Melola Discovery

← Melola Discovery

Open access Journal SINTA 1

Comparative analysis of multi-output machine learning models for solar irradiance and wind speed forecasting: A case study in Tamil Nadu, India

International Journal of Power Electronics and Drive Systems · Vol. 17 No. 1 (2026) · pp. 786–796

DOI
10.11591/ijpeds.v17.i1.pp786-796
ISSN
2722-256X, 2088-8694
Published
2026-03-01
Publisher
Institute of Advanced Engineering and Science
Language
eng
License
creativecommons.org/licenses/by-sa/4.0

Abstract

The growing share of wind and solar energy has created challenges in electrical networks, mainly due to intermittency, fluctuations, and uncertainty. These issues affect power system stability, grid operations, and the balance between supply and demand. To address this, accurate prediction of solar irradiance and wind speed is critical for integrating renewable energy into power systems. In this study, we propose a multi-output machine learning approach to predict both global horizontal irradiance (GHI) and wind speed simultaneously. The study uses historical meteorological data obtained from the National Solar Radiation Database (NSRDB) for Tamil Nadu, India. Six regression algorithms: linear regression, gradient boosting, random Forest, extreme gradient boosting (XGB), light gradient boosting machine (LightGBM), and categorical boosting (CatBoost) are tested under identical conditions. Model hyperparameters were tuned using GridSearchCV and Bayesian optimization to ensure robust performance. Before modeling, a comprehensive statistical analysis, including input feature distribution and correlation analysis, was conducted. Model accuracy was evaluated using RMSE, MAE, and R² metrics on both training and testing datasets. The results showed that ensemble tree-based methods outperformed the baseline linear model. Among them, CatBoost produced the best results for GHI prediction, while random forest delivered the most reliable wind speed forecasts, demonstrating strong predictive capability for renewable energy applications.

Keywords

Collaboration network of the authors

31 authors · 107 co-authorship links · 18 across different organisations

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • AMET University
  • Rajalakshmi Engineering College
  • Saveetha University
  • University of Technology and Applied Sciences
  • Easwari Engineering College
  • Dr. M.G.R. Educational and Research Institute
  • CMR University
  • Other organisations
  • Affiliation unknown
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Kalaivani RamaiyanRajalakshmi Engineering College4
I. Arul Doss AdaikalamEaswari Engineering College2
Jayashree KathirvelRajalakshmi Engineering College2
Pushpa SreenivasanAffiliation unknown2
Jonnadula NarasimharaoCMR University2
K. L. KishoreAditya University2
S. PushpaAffiliation unknown1
Sathya SureshkumarAffiliation unknown1
Kannan AndiDr. M.G.R. Educational and Research Institute1
Prabakaran PramasivamAffiliation unknown1
P. KavithaAffiliation unknown1
Deepa SomasundaramAffiliation unknown1
M. VanithaSaveetha University1
Pushpa SreenivasanAMET University1
Soni MohammedDayananda Sagar College of Engineering1
M. VanithaSaveetha University1
N. RajavinuAffiliation unknown1
Pazhanisamy KavithaAffiliation unknown1
Ponkumar GanesapandiyanAffiliation unknown1
P. HemachanduAffiliation unknown1
Gobimohan SivasubramanianAffiliation unknown1
Annamalai MuthuUniversity of Technology and Applied Sciences1
Murali NarayanamurthyUniversity of Technology and Applied Sciences1
B. Ardly Melba ReenaAffiliation unknown1
T. LogeswaranAffiliation unknown1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) http://ijpeds.iaescore.com/index.php/IJPEDS/oai, first harvested 8 Nov 2026, last seen 16 Nov 2026.
Original metadata (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">Comparative analysis of multi-output machine learning models for solar irradiance and wind speed forecasting: A case study in Tamil Nadu, India</dc:title>
	<dc:creator>Selvi, S.</dc:creator>
	<dc:creator>Shanti, N.</dc:creator>
	<dc:creator>Dhandapani, Lakshmi</dc:creator>
	<dc:creator>Bhoopathi, M.</dc:creator>
	<dc:creator>Kumar, T. Sathish</dc:creator>
	<dc:creator>Kavitha, P.</dc:creator>
	<dc:subject xml:lang="en-US">ensemble learning; gradient boosting; multi-output regression; solar irradiance forecasting; wind speed forecasting</dc:subject>
	<dc:description xml:lang="en-US">The growing share of wind and solar energy has created challenges in electrical networks, mainly due to intermittency, fluctuations, and uncertainty. These issues affect power system stability, grid operations, and the balance between supply and demand. To address this, accurate prediction of solar irradiance and wind speed is critical for integrating renewable energy into power systems. In this study, we propose a multi-output machine learning approach to predict both global horizontal irradiance (GHI) and wind speed simultaneously. The study uses historical meteorological data obtained from the National Solar Radiation Database (NSRDB) for Tamil Nadu, India. Six regression algorithms: linear regression, gradient boosting, random Forest, extreme gradient boosting (XGB), light gradient boosting machine (LightGBM), and categorical boosting (CatBoost) are tested under identical conditions. Model hyperparameters were tuned using GridSearchCV and Bayesian optimization to ensure robust performance. Before modeling, a comprehensive statistical analysis, including input feature distribution and correlation analysis, was conducted. Model accuracy was evaluated using RMSE, MAE, and R² metrics on both training and testing datasets. The results showed that ensemble tree-based methods outperformed the baseline linear model. Among them, CatBoost produced the best results for GHI prediction, while random forest delivered the most reliable wind speed forecasts, demonstrating strong predictive capability for renewable energy applications.</dc:description>
	<dc:publisher xml:lang="en-US">Institute of Advanced Engineering and Science</dc:publisher>
	<dc:contributor xml:lang="en-US"></dc:contributor>
	<dc:date>2026-03-01</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US"></dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://ijpeds.iaescore.com/index.php/IJPEDS/article/view/24478</dc:identifier>
	<dc:identifier>10.11591/ijpeds.v17.i1.pp786-796</dc:identifier>
	<dc:source xml:lang="en-US">International Journal of Power Electronics and Drive Systems (IJPEDS); Vol 17, No 1: March 2026; 786-796</dc:source>
	<dc:source>2722-256X</dc:source>
	<dc:source>2088-8694</dc:source>
	<dc:source>10.11591/ijpeds.v17.i1</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://ijpeds.iaescore.com/index.php/IJPEDS/article/view/24478/15197</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2026 S. Selvi, N. Shanti, Lakshmi Dhandapani, M. Bhoopathi, T. Sathish Kumar, P. Kavitha</dc:rights>
	<dc:rights xml:lang="en-US">http://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>