17 March 2021 in IEEE Transactions on Industrial Informatics
Nonintrusive load monitoring (NILM) is a technique to disaggregate an appliance's load consumption from the aggregate load in a house. Monitoring the energy behavior has become increasingly important for home energy management. For many machine learning-based models, model training needs enough, and diverse appliance-level labeled data from different houses, which is very time-consuming, expensive, and unacceptable for users. In this article, we propose an algorithm based on the adversarial network and the joint adaptation network for energy disaggregation to decrease the distribution gaps of both the feature space and the label space between the source and target domains. With only very limited labeled data in the source domain and enough unlabeled data in the target domain, our proposed algorithm can obtain satisfactory accuracy results for NILM. Extensive experiments for intradomain and interdomain demonstrate that the proposed algorithm can significantly improve the domain adaptation. Comparing with the baseline method that without any domain adaptation, the improvement on mean absolute error with the proposed algorithm can reach 67.72%, 67.53%, and 66.56% for the washing machine (W.M), the dishwasher (D.W), and the microwave (M.V), respectively.
30 December 2020 in arXiv
Unsupervised domain adaptation (UDA) aims to train a target classifier with labeled samples from the source domain and unlabeled samples from the target domain. Classical UDA learning bounds show that target risk is upper bounded by three terms: source risk, distribution discrepancy, and combined risk. Based on the assumption that the combined risk is a small fixed value, methods based on this bound train a target classifier by only minimizing estimators of the source risk and the distribution discrepancy. However, the combined risk may increase when minimizing both estimators, which makes the target risk uncontrollable. Hence the target classifier cannot achieve ideal performance if we fail to control the combined risk. To control the combined risk, the key challenge takes root in the unavailability of the labeled samples in the target domain. To address this key challenge, we propose a method named E-MixNet. E-MixNet employs enhanced mixup, a generic vicinal distribution, on the labeled source samples and pseudo-labeled target samples to calculate a proxy of the combined risk. Experiments show that the proxy can effectively curb the increase of the combined risk when minimizing the source risk and distribution discrepancy. Furthermore, we show that if the proxy of the combined risk is added into loss functions of four representative UDA methods, their performance is also improved.