Enhanced Task Scheduling in Cloud Computing: A Comparative Analysis and Hybrid Algorithm Implementation Using CloudSim
Padigela Srinithya Reddy, Kariveda Trisha, Nichenametla Hima Sree, Sreebha Bhaskaran, Nalini Sampath
Abstract
Task scheduling is crucial in cloud environments to optimize resource allocation and performance. This research presents a comprehensive comparative analysis of task scheduling algorithms, that includes First-Come-First Serve (FCFS), Shortest Job First (SJF), Genetic Algorithm (GA), and Particle Swarm Optimization (PSO). FCFS schedules tasks based on their arrival order, SJF prioritizes tasks based on the shortest execution time, and GA and PSO use metaheuristic approaches that use evolutionary methods for optimization. The hybrid algorithm is proposed combining SJF and GA to improve scheduling efficiency. The main objective is to improve the performance of task-scheduling algorithms in cloud environments. The performance of the individual algorithms and of the proposed hybrid algorithm are analyzed under static and dynamic workload scenarios. Metrics such as makespan and response time are evaluated using simulations.