Descripción del proyecto
The central challenge in energy systems is to balance cost-efficiency, environmental responsibility, and living standards. Multi-objective optimization in such systems is critical for striking compromises among stakeholders and ensuring competitiveness and sustainability. As energy systems face uncertainty, volatility, and environmental regulations, holistic optimization becomes more critical.
However, three main challenges currently hinder energy system optimization: complex models demanding substantial computational power, a lack of holistic and robust approaches, and the use of real-time data for proper operation and analysis. Although each of these challenges has been addressed individually, no contribution was able to bring them all together in a consistent methodological framework. This is the main objective of this fellowship.
This fellowship will be conducted at IST/University of Lisbon under the supervision of Prof. Henrique Matos, and aims to bridge these gaps by integrating machine learning, systems optimization, uncertainty analysis, and real-time operation. It seeks to develop advanced surrogate generation techniques, emphasize system integration and holistic analysis, optimization under uncertainty, and the use of real-time data for operation. These methods will be applied to real industrial challenges in an industrial secondment. This research project will develop methods and tools to address such challenges and contribute to a sustainable, profitable, and responsible European economy.