Certain investigations on allocation of task based cost effectiveness using genetic algorithm ga ta in hybrid cloud computing environment

Abstract

Cloud Computing (CC) allows consumers to access computing newlineresources and services in the modern world without having to own the newlineunderlying infrastructure. In the notion of quotcloud computing,quot a network of newlineremote devices is connected to carry out tasks like data gathering, processing, newlineprofiling, and storage. In this setting, work scheduling and resource allocation newlineare crucial activities that must be controlled in accordance with user needs. newlineHybrid cloud is used to efficiently distribute the resources because it is a newlinesolution that can handle processing massive consumer applications on a payper- newlineuse basis. Thus, the model must be created as a profit-driven structure to newlinesave costs and increase revenue.In the first module, a Cost-Effective Optimal Task Scheduling Model (CEOTS) is used in the proposed work for hybrid clouds. Additionally,the algorithm uses an efficient resource allocation strategy to complete many deliberate tasks. The model was successfully simulated to confirm its viability newlinein light of elements like processing speed, make span, and effective use of newlinevirtual machines. According to the findings, the suggested model performed newlinebetter than the current works and may be trusted going forward for real-time newlineapplications. In the second module, a Genetic Algorithm based Task Allocation newline(GA-TA) model has been proposed to overcome these considered issues. The newlineproposed model intends to solve the issues of optimal resource allocation and newlinescheduling in Cloud model, using a parallel scheduling process can improve newlinethe task scheduling during the connectivity between serial operations remains newlineconstant. The significant factor of dynamic tasks is provided by users in serial newlinemanner as queue, in which the tasks are having different priorities based on newlinethe order of execution. Moreover, the model developed a Deadline-based newlineTask Classification (DTC) for efficient results on scheduling. The paper uses newlineFirefly Algorithm for scheduling tasks in minimal latency, through which the newlineuser satisfaction is improved. The experimental result