Scholarlink

<p>The proposed scheduling method for cloud computing called “quality-aware batch scheduling of containers (QABSC)” gives priority to timely completion of tasks that are sensitive to delays. This five-stage approach guarantees task execution with the least amount of delay and the greatest amount of resource efficiency. Throughout Batch Formation, the QABSC framework arranges tasks and containers, and during Batch Correlation, it pairs them effectively. In order to set the stage for scheduling decisions that order task execution, batch priority assignment carefully prioritizes tasks based on resource demand and traffic sensitivity. The scheduling algorithm takes delay-sensitive traffic requirements and energy consumption metrics into account in the last phase, energy consideration and delay sensitivity. The QABSC model performs cloud scheduling tasks more effectively than deep reinforcement learning. The effectiveness of the model is demonstrated by a thorough evaluation, which includes an average resource utilization of 85.9% with a standard deviation of 3.21, an average makespan of 407.4&#xa0;ms, throughput averaging 133.5 tasks/sec, and an average waiting time of 82.2&#xa0;ms. QABSC’s strong performance is demonstrated by low SLA violations at 2.3%, energy efficiency at 1156.2 tasks/kWh, scalability at 148.5 tasks/sec, and fault tolerance at 99.45%. The intricacy of batch scheduling and QABSC’s capacity to enhance cloud scheduling operations draw attention to areas in need of ongoing development and innovation.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Quality aware batch scheduling of containers in cloud computing environment

  • 期刊论文

  • 发表日期：

    2025年1月4日

查看全文
  • S. A. Poojitha,
  • K. Ravindranath

摘要

The proposed scheduling method for cloud computing called “quality-aware batch scheduling of containers (QABSC)” gives priority to timely completion of tasks that are sensitive to delays. This five-stage approach guarantees task execution with the least amount of delay and the greatest amount of resource efficiency. Throughout Batch Formation, the QABSC framework arranges tasks and containers, and during Batch Correlation, it pairs them effectively. In order to set the stage for scheduling decisions that order task execution, batch priority assignment carefully prioritizes tasks based on resource demand and traffic sensitivity. The scheduling algorithm takes delay-sensitive traffic requirements and energy consumption metrics into account in the last phase, energy consideration and delay sensitivity. The QABSC model performs cloud scheduling tasks more effectively than deep reinforcement learning. The effectiveness of the model is demonstrated by a thorough evaluation, which includes an average resource utilization of 85.9% with a standard deviation of 3.21, an average makespan of 407.4 ms, throughput averaging 133.5 tasks/sec, and an average waiting time of 82.2 ms. QABSC’s strong performance is demonstrated by low SLA violations at 2.3%, energy efficiency at 1156.2 tasks/kWh, scalability at 148.5 tasks/sec, and fault tolerance at 99.45%. The intricacy of batch scheduling and QABSC’s capacity to enhance cloud scheduling operations draw attention to areas in need of ongoing development and innovation.