Scholarlink

<p>This research introduces an Adaptive Artificial Hummingbird algorithm (AAHA)-based virtual machine (VM) consolidation strategy (AAHA-VMC) to reduce energy consumption with optimal utilization of resources in modern cloud data centers (CDCs). Existing VM consolidation approaches primarily emphasize CPU utilization, often overlooking the role of memory and workload constraints, which are essential for sustaining workload stability and mitigating performance degradation. In addition, these techniques do not consider the impact of CPU utilization on the performance of the VMs. These oversights result in inefficient resource allocation, increased VM migrations, and frequent Service Level Agreement (SLA) violations (SLAVs). To address these gaps, the proposed AAHA-VMC framework integrates: (i) a multi-objective PM overload detection mechanism, (ii) a memory-aware VM selection strategy, and (iii) an AAHA VM placement algorithm. The proposed technique ensures balanced resource allocation while minimizing energy consumption, unnecessary VM migrations, and SLAVs. The proposed approach is compared with state-of-the-art VM consolidation approaches using real-world workload-based random workloads. The outcome demonstrates that AAHA-VMC outperforms state-of-the-art approaches by achieving a reduction of up to 35% energy and SLAV (ESV). It mitigates SLAVs due to memory overutilization and performance degradation, thereby reducing SLAV by more than 60%. The model ensures optimal CPU utilization (78–80%) and memory utilization (82–84%), promoting energy efficiency while ensuring scalability for next-generation CDCs. The implementation code is available at the following GitHub repository: <a href="https://github.com/sahulgcs19-gif/CloudSimFiles">https://github.com/sahulgcs19-gif/CloudSimFiles</a>.</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

Multi-resource aware virtual machine consolidation approach for modern cloud data centers

  • 期刊论文

  • 发表日期：

    2025年10月15日

查看全文
  • Sahul Goyal,
  • Lalit Kumar Awasthi,
  • Vaneet Garg,
  • Gagan Kumar

摘要

This research introduces an Adaptive Artificial Hummingbird algorithm (AAHA)-based virtual machine (VM) consolidation strategy (AAHA-VMC) to reduce energy consumption with optimal utilization of resources in modern cloud data centers (CDCs). Existing VM consolidation approaches primarily emphasize CPU utilization, often overlooking the role of memory and workload constraints, which are essential for sustaining workload stability and mitigating performance degradation. In addition, these techniques do not consider the impact of CPU utilization on the performance of the VMs. These oversights result in inefficient resource allocation, increased VM migrations, and frequent Service Level Agreement (SLA) violations (SLAVs). To address these gaps, the proposed AAHA-VMC framework integrates: (i) a multi-objective PM overload detection mechanism, (ii) a memory-aware VM selection strategy, and (iii) an AAHA VM placement algorithm. The proposed technique ensures balanced resource allocation while minimizing energy consumption, unnecessary VM migrations, and SLAVs. The proposed approach is compared with state-of-the-art VM consolidation approaches using real-world workload-based random workloads. The outcome demonstrates that AAHA-VMC outperforms state-of-the-art approaches by achieving a reduction of up to 35% energy and SLAV (ESV). It mitigates SLAVs due to memory overutilization and performance degradation, thereby reducing SLAV by more than 60%. The model ensures optimal CPU utilization (78–80%) and memory utilization (82–84%), promoting energy efficiency while ensuring scalability for next-generation CDCs. The implementation code is available at the following GitHub repository: https://github.com/sahulgcs19-gif/CloudSimFiles.