With the large-scale roll-out of smart metering worldwide, there is a growing need to account for the individual contribution of appliances to the load demand. In this paper, we design a Graph signal processing (GSP)-based approach for nonintrusive appliance load monitoring (NILM), i.e., disaggregation of total energy consumption down to individual appliances used. Leveraging piecewise smoothness of the power load signal, two GSP-based NILM approaches are proposed. The first approach, based on total graph variation minimization, searches for a smooth graph signal under known label constraints. The second approach uses the total graph variation minimizer as a starting point for further refinement via simulated annealing. The proposed GSP-based NILM approach aims to address the large training overhead and associated complexity of conventional graph-based methods through a novel event-based graph approach. Simulation results using two datasets of real house measurements demonstrate the competitive performance of the GSP-based approaches with respect to traditionally used Hidden Markov Model-based and Decision Tree-based approaches.
The large-scale deployment of smart metering worldwide has ignited renewed interest in electrical load disaggregation, or non-intrusive load monitoring (NILM). Most NILM algorithms disaggregate one appliance at a time, remove the estimated appliance contribution from the total load, and then move on to disaggregate the next appliance. On one hand, this is efficient since multi-class classification is avoided and analytical models for each appliance can be developed independently of other appliances with the benefit of being transferred to unseen houses that have different sets of appliances. On the other hand, however, these methods can significantly under-or over-estimate the total consumption since they do not minimise the difference between the measured aggregate load and the sum of estimated individual loads. Motivated by minimising the latter difference without losing the benefits of existing NILM algorithms, we propose novel post-processing approaches for improving the accuracy of existing NILM. This is posed as an optimisation problem to refine the final NILM result using regularisation, based on the level of confidence in the original NILM output. First, we propose a heuristic method to solve this (combinatorial) boolean quadratic problem through relaxing zero-one constraint sets to compact zero-one intervals. Convex-based solutions, including norm-1, norm-2 and semi-definite programming-based relaxation, are proposed trading off accuracy and complexity. We demonstrate good performance of the proposed post-processing methods, applicable to any event-based NILM, compared with 4 state-of-the-art benchmarks, using public REFIT and REDD electrical load datasets.
Building on recent unsupervised Non-intrusive load monitoring (NILM) algorithms that use graph Laplacian regularization (GLR) and achieve state-of-the-art performance, in this paper, we propose a novel unsupervised approach to design an underlying graph to model the correlation within time-series smart meter measurements. We propose a variable-length data segmentation approach to extract potential events, assign all measurements associated with an identified event to each graph node, employ dynamic time warping to define the adjacency matrix of the graph, and propose a robust cluster labeling approach. Our simulation results on four different datasets show up to 10% improvement in classification performance over competing approaches.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.