Solar irradiation estimation by monthly principal component analysis

Abstract

Simple solar irradiation estimation models most often use classical regression analysis with a set of restrictive assumptions. They work with actual measurements on Cartesian coordinate systems, and given the predictor as sunshine duration, the solar irradiation amount is estimated through a regression model. The variances of solar irradiation and sunshine data are not considered explicitly whereas they are physically significant in representing diffusion, absorption and reflection of the solar irradiation depending on the atmospheric composition and weather situation, especially, in terms of cloudiness, which is directly related to sunshine duration during day light. This paper proposes more efficient approach in terms of physical interpretations and mathematical convenience in modeling solar irradiation and sunshine duration relationship. For this purpose, two dimensional principal component analysis is employed and the solar irradiation estimations are found more reliably than the classical approaches. The application of the methodology is presented for five sunshine duration and irradiation record stations in Turkey.