Dalarna University's logo and link to the university's website

du.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Enhancing electric vehicle charging load prediction in data-scarce scenarios: A hybrid deep learning-based approach integrating clustering analysis and transfer learning
Dalarna University, School of Information and Engineering, Energy Technology. Sustainable Energy Res Ctr SERC, Falun, Sweden..ORCID iD: 0000-0001-9261-3784
Dalarna University, School of Information and Engineering, Energy Technology. Dalarna Univ, Sustainable Energy Res Ctr SERC, Falun, Sweden..ORCID iD: 0000-0003-3025-6333
City Univ Hong Kong, Dept Architectural & Civil Engn, Hong Kong, Peoples R China, CN..
2025 (English)In: Energy and AI, E-ISSN 2666-5468, Vol. 21, article id 100545Article in journal (Refereed) Published
Sustainable development
SDG 7: Affordable and clean energy
Abstract [en]

Accurate electric vehicle (EV) load forecasting is crucial for efficient grid operations and demand-side management, yet it is challenging in data-scarce scenarios. Transfer learning (TL) offers a solution by transferring knowledge from data-rich to data-limited scenarios. However, when the knowledge domain exhibits highly diverse behaviors, applying TL alone could introduce large biases, reducing accuracy and limiting its effectiveness. To address this problem, this study proposes a hybrid deep learning-based framework that integrates TL and K-means clustering. The proposed approach consists of two phases. In the source domain phase, a deep-learning-based model is trained using the full dataset and then fine-tuned using clustered user behaviors. In the target domain phase with limited data, TL is applied to transfer knowledge from the source-domain finetuned cluster models. For validation, the developed prediction method has been tested using real-world datasets and compared with two other cases: one with applying TL from the source-domain base model trained from full dataset, and one without applying TL. Results show the hybrid method improves forecasting accuracy, reducing the normalized root mean squared error by 3.99 % and 8.22 %, respectively. This study establishes a structured approach for targeted knowledge transfer, enhancing prediction accuracy in data-scarce settings. The framework is scalable and adaptable to other energy forecasting applications, supporting sustainable and resilient energy management.

Place, publisher, year, edition, pages
ELSEVIER , 2025. Vol. 21, article id 100545
Keywords [en]
EV load forecasting, Transfer learning, Fine tuning, BiLSTM, Deep learning, Clustering
National Category
Computer Sciences Computer Systems
Identifiers
URN: urn:nbn:se:du-50889DOI: 10.1016/j.egyai.2025.100545ISI: 001525294800001Scopus ID: 2-s2.0-105009288209OAI: oai:DiVA.org:du-50889DiVA, id: diva2:1985977
Available from: 2025-07-29 Created: 2025-07-29 Last updated: 2025-10-13Bibliographically approved

Open Access in DiVA

fulltext(9824 kB)32 downloads
File information
File name FULLTEXT01.pdfFile size 9824 kBChecksum SHA-512
2257bc6da8b7a8653b85e49600dcddc4ecd199e177583c589af7383a419c8e4cfef8fbde2a294cf32922346cd6709292a8792b1726f25b314f7ac1fd625994af
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Zafar, RehmanHuang, Pei

Search in DiVA

By author/editor
Zafar, RehmanHuang, Pei
By organisation
Energy Technology
In the same journal
Energy and AI
Computer SciencesComputer Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 32 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 114 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf