Next Article in Journal
Potential and Scenarios of Variants of Thermo-Modernization of Single-Family Houses: An Example of the Lubuskie Voivodeship
Next Article in Special Issue
Identification of the State of Electrical Appliances with the Use of a Pulse Signal Generator
Previous Article in Journal
Techno-Economic Feasibility Analysis of Grid-Connected Microgrid Design by Using a Modified Multi-Strategy Fusion Artificial Bee Colony Algorithm
Previous Article in Special Issue
A Framework to Generate and Label Datasets for Non-Intrusive Load Monitoring
Article

The Impact of Ambient Sensing on the Recognition of Electrical Appliances

Department of Informatics, TU Clausthal, 38678 Clausthal-Zellerfeld, Germany
*
Author to whom correspondence should be addressed.
Energies 2021, 14(1), 188; https://doi.org/10.3390/en14010188
Received: 5 December 2020 / Revised: 21 December 2020 / Accepted: 23 December 2020 / Published: 1 January 2021
(This article belongs to the Special Issue Energy Data Analytics for Smart Meter Data)
Smart spaces are characterized by their ability to capture a holistic picture of their contextual situation. This often includes the detection of the operative states of electrical appliances, which in turn allows for the recognition of user activities and intentions. For electrical appliances with largely different power consumption characteristics, their types and operational times can be easily inferred from data collected at a single metering point (typically, a smart meter). However, a disambiguation between consumers of the same type and model, yet located in different areas of a smart building, is not possible this way. Likewise, small consumers (e.g., wall chargers) are often indiscernible from measurement noise and spurious power consumption events of other appliances. As a consequence thereof, we investigate how additional sensing modalities, i.e., data beyond electrical signals, can be leveraged to improve the appliance detection accuracy. Through a set of practical experiments, recording ambient influences in eight dimensions and testing their effects on 21 appliance types, we evaluate the importance of such added features in the context of appliance recognition. Our results show that electrical power measurements already yield a high appliance recognition accuracy, yet further accuracy improvements are possible when considering ambient parameters as well. View Full-Text
Keywords: appliance load signatures; ambient influences; device classification accuracy appliance load signatures; ambient influences; device classification accuracy
Show Figures

Figure 1

MDPI and ACS Style

Huchtkoetter, J.; Tepe, M.A.; Reinhardt, A. The Impact of Ambient Sensing on the Recognition of Electrical Appliances. Energies 2021, 14, 188. https://doi.org/10.3390/en14010188

AMA Style

Huchtkoetter J, Tepe MA, Reinhardt A. The Impact of Ambient Sensing on the Recognition of Electrical Appliances. Energies. 2021; 14(1):188. https://doi.org/10.3390/en14010188

Chicago/Turabian Style

Huchtkoetter, Jana, Marcel A. Tepe, and Andreas Reinhardt. 2021. "The Impact of Ambient Sensing on the Recognition of Electrical Appliances" Energies 14, no. 1: 188. https://doi.org/10.3390/en14010188

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop