Applying Task Scheduling For IOMT-Cloud Business Optimisation Using AI

Abstract The IoMT-cloud enables a surplus extent of customers to get disseminated, versatile, and virtualized gear just as programming structure over the Internet. The IoMT-cloud is one of the principal headway used recently, it grants customers to get cloud resources over the internet remotely. Hence, we need to complete a reasonable task scheduling estimation to tolerably and viably meet these requests. The scheduling of task issue is perhaps the most essential issue in the IoMT-cloud since cloud execution depends prevalently upon it. Capable task scheduling administration should meet customer's requirements and improve the resources used to overhaul the introduction of the IoMT-cloud framework. To deal with this issue, in this investigation, we attempt to show the two most notable static and one dynamic task scheduling execution separately, short job first (SJF), first come first serve (FCFS), and round-robin (RR). Likewise, it was advanced using the AI technique known as genetic algorithm (GA). The CloudSim simulation framework is used to measure their impact on total execution time (TET), algorithm complexity, throughput, resource utilization, total waiting time (TWT), availability of assets, total finish time (TFT), cost, and resource utilization. The model proposed is to improve the viability of task scheduling for the IoMT-cloud stage with the best execution rate of 32.47ms. The exploratory results show that GA cuts down the cost of planning and reduces the total time, which is a convincing computation for the IoMT-cloud task scheduling.