Abstract: Accurate forecasting of solar resource is the key issue for a successful integration of solar plants into the grid. This paper proposes a fuzzy logic approach as an alternative to classical statistics, aiming to forecast hourly global solar irradiation. Hourly clearness index is the quantity directly processed by the proposed fuzzy algorithms. Hourly clearness index is defined as the hourly horizontal global solar irradiation at the ground and the hourly solar irradiation at the top of the atmosphere. Clearness index takes into account all random meteorological influences, being a measure of the atmospheric transparency. Thus, the stochastic component of hourly solar irradiation can be isolated by means of the clearness index. Four new autoregressive-fuzzy models are studied in this paper. The models are mainly differentiated by the number of the input variables and the number of attributes. The model #1 has only one variable at the input (hourly clearness index measured at time t-1) which is characterized by 3 attributes. The model #2 extends the number of inputs increasing the order of auto-regressive terms to two. The model #3 adds to model #1 an exogenous input, namely relative sunshine. The model #4 includes a seasonality term. Overall results show that the model #4 performs the best. The novelties related to the fuzzy model assembly are the membership functions of the attributes and the simple matrix of fuzzy rules. In principle, the actual model can be applied in sites where measurement of hourly global solar irradiation is currently performed, only a re-estimation of the parameters being necessary. The results demonstrate that the fuzzy models have the strength to translate the information enclosed in past measurements into an actual prediction with acceptable accuracy.