Key points are not available for this paper at this time.
The utilization of solar energy is picking up speed to counter climate change. New large-scale photovoltaic power stations are being constructed to increase solar utilization in the energy mix. A critical input of site selection for solar farms is the solar energy generation potential at a given location. Various physical and satellite-based inversion models are proposed to estimate the solar irradiation reaching the ground at potential locations, based on the meteorological features. However, the meteorological features generally contain outlier observations that distract the solar irradiation estimation models. To address this challenge, this study employs a robust fuzzy regression functions framework against the outliers to estimate the global horizontal irradiance (GHI) in Australia. Our framework is benchmarked with support vector machines, deep neural networks, and an adaptive network-based fuzzy inference system, and better GHI estimation performance is observed. The proposed framework provides 24 %, 18 %, and 23 % gain over the second-best method in terms of the rescaled mean absolute error, absolute percentage bias and rescaled root-mean-squared error. Monthly and annual GHI maps are created for Australia and compared to those from NASA POWER GHI estimates and Solargis annual GHI estimates. Our framework has an error range between 0.075 % and 2.9 % when validated against ground measurements. It provides at least an average of 40% lower monthly and annual error rates than POWER. This rate of gain rises to 69% when compared to Solargis. Our maps are not impacted by terrestrial characteristics and clear-sky conditions. This study's results are beneficial in site selection and construction of high-precision GHI estimation models for practitioners.
Chakravarty et al. (Mon,) studied this question.