Sparse Optimization for Automated Energy End Use Disaggregation

Abstract

Retrieving the household electricity consumption at individual appliance level is an essential requirement to assess the contribution of different end uses to the total household consumption, and thus to design energy saving policies and user-tailored feedback for reducing household electricity usage. This has led to the development of nonintrusive appliance load monitoring (NIALM), or energy disaggregation, algorithms, which aim to decompose the aggregate energy consumption data collected from a single measurement point into device-level consumption estimations. Existing NIALM algorithms are able to provide accurate estimate of the fraction of energy consumed by each appliance. Yet, in the authors’ experience, they provide poor performance in reconstructing the power consumption trajectories overtime. In this brief, a new NIALM algorithm is presented, which, besides providing very accurate estimates of the aggregated consumption by appliance, also accurately characterizes the appliance power consumption profiles overtime. The proposed algorithm is based on the assumption that the unknown appliance power consumption profiles are piecewise constant overtime (as it is typical for power use patterns of household appliances) and it exploits the information on the time-of-day probability in which a specific appliance might be used. The disaggregation problem is formulated as a least-square error minimization problem, with an additional (convex) penalty term aiming at enforcing the disaggregate signals to be piecewise constant overtime. Testing on household electricity data available in the literature is reported

Water End Use Disaggregation Based on Soft Computing Techniques

“…The initially identified 5880 overlapped events were separated into 24,024 subevents after the disaggregation process. Most of these new subevents were classified as single-use events (17,908), and the rest (6116) as uncertain. In total, the analysis of the worst case scenario of study R1 produced 24,302 single-use events (74.1%) and 8490 uncertain events (25.9%).…”

“…Furthermore, the set of data employed for the training of the proposed machine learning tool has been obtained using Trace Wizard ® software, which has limited capabilities for disaggregating overlapped consumption events [13]. Following a similar approach, Piga et al [17] proposed an automated water and energy end use disaggregation, which has only been tested against electric energy data. Also, several start-ups claim to have developed software to automatically classify residential water consumption events into various uses [18][19][20].…”

Robust energy disaggregation using appliance-specific temporal contextual information

“…In our experimental set-up, the real aggregated signal (which includes ghost power from unknown devices) was used to evaluate the performance of the proposed NILM methodology, thus making the experimental set-up identical to real-life conditions. Specifically, the input aggregated power consumption signal we used was the originally measured by the smart meter (one sensor only) during data acquisition (similarly to [60]) and not an artificially generated aggregated signal created by adding the power consumption signals from a manually selected closed set of devices (synthesized data), as in [29,[61][62][63], which was criticized in [64] for not corresponding to real-world conditions.…”

A Socio-Technical System Based on Gamification Towards Energy Savings

“…the indoor environmental conditions, and fine grained energy consumption measurements from the smart meters. All these data are processed utilizing advanced analysis and classification techniques (such as those described in [29], [30]) for deducing the number of occupants and/or presence/absence in a building and categorizing the comfort levels of the building occupants. The comfort is divided into two main classes, i.e., visual and thermal comfort.…”