iVMp: An Interactive VM Placement Algorithm for Agile Capital Allocation

Li, Xi; Ventresque, Anthony; Stokes, Nicola; Thorburn, James; Murphy, John

doi:10.1109/cloud.2013.4

Cited by 6 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the existing algorithms of multi-dimensional resource scheduling strategies, one type dominates: the simple heuristic algorithms based on a greedy strategy evolved from onedimensional resource scheduling. This type includes First Fit Algorithm (FF), First Fit Decreasing Algorithm (FFD), Best Fit Algorithm (BF), Best Fit Decreasing algorithm (BFD), Next Fit Algorithm (NF), Worst Fit Algorithm (WF), etc [14]- [17]. Many algorithms reported in recent years are improved versions of the FFD algorithm [16], among which the following algorithms stand out with relatively good performance: FFDProd and FFDSum algorithms developed by Panigrahy et al on the basis of FFD, which are two heuristic geometric algorithms suitable for largescale resource scheduling in cloud data centers [18].…”

Section: Related Studiesmentioning

confidence: 99%

A Multi-Dimensional Resource Scheduling Strategy Based on Multilateral Complementarity

et al. 2019

View full text Add to dashboard Cite

The diversification of computing resources and the increasing complexity of resource demand from applications in terms of type, granularity, and quantity call for more efficiency in resource scheduling. To meet this challenge, this paper proposes a resource description model based on a quantized polygon. It explores the theoretical basis for the multilateral complementarity strategy (MCS), analyzes the basic mechanisms and application architecture of the MCS, and, finally, proposes the multi-dimensional quantized polygon (MQP) algorithm-a multi-dimensional resource scheduling algorithm based on multilateral complementarity (MC-MDRS algorithm). The experiments show that the multi-dimensional resource scheduling strategy based on the MQP, when implemented in an environment in which multi-dimensional (3 ≤ d ≤ 6) computing resources are provisioned, can effectively respond to the requests for various computing resources by granular services and facilitate the deployment of granular application services arriving in batches. The analysis of the experimental results indicates that the MQP algorithm outperforms other multi-dimensional resource scheduling algorithms by 2%-5% in node utilization.

show abstract

Section: Related Studiesmentioning

confidence: 99%

A Multi-Dimensional Resource Scheduling Strategy Based on Multilateral Complementarity

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The execution time of RBP is less than one second when executed using the small IBM dataset [5]. The scalability of RBP is evaluated using the set of PMs from the big IBM dataset and duplicating the VM set of the small IBM dataset (2, 869 VMs) in order to obtain various number of VMs.…”

Section: Comparison With Cplexmentioning

confidence: 99%

“…This underlying VM placement problem is usually considered as an instance of the NP-hard bin-packing problem (BPP), which makes the finding of an optimal solution a challenge in terms of quality and time, given that the problem consists of tens of thousands of PMs and hundreds of thousands of VMs. Quality (e.g., number of PMs required and resource wastage [4]) and time to find a good solution are both important as the first one allows the solutions to save money and the second is essential for capital allocators to make their decisions (see [5]). …”

Section: Introductionmentioning

confidence: 99%

A Fair Comparison of VM Placement Heuristics and a More Effective Solution

Ventresque

Murphy

et al. 2014

2014 IEEE 13th International Symposium on Parallel and Distributed Computing

Self Cite

View full text Add to dashboard Cite

“…This is a perfect example of a problem where multi-objective decision making makes sense: an optimisation problem with various independent objectives that only decision-makers can compare -possibly collectively. For instance, Li et al (2013) describe such an enterprise environment where managers of hosting departments have various perspectives when it comes to placement decisions. Hence we call the problem we address in this paper Multi-Objective Optimisation for the Machine Reassignment Problem (MOMRP).…”

Section: Introductionmentioning

confidence: 99%

A comparative study of multi-objective machine reassignment algorithms for data centres

et al. 2019

Self Cite

View full text Add to dashboard Cite

At a high level, data centres are large IT facilities hosting physical machines (servers) that often run a large number of virtual machines (VMs)but at a lower level, data centres are an intricate collection of interconnected and virtualised computers, connected services, complex service-level agreements. While data centre managers know that reassigning VMs to the servers that would best serve them and also minimise some cost for the company can potentially save a lot of money-the search space is large and constrained, and the decision complicated as they involve different dimensions. This paper consists of a comparative study of heuristics and exact algorithms for the Multi-objective Machine Reassignment problem. Given the common intuition that the problem is too complicated for exact resolutions, all previous works have focused on various (meta)heuristics such as First-Fit, GRASP, NSGA-II or PLS. In this paper, we show that the state-of-art solution to the single objective formulation of the problem (CBLNS) and the classical multi-objective solutions fail to bridge the gap between the number, quality and variety of

show abstract

iVMp: An Interactive VM Placement Algorithm for Agile Capital Allocation

Cited by 6 publications

References 3 publications

A Multi-Dimensional Resource Scheduling Strategy Based on Multilateral Complementarity

A Multi-Dimensional Resource Scheduling Strategy Based on Multilateral Complementarity

A Fair Comparison of VM Placement Heuristics and a More Effective Solution

A comparative study of multi-objective machine reassignment algorithms for data centres

Contact Info

Product

Resources

About