System Resilience and Fault-Tolerant Architectures for Autonomous Reconfigurable Computing Systems

Submission Deadline: 20 October 2022 (closed)

Guest Editors

Dr. Adhiyaman Manickam, University of Moncton, Canada. Dr. J. Alfred Daniel, Anna University, India. Dr. Dinesh Jackson Samuel, the University of Texas MD Anderson Cancer Center, United States.


Resilience and fault tolerance are very crucial factors in the design and development of safety-critical embedded devices and self-configurable computing systems. This is highly attributed to the risks involved in case of failure of such systems due to their autonomous and independent status. A failure in such systems will cause repercussions and will have a direct and adverse impact on the lives and safety of people and property. Recent developments in resilient and fault-tolerant system architectures have been focused on the development of models inspired by nature. Such systems find their applications in a variety of fields including cyber-physical computing, advanced production and manufacturing, life-critical and safety-critical applications etc. The autonomous reconfigurable systems that are resilient and fault-tolerant are called resilient and reconfigurable computing systems. A good example of such robust systems is the Field Programmable Array which is made up of autonomous reconfigurable memory blocks, routers, and multiplexers. Such reconfigurable systems can seamlessly change the hardware during run-time either partly or completely unlike conventional processing or computing systems.


One of the recent developments in this field includes an architecture that is based on biological systems for achieving system resilience and fault tolerance in self-reconfigurable or self-healing computing systems. The major components of the architecture include a local healing layer, a critical service layer, and a global healing layer. The healing layer in the local division will take care of all the corresponding activities of the system’s life cycle. Any intended or ad-hoc functions or services in case of changes or faults are provided by the critical services architectural layer. Finally, the overall resilience and fault-tolerance of the self-reconfigurable systems are overlooked by the global layer. The above technique has potential applications in emergency diesel generators, cruise control systems, and other safety-critical operations. Another significant research focuses on identifying and locating the faults within multicore hardware systems. Fault isolation in these multicore systems has led to the containment of the errors within the core in question. Hence such systems will enable high efficiency in spite of faults and limits the whole system failure. Future research can be directed towards minimising the cost and space overheads in such autonomous reconfigurable systems.


Design of instrumentation and control systems, Reconfigurable Systems, Fault-Tolerant Architectures, Multiprocessor Chip, Programmable Gate Arrays

Share Link

WeChat scan