Energy-aware Task Scheduling in Cloud Compting Based on Discrete Pathfinder Algorithm

Task scheduling is one of the fundamental issues that attract the attention of lots of researchers to enhance cloud performance and consumer satisfaction. Task scheduling is an NP (non-deterministic polynomial)-hard problem that is challenging due to the several conflicting objectives of users and service providers. Therefore, meta-heuristic algorithms are the more preferred option for solving scheduling problems in a reasonable time. Although many task scheduling algorithms are proposed, existing strategies mainly focus on minimizing makespan or energy consumption while ignoring other performance factors. In this paper, we propose a new task scheduling algorithm based on the Discrete Pathfinder Algorithm (DPFA) that is inspired by the collective movement of the animal group and mimics the guidance hierarchy of swarms to find hunt. The proposed scheduler considers five objectives (i.e., makespan, energy consumption, throughput, tardiness, and resource utilization) as cost functions. Finally, different algorithms such as Firefly Algorithm (FA), Particle Swarm Optimization (PSO), Grasshopper Optimization Algorithm (GOA), and Bat Algorithm (BA), are used for comparison. The experimental results indicate that the proposed scheduling algorithm with FA, BA, PSO, and GOA improved up to 9.16%, 38.44%, 3.59%, and 3.44%, respectively. Moreover, the results show dramatic improvements in terms of resource utilization, throughput, and energy consumption.

Automated summary

Task scheduling is a fundamental issue in cloud computing, and the proposed scheduling algorithm based on the Discrete Pathfinder Algorithm (DPFA) shows significant improvements in performance compared to other algorithms. The algorithm considers multiple objectives and achieves better resource utilization, throughput, and energy consumption results.