Paper Info
Title
Electricity load forecasting for residential customers: Exploiting aggregation and correlation between households
Abstract
The recent development of smart meters has allowed the analysis of household electricity consumption in real time. Predicting electricity consumption at such very low scales should help to increase the efficiency of distribution networks and energy pricing. However, this is by no means a trivial task since household-level consumption is much more irregular than at the transmission or distribution levels. In this work, we address the problem of improving consumption forecasting by using the statistical relations between consumption series. This is done both at the household and district scales (hundreds of houses), using various machine learning techniques, such as support vector machine for regression (SVR) and multilayer perceptron (MLP). First, we determine which algorithm is best adapted to each scale, then, we try to find leaders among the time series, to help short-term forecasting. We also improve the forecasting for district consumption by clustering houses according to their consumption profiles.
Year
DOI
Venue
2013
10.1109/SustainIT.2013.6685208
Sustainable Internet and ICT for Sustainability
Keywords
Field
DocType
distribution networks,learning (artificial intelligence),load forecasting,power consumption,power engineering computing,smart meters,distribution network,electricity load forecasting,energy pricing,household electricity consumption,machine learning technique,residential customer,smart meter,transmission level
Econometrics,Regression,Smart grid,Electricity,Support vector machine,Correlation,Multilayer perceptron,Mains electricity,Engineering,Cluster analysis,Operations management
Conference
Citations 
PageRank 
References 
29
1.85
10
Authors
4
Name
Order
Citations
PageRank
Samuel Humeau1514.52
Tri Kurniawan Wijaya214014.20
Matteo Vasirani329328.75
Karl Aberer46459662.26