article · Big Data Mining and Analytics
Solar energy can generate electricity, provide heat, or drive chemical reactions, making reliable measurements of solar radiation vital for designing and outfitting solar energy systems. Essential components include Direct Normal Irradiance, Diffuse Horizontal Irradiance, and Global Horizontal Irradiance. However, physical measurements of these solar radiation components remain scarce across many parts of the world. To address this limitation, deep learning models combined with feature importance algorithms were developed to predict Direct Normal Irradiance. The models utilised historical meteorological records and solar radiation measurements collected at hourly intervals between January 2017 and December 2019 in Errachidia, Morocco. The results demonstrate that incorporating feature selection techniques significantly improves the accuracy of solar radiation forecasts when evaluated against recorded data, offering a viable method to model irradiance where direct ground measurements are unavailable.
Designing efficient solar energy systems requires accurate knowledge of solar radiation levels throughout the day. Because direct measurement stations are rare globally, computational forecasting models offer a practical alternative. Demonstrating that feature selection enhances the accuracy of deep learning predictions helps improve resource assessment for clean energy installations in regions lacking extensive measurement infrastructure.
The predictive models could support solar energy developers, grid operators, and engineering firms in assessing solar resource availability when designing new solar power installations. Because the research is validated against historical regional data from Morocco, it represents applied research at an early computational stage rather than an integrated commercial forecasting tool. Further operational testing and software deployment would be needed before integration into commercial site evaluation platforms.
AI-generated from the published abstract. Always read the original work before citing.
Solar radiation is capable of producing heat, causing chemical reactions, or generating electricity. Thus, the amount of solar radiation at different times of the day must be determined to design and equip all solar systems. Moreover, it is necessary to have a thorough understanding of different solar radiation components, such as Direct Normal Irradiance (DNI), Diffuse Horizontal Irradiance (DHI), and Global Horizontal Irradiance (GHI). Unfortunately, measurements of solar radiation are not easily accessible for the majority of regions on the globe. This paper aims to develop a set of deep learning models through feature importance algorithms to predict the DNI data. The proposed models are based on historical data of meteorological parameters and solar radiation properties in a specific location of the region of Errachidia, Morocco, from January 1, 2017, to December 31, 2019, with an interval of 60 minutes. The findings demonstrated that feature selection approaches play a crucial role in forecasting of solar radiation accurately when compared with the available data.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.26599/bdma.2022.9020003
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
