A Semi-Supervised Approach for Improving Generalization in Non-Intrusive Load Monitoring

Abstract

Non-intrusive load monitoring (NILM) considers different approaches for disaggregating energy consumption in residential, tertiary, and industrial buildings to enable smart grid services. The main feature of NILM is that it can break down the bulk electricity demand, as recorded by conventional smart meters, into the consumption of individual appliances without the need for additional meters or sensors. Furthermore, NILM can identify when an appliance is in use and estimate its real-time consumption based on its unique consumption patterns. However, NILM is based on machine learning methods and its performance is dependent on the quality of the training data for each appliance. Therefore, a common problem with NILM systems is that they may not generalize well to new environments where the appliances are unknown, which hinders their widespread adoption and more significant contributions to emerging smart grid services. The main goal of the presented research is to apply a domain adversarial neural network (DANN) approach to improve the generalization of NILM systems. The proposed semi-supervised algorithm utilizes both labeled and unlabeled data and was tested on data from publicly available REDD and UK-DALE datasets. The results show a 3% improvement in generalization performance on highly uncorrelated data, indicating the potential for real-world applications.

Real-Time Non-Intrusive Load Monitoring for Low-Power Appliances Using Odd Current Harmonics

“…Although their results are comparable to the objective of this work, there are some key differences, which are highlighted in Table I. Researchers have also proposed and assessed transferable NILM (i.e., generalized) solutions using different public datasets [35][36][37], and have investigated their key differences thoroughly in [38].…”

Non-intrusive load identification based on semi-supervised learning with flexible threshold and V-I trajectory signature

“…In order to overcome the labeled data bottleneck in NILM, researchers and developers are developing various techniques such as transfer learning [15], [31], [32], domain adaptation [33], [34], synthetic appliance power data generation [35], [36], Semi-supervised learning (SSL) techniques [37]- [39]. The world of SSL techniques is a particularly fascinating field, which could be the bridge between label-heavy supervised learning and a future of data-efficient modeling.…”