An Indicator-Based Algorithm for Task Scheduling in Multi-Cloud Environments

Abstract

Cloud computing is the ability to scale various resources and services that can be dynamically configured by the cloud service provider (CSP) and delivered on demand by the customers. The objective of most of the task scheduling algorithms is to ensure that the overall processing time of all the tasks (i.e., makespan) is minimized. Here, minimization of makespan in no way guarantees the minimization of execution cost. In indicator-based (IBTS) task scheduling algorithm for the multi-cloud environment, we can outline the significant contributions as the following: (1) IBTS achieves multi-objective solutions while considering parameters, makespan, and execution cost. (2) IBTS proposes a normalization framework with time and cost length indicators for efficient task scheduling. (3) The efficacy of the IBTS algorithm is demonstrated using both the benchmark and synthetic datasets. (4) The simulation outcomes of the IBTS algorithm in comparison with three existing task scheduling algorithms, namely ETBTS, MOTS, and PBTS, clearly exhibit superiority, which proves acceptance of IBTS algorithm.