Between November 18 to 20, Diana Estefanía Chérrez Barragán, a Dual Degree Ph.D. student affiliated with the University of Campinas (UNICAMP) in Brazil and Instituto Superior Técnico I INESC ID in Portugal, showcased her research at the IEEE URUCON 2024 conference. Her paper titled “Day-Ahead Photovoltaic Power Forecasting with Limited Data,” which was partially supported by the U2demo Project, introduces a novel methodology for predicting photovoltaic (PV) power generation using minimal historical data. The paper was co-authored by Hugo Morais, U2DEMO project coordinator at INESC ID and researcher Cindy P. Guzman.
“Our paper presents a new methodology for day-ahead photovoltaic (PV) power forecasting using only five historical days of power generation and with no exogenous data such as air temperature, wind speed, pressure, cloud cover, and relative humidity. Results show our proposed approach outperforms previous state-of-the-art deep learning models such as Long short-term memory (LSTM), Gated Recurrent Unit (GRU), and traditional Autoregressive Integrated Moving Average (ARIMA) statistical model, using limited data. The proposed method is flexible and can be easily adapted to other PV power generation systems with limited data”, explains the researcher.
The conference, held in Montevideo in Uruguai from November 18 to 20, brought together researchers and experts from around the world to discuss the latest developments in electrical and electronic engineering. Diana’s participation was a unique opportunity to share her work in advancing renewable energy solutions through innovative technology and disclose the work being developed under the U2DEMO Project.
For more information about the conference, visit IEEE URUCON 2024.
Paper available here.
Comments are closed.