Department of Computer Science, Virtual University of Pakistan, Rawalpindi 46300, Pakistan.
Department of Computer Science, Capital University of Science & Technology (CUST), Islamabad 46300, Pakistan.
Sensors (Basel). 2022 Jan 25;22(3):920. doi: 10.3390/s22030920.
Cloud computing has emerged as the most favorable computing platform for researchers and industry. The load balanced task scheduling has emerged as an important and challenging research problem in the Cloud computing. Swarm intelligence-based meta-heuristic algorithms are considered more suitable for Cloud scheduling and load balancing. The optimization procedure of swarm intelligence-based meta-heuristics consists of two major components that are the local and global search. These algorithms find the best position through the local and global search. To achieve an optimized mapping strategy for tasks to the resources, a balance between local and global search plays an effective role. The inertia weight is an important control attribute to effectively adjust the local and global search process. There are many inertia weight strategies; however, the existing approaches still require fine-tuning to achieve optimum scheduling. The selection of a suitable inertia weight strategy is also an important factor. This paper contributed an adaptive Particle Swarm Optimisation (PSO) based task scheduling approach that reduces the task execution time, and increases throughput and Average Resource Utilization Ratio (ARUR). Moreover, an adaptive inertia weight strategy namely is introduced. The proposed scheduling approach provides a better balance between local and global search leading to an optimized task scheduling. The performance of the proposed approach has been evaluated and compared against five renown PSO based inertia weight strategies concerning makespan and throughput. The experiments are then extended and compared the proposed approach against the other four renowned meta-heuristic scheduling approaches. Analysis of the simulated experimentation reveals that the proposed approach attained up to 10%, 12% and 60% improvement for makespan, throughput and ARUR respectively.
云计算已成为研究人员和业界最受欢迎的计算平台。负载均衡任务调度已成为云计算中的一个重要且具有挑战性的研究问题。基于群体智能的启发式元启发式算法被认为更适合云调度和负载均衡。基于群体智能的启发式元启发式算法的优化过程由两个主要组成部分组成，即局部搜索和全局搜索。这些算法通过局部搜索和全局搜索找到最佳位置。为了实现任务到资源的最佳映射策略，局部搜索和全局搜索之间的平衡起着有效的作用。惯性权重是有效调整局部和全局搜索过程的重要控制属性。有许多惯性权重策略，但是现有的方法仍然需要微调才能实现最佳调度。选择合适的惯性权重策略也是一个重要因素。本文提出了一种基于自适应粒子群优化（PSO）的任务调度方法，该方法可以减少任务执行时间，并提高吞吐量和平均资源利用率（ARUR）。此外，还引入了一种自适应惯性权重策略。所提出的调度方法在局部搜索和全局搜索之间提供了更好的平衡，从而实现了优化的任务调度。已经评估并比较了所提出的方法与五个著名的基于 PSO 的惯性权重策略在完成时间和吞吐量方面的性能。然后，将实验扩展并将所提出的方法与其他四个著名的元启发式调度方法进行比较。模拟实验的分析表明，所提出的方法在完成时间、吞吐量和 ARUR 方面分别提高了 10%、12%和 60%。
