Priority scheduling algorithm with fault tolerance in cloud environment

Abstract

Cloud computing is an upcoming model for business computing, which makes computing tasks maintain resource pool which constitutes of a large number of computer resources, so that all application programs can get computing power, storage space and all kinds of software services. The computability of the various resource scheduling algorithms is different in different environments. Algorithm according to topology, aspect and many others ways are present. Energy efficient, dynamic priority based, virtual resources model and many other algorithms are present for scheduling tasks, resources and workflows. In this work the Fault tolerance aspect of the server is taken into consideration. An attempt to embed fault tolerance functionality in priority scheduling algorithm is made. This algorithm focuses on the allocating the functionality of the faulty server to another server. Further this algorithm concentrates on the type of cloud architecture too. The performance is measured by providing different inputs. The results provided focuses on better execution of the tasks provided to the servers and depicted through graph.