Prediction method based on VMD and DNN and application in short-term load prediction

A technology for short-term load forecasting and forecasting methods, applied in forecasting, data processing applications, instruments, etc., can solve problems such as adverse effects of forecasting accuracy, false eigenmode functions, etc., to reduce the amount of calculation, reduce the calculation scale, and shorten the calculation effect of time

Pending Publication Date: 2019-09-10
STATE GRID ANHUI ELECTRIC POWER +2
View PDF2 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the EMD decomposition method is difficult to avoid the occurrence of modal aliasing, resulting in false Intrinsic Mode Functions (IMF), which adversely affects the prediction accuracy

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
  • Prediction method based on VMD and DNN and application in short-term load prediction
  • Prediction method based on VMD and DNN and application in short-term load prediction
  • Prediction method based on VMD and DNN and application in short-term load prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The technical solution of the present invention will be further described below in conjunction with the accompanying drawings of the description.

[0045] The power load is affected by human activities and meteorological conditions to varying degrees, showing a certain degree of volatility and randomness. However, human life and production activities have certain regularity, so the load also has strong periodic characteristics. In order to finely analyze the characteristics of the load sequence, the VMD method is used to decompose the original load sequence to obtain a series of components that are conducive to prediction. Combined with the DNN training prediction, the prediction results of each component are superimposed to obtain the final prediction result of the VMD-DNN model. predictive models such as figure 1 shown. The specific method is as follows:

[0046] Step 1: Collect load data, and the data collection interval is T min; every time N days are collected, ...

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 prediction method based on VMD and DNN and application in short-term load prediction, and belongs to the technical field of power system short-term load prediction. The method comprises the steps of 1, collecting load data; step 2, performing normalization processing on the acquired data; step 3, decomposing the normalized original load sequence by adopting a VMD method;4, performing deep neural network (DNN) training on the K components obtained in the step 3; and 5, introducing the decomposed test sample into the DNN, and carrying out superposition to obtain a final prediction result. The method is accurate in data prediction with volatility and randomness, can effectively reduce the calculation amount of data, shortens the calculation time, is accurate in prediction result, improves the accuracy of load prediction, and is of great significance for economic dispatching and stable operation of a power system.

Description

technical field [0001] The present invention relates to the technical field of power system short-term load forecasting, in particular to a forecasting method based on variational mode decomposition (Variational Mode Decomposition, VMD) and deep neural network (Deep Neural Networks, DNN) and its application in short-term load forecasting. Background technique [0002] Load forecasting is one of the key challenges in power supply planning and grid supply and demand balancing. It is the basis for the operation of the electricity market and an important part of electricity planning. Improving the accuracy of short-term load forecasting will help to improve the utilization rate of power equipment, reduce energy consumption, and alleviate the imbalance between the supply side and the demand side of energy. The load sequence has a certain timing and nonlinearity. Around its characteristics, the current short-term load forecasting methods include multiple linear regression method,...

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 Applications(China)
IPC IPC(8): G06Q10/04G06Q50/06
CPCG06Q10/04G06Q50/06
Inventor 马金辉李智赵晓春李顺丁津津张倩马愿高博郑国强徐斌谢毓广陈凡赵恒阳
Owner STATE GRID ANHUI ELECTRIC POWER
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