Improved Intelligent Pelican Optimization Algorithm-Based IoT Task Scheduling Model for Fog Integrated Cloud Platform

The benefits facilitated with utilization of integrated fog and cloud computing platforms are frequently adopted by enterprises and corporations that build Internet of Things (IoT)-based systems. Fog-Cloud (FC) computing models provide the strategy of pay-as-you-go and virtualization for facilitating resources of information technology that include storage, network, memory and CPU. Achieving efficient resource management in an integrated FC computing platform is more challenging, since tasks generated from IoT environment are always processed in real-time using heterogeneous data with deadline-driven constraints. In this paper, Improved Intelligent Pelican Optimization Algorithm-based IoT Task Scheduling (IIPOA-ITS) model for FC platform is proposed for dealing with the requirements that are essential for satisfying the factors to support real-time processing. This proposed IIPOA-ITS approach is formulated as an efficient two-step scheduling algorithm in which, the first phase is responsible for priority and deadline-based task classification. In the second phase, IIPOA is proposed for IoT task scheduling. It adopts a fitness function for achieving effective resource management using fog and cloud-assisted factors that include number of Virtual Machines (VMs), number of tasks, size of tasks, capacity and speed. Real-time situation matching scenarios related to huge and small workloads are considered for assessing the proposed IIPOA-ITS and benchmarked algorithms with different number of tasks. It is also proposed as a model for handling and satisfying the requirements of Quality of Service (QoS) such that task batch makespan time and cost are minimized with increase in rate of resource utilization. The simulation results also confirm 14.58% minimized response time and 19.42% maximized throughput in contrast to baseline approaches taken for investigation.