Bansal, VibhutiVibhutiBansalKhoiwal, RohitRohitKhoiwalShastri, HetviHetviShastriKhandor, HaikooHaikooKhandorBatra, NipunNipunBatra2025-08-312025-08-312022-11-09[9781450398909]10.1145/3563357.35640632-s2.0-85143575738https://d8.irins.org/handle/IITG2025/25868Non-intrusive load monitoring (NILM) refers to the task of disaggregating total household power consumption into the constituent appliances. In recent years, various neural network (NN) based approaches have emerged as state-of-the-art for NILM. In conventional settings, NN(s) provide point estimates for appliance power. In this paper, we explore the question-can we learn models that tell when they are unsure? Or, in other words, can we learn models that provide uncertainty estimates? We explore recent advances in uncertainty for NN(s), evaluate 14 model variants on the publicly available REDD dataset, and find that our models can accurately estimate uncertainty without compromising on traditional metrics. We also find that different appliances in their different states have varying performance of uncertainty. We also propose "recalibration"methods and find they can improve the uncertainty estimation.falsebayesian analysis | calibration | neural networks | non-intrusive load monitoring | uncertaintyConference Paper79-889 November 20221cpConference Proceeding2