Sökning: onr:"swepub:oai:DiVA.org:kau-95022" >
DA-LSTM: A dynamic ...
-
Bayram, FirasKarlstads universitet,Institutionen för matematik och datavetenskap (from 2013)
(författare)
DA-LSTM: A dynamic drift-adaptive learning framework for interval load forecasting with LSTM networks
- Artikel/kapitelEngelska2023
Förlag, utgivningsår, omfång ...
-
Elsevier,2023
-
electronicrdacarrier
Nummerbeteckningar
-
LIBRIS-ID:oai:DiVA.org:kau-95022
-
https://urn.kb.se/resolve?urn=urn:nbn:se:kau:diva-95022URI
-
https://doi.org/10.1016/j.engappai.2023.106480DOI
Kompletterande språkuppgifter
-
Språk:engelska
-
Sammanfattning på:engelska
Ingår i deldatabas
Klassifikation
-
Ämneskategori:ref swepub-contenttype
-
Ämneskategori:art swepub-publicationtype
Anmärkningar
-
Load forecasting is a crucial topic in energy management systems (EMS) due to its vital role in optimizing energy scheduling and enabling more flexible and intelligent power grid systems. As a result, these systems allow power utility companies to respond promptly to demands in the electricity market. Deep learning (DL) models have been commonly employed in load forecasting problems supported by adaptation mechanisms to cope with the changing pattern of consumption by customers, known as concept drift. A drift magnitude threshold should be defined to design change detection methods to identify drifts. While the drift magnitude in load forecasting problems can vary significantly over time, existing literature often assumes a fixed drift magnitude threshold, which should be dynamically adjusted rather than fixed during system evolution. To address this gap, in this paper, we propose a dynamic drift-adaptive Long Short-Term Memory (DA-LSTM) framework that can improve the performance of load forecasting models without requiring a drift threshold setting. We integrate several strategies into the framework based on active and passive adaptation approaches. To evaluate DA-LSTM in real-life settings, we thoroughly analyze the proposed framework and deploy it in a real-world problem through a cloud-based environment. Efficiency is evaluated in terms of the prediction performance of each approach and computational cost. The experiments show performance improvements on multiple evaluation metrics achieved by our framework compared to baseline methods from the literature. Finally, we present a trade-off analysis between prediction performance and computational costs.
Ämnesord och genrebeteckningar
Biuppslag (personer, institutioner, konferenser, titlar ...)
-
Aupke, PhilKarlstads universitet,Institutionen för matematik och datavetenskap (from 2013)(Swepub:kau)philaupk
(författare)
-
Ahmed, Bestoun S.,1982-Karlstads universitet,Institutionen för matematik och datavetenskap (from 2013)(Swepub:kau)bestalbe
(författare)
-
Kassler, Andreas,1968-Karlstads universitet,Institutionen för matematik och datavetenskap (from 2013)(Swepub:kau)andrkass
(författare)
-
Theocharis, AndreasKarlstads universitet,Institutionen för ingenjörsvetenskap och fysik (from 2013)(Swepub:kau)andrtheo
(författare)
-
Forsman, JonasCGI, Karlstad, Sweden
(författare)
-
Karlstads universitetInstitutionen för matematik och datavetenskap (from 2013)
(creator_code:org_t)
Sammanhörande titlar
-
Ingår i:Engineering applications of artificial intelligence: Elsevier1230952-19761873-6769
Internetlänk
Hitta via bibliotek
Till lärosätets databas