 is as follows:

[0027] Before using these sample data, process it, remove irregular data and fill in missing data, eliminate the influence of bad data or bad data, further data preprocessing can also reduce short-term power load intelligent forecasting method research and reduce input vector capacity , to avoid problems due to increased sample size and irregularities in the data;

[0028] Process the sample data, remove irregular data and fill in missing data. The change law of power system load data is expressed as:

[0029]

[0030] where Y is the true value of the load, is the observed value, V is the comprehensive action value of noise and random interference; let the mean value of V be Variance is σ 2 ; Select the threshold θ, when the observed value When the error value with the load true value Y is greater than θ...

specific Embodiment approach 3

[0032] Specific implementation mode three: the difference between this implementation mode and specific implementation mode one or two is: the specific process of selecting sample data in said step two is:

[0033] Use historical load data of similar days as historical load samples for forecasting. Therefore, the key to selecting historical load samples is the selection of similar days. The selection of similar days has a direct impact on the prediction accuracy. A similar day selection algorithm based on correlation factor mapping is adopted.

[0034] A similar day selection algorithm based on correlation factor mapping is adopted, which is divided into the following two parts:

[0035] (1) Calculation of the characteristic quantities of related factors between different days:

[0036] Introduce the quantitative index vector of each day, X i =[x i1 ,x i2 ,...,x im ], is the value of all feature quantities on the i-th day, assuming that there are m feature quantities in...

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

Disclosed in the invention is an improved wavelet-analysis-based short-term power load prediction method. The invention relates to a wavelet-analysis-based short-term power load prediction method. With the method, a problem that the short-term power load can not be predicted accurately in the prior art can be solved. The method comprises the following steps: step one, selecting sample data; step two, carrying out pseudo-data monitoring on the selected sample data and correcting the pseudo-data; and step three, determining a sample set and carrying out normalization. Therefore, smooth and accurate sample data can be obtained and association with a predicted point load is high; and prediction becomes accurate and a prediction error is small. The load prediction technical level is improved reasonably; the planned electricity management can be realized well; the grid operation way and the generator set overhaul plan can be arranged reasonably; the coal and oil can be saved and the generating cost is lowered; the reasonable power supply building plan is formulated reasonably in real time; and the economic and social benefits of the power supply increase. The method provided by the invention is applied to the power load prediction field.

Description

technical field [0001] The invention relates to a short-term power load forecasting method based on wavelet analysis. Background technique [0002] Power system load forecasting is based on certain historical data of electric load, researches the impact of historical data of electric load on future load, finds out the internal and external relations between electric load and various related factors, and then predicts the future electric load. Scientifically sound predictions. Short-term load forecasting is one of the important components of power load forecasting. Usually, the daily load curve is used as the forecasting object. It is the basis for formulating the day-ahead power generation plan, which is of great significance to the optimal combination of units, economic dispatch, and power market regulation. . [0003] At present, short-term power load forecasting has become one of the important tasks of the power sector. Reasonably improving the technical level of load ...

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): G06Q10/04G06Q50/06
CPCG06Q10/04G06Q50/06Y04S10/50
Inventor 陈洪涛吴刚单小东孟祥辰陈艳孙振胜张海明李伟李军韩显华李冬梅黄树春赵强李一凡韩兆婷
Owner STATE GRID CORP 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