Synthetic-to-Real Domain Adaptation for Nonintrusive Load Monitoring via Reconstruction-Based Transfer Learning

Recently, transfer learning has gained attention in nonintrusive load monitoring (NILM) as it improves the generalization of the models, particularly when transferring knowledge from one real-world dataset to another. Considering the privacy concerns arising from model transfer training due to the large-scale collection of annotated real-world data, synthetic datasets have become a viable alternative for improving generalization performance in NILM. However, the generalization in research scenarios with domain distribution gaps, like synthetic-to-real settings, still needs exploration. In this article, we present a feature reconstruction-based network model for NILM, designed to capture both common shared and unique representations across synthetic and real data domains. An external attention mechanism (EAM) is adopted to compensate for the lack of measurement data, utilizing synthetic datasets to address both the scarcity of annotated data and privacy concerns. Ultimately, the analysis of interdomain data features influences the model's generalizability. Our experimental results demonstrate that the proposed network shows promise for the transfer learning from a synthetic dataset to a real dataset, and its performance relies on the power consumption of the appliance and the dissimilarity of probability mass functions (PMFs) between the two datasets.