Static redundancy allocation is inappropriate in hard realtime systems that operate in variable and dynamic environments, (e.g., radar tracking, avionics). Aduprive Fault Tolerance (AFT) can assure adequate reliability of critical niodules, under temporal and resources constraints, by allocating just as much redundiincy to less critical modules as can be afforded, thus gracefirlly reducing their resource requirement.In this paper; we propose a mechanism for supporting adaptive fault tolerance in a real-time system. Adaptation is achieved by choosing a suitable redundancy strategy for a dynamically arriving computation to assure required reliability and to maximize the potential for fault tolerance while ensuring that deadlines are met. The proposed approach is evaluated using a red-life workload simulating radar tracking software in AWACS early wanting aircraf. The results demonstrate that our technique outpevornu static fault tolerance strategies in terms of tasks meeting their timing constraints. Further; we show that the gain in this timing-centric petfonnance metric does not reduce the fault tolerance of the executing tasks below a predejned minimum level. Overall, the evaluation indicates that the proposed ideas result in a system that dynamically provides QOS guarantees along the fault-tolerance dimension.
AFT in a Hard Real Time SystemA key issue in developing such a framework is the efficient integration of on-line adaptive management of redundancy and the real-time scheduler in a multi-processor hard real-79 0-8186-8268-X/97 $10.00 0 1997 IEEE
Pervasive computing demands pervasive networks; such networks need to scale up to billions, or even trillions, of nodes.The aggregate data-storage and data-processing power, as also the useful distributed sensory and actuatory capability, in such networks will be unprecedented, but yet hard to harness. Nodes used in such networks may be composed of mere slivers of silicon powered wirelessly, or built out of combinations of inorganic, metallic, organic or bio-materials; their small size and low cost would also contribute to their extreme mobility.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.