No abstract

Real-Time virtualization is commonly accepted to act as one of the key enablers of Fog Computing and the Industrial Internet of Things (IIoT). We motivate requirements which any hypervisor qualifying as a deterministic virtualization solution for IIoT should fulfill. We characterize existing work in the field of real-time virtualization to illustrate the trade-off between flexibility and deterministic execution. Furthermore, we indicate a lack of hypervisors that meet all of our requirements on deterministic virtualization. Our preliminary experimental results comparing the system latencies of ACRN, KVM, and Xen RTDS support our claim for the need of further investigation of deterministic virtualization. CCS CONCEPTS • Computer systems organization → Real-time operating systems; Multicore architectures; Real-time system architecture.

Converging Information Technology (IT) and Operations Technology (OT) in modern factories remains a challenging task. Several approaches such as Cloud, Fog or Edge computing aim to provide possible solutions for bridging OT that requires strict real-time processing with IT that targets computing functionality. In this context, this paper contributes to ongoing Fog computing research by presenting three industrial use cases with a specific focus on consolidation of functionality. Each use case exemplifies scenarios on how to use the computational resources closer to the edge of the network provided by a Fog Computing Platform (FCP). All use-cases utilize the same proposed FCP, which allows drawing a set of requirements on future FCPs, e.g. hardware, virtualization, security, communication and resource management. The central element of the FCP is the Fog Node (FN), built upon commercial off-the-shelf (COTS) multicore processors (MCPs) and virtualization support. Resource management tools, advanced security features and state of the art communication protocols complete the FCP. The paper concludes by outlining future research challenges by comparing the proposed FCP with the identified requirements.

The research leading to these results has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No. 764785, FORA -Fog Computing for Robotics and Industrial Automation ABSTRACT Virtualization of distributed real-time systems enables the consolidation of mixed-criticality functions on a shared hardware platform, easing system integration. Time-triggered communication and computation can act as an enabler of safe hard real-time systems. A time-triggered hypervisor that activates virtual CPUs according to a global schedule can provide the means to allow for a resource-efficient implementation of the time-triggered paradigm in virtualized distributed real-time systems. A prerequisite of time-triggered virtualization for hard real-time systems is providing access to a global time base to VMs and the hypervisor. A global time base results from clock synchronization with an upper bound on the clock synchronization precision. We present a formalization of the notion of time in virtualized distributed real-time systems. We use this formalization to propose a virtual clock condition that enables us to test the suitability of a virtual clock for the design of virtualized time-triggered real-time systems focusing on clock synchronization. We discuss and model how virtualization, particularly resource consolidation versus resource partitioning, degrades clock synchronization precision. Finally, we apply our insights to model the IEEE 802.1AS clock synchronization protocol and derive an upper bound on the clock synchronization precision of IEEE 802.1AS in a virtualized distributed real-time system. We present our implementation of a dependent clock for ACRN that can be synchronized to a grandmaster clock. The results of our experiments illustrate that a type-1 hypervisor like ACRN implementing the dependent clock paradigm yields native clock synchronization precision. Furthermore, we show that the upper bound of clock synchronization precision derived from our model holds for a series of experiments featuring native and virtualized setups.

No abstract