EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Short‐ and Long‐Term Load Forecasting Using VMD With Temporal Dual Learners Network: A Case Study in Kuwait

Maha Alqallaf, Nour Hameed Hasan, Dina Alostath, Salman Zakareya

International Journal of Energy Research · 2026-01 · 2026 (1)

DOI: 10.1155/er/1202369 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Energy Research, online erschienen am 21.05.2026. Verfasst von Maha Alqallaf und 3 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Forecasting the demand for electrical load precisely is essential for the steady and energy‐efficient operation of today’s power systems, especially in places where there is much variability in demand. In this study, we propose a novel hybrid deep learning framework, termed variational mode decomposition with temporal dual learners network (VMD‐TDLNet), for both short‐term and long‐term electricity load forecasting. At the beginning, VMD is used on the daily peak load time series to extract different intrinsic mode functions (IMFs) of various frequencies. Every decomposed mode is processed in parallel with long short‐term memory (LSTM) and Autoformer architectures. LSTM handles short‐term changes in the data, and Autoformer focuses on long‐term trends via its autocorrelation property. After that, the outputs from both network branches are passed through fully connected (FC) layers and a final regression layer for precise prediction of load. The effectiveness of VMD‐TDLNet is evaluated using real‐world daily electricity consumption data from Kuwait over a 1‐year period, demonstrating its superior performance in terms of prediction accuracy, robustness to noise, and ability to generalize across temporal scales compared to baseline models. The proposed method reduces normalized mean absolute error (NMAE) by 10.1% compared to Transformer and 25.83% compared to LSTM in 1‐year forecasting. The method presents a strong and highly adjustable way to forecast loads in smart grid and energy management applications.

Zitieren

APA

Alqallaf, M., Hasan, N. H., Alostath, D., & Zakareya, S. (2026). Short‐ and Long‐Term Load Forecasting Using VMD With Temporal Dual Learners Network: A Case Study in Kuwait. International Journal of Energy Research, 2026(1). https://doi.org/10.1155/er/1202369

Vancouver

Alqallaf M, Hasan NH, Alostath D, Zakareya S. Short‐ and Long‐Term Load Forecasting Using VMD With Temporal Dual Learners Network: A Case Study in Kuwait. International Journal of Energy Research. 2026;2026(1). doi:10.1155/er/1202369

BibTeX
@article{Alqallaf2026,
  author = {Alqallaf, Maha and Hasan, Nour Hameed and Alostath, Dina and Zakareya, Salman},
  title = {Short‐ and Long‐Term Load Forecasting Using VMD With Temporal Dual Learners Network: A Case Study in Kuwait},
  journal = {International Journal of Energy Research},
  year = {2026},
  volume = {2026},
  number = {1},
  doi = {10.1155/er/1202369}
}
Kostenlos starten →