Title: Accelerating and Automating Renewable Energy Deployment Using Artificial Intelligence & Optimization
Abstract:
Solar energy is envisioned to be a major contributor to meeting the ever-increasing global energy demand. Rooftop photovoltaic (PV) systems represent a significant portion of the world's solar energy potential. However, automating and optimizing the size and layout of these systems is still a difficult problem. This work presents a Mixed-Integer Programming (MIP) model to address this problem for rooftop PV systems. The proposed model is based on optimizing the Net Present Value (NPV) and can produce non-uniform panel layouts while accounting for practical considerations, including mitigating self-shading and ensuring rooftop walkability. The model is also adapted for systems that utilize micro-inverters or string-inverters. The model solutions were compared to an existing installation, and It was shown that the model non-uniform panel layout solution improved the NPV by 10.17%. When restricted to uniform layouts, the model produced the same layout as the existing installation in a matter of a few seconds.
Biography:
Abdulelah Habib earned a Mechanical Engineering Ph.D. from UC San Diego’s Solar Resource Assessment & Forecasting Laboratory and The Synchrophasor Grid Monitoring and Automation (SyGMA) lab. He graduated with honors from King Fahd University of Petroleum and Minerals (KFUPM) with a B.Sc in control and instrumentation system engineering in 2010. He then received an M.Sc in electrical engineering from King Abdullah University of Science and Technology (KAUST) in 2012 where he specialized in Signal Processing and Communication as well as Renewable Energy. Prior to his studies, Abdulelah worked as a field engineer trainee under the artificial lift group with Baker Hughes in Saudi Arabia. Abdulelah’s research interests include renewable energy, modern controls application, and mathematical modeling for renewable energies.
