Multitime-Scale Data-Driven Spatio-Temporal Forecast of Photovoltaic Generation

The increasing penetration of stochastic photovoltaic (PV) generation in electric power systems poses significant challenges to system operators. To ensure reliable operation of power systems, accurate forecasting of PV power production is essential. In this paper, we propose a novel multitime-scale data-driven forecast model to improve the accuracy of short-term PV power production. This model leverages both spatial and temporal correlations among neighboring solar sites, and is shown to have improved performance compared to the conventional persistence (PSS) model. The tradeoff between computation cost and improved forecast quality is studied using real datasets from PV sites in California and Colorado.