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.
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 |
= | Maximum value of dataset | |
= | Minimum value of dataset | |
= | Trees based on the Gini impurity | |
= | Weight allotted to the n-th attribution | |
= | Set of predictive variables | |
= | Total iteration count | |
= | Step size shrinkage | |
= | Power outputs | |
= | Weights | |
= | k nearest instances | |
= | 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
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.