Performance and Power Management for Cloud Infrastructures

Abstract

International audienceA key issue for Cloud Computing data-centers is to maximize their profits by minimizing power consumption and SLA violations of hosted applications. In this paper, we propose a resource management framework combining a utility-based dynamic Virtual Machine provisioning manager and a dynamic VM placement manager. Both problems are modeled as constraint satisfaction problems. The VM provisioning process aims at maximizing a global utility capturing both the performance of the hosted applications with regard to their SLAs and the energy- related operational cost of the cloud computing infrastructure. We show several experiments how our system can be controlled through high level handles to make different trade-off between application performance and energy consumption or to arbitrate resource allocations in case of contention

Virtual Machine Consolidation in Cloud Data Centers Using ACO Metaheuristic

“…16) using a probabilistic decision rule (Eq. 15) [line [11][12][13][14][15][16][17][18][19][20][21][22]. If the current PM is fully utilized or there are no feasible VMs left to assign to the PM, a new empty PM is taken to fill in [line [14][15][16].…”

“…Pheromone levels are implemented using a n×m matrix τ . Each ant starts with an empty solution, a set of PMs, and a randomly shuffled set of VMs [line [6][7][8][9][10][11][12]. Inside the while loop, an ant is chosen at random and is allowed to choose a VM to assign next to its current PM among all the feasible VMs (Eq.…”

Evaluation Metrics for VM Allocation Mechanisms in Desktop Clouds

“…Most papers in the literature focus on the performance notion which includes attributes such as response time and average turnover time such as (Van et al, 2010) and (Stantchev, 2009). This is because researchers assume that Cloud nodes are very reliable (Buyya et al, 2010).…”

An energy management system for cluster infrastructures

“…[6] considers a power-aware scheduling algorithm for DVFS-enabled clusters, where processor frequencies are scaled down in order to minimize power consumed without substantially increasing execution times. [11] describes an approach to load balance Virtual Machine (VM) provisioning across different servers to save energy and to maintain the performance of the system. The underlying idea of such technique is to try to reduce energy consumption even if nodes cannot be idle.…”