Non-intrusive load monitoring (NILM) is a popular approach to estimate appliance-level electricity consumption from aggregate consumption data of households. Assessing the suitability of NILM algorithms to be used in real scenarios is however still cumbersome, mainly because there exists no standardized evaluation procedure for NILM algorithms and the availability of comprehensive electricity consumption data sets on which to run such a procedure is still limited. This paper contributes to the solution of this problem by: (1) outlining the key dimensions of the design space of NILM algorithms; (2) presenting a novel, comprehensive data set to evaluate the performance of NILM algorithms; (3) describing the design and implementation of a framework that significantly eases the evaluation of NILM algorithms using different data sets and parameter configurations; (4) demonstrating the use of the presented framework and data set through an extensive performance evaluation of four selected NILM algorithms. Both the presented data set and the evaluation framework are made publicly available.
Detecting when a household is occupied by its residents is fundamental to enable a number of home automation applications. Current systems for occupancy detection usually require the installation of dedicated sensors, like passive infrared sensors, magnetic reed switches or cameras. In this paper, we investigate the suitability of digital electricity meters -which are already available in millions of households worldwide -to be used as occupancy sensors. To this end, we have collected fine-grained electricity consumption data along with ground-truth occupancy information for 5 households during a period of about 8 months. Our results show that using common classification methods it is possible to achieve occupancy detection accuracies of more than 80%.
Utilities are currently deploying smart electricity meters in millions of households worldwide to collect fine-grained electricity consumption data. We present an approach to automatically analyzing this data to enable personalized and scalable energy efficiency programs for private households. In particular, we develop and evaluate a system that uses supervised machine learning techniques to automatically estimate specific "characteristics" of a household from its electricity consumption. The characteristics are related to a household's socio-economic status, its dwelling, or its appliance stock. We evaluate our approach by analyzing smart meter data collected from 4,232 households in Ireland at a 30-minute granularity over a period of 1.5 years. Our analysis shows that revealing characteristics from smart meter data is feasible, as our method achieves an accuracy of more than 70% over all households for many of the characteristics and even exceeds 80% for some of the characteristics. The findings are applicable to all smart metering systems without making changes to the measurement infrastructure. The inferred knowledge paves the way for targeted energy efficiency programs and other services that benefit from improved customer insights. On the basis of these promising results, the paper discusses the potential for utilities as well as policy and privacy implications.
Abstract-The recent trend of ubiquitous access to embedded physical devices over the Internet as well as increasing penetration of wireless protocols such as ZigBee has raised attention to smart homes. These systems consist of sensors, devices and smart appliances that can be monitored and controlled remotely by human users and cloud services. However, the lack of a de facto communication standard for smart homes creates a barrier against the interoperability of devices from different vendors. We address this challenge by proposing a holistic, extensible software architecture that seamlessly integrates heterogeneous protocol-and vendor-specific devices and services, while making these services securely available over the Internet. Our architecture is developed on top of the OSGi framework and incorporates a semantic model of a smart home system. As a result, we achieve semantic interoperability -the ability to integrate new applications and drivers into the deployed system during runtime. Furthermore, we integrate a new access control model for specific smart home scenarios. As a proof of our concept, we demonstrate the seamless semantic discovery of home devices at runtime by integrating several protocols including X10, Insteon, ZigBee and UPnP into a real test. Using smart phones and cloud services together with our home gateway implementation, we further demonstrate the ease of integration of new applications and drivers.
The ongoing liberalization of the energy market makes energy providers increasingly look at premium serviceslike personalized energy consulting -as preferred methods to bind existing customers and attract new ones. Providing such services, however, requires knowledge of specific properties of the customer's household -like its size and the number of persons living in it. In this paper, we investigate how such properties can be inferred from the fine-grained electricity consumption data provided by digital electricity meters. In particular, we focus on exploring which properties are both interesting and likely to be identified using wellknown classification methods. To this end, we first elicit a set of interesting properties by performing in-depth interviews with employees of three different energy providers. We then explore a large set of electricity consumption traces using a self-organizing map. This analysis allows to identify a set of household properties that are likely to be inferable from electricity consumption data using standard classification methods. For instance, our results show that the size of a household and the income of its occupants are properties that are both highly useful to energy providers as well as likely to be detectable using an automatic classification system.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.