Please use this identifier to cite or link to this item:
https://doi.org/10.1109/SusTech.2013.6617293
DC Field | Value | |
---|---|---|
dc.title | Constrained support vector machines for photovoltaic in-feed prediction | |
dc.contributor.author | Hildmann, M. | |
dc.contributor.author | Rohatgi, A. | |
dc.contributor.author | Andersson, G. | |
dc.date.accessioned | 2016-10-18T06:26:52Z | |
dc.date.available | 2016-10-18T06:26:52Z | |
dc.date.issued | 2013 | |
dc.identifier.citation | Hildmann, M.,Rohatgi, A.,Andersson, G. (2013). Constrained support vector machines for photovoltaic in-feed prediction. 2013 1st IEEE Conference on Technologies for Sustainability, SusTech 2013 : 23-28. ScholarBank@NUS Repository. <a href="https://doi.org/10.1109/SusTech.2013.6617293" target="_blank">https://doi.org/10.1109/SusTech.2013.6617293</a> | |
dc.identifier.isbn | 9781467346306 | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/128485 | |
dc.description.abstract | In this paper, we introduce a constrained Support Vector Machine (SVM) to predict photovoltaic (PV) in-feed. We derive the SVM algorithm with linear constraints and test the method on German PV in-feed with constraints reflecting physical boundaries. We show that the new algorithm shows a significant better performance than a constrained ordinary least squares (OLS) estimator. © 2013 IEEE. | |
dc.description.uri | http://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1109/SusTech.2013.6617293 | |
dc.source | Scopus | |
dc.type | Conference Paper | |
dc.contributor.department | ENERGY STUDIES INSTITUTE | |
dc.description.doi | 10.1109/SusTech.2013.6617293 | |
dc.description.sourcetitle | 2013 1st IEEE Conference on Technologies for Sustainability, SusTech 2013 | |
dc.description.page | 23-28 | |
dc.identifier.isiut | NOT_IN_WOS | |
Appears in Collections: | Staff Publications |
Show simple item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.