GTO based Multi Objective Task Scheduling for Energy Efficient and Reliable Cloud Environments
K. Venkateswarlu, K. Sruthi, G Mirona, G. Soma Sekhar, A. L. Narasimha Reddy, Santhosh Kumar Medishetti
Abstract
Task scheduling in cloud computing is a critical challenge that directly affects system performance, energy efficiency, and reliability. This paper proposes an advanced scheduling approach based on the Artificial Gorilla Troops Optimizer (GTO) a bio-inspired metaheuristic designed to balance exploration and exploitation in complex optimization problems. The GTO algorithm is applied to schedule tasks using the NASA Ames iPSC/860 workload within the CloudSim simulation framework. It is evaluated against widely used algorithms GA, PSO, and ACO under three performance metrics such as makespan, energy consumption, and VM failure rate. Simulation results clearly demonstrate the superiority of GTO across all evaluated parameters. On average, GTO achieved a 32.7% reduction in makespan compared to GA, 50.3% compared to ACO, and 42.5% compared to PSO. In terms of energy efficiency, GTO reduced energy consumption by 24.0% over GA, 28.2% over ACO, and 22.4% over PSO. Additionally, GTO significantly lowered VM failure rates, achieving reductions of 35.6%, 38.7%, and 34.0% compared to GA, ACO, and PSO respectively. These improvements validate GTO’s effectiveness in providing faster, more energy-efficient, and reliable task scheduling, making it a promising solution for modern cloud infrastructures operating under dynamic and high-demand workloads.