Journal of Cloud Computing Advances Systems and Applications · 2019 · 120 citations · 20 references
ComputingCloud ComputingComputer SystemsCloud Service ModelsContainerizationVirtualizationCloud Resource ManagementCompute Resource ManagementContainer ArchitectureResource SchedulingVirtualization ArchitectureWorkload PlacementCloud SchedulingContainer PlacementLightweight VirtualizationPlacementPlacement ArchitectureResource PlacementVirtual Machine PlacementVirtual Machines
Container as a Service (CaaS) is an emerging lightweight virtualization model that is gaining popularity, yet existing placement strategies treat virtual machine and physical machine resource utilization separately, leading to under‑ or over‑utilization and motivating the need for a unified container placement algorithm. This study aims to enhance CPU core and memory utilization for both virtual machines and physical machines while reducing the number of instantiated VMs and active PMs in a cloud environment. The authors propose a placement architecture that employs Best Fit and Max Fit heuristics guided by a fitness function evaluating residual resource waste on both PMs and VMs, and a meta‑heuristic Ant Colony Optimization based on Best Fit (ACO‑BF) that uses the same fitness function. Experimental results demonstrate that ACO‑BF outperforms BF and MF heuristics and achieves significant improvements in resource utilization for both VMs and PMs.
Unlike a traditional virtual machine (VM), a container is an emerging lightweight virtualization technology that operates at the operating system level to encapsulate a task and its library dependencies for execution. The Container as a Service (CaaS) strategy is gaining in popularity and is likely to become a prominent type of cloud service model. Placing container instances on virtual machine instances is a classical scheduling problem. Previous research has focused separately on either virtual machine placement on physical machines (PMs) or container, or only tasks without containerization, placement on virtual machines. However, this approach leads to underutilized or overutilized PMs as well as underutilized or overutilized VMs. Thus, there is a growing research interest in developing a container placement algorithm that considers the utilization of both instantiated VMs and used PMs simultaneously. The goal of this study is to improve resource utilization, in terms of number of CPU cores and memory size for both VMs and PMs, and to minimize the number of instantiated VMs and active PMs in a cloud environment. The proposed placement architecture employs scheduling heuristics, namely, Best Fit (BF) and Max Fit (MF), based on a fitness function that simultaneously evaluates the remaining resource waste of both PMs and VMs. In addition, another meta-heuristic placement algorithm is proposed that uses Ant Colony Optimization based on Best Fit (ACO-BF) with the proposed fitness function. Experimental results show that the proposed ACO-BF placement algorithm outperforms the BF and MF heuristics and maintains significant improvement of the resource utilization of both VMs and PMs.
20
Marco Dorigo, Mauro Birattari, Thomas Stützle · IEEE Computational Intelligence Magazine · 2006 · 5.2K citations
Marco Dorigo, Mauro Birattari, Thomas Stützle · IEEE Computational Intelligence Magazine · 2006 · 1.9K citations · Full text