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

Short-term electricity price prediction method, system and device and storage medium

A forecasting method and electricity price technology, applied in forecasting, nuclear method, market forecasting and other directions, can solve the problems of disturbing the original electricity price data, reducing forecasting accuracy, false components, etc., to improve modal aliasing and false components, and improve forecasting accuracy. , improve the effect of limitation

Pending Publication Date: 2021-10-15
XIAN THERMAL POWER RES INST CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the traditional short-term electricity price forecasting method has the following problems in the forecasting process: 1. The original data of electricity price has strong volatility, nonlinearity and multi-frequency, and the electricity price data is directly used for forecasting, ignoring the characteristics of the electricity price data itself ; 2. After the original electricity price data is decomposed by some decomposition methods, modal aliasing and false components will appear, disturbing the original electricity price data and increasing the workload of prediction; 3. After the original data is decomposed, it will get different fluctuation characteristics For modal components, only one method is used to predict each component obtained by decomposition, and the fluctuation characteristics of each component cannot be fully utilized, which virtually reduces the prediction accuracy of each component, thereby reducing the prediction accuracy of the entire electricity price sequence

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 electricity price prediction method, system and device and storage medium
  • Short-term electricity price prediction method, system and device and storage medium
  • Short-term electricity price prediction method, system and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0032] refer to figure 1 , the wind power prediction method of the present invention comprises the following steps:

[0033] 1) Using the variational modal decomposition method to decompose the historical electricity price data into a plurality of modal components with different fluctuation characteristics, and divide the plurality of modal components with different fluctuation characteristics into high-frequency modal components and low-frequency modal components;

[0034] The specific process of step 1) is:

[0035] 11) Determine the number of modes k and the penalty factor;

[0036] Specifically, estimate the initial value k of the number of modes through the frequency spectrum diagram of historical electricity price data; when the number of modes is judged to be K, determine whether the center frequencies of each mode overlap each other; when the center frequencies of each mode overlap, Then reduce K; when the center frequency does not overlap, increase K until the cente...

Embodiment 1

[0110] Based on the historical electricity price data of the US PJM market in January 2016 for analysis. The present invention uses a total of 624 data points from the 1st to the 26th to carry out modeling, and a total of 120 data points from the 27th to the 31st are used for prediction testing using the established prediction model, and the prediction results are compared with the least squares support vector machine ( LSSVM), BP neural network (BPNN), BP neural network optimized by beetle-beard algorithm (BAS-BPNN), improved particle swarm algorithm optimized least squares vector machine (improved PSO-LSSVM), EMD combined forecasting model, EEMD combined forecasting model , VMD combined prediction model for comparison, the comparison results are shown in Table 2;

[0111] Table 2

[0112]

[0113]

[0114] It can be seen from Table 2 that the prediction accuracy of the combined forecasting model is higher than that of the single forecasting model; for the combined for...

Embodiment 2

[0116] A short-term electricity price forecasting system includes:

[0117] A preprocessing module, configured to decompose the historical electricity price data into a plurality of modal components with different fluctuation characteristics, and divide the plurality of modal components with different fluctuation characteristics into high-frequency modal components and low-frequency modal components;

[0118] The prediction module is used to input the high-frequency modal component into the first prediction model for prediction to obtain the first prediction modal component, and input the low-frequency modal component into the second prediction model for prediction to obtain the second prediction modal component;

[0119] The integration module is used to integrate the first prediction modal component and the second prediction modal component to obtain the final electricity price prediction value.

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 electricity price prediction method, system and device and a storage medium, and the method comprises the following steps: decomposing historical electricity price data into a plurality of modal components with different fluctuation characteristics, and dividing the plurality of modal components with different fluctuation characteristics into a high-frequency modal component and a low-frequency modal component; inputting the high-frequency modal component into a first prediction model for prediction to obtain a first prediction modal component, and inputting the low-frequency modal component into a second prediction model for prediction to obtain a second prediction modal component; and integrating the first prediction mode component and the second prediction mode component to obtain a final electricity price prediction value. According to the invention, the method, the system, the equipment and the storage medium can accurately predict the short-term electricity price.

Description

technical field [0001] The invention belongs to the field of electricity market research, and relates to a short-term electricity price prediction method, system, equipment and storage medium. Background technique [0002] Under the background of my country's current open electricity market, electricity price, as the fulcrum of the electricity market, can directly affect the economic benefits of each market participant. The electricity market is essentially an auction market, which leads to fluctuations in electricity prices, and market participants can avoid fluctuations through electricity price forecasts. [0003] At present, the traditional short-term electricity price forecasting method has the following problems in the forecasting process: 1. The original data of electricity price has strong volatility, nonlinearity and multi-frequency, and the electricity price data is directly used for forecasting, ignoring the characteristics of the electricity price data itself ; ...

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): G06Q10/04G06Q30/02G06Q50/06G06N3/08G06N20/10
CPCG06Q10/04G06Q30/0206G06Q50/06G06N3/08G06N20/10
Inventor 张灏杨昭蔺奕存赵俊杰张钢雷阳
Owner XIAN THERMAL POWER RES INST 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