A tiered NARX model for forecasting day-ahead energy production in distributed solar PV systems

This study presents a hierarchical forecasting approach for day-ahead energy production in distributed solar Photovoltaic (PV) systems using a tiered Nonlinear Autoregressive Exogenous (NARX) model. The methodology was applied to 52 PV systems installed at The University of Jordan, covering three pr...

Full description

Saved in:
Bibliographic Details
Main Authors: Sameer Al-Dahidi, Mohammad Alrbai, Bilal Rinchi, Loiy Al-Ghussain, Osama Ayadi, Ali Alahmer
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Cleaner Engineering and Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666790824001113
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850122857970925568
author Sameer Al-Dahidi
Mohammad Alrbai
Bilal Rinchi
Loiy Al-Ghussain
Osama Ayadi
Ali Alahmer
author_facet Sameer Al-Dahidi
Mohammad Alrbai
Bilal Rinchi
Loiy Al-Ghussain
Osama Ayadi
Ali Alahmer
author_sort Sameer Al-Dahidi
collection DOAJ
description This study presents a hierarchical forecasting approach for day-ahead energy production in distributed solar Photovoltaic (PV) systems using a tiered Nonlinear Autoregressive Exogenous (NARX) model. The methodology was applied to 52 PV systems installed at The University of Jordan, covering three prediction scales: fleet-wide, zone-specific, and site-specific. The model incorporated weather data, including solar irradiation, temperature, and humidity, to forecast the next day's energy production. Based on a new metric called the OverallMetric, fleet-wide predictions outperform the zone-specific and site-specific averages by 3.21% and 5.35%, respectively. Normalized Root Mean Square Errors (nRMSE) for fleet-wide, zone-specific, and site-specific predictions are 0.148, 0.141, and 0.137, respectively. The Correlation Coefficient (R) is above 80% for all prediction scales, with the accuracy constrained by the model's difficulty in adapting to abrupt weather changes, leading to overestimation. The model performs best when weather patterns and PV generation are consistent with previous days. This demonstrates that adapting models to the characteristics of each scale significantly improves forecast accuracy, enabling more effective macro-level planning and micro-level operational decisions.
format Article
id doaj-art-b2b2cbb6b3534c72aa585bf44b8d8f82
institution OA Journals
issn 2666-7908
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Cleaner Engineering and Technology
spelling doaj-art-b2b2cbb6b3534c72aa585bf44b8d8f822025-08-20T02:34:44ZengElsevierCleaner Engineering and Technology2666-79082024-12-012310083110.1016/j.clet.2024.100831A tiered NARX model for forecasting day-ahead energy production in distributed solar PV systemsSameer Al-Dahidi0Mohammad Alrbai1Bilal Rinchi2Loiy Al-Ghussain3Osama Ayadi4Ali Alahmer5Department of Mechanical and Maintenance Engineering, School of Applied Technical Sciences, German Jordanian University, Amman, 11180, Jordan; Corresponding author.Department of Mechanical Engineering, School of Engineering, University of Jordan, Amman, 11942, JordanDepartment of Mechanical and Maintenance Engineering, School of Applied Technical Sciences, German Jordanian University, Amman, 11180, Jordan; Department of Mechanical Engineering, School of Engineering, University of Jordan, Amman, 11942, JordanEnergy Systems and Infrastructure Analysis Division, Argonne National Laboratory, Lemont, IL, 60439, USADepartment of Mechanical Engineering, School of Engineering, University of Jordan, Amman, 11942, JordanDepartment of Mechanical Engineering, Tuskegee University, Tuskegee, AL, 36088, USAThis study presents a hierarchical forecasting approach for day-ahead energy production in distributed solar Photovoltaic (PV) systems using a tiered Nonlinear Autoregressive Exogenous (NARX) model. The methodology was applied to 52 PV systems installed at The University of Jordan, covering three prediction scales: fleet-wide, zone-specific, and site-specific. The model incorporated weather data, including solar irradiation, temperature, and humidity, to forecast the next day's energy production. Based on a new metric called the OverallMetric, fleet-wide predictions outperform the zone-specific and site-specific averages by 3.21% and 5.35%, respectively. Normalized Root Mean Square Errors (nRMSE) for fleet-wide, zone-specific, and site-specific predictions are 0.148, 0.141, and 0.137, respectively. The Correlation Coefficient (R) is above 80% for all prediction scales, with the accuracy constrained by the model's difficulty in adapting to abrupt weather changes, leading to overestimation. The model performs best when weather patterns and PV generation are consistent with previous days. This demonstrates that adapting models to the characteristics of each scale significantly improves forecast accuracy, enabling more effective macro-level planning and micro-level operational decisions.http://www.sciencedirect.com/science/article/pii/S2666790824001113Solar photovoltaic systemsPrediction scalesEnergy productionForecasting analysisNonlinear autoregressive exogenousReal case study
spellingShingle Sameer Al-Dahidi
Mohammad Alrbai
Bilal Rinchi
Loiy Al-Ghussain
Osama Ayadi
Ali Alahmer
A tiered NARX model for forecasting day-ahead energy production in distributed solar PV systems
Cleaner Engineering and Technology
Solar photovoltaic systems
Prediction scales
Energy production
Forecasting analysis
Nonlinear autoregressive exogenous
Real case study
title A tiered NARX model for forecasting day-ahead energy production in distributed solar PV systems
title_full A tiered NARX model for forecasting day-ahead energy production in distributed solar PV systems
title_fullStr A tiered NARX model for forecasting day-ahead energy production in distributed solar PV systems
title_full_unstemmed A tiered NARX model for forecasting day-ahead energy production in distributed solar PV systems
title_short A tiered NARX model for forecasting day-ahead energy production in distributed solar PV systems
title_sort tiered narx model for forecasting day ahead energy production in distributed solar pv systems
topic Solar photovoltaic systems
Prediction scales
Energy production
Forecasting analysis
Nonlinear autoregressive exogenous
Real case study
url http://www.sciencedirect.com/science/article/pii/S2666790824001113
work_keys_str_mv AT sameeraldahidi atierednarxmodelforforecastingdayaheadenergyproductionindistributedsolarpvsystems
AT mohammadalrbai atierednarxmodelforforecastingdayaheadenergyproductionindistributedsolarpvsystems
AT bilalrinchi atierednarxmodelforforecastingdayaheadenergyproductionindistributedsolarpvsystems
AT loiyalghussain atierednarxmodelforforecastingdayaheadenergyproductionindistributedsolarpvsystems
AT osamaayadi atierednarxmodelforforecastingdayaheadenergyproductionindistributedsolarpvsystems
AT alialahmer atierednarxmodelforforecastingdayaheadenergyproductionindistributedsolarpvsystems
AT sameeraldahidi tierednarxmodelforforecastingdayaheadenergyproductionindistributedsolarpvsystems
AT mohammadalrbai tierednarxmodelforforecastingdayaheadenergyproductionindistributedsolarpvsystems
AT bilalrinchi tierednarxmodelforforecastingdayaheadenergyproductionindistributedsolarpvsystems
AT loiyalghussain tierednarxmodelforforecastingdayaheadenergyproductionindistributedsolarpvsystems
AT osamaayadi tierednarxmodelforforecastingdayaheadenergyproductionindistributedsolarpvsystems
AT alialahmer tierednarxmodelforforecastingdayaheadenergyproductionindistributedsolarpvsystems