Robust Optimal Sizing of a Stand-Alone Hybrid Renewable Energy System Using Machine Learning-Based Uncertainty Sets

This study introduces an adaptive robust approach for optimally sizing hybrid renewable energy systems (HRESs) comprising solar panels, wind turbines, batteries, and a diesel generator. It integrates vector auto-regressive models (VAR) and neural networks (NN) into dynamic uncertainty sets (DUSs) to...

Full description

Saved in:
Bibliographic Details
Main Authors: Ali Keyvandarian, Ahmed Saif, Ronald Pelot
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/5/1130
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850030366498226176
author Ali Keyvandarian
Ahmed Saif
Ronald Pelot
author_facet Ali Keyvandarian
Ahmed Saif
Ronald Pelot
author_sort Ali Keyvandarian
collection DOAJ
description This study introduces an adaptive robust approach for optimally sizing hybrid renewable energy systems (HRESs) comprising solar panels, wind turbines, batteries, and a diesel generator. It integrates vector auto-regressive models (VAR) and neural networks (NN) into dynamic uncertainty sets (DUSs) to address temporal auto-correlations and cross-correlations among uncertain parameters like energy demand and solar and wind energy supply. These DUSs are compared to static and independent dynamic uncertainty sets based on time series (TS) from the literature. An exact iterative algorithm is developed to solve the problem effectively. A case study of a northern Ontario community evaluates the proposed framework and the solution method using real test data. Simulation reveals a 10.7% increase in capital cost on average but a 36.2% decrease in operational cost, resulting in a 16.4% total cost reduction and an 8.1% improvement in system reliability compared to the nominal model employing point estimates. Furthermore, the proposed VAR- and NN-based DUSs significantly outperform classical static and TS-based dynamic sets, underscoring the necessity of considering cross-correlations in uncertainty quantification.
format Article
id doaj-art-c4f044d1501f4b0183e9984b342232cf
institution DOAJ
issn 1996-1073
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-c4f044d1501f4b0183e9984b342232cf2025-08-20T02:59:14ZengMDPI AGEnergies1996-10732025-02-01185113010.3390/en18051130Robust Optimal Sizing of a Stand-Alone Hybrid Renewable Energy System Using Machine Learning-Based Uncertainty SetsAli Keyvandarian0Ahmed Saif1Ronald Pelot2Department of Industrial Engineering, Dalhousie University, 5269 Morris Street, Halifax, NS B3H 4R2, CanadaDepartment of Industrial Engineering, Dalhousie University, 5269 Morris Street, Halifax, NS B3H 4R2, CanadaDepartment of Industrial Engineering, Dalhousie University, 5269 Morris Street, Halifax, NS B3H 4R2, CanadaThis study introduces an adaptive robust approach for optimally sizing hybrid renewable energy systems (HRESs) comprising solar panels, wind turbines, batteries, and a diesel generator. It integrates vector auto-regressive models (VAR) and neural networks (NN) into dynamic uncertainty sets (DUSs) to address temporal auto-correlations and cross-correlations among uncertain parameters like energy demand and solar and wind energy supply. These DUSs are compared to static and independent dynamic uncertainty sets based on time series (TS) from the literature. An exact iterative algorithm is developed to solve the problem effectively. A case study of a northern Ontario community evaluates the proposed framework and the solution method using real test data. Simulation reveals a 10.7% increase in capital cost on average but a 36.2% decrease in operational cost, resulting in a 16.4% total cost reduction and an 8.1% improvement in system reliability compared to the nominal model employing point estimates. Furthermore, the proposed VAR- and NN-based DUSs significantly outperform classical static and TS-based dynamic sets, underscoring the necessity of considering cross-correlations in uncertainty quantification.https://www.mdpi.com/1996-1073/18/5/1130hybrid renewable energy systemsadaptive robust optimizationdynamic uncertainty setsvector auto-regressive modelsneural networks
spellingShingle Ali Keyvandarian
Ahmed Saif
Ronald Pelot
Robust Optimal Sizing of a Stand-Alone Hybrid Renewable Energy System Using Machine Learning-Based Uncertainty Sets
Energies
hybrid renewable energy systems
adaptive robust optimization
dynamic uncertainty sets
vector auto-regressive models
neural networks
title Robust Optimal Sizing of a Stand-Alone Hybrid Renewable Energy System Using Machine Learning-Based Uncertainty Sets
title_full Robust Optimal Sizing of a Stand-Alone Hybrid Renewable Energy System Using Machine Learning-Based Uncertainty Sets
title_fullStr Robust Optimal Sizing of a Stand-Alone Hybrid Renewable Energy System Using Machine Learning-Based Uncertainty Sets
title_full_unstemmed Robust Optimal Sizing of a Stand-Alone Hybrid Renewable Energy System Using Machine Learning-Based Uncertainty Sets
title_short Robust Optimal Sizing of a Stand-Alone Hybrid Renewable Energy System Using Machine Learning-Based Uncertainty Sets
title_sort robust optimal sizing of a stand alone hybrid renewable energy system using machine learning based uncertainty sets
topic hybrid renewable energy systems
adaptive robust optimization
dynamic uncertainty sets
vector auto-regressive models
neural networks
url https://www.mdpi.com/1996-1073/18/5/1130
work_keys_str_mv AT alikeyvandarian robustoptimalsizingofastandalonehybridrenewableenergysystemusingmachinelearningbaseduncertaintysets
AT ahmedsaif robustoptimalsizingofastandalonehybridrenewableenergysystemusingmachinelearningbaseduncertaintysets
AT ronaldpelot robustoptimalsizingofastandalonehybridrenewableenergysystemusingmachinelearningbaseduncertaintysets