Intelligent power plant coal-fired generator set short-term load prediction method based on RF-DTW

A short-term load forecasting, RF-DTW technology, applied in forecasting, computer parts, instruments, etc., can solve problems such as lack of convincingness, achieve accurate forecasting results, improve economic operation level, and strengthen the effect of practical promotion value

Pending Publication Date: 2021-12-24
浙江浙能数字科技有限公司 +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this way, the load forecast of coal-fired generating units based only on historical load data is not convincing enough.

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
  • Intelligent power plant coal-fired generator set short-term load prediction method based on RF-DTW
  • Intelligent power plant coal-fired generator set short-term load prediction method based on RF-DTW
  • Intelligent power plant coal-fired generator set short-term load prediction method based on RF-DTW

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0076] Embodiment 1 of the present application provides a method such as figure 2 The RF-DTW-based short-term load forecasting method for coal-fired generating units in smart power plants includes the following steps:

[0077] Step 1. Obtain the current time as the predicted time T now ;

[0078] Step 2. Obtain historical data from the database of the unit. The form of historical data is:

[0079]

[0080] In the above formula, the historical data matrix F a1 Each column in represents unit load, precipitation, air pressure, wind speed, air temperature, and humidity data respectively; historical data matrix F a1 Each row in represents the unit load, precipitation, air pressure, wind speed, temperature, and humidity data at different times; the historical data matrix F a1 A matrix composed of historical data;

[0081] Step 3, preprocessing the historical data;

[0082] Step 4. According to the predicted time T now Calculate the average load F of the week before the fo...

Embodiment 2

[0105] On the basis of Embodiment 1, Embodiment 2 of this application provides the application of the RF-DTW-based short-term load forecasting method for coal-fired generator sets in a power plant in Embodiment 1:

[0106] Two 1050MW coal-fired generating units in a power plant, the data used are the meteorological data between January 1, 2018 and July 1, 2020 and the load data of these two units, the goal is to achieve the time period required by the power plant (24 hours The load forecast in ) is convenient to determine the start and stop of important auxiliary machines such as circulating water pumps according to the load forecast results.

[0107] In the historical data, the period from January 1, 2018 to June 30, 2019 is used as modeling data, and the period from June 1 to June 30, 2020 is used as test data.

[0108] The specific process of unit load forecasting based on RF-DTW algorithm is as follows:

[0109] Step 1. Obtain the current time as the predicted time T now...

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 relates to an Intelligent power plant coal-fired generator set short-term load prediction method based on RF-DTW. The method comprises the following steps: acquiring current time as a prediction moment; acquiring historical data from a database of the unit; preprocessing the historical data; and calculating the average load of the week before the prediction moment according to the prediction moment. The invention has the advantages that the limitation that the unit load is predicted only through historical load data of the unit is overcome, the unit load prediction value of any current time point within 24 hours is given based on the RF-DTW algorithm, and it is ensured that the maximum error of unit load prediction within 24 hours in the future is smaller than 5%; therefore, decision support can be provided for start-stop optimization operation of important auxiliary machines such as a circulating water pump, a coal mill and a desulfurization slurry circulating pump of the coal-fired power generation unit, and the method has important significance for improving the economic operation level of the unit as much as possible on the basis of ensuring the safety of the coal-fired power generation unit, and has wide popularization prospects.

Description

technical field [0001] The invention belongs to the field of process control of coal-fired power generation, and in particular relates to a short-term load forecasting method for a coal-fired generating set in an intelligent power plant combining RF and DTW. Background technique [0002] Today is in the era of intelligence, and all walks of life are actively striving to transform and upgrade to intelligence. Coal-fired power generation companies with dual characteristics of capital-intensive and technology-intensive have also begun to move from traditional power plants to smart power plants. The core of smart power plants is the intelligence of power generation process control. Among them: as the load of the unit changes, the start-stop optimization of the circulating water pump on the turbine side, the coal mill on the boiler side, the desulfurization slurry circulating pump and other important auxiliary equipment has considerable economic benefits, so it has become one of ...

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): G06Q10/04G06Q50/06G06K9/62G06F17/16
CPCG06Q10/04G06Q50/06G06F17/16G06F18/22Y02E40/70Y04S10/50
Inventor 杨勤孙永平袁伟中王豆傅骏伟郑必君安佰京刘胜成姜志峰屠海彪王策
Owner 浙江浙能数字科技有限公司
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