ABODE-Net: An Attention-based Deep Learning Model for Non-intrusive Building Occupancy Detection Using Smart Meter Data
Occupancy information is useful for efficient energy management in the building sector. The massive high-resolution electrical power consumption data collected by smart meters in the advanced metering infrastructure (AMI) network make it possible to infer buildings’ occupancy status in a on-intrusive way. In this paper, we propose a deep leaning model called ABODE-Net which employs a novel Parallel Attention (PA) block for building occupancy detection using smart meter data. The PA block combines the temporal, variable, and channel attention modules in a parallel way to signify important features for occupancy detection. We adopt two smart meter datasets widely used for building occupancy detection in our performance evaluation. A set of state-ofthe-art shallow machine learning and deep learning models are included for performance comparison. The results show that ABODE-Net significantly outperforms other models in all experimental cases, which proves its validity as a solution for non-intrusive building occupancy detection.
Luo, Z., Qi, R, Q. Li, Zheng, J., Shao, S. (2023). ABODE-Net: An Attention-based Deep Learning Model for Non-intrusive Building Occupancy Detection Using Smart Meter Data. In: Qiu, M., Lu, Z., Zhang, C. (eds) Smart Computing and Communication. SmartCom 2022. Lecture Notes in Computer Science, vol 13828. Springer, Cham. https://doi.org/10.1007/978-3-031-28124-2_15
conda create -n abode_net python=3.11
conda activate abode_net
pip install -r requirements.txt
python train.py --model ABODE_Net --dataset ECO
@InProceedings{10.1007/978-3-031-28124-2_15,
author="Luo, Zhirui
and Qi, Ruobin
and Li, Qingqing
and Zheng, Jun
and Shao, Sihua",
editor="Qiu, Meikang
and Lu, Zhihui
and Zhang, Cheng",
title="ABODE-Net: An Attention-based Deep Learning Model for Non-intrusive Building Occupancy Detection Using Smart Meter Data",
booktitle="Smart Computing and Communication",
year="2023",
publisher="Springer Nature Switzerland",
address="Cham",
pages="152--164",
}