Edge-based physical asset and digital twin virtualization framework to support cognitive digital twins

In Cyber-Physical Systems (CPSs), devices interact with smart applications by relying on Internet of Things (IoT) protocols to transmit sensor readings from monitoring Physical Assets (PAs). The applications support mapping mechanisms that constitute Digital Twins (DTs) to mimic the behavior of the actual PAs. Changes in PAs are mirrored in the DTs, and vice versa. This duality enables the creation of Cognitive Digital Twins (CDTs), where the readings generated by PAs enable the extraction of knowledge to support actuation through AI models on the PAs. This paper introduces a generic PA and DT Virtualization (PDV) framework that leverages the Internet Engineering Task Force layered architecture through an application layer smart sublayer that learns from the interaction between PAs and DTs to enable edge-based CDT support. Although this framework is agnostic of the CPS under consideration, its focus in this paper is on Industry 5.0 applications. In this context, a new IoT protocol is proposed to enable a PDV scheme that provides the reliable automation of the interaction between PAs and DTs even in the presence of different levels of wireless network layer impairments.