Non-Invasive Load Recognition Model Based on CNN and Mixed Attention Mechanism

Chenchen Zhang, Yujun Song, Dong Wang, Shifang Song, Xuesong Pan, Lanzhou Liu

2023

Abstract

In recent years, deep learning has been widely applied in various fields, including the field of load recognition. Machine learning methods such as SVM and K-means, as well as various neural network approaches, have shown promising results. However, due to the significant differences among similar appliances and the existence of multiple operating states for each appliance, misjudgments often occur during load recognition. Therefore, this paper proposes a preprocessing method that transforms current-voltage data into V-If trajectories. Additionally, a non-intrusive load recognition algorithm is presented, which incorporates a self-designed convolutional neural network (CNN), a hybrid attention mechanism (ECA_NET and Spatial attention mechanism, ECA-SAM), and a hybrid loss function (Center Loss and ArcFace, CA). The effectiveness of this approach is demonstrated through simulation experiments conducted on the PLAID dataset, achieving a remarkable 98% accuracy in the identification of electrical appliances.

Paper Citation

in Harvard Style

Zhang C., Song Y., Wang D., Song S., Pan X. and Liu L. (2023). Non-Invasive Load Recognition Model Based on CNN and Mixed Attention Mechanism. In Proceedings of the 2nd International Seminar on Artificial Intelligence, Networking and Information Technology - Volume 1: ANIT; ISBN 978-989-758-677-4, SciTePress, pages 70-74. DOI: 10.5220/0012274000003807

in Bibtex Style

@conference{anit23,
author={Chenchen Zhang and Yujun Song and Dong Wang and Shifang Song and Xuesong Pan and Lanzhou Liu},
title={Non-Invasive Load Recognition Model Based on CNN and Mixed Attention Mechanism},
booktitle={Proceedings of the 2nd International Seminar on Artificial Intelligence, Networking and Information Technology - Volume 1: ANIT},
year={2023},
pages={70-74},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012274000003807},
isbn={978-989-758-677-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Seminar on Artificial Intelligence, Networking and Information Technology - Volume 1: ANIT
TI - Non-Invasive Load Recognition Model Based on CNN and Mixed Attention Mechanism
SN - 978-989-758-677-4
AU - Zhang C.
AU - Song Y.
AU - Wang D.
AU - Song S.
AU - Pan X.
AU - Liu L.
PY - 2023
SP - 70
EP - 74
DO - 10.5220/0012274000003807
PB - SciTePress