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

Short-term load predicting method based on quick fuzzy rough set

A short-term load forecasting and fuzzy rough set technology, applied in the field of electric power information, can solve the problems of long time required for attribute reduction and large amount of calculation

Active Publication Date: 2014-12-24
ZHEJIANG UNIV
View PDF2 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In recent years, people have used the fuzzy rough set method to obtain the input parameters of neural network load forecasting, which has improved the prediction accuracy, but the fuzzy rough set method has a large amount of calculation and takes a long time for attribute reduction.

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
  • Short-term load predicting method based on quick fuzzy rough set
  • Short-term load predicting method based on quick fuzzy rough set
  • Short-term load predicting method based on quick fuzzy rough set

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0176] After attribute reduction using the fuzzy rough set method above, 8 conditional attributes with the same classification ability as the original data set can be obtained, namely the maximum temperature on the forecast day, the maximum load 7 days before the forecast date, and the maximum load 1 day before the forecast date. load, the maximum load of the 3 days before the forecast date, the average relative humidity of the 2 days before the forecast date, the date type of the forecast day, the date type of the 2 days before the forecast date and the average relative humidity of the 5 days before the forecast date; Table 2 gives the 8 Attribute importance for reduced attributes.

[0177] Table 2 Condition attribute set obtained after reduction

[0178]

Embodiment 2

[0180] Taking the historical maximum load data of an electric power bureau as the original data and the corresponding data in 2000 and 2001 as the training data, the daily maximum load from March to August 2002 is predicted. The data of the first two weeks of each month is selected as the test set, a total of 6 time periods, and 50 predictions are made in each time period. The BP neural network and the RBF neural network are used for training and prediction, and the evaluation index adopts the absolute value of the average relative error.

[0181] MAPE = 1 N Σ i = 1 N | P A i - P F i | P A ...

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 short-term load predicting method based on a quick fuzzy rough set. The method comprises the following steps that firstly, electrical load data recorded by an electricity meter installed in a power grid are collected, and an initial attribute decision table is constructed; secondly, a fuzzy subordinate function of the condition attribute and the decision attribute is determined; thirdly, the attribute reduction is carried out according to the quick fuzzy rough set method, and the reduction condition attribute is obtained; fourthly, the reduction condition attribute serves as input data of a neural network to train normalized historical load data; fifthly, the neural network obtained through training is utilized for carrying out the short-term load prediction on an electric power system; sixthly, reverse normalization processing is carried out on the obtained normalization value of the maximum load of the prediction day, and a short-term electric power load prediction result is obtained and is the maximum load of the prediction day. The computing amount of the fuzzy rough set attribute reduction is small, the computing time is short, and the computing efficiency is improved.

Description

technical field [0001] The invention belongs to the technical field of electric power information, and in particular relates to a fast fuzzy rough set short-term load forecasting method. Background technique [0002] Power system load forecasting plays a very important role in the safe, economical and reliable operation of the power system. Among them, short-term load forecasting is the basis for power system dispatching and management departments to formulate start-up and shutdown plans and online safety analysis, and is also the basis for realizing power plan management in the power market. The neural network has a strong nonlinear fitting ability, and can comprehensively consider various factors that affect the load, such as weather conditions, date types, etc., so the neural network method is widely used in power system load forecasting, but if various influencing factors All are included in the input variables of the input layer, which will cause too many input variabl...

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
CPCY04S10/50
Inventor 詹俊鹏郭创新黄刚
Owner ZHEJIANG UNIV
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