Evaluation of Nonlinear Autoregressive Network with Exogenous Inputs Architectures for Wind Speed forecasting

This research investigates the optimal NARX neural network architecture for forecasting daily maximum wind speed in Dakhla, a region with substantial wind energy resources. Two configurations NARX-SP (open loop) and NARX-P (closed loop) were evaluated using the Levenberg-Marquardt algorithm, known f...

Full description

Saved in:
Bibliographic Details
Main Authors: Kacimi Houda, Fennane Sara, Mabchour Hamza, ALtalqi Fatehi, Echchelh Adil
Format: Article
Language:English
Published: EDP Sciences 2025-01-01
Series:EPJ Web of Conferences
Online Access:https://www.epj-conferences.org/articles/epjconf/pdf/2025/11/epjconf_cofmer2025_05003.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849387342670856192
author Kacimi Houda
Fennane Sara
Mabchour Hamza
ALtalqi Fatehi
Echchelh Adil
author_facet Kacimi Houda
Fennane Sara
Mabchour Hamza
ALtalqi Fatehi
Echchelh Adil
author_sort Kacimi Houda
collection DOAJ
description This research investigates the optimal NARX neural network architecture for forecasting daily maximum wind speed in Dakhla, a region with substantial wind energy resources. Two configurations NARX-SP (open loop) and NARX-P (closed loop) were evaluated using the Levenberg-Marquardt algorithm, known for its fast and efficient training. Predictive performance was assessed using RMSE to measure the gap between predicted and actual values. Results show that NARX-SP outperforms NARX-P, achieving lower RMSE and better forecasting accuracy.
format Article
id doaj-art-d07bb64b603b438186180d7ad2d6789f
institution Kabale University
issn 2100-014X
language English
publishDate 2025-01-01
publisher EDP Sciences
record_format Article
series EPJ Web of Conferences
spelling doaj-art-d07bb64b603b438186180d7ad2d6789f2025-08-20T03:53:51ZengEDP SciencesEPJ Web of Conferences2100-014X2025-01-013260500310.1051/epjconf/202532605003epjconf_cofmer2025_05003Evaluation of Nonlinear Autoregressive Network with Exogenous Inputs Architectures for Wind Speed forecastingKacimi Houda0Fennane Sara1Mabchour Hamza2ALtalqi Fatehi3Echchelh Adil4Laboratory of Electronic systems, Information Processing, Mechanic and Energy, Faculty of Science - Ibn Tofail University-Laboratory of Electronic systems, Information Processing, Mechanic and Energy, Faculty of Science - Ibn Tofail University-Laboratory of Electronic systems, Information Processing, Mechanic and Energy, Faculty of Science - Ibn Tofail University-Laboratory of Electronic systems, Information Processing, Mechanic and Energy, Faculty of Science - Ibn Tofail University-Laboratory of Electronic systems, Information Processing, Mechanic and Energy, Faculty of Science - Ibn Tofail University-This research investigates the optimal NARX neural network architecture for forecasting daily maximum wind speed in Dakhla, a region with substantial wind energy resources. Two configurations NARX-SP (open loop) and NARX-P (closed loop) were evaluated using the Levenberg-Marquardt algorithm, known for its fast and efficient training. Predictive performance was assessed using RMSE to measure the gap between predicted and actual values. Results show that NARX-SP outperforms NARX-P, achieving lower RMSE and better forecasting accuracy.https://www.epj-conferences.org/articles/epjconf/pdf/2025/11/epjconf_cofmer2025_05003.pdf
spellingShingle Kacimi Houda
Fennane Sara
Mabchour Hamza
ALtalqi Fatehi
Echchelh Adil
Evaluation of Nonlinear Autoregressive Network with Exogenous Inputs Architectures for Wind Speed forecasting
EPJ Web of Conferences
title Evaluation of Nonlinear Autoregressive Network with Exogenous Inputs Architectures for Wind Speed forecasting
title_full Evaluation of Nonlinear Autoregressive Network with Exogenous Inputs Architectures for Wind Speed forecasting
title_fullStr Evaluation of Nonlinear Autoregressive Network with Exogenous Inputs Architectures for Wind Speed forecasting
title_full_unstemmed Evaluation of Nonlinear Autoregressive Network with Exogenous Inputs Architectures for Wind Speed forecasting
title_short Evaluation of Nonlinear Autoregressive Network with Exogenous Inputs Architectures for Wind Speed forecasting
title_sort evaluation of nonlinear autoregressive network with exogenous inputs architectures for wind speed forecasting
url https://www.epj-conferences.org/articles/epjconf/pdf/2025/11/epjconf_cofmer2025_05003.pdf
work_keys_str_mv AT kacimihouda evaluationofnonlinearautoregressivenetworkwithexogenousinputsarchitecturesforwindspeedforecasting
AT fennanesara evaluationofnonlinearautoregressivenetworkwithexogenousinputsarchitecturesforwindspeedforecasting
AT mabchourhamza evaluationofnonlinearautoregressivenetworkwithexogenousinputsarchitecturesforwindspeedforecasting
AT altalqifatehi evaluationofnonlinearautoregressivenetworkwithexogenousinputsarchitecturesforwindspeedforecasting
AT echchelhadil evaluationofnonlinearautoregressivenetworkwithexogenousinputsarchitecturesforwindspeedforecasting