Mr-Moonlight：使用多元回归多目标七点瓢虫优化进行主机过载检测的VM整合
Mr-moslo: vm consolidation using multiple regression multi-objective seven-spot ladybird optimization for host overload detection
摘要：
虚拟机（VM）整合是提高云计算服务中资源利用率的关键过程。由于云数据中心的高电力消耗，运营成本和二氧化碳排放量增加。资源的低效使用是这些问题的主要原因，VM整合是一种可行的解决方案。VM整合包括主机过载/欠载检测，虚拟机选择和虚拟机放置过程。大多数现有的虚拟机整合的主机过载/欠载检测方法仅使用CPU利用率来确定主机负载。本文提出了三个资源，即CPU利用率，内存利用率和带宽利用率用于主机过载检测，并使用基于自适应回归的模型（称为多元回归多元回归），目标七点瓢虫优化提出了一种基于自适应阈值和回归的主机过载检测模型（MR-MOSLO），该模型结合了基于自适应阈值和回归的主机过载检测算法的优点，为动态环境下的阈值设置提供了更多的优势，并能准确地预测主机过载。为此，首先采用基于CPU利用率的多元回归（MR）算法，内存利用率和带宽利用率来估计主机的负载状况，然后引入多目标七点瓢虫优化算法（MOSLO）来选择主机利用率的上下限阈值，在此基础上，主机过载/欠-在CloudSim工具中进行了仿真，实验结果表明，提出的MR-1负载检测方法具有较高的精度和较低的功耗，MOSLO算法能有效地检测主机过载，其能量和SLA值相当接近，而SLATAH、PDM、SLAV和ESV值比大多数现有方法都要小。
英文摘要：
Virtual Machine (VM)consolidation is a crucial process in improving the utilization of the resource in cloud computing services.As the cloud data centers consume high electrical power,the operational costs and carbon dioxide releases increases.The inefficient usage of the resources is the main reason for these problems and VM consolidation is a viable solution.VM consolidation includes host overload/under-load detection,VM selection and VM placement processes.Most existing host overload/under-load detection approaches of VM consolidation uses CPU utilization only for the determining host load.In this paper,three resources namely CPU utilization,memory utilization and bandwidth utilization are used for host overload detection and an adaptive regression based model called Multiple Regression Multi-Objective Seven-Spot Ladybird Optimization(MR-MOSLO) is proposed.This model is based on combining the benefits of adaptive threshold based and regression based host overload detection algorithms.This approach of combining these features provide more advantages for threshold setting in dynamic environments with accurate prediction of host overloading.For this purpose, initially,Multiple Regression (MR)algorithm is used which relay on CPU utilization,memory utilization and bandwidth utilization for estimation of the host load conditions.Then a Multi-Objective Seven-Spot Ladybird Optimization(MOSLO)algorithm is introduced to select the upper and lower threshold limits for host utilization.Based on these algorithms,the host overload/under-load is detected with high accuracy and less power consumption.The simulations are conducted in CloudSim tool and the empirical results shows that the proposed MR-MOSLO algorithm detects the host overload efficiently with reasonably similar energy and SLA values while comparatively lesser SLATAH,PDM,SLAV and ESV values than most of the existing methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
