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

A real-time load online forecasting method for power plants

A technology for real-time load and forecasting methods, applied in electrical digital data processing, instruments, calculations, etc., can solve problems such as low scalability, unclear physical meaning of parameters, single modeling method, etc., to achieve a high degree of understandability and convenience. Analysis and understanding, the effect of model flexibility

Inactive Publication Date: 2017-11-10
BOHAI UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods have certain applicable conditions. In the process of modeling and forecasting, there are generally problems such as single modeling means, unclear physical meaning of parameters, and poor scalability.

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 real-time load online forecasting method for power plants
  • A real-time load online forecasting method for power plants
  • A real-time load online forecasting method for power plants

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The specific implementation manners of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0045] This embodiment uses sensors to collect on-site online operation data of generator sets through the network, and collects real-time load data of power plants. Taking the load data of a large thermal power plant shown in Table 1 as an example, the time is a certain month in 2014, and the sampling period is 15 minutes, a total of 90 minutes of data collection, specific data in Table 1. Among them, 1 to 6 data are original data, and the seventh is the power plant load data at the next moment, that is, forecast data.

[0046] Table 1 Load data of a large thermal power plant

[0047] Number of data

1

2

3

4

5

6

7

Actual load (MW)

207.7

216.2

231.3

241.3

274.0

275.3

280.3

[0048] A real-time load online forecasting method for a power plant, such as Figure 7 show...

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 provides a real-time load online prediction method of a power plant, which includes: collecting real-time load data of the power plant at the current moment, and obtaining the load data of the power plant at the historical time, and performing fractional order accumulation preprocessing; using the original load data of the power plant to generate a sequence of fractional order accumulation, and establishing a forecast Fractional cumulative GM(1,1) model of power plant load data; real-time prediction of power plant load data at the next moment by using the power plant load data prediction model; correction of real-time prediction results of power plant load data at the next moment. The present invention adopts the fractional-order cumulative GM(1,1) model for predicting the real-time load data of the power plant, and uses small-sample historical data in the modeling process to avoid the storage, calculation and complexity problems caused by the large amount of data, and effectively improve the accuracy of the data. Utilization rate, at the same time, its intermediate data parameter analysis and results are highly understandable, which is convenient for unit operators to analyze and understand.

Description

technical field [0001] The invention relates to the technical field of power plant data forecasting, in particular to an online real-time load forecasting method of a power plant. Background technique [0002] The real-time data of the thermal power unit records the operation process of the power plant equipment and operators, and provides an important decision-making basis for the operation, maintenance and accident handling of the power plant. These data have positive guiding significance for improving the production efficiency and economic safety of the power plant, and also help to improve the operation optimization, fault diagnosis and condition maintenance technology of the power plant. With the development of power station SIS and MIS, a large amount of historical data is stored in the database, which also brings difficulties to data storage and analysis. Research on the overall characteristics and development trends of real-time data of important parameters of therm...

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): G06F19/00G06N3/12
CPCY04S10/50
Inventor 杨洋郭继宁李兵赵震王东
Owner BOHAI 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

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