Periodic Gamma Autoregressive Model: An application to the Brazilian hydroelectric system

Hydrological time series forecasting play a crucial role in the Brazilian Power System since most of the power generated comes from hydroelectric power plants. A minor improvement in the predictive ability of water inflows time series might lead both to: (i) lower costs to final consumers; and (ii) higher power reliability. This paper explores Periodic Gamma Autoregressive Models (PGAR) to model brazilian water inflows time series. This type of time series has some features which seem to be more adaptable to Gamma models, like nonnegative random values and asymmetric pattern. The main purpose of this study is to compare periodic Normal and Lognormal models to PGAR. The results suggest that: (i) both Gamma and Lognormal models perform better than Normal model; and (ii) the Gamma model is a good alternative to the Lognormal model.