Interval forecasting method of heat supply load based on support vector machine and error estimation

A support vector machine, load interval technology, applied in computing, computer parts, character and pattern recognition, etc., can solve problems such as inability to apply heating energy-saving renovation, thermal scheduling and thermal station control, and low forecast accuracy

Inactive Publication Date: 2012-02-22
HARBIN INST OF TECH
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to solve the problem that the existing interval forecasting method has low forecasting accuracy and cannot be applied to heating energy-saving renovation, thermal scheduling and thermal station control, the present invention further provides a heating load interval forecasting method based on support vector machine and error estimation

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
  • Interval forecasting method of heat supply load based on support vector machine and error estimation
  • Interval forecasting method of heat supply load based on support vector machine and error estimation
  • Interval forecasting method of heat supply load based on support vector machine and error estimation

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0064] Specific implementation mode one: as figure 1 As shown, the heating load interval forecasting method based on support vector machine and error estimation described in this embodiment is implemented according to the following steps:

[0065] Step 1. Establish a support vector regression forecasting model on the basis of obtaining sample data, and perform point forecasting:

[0066] Step 1 (1), sample data and training sample construction:

[0067] Suppose the heating load time series {L t (i)}, wherein, i=1,2,...,24, t=1,2,...,n 2 , here, n 2 is the number of days of the heating load collected;

[0068] For the current heating load L t (i), which can be obtained from the previous m of its current heating load 1 load value forecast, that is, L t (i-m 1 ), L t (i-(m 1 -1)), ..., L t (i-1)(i>m 1 );or

[0069] {L t (1), L t (2),...,L t (i-1); L t-1 [24-(m 1 -(i-1))],...,L t-1 (23), L t-1 (24)}, (1≤i≤m 1 )

[0070] The first m of the current heating load...

specific Embodiment approach

[0121] During the heating period from the winter of 2007 to the spring of 2008, a certain heat source was sampled every 1 hour, and the data obtained from the average daily outdoor temperature during the same period were used as the original data for the load forecast of the heating system, such as figure 2 and image 3 As shown, the specific process is:

[0122] 1. Sample data selection and sample input dimension determination

[0123] Using the pseudo-neighborhood method to calculate the input dimension of the horizontal and vertical forecasts, m 1 = 4, m 2 = 3, form the training sample recursive formula, and obtain the training sample {x i ,y i}.

[0124]

[0125] (15)

[0126]

[0127] 2. Support vector regression point forecast parameter selection

[0128] The accuracy of support vector regression prediction depends on the selection of model parameters. In this paper, the SVR kernel function chooses the radial basis function, that is, K(x j , x l )=exp(-||...

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 an interval forecasting method of a heat supply load based on a support vector machine and error estimation, relates to a method for forecasting the heat supply load, and aims to solve the problems of low forecasting accuracy and difficulty in application to heat-supply energy-saving reforming, heat power scheduling and control of a heat power station in the conventional interval forecasting method. The interval forecasting method of the heat supply load based on the support vector machine and the error estimation comprises the following steps of: firstly, on the basis of acquisition of sample data, establishing a support vector regression forecasting model, and performing point forecasting; secondly, on the basis of point forecasting, acquiring a forecasting error, and estimating an error interval; thirdly, with the point forecasting and the error interval, performing interval forecasting; and fourthly, evaluating forecasting effects of the point forecasting and the interval forecasting. The method provided by the invention can be directly applied to the heat-supply energy-saving reforming, the heat power scheduling and the control of the heat power station.

Description

technical field [0001] The invention relates to a method for forecasting heating load. Background technique [0002] The traditional forecast results are all deterministic, that is, point forecast. The disadvantage is that the fluctuation range of the forecast results cannot be determined. Due to the advanced nature of the forecast problem, the realization of probabilistic forecast is more in line with the objective needs. In the heat supply load forecasting process, because there are many factors affecting the heat supply load and there may be coupling among the factors, it is difficult to establish a mathematical model for the heat supply load forecast. In view of the requirement of heat dispatching for load forecasting in heating system, the reliability of load forecasting becomes the key to forecasting. The existing heating load is mainly based on points. Although the existing technology refers to the interval forecasting method, there are problems such as low interval ...

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): G06K9/62
Inventor 齐维贵张永明于德亮邓盛川
Owner HARBIN INST OF TECH
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