Predict Beam Normal Irradiation and Global Horizontal Irradiation using Deep learning and Time series Algorithms

Sachdeva, Karan (2020) Predict Beam Normal Irradiation and Global Horizontal Irradiation using Deep learning and Time series Algorithms. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (3MB) | Preview
Preview	PDF (Configuration manual) Download (2MB) | Preview

Abstract

Solar forecasting is one of important use case in field of data analytics that has grown exponentially in past couple of decades. Advent of neural network with improvement in computation systems has radically improved solar forecasts and enabled more accurate prediction. In recent years, a lot of emphasize is given to not only predict solar forecast but also improve existing results by applying various models. This research focus on hybrid approach of combining time series and neural network to improve solar forecasts results and take up existing challenges in the area of solar energy. Hybrid model forecast produced results with decent evaluation metrics, i.e. RMSE of 38.34 W/m2 , MAE of 27.771 W/m2 for GHI while RMSE of 97.7 W/m2 and MAE of 78.46 W/m2 for BNI respectively. Also, Time series and deep neural networks are implemented to compare metrics with hybrid model metrics and comparison is done between metrics in current literature review and those obtained from all model implementation.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Dan English
Date Deposited:	25 Jan 2021 14:32
Last Modified:	25 Jan 2021 14:32
URI:	https://norma.ncirl.ie/id/eprint/4466

Actions (login required)

View Item