E3S Web Conf.
Volume 111, 2019CLIMA 2019 Congress
|Number of page(s)||7|
|Section||Information and Communication Technologies (ICT) for the Intelligent Building Management|
|Published online||13 August 2019|
Identification of Energy Use Time Patterns of Occupied Dwellings using Smart Meter Data
Department of Architecture and Urban Planning, Ghent University, Sint-Pietersnieuwstraat 41-B4, B-9000 Ghent, Belgium
* Corresponding author: firstname.lastname@example.org
The increasing application of smart and digital energy meters leads to an increasing availability of frequent -e.g. hourly- and long-term measurements of the actual energy use in occupied buildings. In the resulting energy use time series, the diurnal fluctuations in energy use are recognised and similarities between diurnal profiles for various days are observed. These recurring profiles are called energy use time patterns and they are a result of various phenomena, such as patterns in the building use, occupational schedules, settings of the system control, short-term weather dynamics etc. These energy use time patterns can provide a better understanding of the energy use, which is useful in many fields including energy feedback, fault detection and energy auditing. In order to identify and characterise energy use time patterns for large data-sets, an automated approach is needed. This paper proposes a methodology for automated mathematical recognition of energy use time patterns based on cluster analysis. Secondly, a methodology to characterise the identified patterns in function of external variables is proposed, using classification analysis techniques. The methodologies allow an automated identification and characterization of energy use time patterns, allowing a better understanding of the variations and changes in building energy use and their relation to weather conditions and calendar aspects.
© The Authors, published by EDP Sciences, 2019
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.