Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Short-term building load probability density prediction method

A technology of probability density and forecasting method, which is applied in forecasting, data processing applications, instruments, etc., can solve problems such as increased computational complexity, insufficient forecasting flexibility, and insufficient precision, so as to reduce data computational complexity, improve model prediction accuracy, The effect of preventing overfitting phenomenon

Active Publication Date: 2021-03-05
SHANGHAI UNIVERSITY OF ELECTRIC POWER
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing forecasts use all factors as input variables of the forecasting model, which greatly increases the computational complexity, leads to the disaster of dimensionality, and affects the results of building load forecasting. Moreover, most of the current short-term building load forecasting is point load forecasting, and point load forecasting The forecasting elasticity of is not enough, the accuracy is not enough, and it cannot describe the uncertainty of load forecasting with higher permeability

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 building load probability density prediction method
  • Short-term building load probability density prediction method
  • Short-term building load probability density prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0098] In this example, the regional electricity load data in my country is used. The length of the data set is one year, and 48 points are sampled every day at intervals of 30 minutes. The annual data set is divided into four seasons: January-March, April-June, July-September, and October-December. Since different types of data have different magnitudes, the data is normalized:

[0099]

[0100] In the formula: x is the input data; x min and x max is the extreme value of the data. Define the lag variable as autocorrelation, weather variable as cross correlation, use Gumble copula function for quantitative feature selection, set the time window as 7*48 a week, and carry out the lag variable in the past week (t-1~t-7*48) filter. Considering the huge calculation, in order to improve efficiency, the maximum autocorrelation coefficient is used for preliminary screening, and the autocorrelation coefficient graph is obtained as follows image 3 shown. From image 3It can b...

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 a short-term building load probability density prediction method, which comprises the following steps of: 1) screening an original exogenous variable by adopting an orthogonalmaximum correlation coefficient by taking a maximum correlation coefficient and minimum redundancy as principles to obtain a selected exogenous variable; 2) for the selected exogenous variable, introducing a binary risk indication variable to improve the accuracy of peak load prediction; 3) constructing a convolution gating quantile regression model, taking the screened exogenous variables and binary risk indication variables as input together, and taking building load prediction values under different quantiles as output for training; and 4) predicting by adopting the trained constructed convolution gating quantile regression model to obtain predicted values under different quantiles, and obtaining a probability density distribution function from the predicted values under the differentquantiles through a fitted kernel function. Compared with the prior art, the method has the advantages of improving the peak time prediction accuracy, improving the prediction precision, fully extracting features and the like.

Description

technical field [0001] The invention relates to the field of big data prediction of building loads, in particular to a short-term building load probability density prediction method based on orthogonal maximum correlation coefficient feature selection and convolution gating neural network. Background technique [0002] Short-term load forecasting (STLF) is crucial for the stability and economic development of modern power systems for regional loads (such as smart homes, microgrids and active distribution networks), the diversity of user characteristics and demands Uncertainty in response makes forecasting more difficult. Inaccurate load forecasting will have an adverse effect on production planning. Power load is affected by factors such as weather, economy, and holidays. If all factors are considered, it will increase computational complexity and affect forecasting. precision. [0003] Short-term building load is the foundation and key of power system economic dispatch, un...

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
IPC IPC(8): G06Q10/04G06Q10/06G06Q50/06G06N3/04
CPCG06Q10/04G06Q10/0635G06Q10/06393G06Q50/06G06N3/047G06N3/045Y04S10/50
Inventor 孙改平刘蓉晖林顺富米阳陈腾马天天赵增凯韦江川王乐凯杨涛张飞翔
Owner SHANGHAI UNIVERSITY OF ELECTRIC POWER
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
Eureka Blog
Learn More
PatSnap group products