Journal
ENERGY
Volume 203, Issue -, Pages -Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.energy.2020.117756
Keywords
Building energy consumption; Intake tower; Peak power; Machine learning; Extreme gradient boosting
Categories
Funding
- National Natural Science Foundation of China [71901184]
- Open Fund of State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation (Southwest Petroleum University) [PLN201710]
- Humanities and Social Science Fund of Ministry of Education of China [19YJCZH119]
- China Scholarship Council [201708030006]
Ask authors/readers for more resources
Accurate prediction of building energy consumption is crucial for building energy management. However, the building energy consumption is affected by many factors and shows obvious nonlinear characteristics in the time series, which is difficult to predict. In this work, a novel hybrid model is proposed for predicting short-term building energy consumption. In this model, the raw data is decomposed into multiple smooth datasets using complete ensemble empirical mode decomposition with adaptive noise, and the building energy consumption is predicted by the traditional extreme gradient boosting. Taking the daily energy consumption of the City of Bloomington Intake Tower as the simulation object, the results show that the mean absolute percentage error of the proposed model is 4.85%, which is much lower than that of five benchmark models. The proposed model is also applied to the prediction of other parameters related to the energy consumption of the intake tower, and shows good prediction performance. Moreover, the influences of the sliding window length and data attributes on the prediction results are also discussed. (C) 2020 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available