Open AccessMulti‐nodal short‐term energy forecasting using smart meter data
Author(s) -
Hayes Barry P.,
Gruber Jorn K.,
Prodanovic Milan
Publication year - 2018
Publication title -
iet generation, transmission and distribution
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.92
H-Index - 110
eISSN - 1751-8695
pISSN - 1751-8687
DOI - 10.1049/iet-gtd.2017.1599
Subject(s) - metering mode , smart meter , smart grid , computer science , demand forecasting , demand response , term (time) , electricity , electric potential energy , energy demand , energy (signal processing) , data aggregator , metre , reliability engineering , operations research , engineering , environmental economics , electrical engineering , statistics , wireless sensor network , mechanical engineering , physics , mathematics , quantum mechanics , economics , computer network , astronomy
This paper deals with the short‐term forecasting of electrical energy demands at the local level, incorporating advanced metering infrastructure (AMI), or ‘smart meter’ data. It provides a study of the effects of aggregation on electrical energy demand modelling and multi‐nodal demand forecasting. This paper then presents a detailed assessment of the variables which affect electrical energy demand, and how these effects vary at different levels of demand aggregation. Finally, this study outlines an approach for incorporating AMI data in short‐term forecasting at the local level, in order to improve forecasting accuracy for applications in distributed energy systems, microgrids and transactive energy. The analysis presented in this study is carried out using large AMI data sets comprised of recorded demand and local weather data from test sites in two European countries.