Vis enkel innførsel

dc.contributor.authorDalal, Nisha
dc.contributor.authorMølnå, Martin
dc.contributor.authorHerrem, Mette
dc.contributor.authorRøen, Magne
dc.contributor.authorGundersen, Odd Erik
dc.date.accessioned2021-01-25T18:35:11Z
dc.date.available2021-01-25T18:35:11Z
dc.date.created2020-11-22T23:16:09Z
dc.date.issued2020
dc.identifier.isbn978-1-57735-823-7
dc.identifier.urihttps://hdl.handle.net/11250/2724630
dc.description.abstractWe present a commercially deployed machine learning system that automates the day-ahead nomination of the expected grid loss for a Norwegian utility company. It meets several practical constraints and issues related to, among other things, delayed, missing and incorrect data and a small data set. The system incorporates a total of 24 different models that performs forecasts for three sub-grids. Each day one model is selected for making the hourly day-ahead forecasts for each sub-grid. The deployed system reduces the MAE with 41% from 3.68 MW to 2.17 MW per hour from mid July to mid October. It is robust and reduces manual work.en_US
dc.language.isoengen_US
dc.publisherAssociation for the Advancement of Artificial Intelligenceen_US
dc.relation.ispartofThe Thirty-Fourth Conference on Artificial Intelligence, AAAI
dc.titleDay-Ahead Forecasting of Losses in the Distribution Networken_US
dc.typeChapteren_US
dc.description.versionpublishedVersionen_US
dc.identifier.doi10.1609/aaai.v34i08.7018
dc.identifier.cristin1850845
dc.description.localcodeThis chapter will not be available due to copyright restrictions (c) 2020 by Association for the Advancement of Artificial Intelligenceen_US
cristin.ispublishedtrue
cristin.fulltextoriginal
cristin.qualitycode1


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel