Fault aware task scheduling in cloud using min-min and DBSCAN

Abstract

Cloud computing leverages computing resources by managing these resources globally in a more efficient manner as compared to individual resource services. It requires us to deliver the resources in a heterogeneous environment and also in a highly dynamic nature. Hence, there is always a risk of resource allocation failure that can maximize the delay in task execution. Such adverse impact in the cloud environment also raises questions on quality of service (QoS). Resource management for cloud application and service have bigger challenges and many researchers have proposed several solutions but there is room for improvement. Clustering the resources clustering and mapping them according to task can also be an option to deal with such task failure or mismanaged resource allocation. Density-based spatial clustering of applications with noise (DBSCAN) is a stochastic approach-based algorithm which has the capability to cluster the resources in a cloud environment. The proposed algorithm considers high execution enabled powerful data centers with least fault probability during resource allocation which reduces the probability of fault and increases the tolerance. The simulation is cone using CloudsSim 5.0 tool kit. The results show 25% average improve in execution time, 6.5% improvement in number of task completed and 3.48% improvement in count of task failed as compared to ACO, PSO, BB-BC (Bib ​= ​g bang Big Crunch) and WHO(Whale optimization algorithm).