Hawk: An Efficient NALM System for Accurate Low-Power Appliance Recognition

TL;DR

Hawk is a novel NALM system that efficiently constructs a diverse dataset and achieves high accuracy in recognizing low-power appliance events, significantly outperforming existing methods.

Contribution

The paper introduces Hawk, a two-stage NALM system with an innovative dataset construction method and an integrated event recognition algorithm, improving efficiency and accuracy.

Findings

HawkDATA collection is 71.5 times faster than baseline.

Hawk achieves over 93% F1 score in state recognition.

Hawk outperforms SOTA algorithms with 47.98% and 11.57% higher accuracy.

Abstract

Non-intrusive Appliance Load Monitoring (NALM) aims to recognize individual appliance usage from the main meter without indoor sensors. However, existing systems struggle to balance dataset construction efficiency and event/state recognition accuracy, especially for low-power appliance recognition. This paper introduces Hawk, an efficient and accurate NALM system that operates in two stages: dataset construction and event recognition. In the data construction stage, we efficiently collect a balanced and diverse dataset, HawkDATA, based on balanced Gray code and enable automatic data annotations via a sampling synchronization strategy called shared perceptible time. During the event recognition stage, our algorithm integrates steady-state differential pre-processing and voting-based post-processing for accurate event recognition from the aggregate current. Experimental results show that HawkDATA takes only 1/71.5 of the collection time to collect 6.34x more appliance state combinations than the baseline. In HawkDATA and a widely used dataset, Hawk achieves an average F1 score of 93.94% for state recognition and 97.07% for event recognition, which is a 47. 98% and 11. 57% increase over SOTA algorithms. Furthermore, selected appliance subsets and the model trained from HawkDATA are deployed in two real-world scenarios with many unknown background appliances. The average F1 scores of event recognition are 96.02% and 94.76%. Hawk's source code and HawkDATA are accessible at https://github.com/WZiJ/SenSys24-Hawk.