Abstract
With the large-scale deployment of smart meters worldwide, research in non-intrusive load monitoring (NILM) has seen a significant rise due to its dual use of real-time monitoring of end-user appliances and user-centric feedback of power consumption usage. NILM is a technique for estimating the state and the power consumption of an individual appliance in a consumer’s premise using a single point of measurement device such as a smart meter. Although there are several existing NILM techniques, there is no meaningful and accurate metric to evaluate these NILM techniques for multi-state devices such as the fridge, heat pump, etc. In this paper, we demonstrate the inadequacy of the existing metrics and propose a new metric that combines both event classification and energy estimation of an operational state to give a more realistic and accurate evaluation of the performance of the existing NILM techniques. In particular, we use unsupervised clustering techniques to identify the operational states of the device from a labeled dataset to compute a penalty threshold for predictions that are too far away from the ground truth. Our work includes experimental evaluation of the state-of-the-art NILM techniques on widely used datasets of power consumption data measured in a real-world environment.
Highlights
Recent social advancements and rapid industrialization have led to concerns about climate change and the ever-increasing demand for energy, which is a recognized problem of international significance.The World Energy Outlook Report [1] indicates that global energy demand is set to grow by 90% by2040
Recent research findings [8,9] on Non-intrusive load monitoring (NILM). Algorithms and their implementation conclude that there are some practical limitations of the existing metrics: first, existing event classification metrics do not classify multi-state devices accurately with respect to events in the original ground truth; second, the overall energy of a device is estimated, it does not measure the energy estimation of each classified state of the device; with relatively large errors the metric result exceeds the usual accuracy interval of 0 and 1, making it less intuitive and explainable. This paper solves these problems by proposing multi-state energy classifier (MEC) which is a new metric based on unsupervised clustering technique that combines event classification and energy estimation by identifying the operational states of the device from a labeled dataset to compute a penalty threshold for predictions that are too far away from the ground truth
We evaluate our approach using the widely accepted NILMKTK [10] framework and various publicly available datasets such as the Reference Energy Disaggregation dataset (REDD) [11], Dutch Residential Energy dataset (DRED) [12] and Almanac of Minutely Power dataset (AMPds) [13]
Summary
Recent social advancements and rapid industrialization have led to concerns about climate change and the ever-increasing demand for energy, which is a recognized problem of international significance. Recent research findings [8,9] on NILM algorithms and their implementation conclude that there are some practical limitations of the existing metrics: first, existing event classification metrics do not classify multi-state devices accurately with respect to events in the original ground truth; second, the overall energy of a device is estimated, it does not measure the energy estimation of each classified state of the device; with relatively large errors the metric result exceeds the usual accuracy interval of 0 and 1, making it less intuitive and explainable This paper solves these problems by proposing multi-state energy classifier (MEC) which is a new metric based on unsupervised clustering technique that combines event classification and energy estimation by identifying the operational states of the device from a labeled dataset to compute a penalty threshold for predictions that are too far away from the ground truth. We evaluate our approach using the widely accepted NILMKTK [10] framework and various publicly available datasets such as the Reference Energy Disaggregation dataset (REDD) [11], Dutch Residential Energy dataset (DRED) [12] and Almanac of Minutely Power dataset (AMPds) [13]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
