Nonintrusive Load Monitoring Based on Self-Supervised Learning

Deep learning models for nonintrusive load monitoring (NILM) tend to require a large amount of labeled data for training. However, it is difficult to generalize the trained models to unseen sites due to different load characteristics and operating patterns of appliances between datasets. For addressing such problems, self-supervised learning (SSL) is proposed in this article, where labeled appliance-level data from the target dataset or house are not required. Initially, only the aggregate power readings from target dataset are required to pretrain a general network via a self-supervised pretext task to map aggregate power sequences to derived representatives. Then, supervised downstream tasks are carried out for each appliance category to fine-tune the pretrained network, where the features learned in the pretext task are transferred. Utilizing labeled source datasets enables the downstream tasks to learn how each load is disaggregated, by mapping the aggregate to labels. Finally, the fine-tuned network is applied to load disaggregation for the target sites. For validation, multiple experimental cases are designed based on three publicly accessible REDD, U.K.-DALE, and REFIT datasets. Besides, the state-of-the-art neural networks are employed to perform NILM task in the experiments. Based on the NILM results in various cases, SSL generally outperforms zero-shot learning in improving load disaggregation performance without any submetering data from the target datasets.