Real-time Digital Twins (2311.14691v1)

Abstract: We live in a world of exploding complexity driven by technical evolution as well as highly volatile socio-economic environments. Managing complexity is a key issue in everyday decision making such as providing safe, sustainable, and efficient industrial control solutions as well as solving today's global grand challenges such as the climate change. However, the level of complexity has well reached our cognitive capability to take informed decisions. Digital Twins, tightly integrating the real and the digital world, are a key enabler to support decision making for complex systems. They allow informing operational as well as strategic decisions upfront through accepted virtual predictions and optimizations of their real-world counter parts. Here we focus on real-time Digital Twins for online prediction and optimization of highly dynamic industrial assets and processes. They offer significant opportunities in the context of the industrial Internet of Things for novel and more effective control and optimization concepts. Thereby, they meet the Internet of Things needs for novel technologies to overcome today's limitations in terms of data availability in industrial contexts. Integrating today's seemingly complementary technologies of model-based and data-based, as well as edge-based and cloud-based approaches has the potential to re-imagine industrial process performance optimization solutions.