ترجمه مقاله مدل تحمل پذیری خطای تطبیقی بهبود یافته برای افزایش قابلیت اطمینان در رایانش ابری

Today’s world is an era of cloud computing. Cloud computing aim to power the data centers as a network of virtual services like hardware , database, user-interface etc so that user can access information and applications via internet from anywhere in the world on demand at competitive costs depending on users quality of service requirements. Real time system is a system in which computation guarantees strict time constraints. In a real time cloud applications computations is done at remote cloud computing nodes which may sometimes result in chances of error due to a loose control over computing nodes. This system should be highly reliable so there is an increased demand of fault tolerance to achieve reliability for real time computing on cloud infrastructure. In this paper, a fault tolerance model for real time computing is proposed. The proposed model, is a model named Enhanced Adaptive Fault Tolerance model for increasing reliability in Cloud Computing. The system tolerates the faults and makes the decision on the basis of reliability of the processing nodes that is virtual machines. If a correct result within the time limit will be produced by a virtual machine increases. And if it fails to produce correct result within time limit then its reliability decreases. This model have RAM (Resource Allocation Module) and User Controlled Exception Handling which make it more elastic to the environment. The proposed technique is based on the execution of task if the task is exceeding the limit then it send the task to exception handling section, but it also checks that if the task is about to finish and required the time that is sustainable then it provide the elasticity to that task. The virtual machine instances can be of same type or of different types. The main essence of the proposed technique is to provide elasticity to the task and then admin will decide whether to resubmit the task of same virtual machine or to reject that task. The resubmitted task will be computed again and assign new reliability value