SOURCE-LINKED INTELLIGENCE

hybrid MOdel-Based optImal DesIgn and Control of energy systems​

CORDIS · observation · Publication date unknown

ficient at capturing complex behaviours, require extensive datasets and often suffer from limited generalisation and physical coherence. Hybrid modelling approaches that blend physical knowledge with machine learning therefore represent a promising path. However, experts in energy systems typically master physics and engineering principles but lack advanced machine-learning skills. Conversely, data-science specialists excel in AI techniques but often lack the domain knowledge required to handle energy systems and their operational constraints. MOBIDIC bridges this gap by training a new generation of researchers who operate at the interface between energy systems engineering and AI. The 15 doctoral candidates advance methodologies for modelling, optimisation, uncertainty handling, and integration, each working on a use case at process, microgrid, or network scale. MOBIDIC ultimately delivers a coherent toolbox of solutions to support the design and control of future energy systems. By being trained at the intersection of physics-based modelling, numerical simulation, data analytics

Read original source ↗ Open in workspace

recordType

award

status

SIGNED

region

EU

value

4473181.8

unit

EUR