Exponential Smoothing Model for Photovoltaic Power Forecasting
Pasquale De Falco, Luigi Pio Di Noia, R. Rizzo
Abstract
The aim of the paper is to develop a method for short-term deterministic and probabilistic photovoltaic (PV) power forecasting, and to present the results for an actual applicative case study. The proposed method is based on the exponential smoothing models, and two variants of this approach are analyzed within both the deterministic and the probabilistic frameworks. In particular, the probabilistic forecasting method is developed through an ensemble-based procedure that includes point forecasts obtained through several smoothing exponents. The case study discussed in this paper is based on experimental data obtained from an existing plant, and the corresponding results are compared with a benchmark based on the persistence model. It is found that the proposed exponential smoothing method significantly improves the result of the short-term PV power forecasting, both in the deterministic and probabilistic frameworks.