An Intelligent SARIMAX-Based Machine Learning Framework for Long-Term Solar Irradiance Forecasting at Muscat, Oman

Mazhar Baloch (), Mohamed Shaik Honnurvali, Adnan Kabbani, Touqeer Ahmed Jumani and Sohaib Tahir Chauhdary
Additional contact information
Mazhar Baloch: College of Engineering, A’Sharqiyah University, Ibra 400, Oman
Mohamed Shaik Honnurvali: Faculty of Engineering & Technology, Muscat University, Muscat 113, Oman
Adnan Kabbani: College of Engineering, A’Sharqiyah University, Ibra 400, Oman
Touqeer Ahmed Jumani: College of Engineering, A’Sharqiyah University, Ibra 400, Oman
Sohaib Tahir Chauhdary: College of Engineering, Dhofar University, Salala 211, Oman

Energies, 2024, vol. 17, issue 23, 1-16

Abstract: The intermittent nature of renewable energy sources (RES) restricts their widespread applications and reliability. Nevertheless, with advancements in the field of artificial intelligence, we can predict the variations in parameters such as wind speed and solar irradiance for the short, medium and long terms. As such, this research attempts to develop a machine learning (ML)-based framework for predicting solar irradiance at Muscat, Oman. The developed framework offers a methodological way to choose an appropriate machine learning model for long-term solar irradiance forecasting using Python’s built-in libraries. The five different methods, named linear regression (LR), seasonal autoregressive integrated moving average with exogenous variables (SARIMAX), support vector regression (SVR), Prophet, k-nearest neighbors (k-NN), and long short-term memory (LSTM) network are tested for a fair comparative analysis based on some of the most widely used performance evaluation metrics, such as the mean square error (MSE), mean absolute error (MAE), and coefficient of determination (R 2 ) score. The dataset utilized for training and testing in this research work includes 24 years of data samples (from 2000 to 2023) for solar irradiance, wind speed, humidity, and ambient temperature. Before splitting the data into training and testing, it was pre-processed to impute the missing data entries. Afterward, data scaling was conducted to standardize the data to a common scale, which ensures uniformity across the dataset. The pre-processed dataset was then split into two parts, i.e., training (from 2000 to 2019) and testing (from 2020 to 2023). The outcomes of this study revealed that the SARIMAX model, with an MSE of 0.0746, MAE of 0.2096, and an R 2 score of 0.9197, performs better than other competitive models under identical datasets, training/testing ratios, and selected features.

Keywords: solar forecasting; machine learning; ML model testing framework; data pre-processing; feature engineering; SARIMAX; ML-based solar irradiance prediction and power system planning (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/17/23/6118/pdf (application/pdf)
https://www.mdpi.com/1996-1073/17/23/6118/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:17:y:2024:i:23:p:6118-:d:1536957

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().