Automated load disaggregation for residences with electrical resistance heating

•An automated load disaggregation methodology is proposed.•It utilizes DBSCAN clustering.•It computes heating energy for space and domestic hot water from total electrical load profile.•This method can be readily applied to residences with an electrical resistance heating system.•A comparative analy...

Full description

Saved in:

Bibliographic Details
Published in:	Energy and buildings 2019-01, Vol.182, p.61-74
Main Authors:	Deb, Chirag, Frei, Mario, Hofer, Johannes, Schlueter, Arno
Format:	Article
Language:	eng
Subjects:	Clustering Data mining Data points Data processing DBSCAN clustering Disaggregation Electric resistance Electrical loads Electrical resistance Electrical resistance heating system Electricity consumption Energy Energy consumption Energy efficiency Heating Heating energy consumption Heating systems Histograms Hot water heating Load disaggregation Parameters Residences Residential areas Residential buildings Residential density Residential energy Resistance heating Water heating
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	•An automated load disaggregation methodology is proposed.•It utilizes DBSCAN clustering.•It computes heating energy for space and domestic hot water from total electrical load profile.•This method can be readily applied to residences with an electrical resistance heating system.•A comparative analysis with two other data mining techniques is also presented. Building-related heating consumes 80% of final energy in the Swiss residential sector. Electrical resistance heating systems consumed 9.3 PJ and 7.9 PJ for space and domestic hot water heating respectively. This is 8.6% of the total electricity consumption in Switzerland. A successful retrofit action requires knowledge of energy consumed by these systems in the pre-retrofit stage. However, it is difficult to deduce the heating energy from the overall electrical load profile of each residence. One of the primary reasons is irregularities in the operation of the heating system. We address this by applying a data mining approach that group data points based on their concentration in the time axis. This is done by using DBSCAN (Density-based spatial clustering of applications with noise) which requires derivation of two clustering parameters, ‘Epsilon’ and ‘MinPts’. We present a method to automatically derive these two parameters based on a combination of histogram analysis and range search method. We also compare our results with those obtained by k-means and density peaks clustering methods. The proposed methodology can effectively disaggregate electrical load into space and domestic hot water heating for residences with an electrical resistance heating system.
ISSN:	0378-7788 1872-6178