Heating load forecast engineering method with crossed time sequence
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A time series, engineering technology, applied in forecasting, instrumentation, data processing applications, etc., can solve the problems of complex calculation, low precision, slow speed, etc., to achieve high precision, fast forecast speed, and reduce the squared error effect.
Inactive Publication Date: 2012-06-20
HARBIN INST OF TECH
View PDF0 Cites 4 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0003] In order to solve the problems of complicated calculation, slow speed and low precision in the existing heating load forecasting method, the pres
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach 1
[0016] Specific implementation mode one: as figure 1 As shown, a time-series cross heating load forecasting engineering method described in this embodiment is implemented according to the following steps:
[0017] Step 1. Horizontal forecast: record the load at the i-th moment on the t-th day as L t (i), according to the lateral load time series, L t (i) From the previous m at the i-th moment 1 historical load forecast at a moment;
[0018] Step 2. Longitudinal forecast: record the load at time i on day t as L t (i), according to the longitudinal loading time series, L t (i) Available from m before the tth day 2 The historical load at the i-th moment of the day is used to forecast;
[0019] Step 3. Time series cross-forecast: On the basis of horizontal forecast and longitudinal forecast, combine the two forecasts, and determine the weighting coefficient of cross-forecast according to the principle of least square error sum, and obtain the cross-forecast model:
[0020] ...
specific Embodiment approach 2
[0022] Specific implementation mode two: the horizontal forecast and the vertical forecast described in this implementation mode are all realized by the AR model, and the AR model is determined by using the modeling theory of the Yule-Walker method and the F-order criterion, and the specific process is as follows:
[0023] Step A, description of AR model:
[0024] The AR model is an autoregressive model, and the system function H(z) of the AR model is expressed as
[0025] H ( z ) = G 1 + Σ i = 1 p a i z - i - - - ( 2 ...
specific Embodiment approach 3
[0055] Specific implementation manner three: In step three of this implementation manner, the weighting coefficients of the cross prediction are determined by the least square method. Other steps are the same as in the first embodiment.
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
Login to view more
Abstract
The invention discloses a heating load forecast engineering method with a crossed time sequence, and relates to a heating load forecast method suitable for engineering application. The invention aims to solve the problems that the existing heating load forecast method has complicated calculation, low speed and low accuracy and is not suitable for the heating load forecast in engineering. The method mainly comprises the following steps of: forecasting data by use of the transverse and longitudinal forecast of a time sequence respectively, wherein the heat load value at each moment per day within a sampling period is selected in the longitudinal forecast to perform modeling, and all heat load data within one day is selected in the transverse forecast to perform forecast; and determining a weighting coefficient for the crossed forecast by use of the least square method according to the least square error sum principle so as to determine a heat load crossed-forecast model. According to the invention, the system error of forecast can be reduced; and the method has higher accuracy than the conventional engineering forecast algorithm, and provides reference for the application in the energy-saving monitoring engineering. Moreover, the method realizes fast forecast and can achieve the best compromise between the forecast speed and forecast accuracy.
Description
technical field [0001] The invention relates to a heating load forecasting method suitable for engineering applications. The invention belongs to the technical field of heating load forecasting. Background technique [0002] Existing heat supply load forecasting methods mostly perform linear forecasting based on the weather, and its forecasting accuracy is low, which cannot meet the needs of heating energy-saving control; one of the existing heat supply adjustment methods is to adjust according to weather temperature, which belongs to horizontal forecasting The accuracy is low, and the other is to predict the load based on the heating load at a few moments before, and the accuracy is relatively low. Moreover, the existing intelligent heating load forecasting methods are researched offline and remain at the laboratory simulation level, and no examples of energy-saving applications in heating engineering are given, and no heating load forecasting software has been developed, ...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more