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 applicat… Show more
“…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].…”
Section: Avvmc Algorithmmentioning
confidence: 99%
“…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.…”
Abstract. In this paper, we propose the AVVMC VM consolidation scheme that focuses on balanced resource utilization of servers across different computing resources (CPU, memory, and network I/O) with the goal of minimizing power consumption and resource wastage. Since the VM consolidation problem is strictly NP-hard and computationally infeasible for large data centers, we propose adaptation and integration of the Ant Colony Optimization (ACO) metaheuristic with balanced usage of computing resources based on vector algebra. Our simulation results show that AVVMC outperforms existing methods and achieves improvement in both energy consumption and resource wastage reduction.
“…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].…”
Section: Avvmc Algorithmmentioning
confidence: 99%
“…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.…”
Abstract. In this paper, we propose the AVVMC VM consolidation scheme that focuses on balanced resource utilization of servers across different computing resources (CPU, memory, and network I/O) with the goal of minimizing power consumption and resource wastage. Since the VM consolidation problem is strictly NP-hard and computationally infeasible for large data centers, we propose adaptation and integration of the Ant Colony Optimization (ACO) metaheuristic with balanced usage of computing resources based on vector algebra. Our simulation results show that AVVMC outperforms existing methods and achieves improvement in both energy consumption and resource wastage reduction.
“…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).…”
Abstract:Desktop Cloud computing is the idea of benefiting from computing resources around us to build a Cloud system in order to have better usage of these resources instead of them being idle. However, such resources are prone to failure at any given time without prior knowledge. Such failure events have a can negative impact on the outcome of a Desktop Cloud system. This paper proposes metrics that can evaluate the behaviour of Virtual Machine (VM) allocation mechanisms in the presence of node failures. The metrics are throughput, power consumption and availability. Three VM allocation mechanisms (Greedy, FCFS and RoundRobin mechanisms) are evaluated using the given metrics.
“…[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.…”
This paper presents a general energy management system for High Performance Computing (HPC) clusters and cloud infrastructures that powers off cluster nodes when they are not being used, and conversely powers them on when they are needed. This system can be integrated with different HPC cluster middleware, such as Batch-Queuing Systems or Cloud Management Systems, and can also use different mechanisms for powering on and off the computing nodes. The presented system makes it possible to implement different energy-saving policies depending on the priorities and particularities of the cluster. It also provides a hook system to extend the functionality, and a sensor system in order to take into account environmental information. The paper describes the successful integration of the system proposed with some popular Batch-Queuing Systems, and also with some Cloud Management middlewares, presenting two real use-cases that show significant energy/costs savings of 27% and 17%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.