Fuzzy c-Regression Models with direction-dependent uncertainty and its application to residential solar electric power analysis

Switching regression is a powerful tool for revealing intrinsic non-linear dependencies among exploratory variables and objective variables. Fuzzy c-Regression Models (FCRM) is an FCM-type switching regression algorithm, which iteratively estimate fuzzy memberships of objects and local regression functions. In this paper, FCRM is applied to a residential solar electric power analysis. Although solar electric power is severely influenced by sunshine duration, meteorological observation of actual sunshine duration is often underestimated from the actual quantity of solar radiation. So, the variable has direction-dependent uncertainty. In this paper, FCRM is modified for handling such uncertain observations and the applicability is demonstrated with several experimental results.