Abstract
The power capacity of solar photovoltaics (PVs) in Korea has grown dramatically in recent years, and an accurate estimation of solar resources is crucial for the efficient management of these solar PV systems. Since the number of solar irradiance measurement sites is insufficient for Korea, satellite images can be useful sources for estimating solar irradiance over a wide area of Korea. In this study, an artificial neural network (ANN) model was constructed to calculate hourly global horizontal solar irradiance (GHI) from Korea Communication, Ocean and Meteorological Satellite (COMS) Meteorological Imager (MI) images. Solar position variables and five COMS MI channels were used as inputs for the ANN model. The basic ANN model was determined to have a window size of five for the input satellite images and two hidden layers, with 30 nodes on each hidden layer. After these ANN parameters were determined, the temporal and spatial applicability of the ANN model for solar irradiance mapping was validated. The final ANN ensemble model, which calculated the hourly GHI from 10 independent ANN models, exhibited a correlation coefficient (R) of 0.975 and root mean square error (RMSE) of 54.44 W/m² (12.93%), which were better results than for other remote-sensing based works for Korea. Finally, GHI maps for Korea were generated using the final ANN ensemble model. This COMS-based ANN model can contribute to the efficient estimation of solar resources and the improvement of the operational efficiency of solar PV systems for Korea.
Highlights
In Korea, solar energy is emerging as a clean and sustainable energy resource, with its biggest advantages being its ability to supply energy globally and the lack of concern over its depletion [1].The installed capacity of solar PV in Korea has increased by more than 16 times over the last ten years, and solar energy has become the largest renewable energy source in Korea, followed by hydropower and wind power (Figure 1)
The artificial neural network (ANN) model developed in this study showed better accuracy—an root mean square error (RMSE) of 54.44 W/m2 (12.93%)—than any other solar irradiance models applied to Korea
The temporal generality of ANN method was evaluated by training the ANN model with 2016 data and testing it with 2017 data
Summary
In Korea, solar energy is emerging as a clean and sustainable energy resource, with its biggest advantages being its ability to supply energy globally and the lack of concern over its depletion [1]. Since the interpolation method assumes a static condition, precipitable water vapor [13,14] These atmospheric parameters can cause significant errors the dynamic movement of clouds can add a degree of uncertainty to this method, if the in solar irradiance estimation for Korea, because observation networks of these parameters are not amount of measurement data is insufficient [5,6,7]. From measured solar irradiance and atmospheric parameters such as aerosol optical depth, turbidity, Various studies have been conducted regarding the use of ANN for the estimation and or precipitable water vapor [13,14] These atmospheric parameters can cause significant prediction of solar resources from satellite images.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
