Trainingless Energy Disaggregation Without Plug-Level Sensing
Angshul Majumdar
Abstract
The majority of studies in non-intrusive load monitoring (NILM) are intrusive and supervised in nature since they require appliance-wise energy consumption data for training. A “true” NILM approach should not require appliance-wise data even for training; this automatically demands the approach to be unsupervised in nature. Four prior studies fall under this category; two of them use integer programming; the third employs graph signal processing (GSP); the fourth one assumes a pre-trained model that generalizes without the requirement of sub-metered training data. This work proposes an alternative approach based on the sparse coding (SC) formulation. Experiments on benchmarks datasets [reference energy disaggregation dataset (REDD) and Pecan Street] show that the proposed method improves by approximately 10%–20% on REDD and about 15% on Pecan Street, over existing true/unsupervised non-intrusive techniques; however, it is worse than the intrusive/supervised approaches on REDD (3%–10%) and Pecan Street (10%).