The Secure Prescriptive Analytics project aims to develop an innovative modeling concept that breaks down complex systems, such as industrial plants, into variable submodels and represents them using proxy models. The aim is to create an open source platform that supports the optimization and linking of these models.
Industrial companies are faced with the challenge of efficiently controlling and maintaining complex systems. Traditional data analysis often reaches its limits here, which increases the need for innovative solutions.
As part of the Secure Prescriptive Analytics project, complex systems are broken down into submodels and mapped using proxy models. These submodels enable faster and more precise evaluations and improve the efficiency and accuracy of data analysis.
By using clear-box and privacy-preserving machine learning, the models are trained in such a way that they can generate trustworthy recommendations for action. These approaches ensure transparency and data protection when modelling and optimizing industrial processes.
RISC Software GmbH plays a central role in the development and implementation of the modeling concepts. Its expertise in the areas of Dynamic Optimization, Modeling and Simulation as well as Interpretable & Privacy-Preserving Machine Learning is crucial to the success of the project. RISC Software GmbH plays a key role in ensuring that the solutions developed meet the highest standards in terms of both technology and data protection.
Modeling and simulation of an energy grid with PV generation, storage and consumers.
Modeling and simulation of a 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. Further information can be found at www.uppervision.at.
Mathematical Optimization Specialist
