LL
Luca Lanzilao
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
2 records found
1
We present a novel framework for spatiotemporal photovoltaic (PV) power forecasting and use it to evaluate the reliability, sharpness, and overall performance of six intraday PV power nowcasting models. The model suite includes satellite-based deep learning and optical-flow approaches and physics-based numerical weather prediction models, covering both deterministic and probabilistic formulations. Forecasts are first validated against satellite-derived surface solar irradiance (SSI). Irradiance fields are then converted into PV power using station-specific machine learning models, enabling comparison with production data from 6434 PV stations across Switzerland. To our knowledge, this is the first study to investigate spatiotemporal PV forecasting at a national scale. We additionally provide the first visualizations of how mesoscale cloud systems shape national PV power production on hourly and sub-hourly timescales. Our results show that satellite-based approaches outperform the Integrated Forecast System (IFS-ENS), particularly at short lead times. Among them, SolarSTEPS and SHADECast deliver the most accurate SSI and PV power predictions, with SHADECast providing the most reliable ensemble spread. The deterministic model IrradianceNet achieves the lowest root mean square error, while probabilistic forecasts of SolarSTEPS and SHADECast provide better-calibrated uncertainty. Forecast accuracy generally decreases with elevation. At a national scale, satellite-based models forecast the daily total PV generation with relative errors below 10% for 82% of the days in 2019–2020, demonstrating robustness and their potential for operational use.
...
We present a novel framework for spatiotemporal photovoltaic (PV) power forecasting and use it to evaluate the reliability, sharpness, and overall performance of six intraday PV power nowcasting models. The model suite includes satellite-based deep learning and optical-flow approaches and physics-based numerical weather prediction models, covering both deterministic and probabilistic formulations. Forecasts are first validated against satellite-derived surface solar irradiance (SSI). Irradiance fields are then converted into PV power using station-specific machine learning models, enabling comparison with production data from 6434 PV stations across Switzerland. To our knowledge, this is the first study to investigate spatiotemporal PV forecasting at a national scale. We additionally provide the first visualizations of how mesoscale cloud systems shape national PV power production on hourly and sub-hourly timescales. Our results show that satellite-based approaches outperform the Integrated Forecast System (IFS-ENS), particularly at short lead times. Among them, SolarSTEPS and SHADECast deliver the most accurate SSI and PV power predictions, with SHADECast providing the most reliable ensemble spread. The deterministic model IrradianceNet achieves the lowest root mean square error, while probabilistic forecasts of SolarSTEPS and SHADECast provide better-calibrated uncertainty. Forecast accuracy generally decreases with elevation. At a national scale, satellite-based models forecast the daily total PV generation with relative errors below 10% for 82% of the days in 2019–2020, demonstrating robustness and their potential for operational use.
Michiel Kenis is a PhD researcher at the Energy Systems Integration & Modeling Group at the University of Leuven with a doctoral mandate from the Flemish Institute for Technological Research (VITO). He was a visiting researcher at the Massachusetts Institute of Technology. His research focuses on cross-border electricity markets. He holds a MSc in energy engineering and a MSc in policy economics, both from the University of Leuven. Luca Lanzilao completed his MSc degree in mathematical engineering from Politecnico di Torino in 2018. Currently, he is pursuing a PhD at KU Leuven. His research focuses on studying the response of the atmospheric boundary layer to wind farm forcing, with particular emphasis on meso-scale phenomena, such as gravity waves. Kenneth Bruninx received a MSc degree in energy engineering in 2011, a MSc in management, and a PhD degree in mechanical engineering in 2016, all from the University of Leuven (KU Leuven), Belgium. Currently, he is an assistant professor at the Faculty of Technology, Policy, and Management of TU Delft, Netherlands and a research fellow at the Department of Mechanical Engineering, KU Leuven, Belgium. His research interests include market design, policies, and regulation for integrated energy systems. Johan Meyers is a professor of mechanical engineering at KU Leuven since 2009. His research focuses on the simulation of turbulent flows and the atmospheric boundary layer with applications in wind energy. In 2012, he obtained an ERC grant on wind farm control and has been involved in various European projects on wind energy since. He served as the vice president of the European Academy of Wind Energy from 2017 to 2019 and as its president from 2019 to end of 2021. He has been active as an associate editor for Computers & Fluids and is currently an associate editor for Wind Energy Science. Erik Delarue received MSc and PhD degrees in mechanical engineering from the University of Leuven, Belgium, in 2005 and 2009, respectively. He is currently an associate professor with the University of Leuven, TME Branch (energy conversion) and active with EnergyVille. His research focus and expertise are on quantitative tools, supporting an efficient operation of, and transition toward, a low-carbon energy system (mathematical modeling of energy systems). Applications relate to flexibility through energy systems integration, market design, and energy policies.
...
Michiel Kenis is a PhD researcher at the Energy Systems Integration & Modeling Group at the University of Leuven with a doctoral mandate from the Flemish Institute for Technological Research (VITO). He was a visiting researcher at the Massachusetts Institute of Technology. His research focuses on cross-border electricity markets. He holds a MSc in energy engineering and a MSc in policy economics, both from the University of Leuven. Luca Lanzilao completed his MSc degree in mathematical engineering from Politecnico di Torino in 2018. Currently, he is pursuing a PhD at KU Leuven. His research focuses on studying the response of the atmospheric boundary layer to wind farm forcing, with particular emphasis on meso-scale phenomena, such as gravity waves. Kenneth Bruninx received a MSc degree in energy engineering in 2011, a MSc in management, and a PhD degree in mechanical engineering in 2016, all from the University of Leuven (KU Leuven), Belgium. Currently, he is an assistant professor at the Faculty of Technology, Policy, and Management of TU Delft, Netherlands and a research fellow at the Department of Mechanical Engineering, KU Leuven, Belgium. His research interests include market design, policies, and regulation for integrated energy systems. Johan Meyers is a professor of mechanical engineering at KU Leuven since 2009. His research focuses on the simulation of turbulent flows and the atmospheric boundary layer with applications in wind energy. In 2012, he obtained an ERC grant on wind farm control and has been involved in various European projects on wind energy since. He served as the vice president of the European Academy of Wind Energy from 2017 to 2019 and as its president from 2019 to end of 2021. He has been active as an associate editor for Computers & Fluids and is currently an associate editor for Wind Energy Science. Erik Delarue received MSc and PhD degrees in mechanical engineering from the University of Leuven, Belgium, in 2005 and 2009, respectively. He is currently an associate professor with the University of Leuven, TME Branch (energy conversion) and active with EnergyVille. His research focus and expertise are on quantitative tools, supporting an efficient operation of, and transition toward, a low-carbon energy system (mathematical modeling of energy systems). Applications relate to flexibility through energy systems integration, market design, and energy policies.