Temporal and Spectral Feature Learning With Two-Stream Convolutional Neural Networks for Appliance Recognition in NILM

Non-intrusive load monitoring (NILM) can monitor the operating state and energy consumption of appliances without deploying sub-meters and is promising to be widely used in residential communities. With the rapid increase of electric loads in amount and type, constructing representative load signatures and designing effective classification models are becoming increasingly crucial for NILM. In this paper, temporal and spectral load signatures that preserve sufficient information are constructed from the monitored energy data. The fusion of these two types of load signatures can provide rich distinguishing features for improving the performance of appliance recognition in NILM. Benefiting from the development of deep learning, this study proposes the two-stream convolutional neural networks (TSCNN) to extract the features from the two types of load signatures and perform classification. Furthermore, this study introduces the affinity propagation clustering strategy to mitigate the negative impact of intra-class variety mainly caused by multi-state loads in appliance recognition. The experimental results on public NILM datasets demonstrate that the proposed method outperforms most of the existing methods based on the voltage-current trajectory or recurrence graph in the recognition accuracy of submetered and aggregated measurements.

Automated summary

Non-intrusive load monitoring (NILM) is a promising technology that can monitor appliance operating state and energy consumption without sub-meters. This paper proposes a method using temporal and spectral load signatures for appliance recognition in NILM. Deep learning techniques and affinity propagation clustering strategy are used to extract features and mitigate the negative impact of multi-state loads. Experimental results show that the proposed method outperforms existing methods in recognition accuracy.