Use of Machine Learning to Forecast Solar and Wind Energy Production for NEOM City

NEOM, one of prominent future project of the Saudi Arabia, set to be the World's largest carbon-free system and globally leading hub to the clean energy, aiming to be powered entirely by renewable energy sources primarily solar and wind. Considering its geographic position which offers abundant...

Full description

Saved in:
Bibliographic Details
Published in2025 4th International Conference on Computing and Information Technology (ICCIT) pp. 1 - 6
Main Author Ayaz, Muhammad
Format Conference Proceeding
LanguageEnglish
Published IEEE 13.04.2025
Subjects
Accuracy
Biological system modeling
energy production forecasting
Forecasting
Machine learning
NEOM city
Predictive models
Production
Renewable energy sources
solar and wind energy
Urban areas
Wind energy
Wind forecasting
Online AccessGet full text
DOI10.1109/ICCIT63348.2025.10989383

Cover

More Information
Summary:NEOM, one of prominent future project of the Saudi Arabia, set to be the World's largest carbon-free system and globally leading hub to the clean energy, aiming to be powered entirely by renewable energy sources primarily solar and wind. Considering its geographic position which offers abundant solar irradiance and strong coastal winds, accurate forecasting of energy production is critical to ensure consistent energy supply, also for the effective integration of renewable resources into NEOM's smart energy infrastructure. Artificial intelligence (AI) is not only supporting renewable energy generation but also improving its reliability, efficiency, and scalability in order to make solar and wind energy a viable mainstream source. This study presents a comprehensive AI based approach to forecast solar and wind energy production in NEOM, utilizing advanced machine learning models and statistical methods, such as time series analysis, artificial neural networks (ANN), and hybrid forecasting models. By integrating historical weather data, satellite observations, and real-time environmental monitoring, precise predictions has been developed for solar irradiance and wind speed, both are critical for optimizing the performance of photovoltaic systems and wind turbines. The results demonstrate that provided methods are capable to enhance forecasting precision, and support to handle the dynamic energy needs of a city designed for renewable self-sufficiency.
DOI:10.1109/ICCIT63348.2025.10989383