Multistep PV power forecasting using deep learning models and the reptile search algorithm

Forecasting Photovoltaic (PV) power output is a key challenge in renewable energy systems, particularly for short- to mid-term operational planning. Accurate multi-step PV forecasting supports efficient energy scheduling, grid stability, and integration of solar resources. This study investigates th...

Full description

Saved in:
Bibliographic Details
Main Authors: Sameer Al-Dahidi, Hussein Alahmer, Bilal Rinchi, Abdullah Bani-Abdullah, Mohammad Alrbai, Osama Ayadi, Loiy Al-Ghussain
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Results in Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590123025023370
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849318273718419456
author Sameer Al-Dahidi
Hussein Alahmer
Bilal Rinchi
Abdullah Bani-Abdullah
Mohammad Alrbai
Osama Ayadi
Loiy Al-Ghussain
author_facet Sameer Al-Dahidi
Hussein Alahmer
Bilal Rinchi
Abdullah Bani-Abdullah
Mohammad Alrbai
Osama Ayadi
Loiy Al-Ghussain
author_sort Sameer Al-Dahidi
collection DOAJ
description Forecasting Photovoltaic (PV) power output is a key challenge in renewable energy systems, particularly for short- to mid-term operational planning. Accurate multi-step PV forecasting supports efficient energy scheduling, grid stability, and integration of solar resources. This study investigates the performance of three advanced deep learning models: Temporal Convolutional Network (TCN), Minimal Gated Unit (MGU), and Temporal Fusion Transformer (TFT), applied to one-day-ahead and three-day-ahead PV power forecasting. The Reptile Search Algorithm (RSA), a novel metaheuristic optimizer, is employed for hyperparameter tuning. Results show that TFT consistently outperforms the other models, achieving Root Mean Square Error (RMSE) values of 6.256 kWh and 8.353 kWh and coefficient of determination (R²) scores of 98.92 % and 98.07 % for the one-day and three-day forecasts, respectively. RSA optimization yields significant performance gains, reducing TFT’s RMSE by 44.57 % and 42.43 % relative to its non-optimized baseline. While MGU had the weakest overall performance, particularly under summer conditions and zero-generation periods, it performed better in the one-day-ahead setting than TCN did in the three-day-ahead scenario. Further, RSA was benchmarked against the Whale Optimization Algorithm (WOA), Gray Wolf Optimizer (GWO), and Constrained Particle Swarm Optimization (CPSO), and consistently outperformed all three across all models in both forecasting horizons. However, this is the first study to evaluate MGU in the context of PV forecasting, and its performance may vary under different case studies. It is shown that TFT and RSA offer superior accuracy and generalization across forecast horizons. These findings support the broader adoption and further benchmarking of TFT future research.
format Article
id doaj-art-0453da21528a4e208d8f7282efea0080
institution Kabale University
issn 2590-1230
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series Results in Engineering
spelling doaj-art-0453da21528a4e208d8f7282efea00802025-08-20T03:50:54ZengElsevierResults in Engineering2590-12302025-09-012710626510.1016/j.rineng.2025.106265Multistep PV power forecasting using deep learning models and the reptile search algorithmSameer Al-Dahidi0Hussein Alahmer1Bilal Rinchi2Abdullah Bani-Abdullah3Mohammad Alrbai4Osama Ayadi5Loiy Al-Ghussain6Department of Mechanical and Maintenance Engineering, School of Applied Technical Sciences, German Jordanian University, Amman, 11180, Jordan; Corresponding authors.Department of Automated Systems, Faculty of Artificial Intelligence, Al-Balqa Applied University, Al-Salt, 19117, Jordan; Corresponding authors.Department of Mechanical and Maintenance Engineering, School of Applied Technical Sciences, German Jordanian University, Amman, 11180, Jordan; Corresponding authors.Department of Electrical Engineering, Faculty of Engineering, Applied Science Private University, Amman, 11931, JordanDepartment of Mechanical Engineering, School of Engineering, The University of Jordan, Amman, 11942, JordanDepartment of Mechanical Engineering, School of Engineering, The University of Jordan, Amman, 11942, JordanSystems Assessment Center, Energy Systems and Infrastructure Analysis Division, Argonne National Laboratory, Lemont, IL, 60439, USAForecasting Photovoltaic (PV) power output is a key challenge in renewable energy systems, particularly for short- to mid-term operational planning. Accurate multi-step PV forecasting supports efficient energy scheduling, grid stability, and integration of solar resources. This study investigates the performance of three advanced deep learning models: Temporal Convolutional Network (TCN), Minimal Gated Unit (MGU), and Temporal Fusion Transformer (TFT), applied to one-day-ahead and three-day-ahead PV power forecasting. The Reptile Search Algorithm (RSA), a novel metaheuristic optimizer, is employed for hyperparameter tuning. Results show that TFT consistently outperforms the other models, achieving Root Mean Square Error (RMSE) values of 6.256 kWh and 8.353 kWh and coefficient of determination (R²) scores of 98.92 % and 98.07 % for the one-day and three-day forecasts, respectively. RSA optimization yields significant performance gains, reducing TFT’s RMSE by 44.57 % and 42.43 % relative to its non-optimized baseline. While MGU had the weakest overall performance, particularly under summer conditions and zero-generation periods, it performed better in the one-day-ahead setting than TCN did in the three-day-ahead scenario. Further, RSA was benchmarked against the Whale Optimization Algorithm (WOA), Gray Wolf Optimizer (GWO), and Constrained Particle Swarm Optimization (CPSO), and consistently outperformed all three across all models in both forecasting horizons. However, this is the first study to evaluate MGU in the context of PV forecasting, and its performance may vary under different case studies. It is shown that TFT and RSA offer superior accuracy and generalization across forecast horizons. These findings support the broader adoption and further benchmarking of TFT future research.http://www.sciencedirect.com/science/article/pii/S2590123025023370Reptile search algorithmPhotovoltaic power forecastingDeep learningOptimizationMultistep forecasting
spellingShingle Sameer Al-Dahidi
Hussein Alahmer
Bilal Rinchi
Abdullah Bani-Abdullah
Mohammad Alrbai
Osama Ayadi
Loiy Al-Ghussain
Multistep PV power forecasting using deep learning models and the reptile search algorithm
Results in Engineering
Reptile search algorithm
Photovoltaic power forecasting
Deep learning
Optimization
Multistep forecasting
title Multistep PV power forecasting using deep learning models and the reptile search algorithm
title_full Multistep PV power forecasting using deep learning models and the reptile search algorithm
title_fullStr Multistep PV power forecasting using deep learning models and the reptile search algorithm
title_full_unstemmed Multistep PV power forecasting using deep learning models and the reptile search algorithm
title_short Multistep PV power forecasting using deep learning models and the reptile search algorithm
title_sort multistep pv power forecasting using deep learning models and the reptile search algorithm
topic Reptile search algorithm
Photovoltaic power forecasting
Deep learning
Optimization
Multistep forecasting
url http://www.sciencedirect.com/science/article/pii/S2590123025023370
work_keys_str_mv AT sameeraldahidi multisteppvpowerforecastingusingdeeplearningmodelsandthereptilesearchalgorithm
AT husseinalahmer multisteppvpowerforecastingusingdeeplearningmodelsandthereptilesearchalgorithm
AT bilalrinchi multisteppvpowerforecastingusingdeeplearningmodelsandthereptilesearchalgorithm
AT abdullahbaniabdullah multisteppvpowerforecastingusingdeeplearningmodelsandthereptilesearchalgorithm
AT mohammadalrbai multisteppvpowerforecastingusingdeeplearningmodelsandthereptilesearchalgorithm
AT osamaayadi multisteppvpowerforecastingusingdeeplearningmodelsandthereptilesearchalgorithm
AT loiyalghussain multisteppvpowerforecastingusingdeeplearningmodelsandthereptilesearchalgorithm