Fault Tolerance Based Load Balancing
Approach for Web
Resources in Cloud Environment
Anju Shukla, Shishir Kumar, and Harikesh
Singh
Department of Computer
Science and Engineering, Jaypee University of Engineering and Technology, India
Abstract: Cloud
computing consists group of heterogeneous resources scattered around the world
connected through the network. Since high performance computing is strongly
interlinked with geographically distributed service to interact with each other
in wide area network, Cloud computing makes the architecture consistent,
low-cost, and well-suited with concurrent services. This paper presents a fault
tolerance load balancing technique based on resource load and fault index
value. The proposed technique works in two phases: resource selection and task
execution. The resource selection phase selects the suitable resource for task
execution. A resource with least resource load and fault index value is
selected for task execution. Further task execution phase sets checkpoints at
various intervals for saving the task state periodically. The checkpoints are
set at various intervals based on resource fault index. When a task is executed
on a resource, fault index value of selected resource is updated accordingly.
This reduces the checkpoint overhead by avoiding unnecessary placements of
checkpoints. The proposed model is validated on CloudSim and provides improved
performance in terms of response time, makespan, throughput and checkpoint
overhead in comparison to other state-of-the-art methods.
Keywords: Scheduler,
checkpoint manager, cloud computing, checkpointing, fault index, high
performance computing.
Received June 6, 2018; accepted July 2, 2019
https://doi.org/10.34028/iajit/17/2/10