22nd IEEE International Conference on
Emerging Technologies And Factory Automation
September 12-15, 2017, Limassol, Cyprus

Keynotes

Roman Obermaisser
University of Siegen, Germany
Dependable Mixed-Criticality Systems with Low Power and Energy Requirements

Abstract: In the past few years, numerous researchers addressed challenges related to mixed criticality such as certification by design, modular safety arguments, virtualization, reconfiguration and fault tolerance. However, some important challenges remain, being one of them the power and energy management in dependable mixed-criticality systems. Energy is an important resource that has to be shared among different applications in a mixed criticality system, while preserving time-space partitioning and the ability for modular certification.

The state-of-the-art encompasses a broad spectrum of low power techniques such as frequency/voltage scaling, power gating, clock gating, effective cache usage, selectively clock gated caches, design techniques for minimizing static power, application-driven and operating-system driven solutions. In the context of mixed-critical systems, these techniques cannot be used at their full potential because of the significant influence on the timing. Variations in execution and response times lead to a more complex global timing behavior and potentially an unpredictable impact of less critical application components on critical ones.

Adaptation mechanisms in time-triggered architectures address this challenge. Branching points in time-triggered communication and execution plans enable the reaction to different environmental conditions or to changes in the resource availability (e.g., low energy, faults). Changes in the system’s global context are determined by fault-tolerant agreement among the components and lead to consistent schedule changes at the distributed network interfaces, routers and operating systems. Consequently, adaptive time-triggered architectures offer power and energy efficiency, while preserving the advantages of time-triggered control such as certifiability, temporal predictability of phase-aligned transactions and implicit synchronization of resource accesses and service executions.

Biodata: Prof. Dr. Roman Obermaisser is full professor at the Division for Embedded Systems of University of Siegen. He has studied computer sciences at Vienna University of Technology, and received the Master's degree in 2001. In February 2004, Roman Obermaisser has finished his doctoral studies in Computer Science with Prof. Hermann Kopetz at Vienna University of Technology as research advisor. In July 2009, Roman Obermaisser has received the habilitation ("Venia docendi") certificate for Technical Computer Science. His research work focuses on system architectures for distributed embedded real-time systems. He wrote a book on an integrated time-triggered architecture published by Springer-Verlag, USA. He is the author of several journal papers and conference publications. He has also participated in numerous EU research projects (e.g., SAFEPOWER, universAAL, DECOS, NextTTA) and was the coordinator of the European research projects DREAMS, GENESYS and ACROSS.

Stefan Svensson
ABB AB, Corporate Research, Västerås, Sweden

Biodata: Stefan U. Svensson first joined the ABB Corporate Research Center in Sweden in 2001. His work initially centered on applications for the mobile workforce, embedded systems and automation network communication. In 2005, he became globally responsible for the wireless research area within the Industrial Communication program, managing joint venture research and business-development projects between ABB, SKF and BP and different research institutes. He left ABB in 2008 to manage a group of researchers and work on business development in the area of printed electronics at the Swedish research institute Acreo. In 2010 he returned to ABB and took on the position of program manager for the Industrial Communication program, which in 2014 became the Communication research area. Since September 2016 he is senior project manager for data center research at ABB. Stefan U. Svensson holds an MSc in electrical engineering from the Lund Institute of Technology in Lund, Sweden.