Fraunhofer Institute for Algorithms and Scientific Computing SCAIParameter analysis and optimization are common tasks in engineering applications. SCAI develops DesParO, a machine learning software package for intuitive exploration, automatic analysis, and optimization of parametrized problems. DesParO can be coupled with simulation packages or used for measurement data. It minimizes the number of simulations needed for building up a model adaptively. Fraunhofer SCAI applies this approach in particular for energy networks.
Networks for transport of gas, electricity, water, steam or chemicals are essential for modern economy. The Energiewende (energy turnaround) requires optimization of energy flows in order to reduce consumption of non-renewable energy sources. The transformation of our energy backbone needs modeling, simulation and optimization of the corresponding networks.
The different energy networks can be mathematically modeled in a very similar way. Their numerical simulation can be based on the same numerical kernels. Our MultiphYsical NeTwork Simulation framework (MYNTS) is suited for all energy networks. MYNTS uses HPC technology. For parameter analysis and optimization, MYNTS provides an interface to DesParO.
ML speeds up Industrial development processes
Simulation, analysis and optimization
In order to set up an energy network model, first, the topology of the network is created. Then all the network elements are modeled. For physical devices, technical documentation is evaluated. If the behavior of a device or subsystem is not known yet, it can be learned with DesParO, based on measurement results. After network initialization, important operating scenarios have to be learned with DesParO, e.g. by clustering and / or classifying sensor data appropriately. Finally, optimization goals must be established, reflecting the intentions of relevant stakeholders.
Besides simulation and optimization workflows, MYNTS offers ensemble analysis based on DesParO. So, the impact of (smaller or larger) variations of parameters can be identified. Combinations of geometrical properties, physical parameters of devices, operating scenarios or profiles of consumers, generators, or prosumers can be varied and analyzed systematically. In addition, MYNTS offers modules for physically equivalent graph reduction and for graph clustering. The latter can be used for analysis of main flow directions or comparative analysis of several operating scenarios.
Applications
- Mathematical techniques for transforming energy networks, e.g. gas and electrical power on long-distance and distribution levels.
- Making the energy infrastructure (electrical power, gas, district heating with converters and storages) of cross-sectoral distribution grids more flexible.
- Simulation and optimization of data center energy flows.
- Energy management (DIN EN ISO 50001) and optimization for the chemical industry based on online process mining.
- Chemical micro- and macrokinetics of fuel cells.