Hybrid Model for Forecasting Solar Power Generation - EGH404

This presentation addresses the increasing global energy demand and the shift towards renewable energy sources, particularly solar power. It highlights the benefits of solar energy, including reduced energy bills and improved grid security, while acknowledging the variability and seasonality affecting its generation. The core focus is on developing an advanced solar power generation forecasting model that incorporates radiation intensity, atmospheric temperature, relative humidity, and wind speed. The proposed model utilizes a hybrid approach, combining satellite-based techniques, artificial intelligence, and statistical methods to improve power generation and usage. The presentation concludes by emphasizing the importance of accurate forecasting for optimizing solar power integration into the energy grid.

HOW CAN SOLAR POWER GENERATION BE
FORECAST?
Name
Course
Professor
University
City/state
Date

• Energy demand is on the rise
worldwide (Doman, 2016).
• Most of the energy is generated
from non-renewable resources.
• Greenhouse gas emissions are also
increasing (Rice, 2018)

• Generation of non-renewable energy
has contributed to increased climate
change and global warming
problems.
• There is great need to promote
renewable energy generation.
• The capacity of renewable energy
stands at about 33.3% of total global
energy (International Renewable
Energy Agency, 2019).
• Solar energy is one of the major
renewable energies (Eissa and Tian,
2017).

• There is great potential in solar energy
generation.
• Its production is predicted to continue
increasing (Gielen, Kempener, Taylor,
Boshell and Seleem, 2016).
• Benefits of solar energy include:
Reduce energy bills
Improved power grid security
Enhances power independence
Creates job opportunities
Production coincides with peak energy
demand (during the daytime when
sunlight intensity is high).
Is universal

• Variability and seasonality affects
solar power generation (Wang, Zou,
Chen, Zhang and Chen, 2018).
• Atmospheric or weather conditions
are the main focus in this
presentation.
• Power generation and use can be
improved by developing advanced
solar power generation forecasting
models.
• The model should factor in radiation
intensity.

• Other important atmospheric variables that
the model should factor in are:
Atmospheric temperature
Relative humidity
Wind speed (Li, Cheng, Lin and Dong,
2017).
• The forecasting model to be developed
using hybrid method that incorporates
Satellite-based techniques
A artificial intelligence approach, and
Statistical techniques (Behera, Majumder
and Nayak, 2018).

Works Cited
Behera, M., Majumder, I., & Nayak, N. (2018). Solar photovoltaic power forecasting using optimized modified
extreme learning machine technique. International Journal of Engineering Science and Technology, 21(3), 428-438.
Doman, L. (2016, May 12). EIA projects 48% increase in world energy consumption by 2040. U.S. Energy Information
Administration. Retrieved from https://www.eia.gov/todayinenergy/detail.php?id=26212
Eissa, M., & Tian, B. (2017). Lobatto-Milstein Numerical Method in Application of Uncertainty Investment of Solar
Power Projects. Energies, 10(1), 43-62.
Gielen, D., Kempener, R., Taylor, M., Boshell, F., & Seleem, A. (2016). Letting in the light: how solar photovoltaics will
revolutionize the electricity system. Abu Dhabi: International Renewable Energy Agency.
International Renewable Energy Agency. (2019, April 2). Renewable Energy Now Accounts for a Third of Global
Power Capacity. IRENA. Retrieved from https://www.irena.org/newsroom/pressreleases/2019/Apr/Renewable-Energy-Now-
Accounts-for-a-Third-of-Global-Power-Capacity
Li, L., Cheng, P., Lin, H., & Dong, H. (2017). Short-term output power forecasting of photovoltaic systems based on the deep belief net .
Advances in Mechanical Engineering, 9(9), 1-8.
Rice, D. (2018, December 6). Emissions of carbon dioxide into Earth's atmosphere reach record high. Retrieved from USA Today:
Emissions
of carbon dioxide into Earth's atmosphere reach record high
Wang, Y., Zou, H., Chen, X., Zhang, F., & Chen, J. (2018). Adaptive Solar Power Forecasting based on Machine Learning Methods . Applied
Sciences, 8(11), 2224-22.