Dimensionality Expansion of Load Monitoring Time Series and Transfer Learning for EMS

Energy management systems (EMS) rely on (non)-intrusive load monitoring (N)ILM to monitor and managing appliances and help residents be more energy efficient and thus more frugal. The generalizability as well as the transfer potential of the most promising machine learning solutions for (N)ILM is not yet fully understood as they are trained and evaluated on relatively limited data. In this paper, we propose a new approach for load monitoring in building EMS (BEMS) based on dimensionality expansion of time series and transfer learning. We perform an extensive evaluation on 5 different low-frequency datasets. The proposed feature dimensionality expansion using video-like transformation and deep learning architecture achieves an average weighted F1 score of 0.88 across the datasets with 29 appliances and is up to 6-times more computationally efficient compared to the state-of-the-art. Investigating %the suitability of the proposed method for cross-dataset transfer learning, we find that 1) our method performs with an average weighted F1 score of 0.80 while requiring 3-times fewer epochs for model training compared to the non-transfer approach, 2) can achieve an F1 score of 0.75 with only 230 data samples, and 3) our transfer approach outperforms the state-of-the-art in precision drop by up to 12 percentage points for unseen appliances