Task scheduling in cloud using resistive and ranking meta-heuristic optimization approach

Abstract

Cloud computing (CC) is an emergent and revolutionary technological paradigm to facilitate data generation over the networking environment. It is determined as the computing edge where it provides cloud services over the networking point. It assists in handling the delay issues during the task scheduling process. With the advent analysis over the existing approaches, inappropriate task scheduling in cloud computing outcomes in huge delay than the other computing models. Therefore, the actual advantages of cloud computing are attained with the adoption of appropriate task scheduling strategies. However, it is an NP-hard issue and needs effectual and optimal approaches to dealing with resource utilization, response time, and latency at the networking model. This research concentrates on modelling an efficient hybrid optimization approach to overcome the drawbacks of single standard optimization approaches. This work hybridizes the resistive-based Particle swarm Optimization) approach with Improved ranking-based Grey wolf optimization approach to handle the exploration and exploitation issues over the standard methods. Here, is used to schedule the task among the connected devices, and helps manage the resources at the device level. The resources are allocated and managed based on the demand generated with the incoming requests in the anticipated model. The ultimate target of this work is to diminish the delay, average response time, and optimal resource utilization by efficiently scheduling the tasks by managing the available resources. The simulation is done with the MATLAB 2016b simulator. The evaluation results show that the anticipated model provides promising outcomes with energy consumption, average response time, execution time, etc. The proposed model shows a better trade-off in contrast to prevailing approaches.