Resource reliability using fault tolerance in cloud computing

Cloud computing offers variety of services from software instance to resource provisioning. As the user demands increase, there is a necessity to enhance cloud offerings. But still in some cases fault-tolerance is the major challenge for cloud environment. Multiple request to access the same server sometime leads to server over loaded and may increase faults and cause unreliability for the server. Few fault-tolerance techniques like self-healing, job migration, static load balancing and replication are existed but they are not fully reliable and effective for cloud environment. In this paper, we propose pro-active approach for fault-tolerance based on Processing power, Memory and Network parameters to increase resource reliability. Through this approach, we first calculate the reliability of each Virtual Machine (VM) based on success rate of task execution and then schedule the task on highly reliable VM. This approach provides comparatively good results for the VM reliability and system stability.