Dyna-Bolt: Domain Adaptive Binary Factorization Of Current Waveforms For Energy Disaggregation

Non-intrusive loading monitoring (NILM) is the a set of algorithmic techniques for inferring the operational states of individual appliances in a household given the aggregate electrical measurements at a single point of instrumentation. Most successful techniques to-date approach the problem from a supervised learning perspective and thus rely on labeled data, which is costly to obtain, and assume similar data distributions for appliances beyond those in the training set. To alleviate this problem, we formulated NILM in a domain adaptation context. Using Binary OnLine FactorizaTion (BOLT) as the baseline model, we first demonstrate that direct application of traditional domain adversarial training without application-specific modifications is unsuccessful, and hypothesize that this may be due to differences in the data distributions. We then propose Dyna-BOLT: a domain- adaptive variant of BOLT, in which we 1) provide private decoders for the source and target domains to account for the differences in current waveforms, and 2) tied the weights between the two decoders using a metric that was specifically trained to distinguish between appliance classes. We evaluated Dyna-BOLT on a publicly available dataset (REDD) and demonstrated that it compares favorably to unsupervised methods.