The University of Southampton
University of Southampton Institutional Repository

Data-driven modelling of the irradiance and temperature effect on the photovoltaic model parameters

Data-driven modelling of the irradiance and temperature effect on the photovoltaic model parameters
Data-driven modelling of the irradiance and temperature effect on the photovoltaic model parameters
The irradiance and temperature impact on the photovoltaic(PV) model has been extensively modelled in the past using analytical physics-based expressions. However,such methods tend to under perform under low irradiance conditions and certain PV technologies. This paper explores the potential of four machine learning (ML) alternatives on this task, i.e. Neural Networks, Support Vector Machine, K Nearest Neighbours, and Extreme Gradient Boosting. This analysis is performed on datasets of mono- and poly- crystalline PV modules provided by NREL. The findings demonstrate that ML methods generally outperform the widely adopted analytical approach, particularly in the parasitic resistances representation. Extreme Gradient Boosting is found to be the front-runner, while the results also indicate potential for transferability of models trained on one PV module to another of the same PV technology.
photovoltaic(PV), single diode model, five parameters, Machine Learning, transferability
Springer
Nikolopoulos, Angelos R.
3a6d9258-9a8f-47f2-8593-083eb9f0f6a3
Batzelis, Efstratios
2a85086e-e403-443c-81a6-e3b4ee16ae5e
Lewin, Paul
78b4fc49-1cb3-4db9-ba90-3ae70c0f639e
Nikolopoulos, Angelos R.
3a6d9258-9a8f-47f2-8593-083eb9f0f6a3
Batzelis, Efstratios
2a85086e-e403-443c-81a6-e3b4ee16ae5e
Lewin, Paul
78b4fc49-1cb3-4db9-ba90-3ae70c0f639e

Nikolopoulos, Angelos R., Batzelis, Efstratios and Lewin, Paul (2024) Data-driven modelling of the irradiance and temperature effect on the photovoltaic model parameters. In Data-driven modelling of the irradiance and temperature effect on the photovoltaic model parameters. Springer. 6 pp . (In Press)

Record type: Conference or Workshop Item (Paper)

Abstract

The irradiance and temperature impact on the photovoltaic(PV) model has been extensively modelled in the past using analytical physics-based expressions. However,such methods tend to under perform under low irradiance conditions and certain PV technologies. This paper explores the potential of four machine learning (ML) alternatives on this task, i.e. Neural Networks, Support Vector Machine, K Nearest Neighbours, and Extreme Gradient Boosting. This analysis is performed on datasets of mono- and poly- crystalline PV modules provided by NREL. The findings demonstrate that ML methods generally outperform the widely adopted analytical approach, particularly in the parasitic resistances representation. Extreme Gradient Boosting is found to be the front-runner, while the results also indicate potential for transferability of models trained on one PV module to another of the same PV technology.

Text
AN_2024_ELECTRIMACS_Accepted_Manuscript - Accepted Manuscript
Restricted to Repository staff only
Request a copy

More information

Accepted/In Press date: 5 March 2024
Venue - Dates: 15th International Conference on Modeling and Simulation of Electric Machines, Converters and Systems, Doctoral School and Board of Trustees' Office building, Riu Sec Campus of the Universitat Jaume I, Castelló de la Plana, Spain, 2024-05-27 - 2024-05-30
Keywords: photovoltaic(PV), single diode model, five parameters, Machine Learning, transferability

Identifiers

Local EPrints ID: 487832
URI: http://eprints.soton.ac.uk/id/eprint/487832
PURE UUID: 0dafaf1f-87ab-4b26-9ba1-827931518c64
ORCID for Efstratios Batzelis: ORCID iD orcid.org/0000-0002-2967-3677
ORCID for Paul Lewin: ORCID iD orcid.org/0000-0002-3299-2556

Catalogue record

Date deposited: 06 Mar 2024 17:31
Last modified: 18 Mar 2024 04:01

Export record

Contributors

Author: Angelos R. Nikolopoulos
Author: Efstratios Batzelis ORCID iD
Author: Paul Lewin ORCID iD

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×