Enhanced Long-Term Prediction Based on 2D Tensorization for Building Energy Consumption

DOI: https://doi.org/10.62517/jike.202404104

Author(s)

Song Deng*

Affiliation(s)

Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi, Jiangsu, China *Corresponding Author.

Abstract

Building energy consumption constitutes a significant contributor to greenhouse gas emissions. Precise forecasting of energy consumption in buildings plays a pivotal role in managing building energy efficiently, thereby aiding in the reduction of greenhouse gas emissions. However, existing prediction algorithms often focus on within-period variations in energy consumption data and overlook between-period variations. This limitation makes it challenging to achieve precise prediction results, especially for long-term forecasts. To address this research gap, this paper proposes an Enhanced Long-Term Prediction based on 2D Tensorization (ELP2T) for building energy consumption. First, a Frequency-Guided 2D Tensorization Network (FG-2TN) is proposed. Energy consumption data, when represented as a one-dimensional time series, faces certain limitations, and FG-2TN is employed to address these limitations. Second, a Progress-Optimized Deep Convolutional Network (PO-DCN) is proposed. It is designed to efficiently extract and learn features from the obtained two-dimensional tensors with fewer parameters and less time. Third, a modular method is proposed to transform one-dimensional time series into two-dimensional tensors using Fast Fourier transform. These tensors are processed and then concatenated into a one-dimensional sequence for output. Ultimately, a comparative analysis was carried out using several traditional forecasting algorithms to highlight the superior performance of the ELP2T model. The obtained average R² score for our proposed method is 0.807, representing an impressive enhancement of 11.06% compared to the most advanced alternatives. This substantial improvement firmly establishes the superiority of our approach. Especially, when considering a prediction length of 720 units, the performance gain of this metric increases to 18.09%, underscoring the pronounced advantage of our method in addressing long-term forecasting scenarios.

Keywords

Buildings electricity consumption; Long-Term prediction; Data-driven method; Deep learning; Frequency-Guided 2D Tensorization Network; Prgress-Optimized Deep Convolutional Network

References

[1]X. Liang, S. Chen, X. Zhu, X. Jin, Z. Du, Domain knowledge decomposition of building energy consumption and a hybrid data-driven model for 24-h ahead predictions, Appl. Energy. 344 (2023) 121244. https://doi.org/10.1016/j.apenergy.2023.121244. [2]X. Niu, Z. Ma, W. Ma, J. Yang, T. Mao, The spatial spillover effects and equity of carbon emissions of digital economy in China, J. Clean. Prod. 434 (2024) 139885. https://doi.org/10.1016/j.jclepro.2023.139885. [3]L. Lei, W. Chen, B. Wu, C. Chen, W. Liu, A building energy consumption prediction model based on rough set theory and deep learning algorithms, Energy Build. 240 (2021) 110886. https://doi.org/10.1016/j. enbuild.2021.110886. [4]Luis Pérez-Lombard, José Ortiz, Christine Pout, A review on buildings energy consumption information, Energy and Buildings, volume 40, issue 3, 2008, pages 394-398, ISSN 0378-7788. https://doi.org/10.1016/j.enbuild.2007.03.007. [5]Y. Chen, M. Guo, Z. Chen, Z. Chen, Y. Ji, Physical energy and data-driven models in building energy prediction: A review, Energy Rep. 8 (2022) 2656–2671. https://doi.org/10.1016/j.egyr.2022.01.162. [6]L. Wen, K. Zhou, S. Yang, Load demand forecasting of residential buildings using a deep learning model, Electr. Power Syst. Res. 179 (2020) 106073. https://doi.org/10.1016/j.epsr.2019.106073. [7]V. Kozitsin, I. Katser, D. Lakontsev, Online Forecasting and Anomaly Detection Based on the ARIMA Model, Appl. Sci. 11 (2021) 3194. https://doi.org/10.3390/app11073194. [8]H. Zhong, J. Wang, H. Jia, Y. Mu, S. Lv, Vector field-based support vector regression for building energy consumption prediction, Appl. Energy. 242 (2019) 403–414. https://doi.org/10.1016/j.apenergy.2019.03.078. [9]K.P. Amber, R. Ahmad, M.W. Aslam, A. Kousar, M. Usman, et. al, Intelligent techniques for forecasting electricity consumption of buildings, Energy. 157 (2018) 886–893. https://doi.org/10.1016/j.energy.2018. 05.155. [10]B. Jiang, Z. Cheng, Q. Hao, N. Ma, A Building Energy Consumption Prediction Method Based on Random Forest and ARMA, in: 2018 Chinese Automation Congress (CAC), 2018. https://doi.org/10.1109/cac.2018.8623540. [11]R. Wang, B. Rong, S. Ma, D. Ma, L. Wu, et. al, Prediction of ash fusion temperatures of municipal solid waste incinerator ash based on support vector regression, J. Energy Inst. 111 (2023) 101438. https://doi.org/10.1016/j.joei.2023.101438. [12]Y.-J. Lee, H.-J. Choi, Forecasting Building Electricity Power Consumption Using Deep Learning Approach, in: 2020 IEEE International Conference on Big Data and Smart Computing (BigComp), 2020. https://doi.org/10.1109/bigcomp48618.2020.000-8. [13]Taik, S. Cherkaoui, Electrical Load Forecasting Using Edge Computing and Federated Learning, in: ICC 2020 - 2020 IEEE International Conference on Communications (ICC), 2020. https://doi.org/10.1109/icc40277.2020.9148937. [14]T. Zhou, Z. Ma, Q. Wen, X. Wang, L. Sun, et. al, FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting, International Conference on Machine Learning. (2022).