Citation: Islam, M.S.S.; Ghosh, P.;
Faruque, M.O.; Islam, M.R.;
Hossain, M.A.; Alam, M.S.;
Islam Sheikh, M.R. Optimizing
Short-Term Photovoltaic Power
Forecasting: A Novel Approach with
Gaussian Process Regression and
Bayesian Hyperparameter Tuning.
Processes 2024, 12, 546. https://
doi.org/10.3390/pr12030546
Academic Editors: Mohan Lal Kolhe
and Peng Li
Received: 23 January 2024
Revised: 24 February 2024
Accepted: 4 March 2024
Published: 11 March 2024
Copyright: © 2024 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
processes
Article
Optimizing Short-Term Photovoltaic Power Forecasting: A Novel
Approach with Gaussian Process Regression and Bayesian
Hyperparameter Tuning
Md. Samin Safayat Islam
1
, Puja Ghosh
1
, Md. Omer Faruque
2
, Md. Rashidul Islam
1
, Md. Alamgir Hossain
3,
* ,
Md. Shafiul Alam
4
and Md. Rafiqul Islam Sheikh
1
1
Department of Electrical & Electronic Engineering, Rajshahi University of Engineering & Technology,
Rajshahi 6204, Bangladesh; samintayafas@gmail.com (M.S.S.I.); pujaghosheee17@gmail.com (P.G.);
rashidul@eee.ruet.ac.bd (M.R.I.); mri.sheikh@eee.ruet.ac.bd (M.R.I.S.)
2
Department of Electrical & Electronic Engineering, Dhaka University of Engineering & Technology,
Gazipur 1707, Bangladesh; omerfaruque1501111@gmail.com
3
Queensland Micro- and Nanotechnology Centre, Griffith University, Nathan, QLD 4111, Australia
4
Applied Research Center for Environment & Marine Studies, King Fahd University of Petroleum & Minerals
(KFUPM), Dhahran 31261, Saudi Arabia; mdshafiul.alam@kfupm.edu.sa
* Correspondence: mdalamgir.hossain@griffith.edu.au
Abstract: The inherent volatility of PV power introduces unpredictability to the power system,
necessitating accurate forecasting of power generation. In this study, a machine learning (ML)
model based on Gaussian process regression (GPR) for short-term PV power output forecasting is
proposed. With its benefits in handling nonlinear relationships, estimating uncertainty, and generating
probabilistic forecasts, GPR is an appropriate approach for addressing the problems caused by PV
power generation’s irregularity. Additionally, Bayesian optimization to identify optimal hyper-
parameter combinations for the ML model is utilized. The research leverages solar radiation intensity
data collected at 60-min and 30-min intervals over periods of 1 year and 6 months, respectively.
Comparative analysis reveals that the data set with 60-min intervals performs slightly better than
the 30-min intervals data set. The proposed GPR model, coupled with Bayesian optimization,
demonstrates superior performance compared to contemporary ML models and traditional neural
network models. This superiority is evident in 98% and 90% improvements in root mean square
errors compared to feed-forward neural network and artificial neural network models, respectively.
This research contributes to advancing accurate and efficient forecasting methods for PV power
output, thereby enhancing the reliability and stability of power systems.
Keywords: Bayesian optimization; PV power forecasting; Gaussian process regression; machine
learning; solar radiation intensity
1. Introduction
The global demand for energy has been steadily increasing over the last few decades,
leading to substantial growth in electricity production worldwide [1]. Traditionally, con-
ventional fossil fuels have served as the primary energy source for electricity generation.
However, the sustainability of these traditional fossil fuel resources is now uncertain due
to their rapid depletion [2]. Moreover, the combustion of fossil fuels is a major contributor
to greenhouse gas emissions, exacerbating severe global warming and posing a threat to
the planet’s health [1,3].
In response to these challenges, there has been a significant shift in focus from fossil
fuels to renewable energy sources (RESs) for electricity generation. This transition involves
harnessing solar energy, wind energy, tidal energy, and biomass energy [4,5]. In the context
of growing energy development, the incorporation of renewable energy sources (RES) into
contemporary power systems is increasingly reliant on hydrogen. Among the various
Processes 2024, 12, 546. https://doi.org/10.3390/pr12030546 https://www.mdpi.com/journal/processes