Authors:
Marco Mittelsdorf
1
;
Andreas Hüwel
2
;
Thole Klingenberg
2
and
Michael Sonnenschein
2
Affiliations:
1
University of Oldenburg, Germany
;
2
OFFIS - Institute for Information Technology, Germany
Keyword(s):
Appliance Recognition, Smart Metering, Submetering, Energy Monitoring, Multi-class Support Vector Machines.
Related
Ontology
Subjects/Areas/Topics:
Energy and Economy
;
Energy Monitoring
;
Energy Profiling and Measurement
;
Energy-Aware Systems and Technologies
;
Mechanisms for Motivating Behaviour Change
;
Smart Cities
Abstract:
In this paper we employ smart meter and support vector machines (SVM) for the problem of recognizing household appliances’ load patterns in measured load time series, which is an important step for various applications in energy consulting, process recognition or health care applications. We present an automated data collection and preprocessing approach that intrinsically avoids many privacy (and security) issues by keeping the whole process local to the household. In the experimental part we investigate multi-class SVMs in the problem domain of automatically recognizing appliances in load profiles of smart meters. For the learning phase, we use low intrusive submeters to automatically and locally generate household specific test data for the supervised training and validation of the SVMs. We analyze classifiers w.r.t. various training sets and feature spaces. Comparing data from household simulator and real household data, we find that excellent recognition rates can be achieved ev
en with low resolution data and rather unsophisticated feature space.
(More)