One of the main world concerns nowadays is related to the environment issues. Such concern is considered in the selection of energy projects and, as a result of that, the generation of electricity from renewable sources has experienced a sharp growth all over the world, Brazil included. Concerning hydropower sources, Small Hydropower Plants (SHPs) are an alternative to reduce environmental impact. These projects produce between 5 and 30 megawatts (MW) and its installation has a low cost and respect to the environment, mainly because there is no need of regulation reservoirs, which is not the case in bigger hydroelectric plants. In recent years the number of SHPs is increasing in a great deal, as a consequence of the incentives to generate electricity from renewable sources. Since hydro power generation is heavily influenced by hydrological regimes, especially in the case of run-of-river plants, as SHPs, improving the assertiveness of electric power generation forecasts in a stochastic way becomes highly important for distributing utilities. This master dissertation has as main objective to present the performance of an arrange of forecasting models applied to SHPs of a real distributing utility. It was used different approaches, including inflow data from neighboring hydro plants as exogenous variable, in causal models and also univariate models.