 Short-term smart learning electrical load prediction algorithm for home energy management systemsWessam El-Baz and Peter Tzscheutschler Applied Energy, 2015, vol. 147, issue C, 10-19 Abstract: Energy management system (EMS) within buildings has always been one of the main approaches for an automated demand side management (DSM). These energy management systems are supposed to increase load flexibility to fit more the generation from renewable energies and micro co-generation devices. For EMS to operate efficiently, it must learn ahead about the available supply and demand so that it can work on supply–demand matching and minimizing the imports from the grid and running costs. This article presents a simple efficient day-ahead electrical load prediction approach for any EMS. In comparison to other approaches, the presented algorithm was designed to be apart of any generic EMS and it does not require to be associated with a prepared statistical or historical databases, or even to get connected to any kinds of sensors. The proposed algorithm was tested over the data of 25 households in Austria and the results have shown an error range that goes down to 8.2% as an initial prediction. Keywords: Smart home; Energy prediction; Energy planning; Electrical load; User behavior; Demand side management (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:147:y:2015:i:c:p:10-19 Ordering information: This journal article can be ordered from DOI: 10.1016/j.apenergy.2015.01.122 Access Statistics for this article Applied Energy is currently edited by J. Yan More articles in Applied Energy from Elsevier |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.