A Data Driven PV Power Forecasting Model
Solar Photovoltaics (PV) is one of the most rapidly growing renewable energy source around the world. For sunny tropical locations such as Puerto Rico, and after the electric energy debacle following Hurricane Maria, forecasting solar power is necessary for the efficient application of the solar resource. The research team is attempting to demonstrate that a reasonably high degree of accuracy is possible by following a purely statistical approach to power forecasting where the starting point is PV and meteorological data collected from an existing experimental test bench in Puerto Rico and developing a neural network-based model. The collected data will be used to train/ teach the model in an autoregressive architecture which finally may provide an estimated future power data at a given time, based on past inputs available at the time when the model is run.
Grant Result
“Electrify Everything” may be the most influential energy policy idea in the world today, and Jorge Santiago-Aviles is strengthening the smart grid backbone of that idea with innovations in distributed solar power.
Read the Spotlight
Jorge Santiago-Aviles
Associate Professor EmeritusJorge Santiago-Aviles is an associate professorrmeritus in electrical and systems engineering in the School of Engineering and Applied Science.
