Adaptive Fault Tolerance in Real Time Cloud Computing

Abstract

With the increasing demand and benefits ofcloud computing infrastructure, real time computing can beperformed on cloud infrastructure. A real time system cantake advantage of intensive computing capabilities andscalable virtualized environment of cloud computing toexecute real time tasks. In most of the real time cloudapplications, processing is done on remote cloud computingnodes. So there are more chances of errors, due to theundetermined latency and loose control over computingnode. On the other side, most of the real time systems arealso safety critical and should be highly reliable. So there isan increased requirement for fault tolerance to achievereliability for the real time computing on cloudinfrastructure. In this paper, a fault tolerance model for realtime cloud computing is proposed. In the proposed model,the system tolerates the faults and makes the decision on thebasis of reliability of the processing nodes, i.e. virtualmachines. The reliability of the virtual machines is adaptive,which changes after every computing cycle. If a virtualmachine manages to produce a correct result within the timelimit, its reliability increases. And