A task scheduling model in heterogeneous cloud resources with a combination of collective intelligence algorithms

Subject Areas : Information Technology in Engineering Design (ITED) Journal

safdar rostami ¹ , Ali Broumandnia ² , Ahmad Khademzadeh ³

1 - Department of Computer Engineering, South Tehran Branch, Islamic Azad University, Tehran, Iran
2 - Department of Computer Engineering, South Tehran Branch, Islamic Azad University, Tehran, Iran
3 - Department of Computer Engineering, South Tehran Branch, Islamic Azad University, Tehran, Iran

Received: 2023-12-11 Accepted : 2024-04-28 Published : 2024-03-18

Keywords: Cloud Computing, Task Scheduling, Non-Dominated Sorting using, Multi-Level Priority Queues. , ,

Abstract :

Cloud computing is an environment where users have access to shared computing resources on an on-demand and pay-per-use basis.Regarding the limitations and dynamism of computing resources for the allocation of tasks to resources in a cloud environment, an effective scheduling mechanism is essential to solving these limitations and user satisfaction. Hence, numerous algorithms have been proposed to reduce execution time and parallelize tasks. To achieve optimal scheduling, existing scheduling algorithms consider the system's current condition. However, most proposed algorithms did not necessarily yield an optimal result in the long term and were only successful in improving one parameter of Quality of Service (QoS). Owing to the low convergence rate of solutions in metaheuristic algorithms, this paper presents a scheduling method in accordance with Multi-Level Priority Queues (MLPQ) based on non-dominated sorting using the Capuchin Search Algorithm (CapSA) for heterogeneous cloud systems. Compared to previous approaches, the proposed method demonstrates superior performance in terms of delay, load balancing, execution cost, and execution time.