Dynamic adaptive encoder-decoder deep learning networks for multivariate time series forecasting of building energy consumption

被引:15
|
作者
Guo, Jing [1 ]
Lin, Penghui [2 ]
Zhang, Limao [3 ]
Pan, Yue [4 ]
Xiao, Zhonghua [5 ]
机构
[1] Huazhong Univ Sci & Technol, Sch Civil & Hydraul Engn, 1037 Luoyu Rd,Hongshan Dist, Wuhan 430074, Hubei, Peoples R China
[2] Nanyang Technol Univ, Sch Civil & Environm Engn, 50 Nanyang Ave, Singapore City 639798, Singapore
[3] Huazhong Univ Sci & Technol, Natl Ctr Technol Innovat Digital Construct, Sch Civil & Hydraul Engn, 1037 Luoyu Rd,Hongshan Dist, Wuhan 430074, Hubei, Peoples R China
[4] Shanghai Jiao Tong Univ, Dept Civil Engn, Shanghai Key Lab Digital Maintenance Bldg & Infras, 800 Dongchuan Rd, Shanghai 200240, Peoples R China
[5] Hubei Ind Construct Grp Co LTD, 42 Xiongchu St,Wuchang Dist, Wuhan 430076, Hubei, Peoples R China
基金
中国国家自然科学基金;
关键词
Encoder-decoder deep learning; Multivariate time series forecasting; Building energy consumption; Data-driven modeling; Attention mechanism; MODEL; PERFORMANCE; MANAGEMENT; DEMAND;
D O I
10.1016/j.apenergy.2023.121803
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Accurate energy consumption prediction models can bring tremendous benefits to building energy efficiency, where the use of data-driven models allows models to be trained based on historical data and to obtain better prediction performance. However, a severe problem has been overlooked where the dynamic spatiotemporal dependence among buildings is often not considered. To settle this issue, this study proposes an asymmetric encoder-decoder learning framework where the spatial relationships and time-series features between multiple buildings are extracted by a convolutional neural network and a gated recurrent neural network to form new input data in the encoder. The decoder then makes predictions based on the input data with an attention mechanism. The model is trained and tested with energy consumption data from 10 different buildings at a university in China. The results show that our proposed model maintains high accuracy using small datasets while predicting different types of buildings, achieving an average R2 of 0.964. Additionally, the accuracy loss in multi-step forecasting is considerably ameliorated by maintaining an average R2 of 0.915 predicting 3 steps ahead of time. Benefiting from the asymmetric encoder-decoder structure, the proposed algorithm resolves the problem of accuracy loss using deep learning in a small dataset and multi-step time series forecasting. Further assisted by the anomaly detection function, the algorithm serves as a reliable guide for the user to effectively manage and control energy consumption in buildings.
引用
收藏
页数:21
相关论文
共 50 条
  • [1] A Novel Encoder-Decoder Model for Multivariate Time Series Forecasting
    Zhang, Huihui
    Li, Shicheng
    Chen, Yu
    Dai, Jiangyan
    Yi, Yugen
    [J]. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2022, 2022
  • [2] Multivariate time series forecasting via attention-based encoder-decoder framework
    Du, Shengdong
    Li, Tianrui
    Yang, Yan
    Horng, Shi-Jinn
    [J]. NEUROCOMPUTING, 2020, 388 (388) : 269 - 279
  • [3] A Bi-GRU-based encoder-decoder framework for multivariate time series forecasting
    Balti, Hanen
    Ben Abbes, Ali
    Farah, Imed Riadh
    [J]. SOFT COMPUTING, 2024, 28 (9-10) : 6775 - 6786
  • [4] Multivariate Time Series Forecasting with Deep Learning Proceedings in Energy Consumption
    Mellouli, Nedra
    Akerma, Mahdjouba
    Minh Hoang
    Leducq, Denis
    Delahaye, Anthony
    [J]. KDIR: PROCEEDINGS OF THE 11TH INTERNATIONAL JOINT CONFERENCE ON KNOWLEDGE DISCOVERY, KNOWLEDGE ENGINEERING AND KNOWLEDGE MANAGEMENT - VOL 1: KDIR, 2019, : 384 - 391
  • [5] Multistep Forecasting of Soil Moisture Using Spatiotemporal Deep Encoder-Decoder Networks
    Li, Lu
    Dai, Yongjiu
    Shangguan, Wei
    Wei, Nan
    Wei, Zhongwang
    Gupta, Surya
    [J]. JOURNAL OF HYDROMETEOROLOGY, 2022, 23 (03) : 337 - 350
  • [6] Deep Encoder-Decoder Networks for Mapping Raw Images to Dynamic Movement Primitives
    Pahic, Rok
    Gams, Andrej
    Ude, Ales
    Morimoto, Jun
    [J]. 2018 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2018, : 5863 - 5868
  • [7] An Encoder-Decoder Deep Learning Framework for Building Footprints Extraction from Aerial Imagery
    Khan, Sultan Daud
    Alarabi, Louai
    Basalamah, Saleh
    [J]. ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING, 2023, 48 (02) : 1273 - 1284
  • [8] Learning From Architectural Redundancy: Enhanced Deep Supervision in Deep Multipath Encoder-Decoder Networks
    Luo, Ying
    Lu, Jinhu
    Jiang, Xiaolong
    Zhang, Baochang
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (09) : 4271 - 4284
  • [9] A Regression Framework for Energy Consumption in Smart Cities with Encoder-Decoder Recurrent Neural Networks
    Carrera, Berny
    Kim, Kwanho
    [J]. ENERGIES, 2023, 16 (22)
  • [10] Unsupervised detecting anomalies in multivariate time series by Robust Convolutional LSTM Encoder-Decoder (RCLED)
    Le, Tuan
    Vu, Hai Canh
    Ponchet-Durupt, Amelie
    Boudaoud, Nassim
    Cherfi-Boulanger, Zohra
    Nguyen-Trang, Thao
    [J]. NEUROCOMPUTING, 2024, 592