Show simple item record

AuthorLiu, R.
AuthorChen, T.
AuthorSun, G.
AuthorMuyeen, S. M.
AuthorLin, S.
AuthorMi, Y.
Available date2022-03-23T08:22:43Z
Publication Date2022
Publication NameElectric Power Systems Research
AbstractDue to various influential factors that lead to instability and volatility of the building load, short-term building load forecasting is a gruelling task. This paper proposes a hybrid short-term building load probability density forecasting method based on Orthogonal Maximum Correlation Coefficient (OMCC) feature selection and Convolutional Gated Recurrent Unit (CGRU) quantile regression. Firstly, the optimal feature set is selected by OMCC. Then Value-At-Risk (VAR) is determined from fitting Copula model to construct indicator variables. Next, the data from the feature selection stage is used as input to the quantile regression model of CGRU for building load forecasting. Finally, the building load probability density distribution is fitted by kernel density estimation. The forecasting performance is evaluated using Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and Mean Arctan Absolute Percentage Error (MAAPE). Simulation results across all three buildings validate the reliability of the proposed model for the short-term building-level probabilistic load forecasting tasks.
SponsorThe authors would like to thank the National Natural Science Foundation of China ( 51977127 ) and Shanghai Municipal Science and Technology Commission ( 19020500800 ).
PublisherElsevier Ltd
Electric power plant loads
Feature extraction
Mean square error
Probability distributions
Regression analysis
Value engineering
Building load
Convolutional gated recurrent unit
Load forecasting
Maximum correlation coefficient
Orthogonal maximum correlation coefficient
Probability densities
Quantile regression
Short term load forecasting
Value at Risk
TitleShort-term probabilistic building load forecasting based on feature integrated artificial intelligent approach
Volume Number206

Files in this item


There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record