Improving solar power forecast from meteorological parameters with regression models

ABSTRACT

Solar power forecasting is crucial in boosting the rivalry of solar power plants in the electricity markets and minimizing economic and social dependence on fossil fuels. This paper describes a method for foretelling solar power by utilizing regression approaches. The proposed regression models are developed using an actual meteorological set of data from Qassim University, KSA for one year (September 2021- August 2022). Forecasting solar power production is crucial to dealing with the smart grid’s demand and supply challenges. This research aims to make ML models that can precisely forecast solar power production. Significantly, the following noteworthy components highlight the main contributions of this work. Primarily a framework for the analysis of data is presented, and then the dataset obtained from the solar photovoltaic (SPV) system is visualized. Secondly, we evaluate the predictive capability of machine learning (ML) models employing numerous performance indices for predicting solar power time-series dataset values. According to the experimental findings, the proposed predictive approaches can lessen forecasting complexity even with a small reconstruction error. Additionally, the GBR (Gradient Boosting regression) model significantly outperformed other benchmark techniques in terms of forecast accuracy with MAPE of 0.7674, RMSE of 0.0191, MAE of 0.0132, MSE of 0.0030, and R² of 0.9723 respectively.

KEYWORDS:

• Machine learning (ML)
• solar photovoltaic system (SPV)
• forecast models
• short-term solar power forecasting
• error correction

Nomenclature

CNN	=	Convolution Neural Network
EEMD	=	Ensemble Empirical Mode Decomposition
GPR	=	Gaussian Process Regression
LSTM	=	Long Short-Term Memory
SPV	=	Solar Photovoltaic System
SVM	=	Support Vector Machine
WT	=	Wavelet Transform
GBRT	=	Gradient-Boosted Regression Tree
IVMD	=	Improved Variational Mode Decomposition
ARIMA	=	Autoregressive Integrated Moving Average
HIMVO	=	Hybrid Improved Multi-verse Optimizer
KNN	=	K-Nearest Neighbor
RF	=	Random Forest
$x_{\mathit{max}}$	=	Maximum value of dataset
$x_{\mathit{min}}$	=	Minimum value of dataset
$t_b$	=	Trees based on the Gini impurity
$w_n$	=	Weight allotted to the n-th attribution
$x_t$	=	Set of predictive variables
$\mathit{M}$	=	Total iteration count
$\mathit{\eta }$	=	Step size shrinkage
$p^K$	=	Power outputs
${\delta }^k$	=	Weights
$X^K$	=	k nearest instances
$p^k$	=	Output of renewable energy

Acknowledgements

The authors would like to sincerely thank the reviewers for their valuable comments and recommendations to improve the quality of the paper.

Disclosure statement

No potential conflict of interest was reported by the author(s).

CRediT authorship contribution statement

Shekhar Singh: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Upma Singh: Writing – original draft, Writing – review & editing, Visualization, Supervision.

Dataset availability statement

Data will be provided upon request.

Declaration

The authors declare that there are no personal or financial links to any group or individual that can have an undue influence on this work. No information from other sources has been used in this manuscript; it is entirely original to the author. This work has never been submitted or published for publication consideration in some other journal, and all data measures are authentic, unedited outcomes. The research described in this paper has no financial or professional conflicts of interest for any of the authors.

Ethical approval

This article does not contain any studies with animals performed by any of the authors.

Additional information

Funding

The author(s) reported there is no funding associated with the work featured in this article.

Notes on contributors

Shekhar Singh

Shekhar Singh received his B.Tech degree in computer science engineering from Guru Govind Indraprastha University 2019 and M.Tech degree in computer science engineering from Indraprastha Institute of Information Technology, India in 2021. His areas of interest are artificial intelligence, data analytics, machine learning, conventional & renewable energy sources and intelligent techniques.

Upma Singh

Upma Singh did her Ph.D. at Delhi Technological University, India. She is presently working as an Assistant Professor at the Department of Electronics and Communication Engineering. Her areas of interest are artificial intelligence, machine learning, conventional & renewable energy sources and intelligent techniques.