The Secure Prescriptive Analytics project aims to develop an innovative modeling concept that breaks down complex systems, such as industrial plants, into variable sub-models and represents them through surrogate models. The goal is to create an open-source platform that supports the optimization and integration of these models.
Industrial companies face the challenge of efficiently controlling and maintaining complex systems. Traditional data analysis often reaches its limits, increasing the need for innovative solutions.
As part of the Secure Prescriptive Analytics project, complex systems are broken down into sub-models and represented by surrogate models. These sub-models enable faster and more accurate evaluations, improving the efficiency and accuracy of data analysis.
By using Clear-Box and Privacy-Preserving Machine Learning, the models are trained to generate trustworthy recommendations. These approaches ensure transparency and data protection in the modeling and optimization of industrial processes.
RISC Software GmbH plays a central role in the development and implementation of the modeling concepts. Their expertise in the areas of Dynamic Optimization, Modeling and Simulation, as well as Interpretable & Privacy-Preserving Machine Learning, is crucial for the success of the project. RISC Software GmbH significantly contributes to ensuring that the developed solutions meet the highest technical and data protection standards.
Modeling and simulation of an energy grid with PV generation, storage and consumers.
Modeling and simulation of production with several stages (red: occupied machines, green: free machines).
The Secure Prescriptive Analytics project is funded by the state of Upper Austria as part of the #upperVISION2030 program. For more information, visit www.uppervision.at.
Mathematical Optimization Specialist
