A game theoretical method for auto-scaling of multi-tiers web applications in cloud

Chi, Ruiqing; Qian, Zhuzhong; Lu, Sanglu

doi:10.1145/2430475.2430478

Cited by 7 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the resources coordination problem for multi‐layer applications which deployed on cloud computing, most of solutions have the assessment and prognostication for circumstance of service quality based on queue theory and use them as the input parameter for the resource coordination algorithm [4, 6, 28, 29 ]. In [4 ], Wei‐Hua Ba et al proposed a method to evaluate the performance of applications on cloud computing.…”

Section: Related Workmentioning

confidence: 99%

Virtual machines migration game approach for multi‐tier application in infrastructure as a service cloud computing

Bui

Ho²,

Pham

et al. 2020

IET Networks

View full text Add to dashboard Cite

Virtual machines migration is an essential feature of virtualisation technology which brings many advantages in cloud computing management process such as proactive fault tolerance, load balancing, and power management. There have been many virtual migration algorithms that have been developed but it is hard to find one that best suits all applications as well as ensures the desire of all stakeholders. The optimal virtual machines migration of cloud computing is usually NP-hard or NPcomplete. In addition, determining when virtual machines migrate is a challenge because of the difficulty of fault detection in cloud computing. In this study, the authors propose a virtual machines migration game approach for multi-tier application in infrastructure-as-a-service cloud computing where they first proposed fault detection model based on Takagi-Sugeno fuzzy system with metric's physical machines and then optimal or near optimal migration solution is approximated based on Nash equilibrium. The results of experiment demonstrate the efficiency of their proposal. The proposed virtual machines migration algorithm has been benchmarked in order to highlight their strength and feasibility.

show abstract

Section: Related Workmentioning

confidence: 99%

Virtual machines migration game approach for multi‐tier application in infrastructure as a service cloud computing

Bui

Ho²,

Pham

et al. 2020

IET Networks

View full text Add to dashboard Cite

show abstract

“…The most coarse level of control granularity is at the cloud level for SSCAS. The majority of the studies achieves autoscaling at the cloud level by using a centralized and global controller, with an aim to manage utility [57,28,44,73,21,120], profits [104,155], and availability [65]. Among others, Ferretti et al [70] control the QoS for all cloudbased services in a global manner.…”

Section: Controlling At Cloud Levelmentioning

confidence: 99%

“…To apply explicit search-based optimization for SSCAS, the most widely solution for handling the multi-objectivity is to aggregate all related objectives into a weighted (usually weighted-sum) formulation, which converts the decision-making process into a singleobjective optimization problem. The search-based algorithms include the following: exhaustive search [57,41,74,89], the auxiliary network flow model [104], force-directed search [81], and binary search [91]. For example, the FoSII project [37,114] regards autoscaling decision making as a case-based reasoning process, where the decision is made by looking for similar historical cases using exhaustive search.…”

Section: Search-based Optimizationmentioning

confidence: 99%

A Survey and Taxonomy of Self-Aware and Self-Adaptive Cloud Autoscaling Systems

2018

View full text Add to dashboard Cite

Autoscaling system can recon gure cloud-based services and applications, through various con gurations of cloud so ware and provisions of hardware resources, to adapt to the changing environment at runtime. Such a behavior o ers the foundation for achieving elasticity in modern cloud computing paradigm. Given the dynamic and uncertain nature of the shared cloud infrastructure, cloud autoscaling system has been engineered as one of the most complex, sophisticated and intelligent artifacts created by human, aiming to achieve self-aware, self-adaptive and dependable runtime scaling. Yet, existing Self-aware and Self-adaptive Cloud Autoscaling System (SSCAS) is not mature to a state that it can be reliably exploited in the cloud. In this article, we survey the state-of-the-art research studies on SSCAS and provide a comprehensive taxonomy for this eld. We present detailed analysis of the results and provide insights on open challenges, as well as the promising directions that are worth investigated in the future work of this area of research. Our survey and taxonomy contribute to the fundamentals of engineering more intelligent autoscaling systems in the cloud.

show abstract

“…There are several contributions that relate to our work. The first group of related studies focus on capacity autoscaling in clouds [7,3,14,5,16,2]. Their objective is typically to adjust the allocated capacity to demand so that the required performance is provided, and their main concern is to predict the capacity as accurate as possible to ensure that the capacity is available when needed.…”

Section: Related Workmentioning

confidence: 99%

“…Their objective is typically to adjust the allocated capacity to demand so that the required performance is provided, and their main concern is to predict the capacity as accurate as possible to ensure that the capacity is available when needed. Methods such as, static threshold based controllers [16,2], control theory [18,19], queuing theory [3,5], and time series analysis of workloads [9,11] are used to handle autscaling problem in clouds.…”

Section: Related Workmentioning

confidence: 99%

A virtual machine re-packing approach to the horizontal vs. vertical elasticity trade-off for cloud autoscaling

Sedaghat

Hernández-Rodríguez

Elmroth

2013

Proceedings of the 2013 ACM Cloud and Autonomic Computing Conference

View full text Add to dashboard Cite

An automated solution to horizontal vs. vertical elasticity problem is central to make cloud autoscalers truly autonomous. Today's cloud autoscalers are typically varying the capacity allocated by increasing and decreasing the number of virtual machines (VMs) of a predefined size (horizontal elasticity), not taking into account that as load varies it may be advantageous not only to vary the number but also the size of VMs (vertical elasticity). We analyze the price/performance effects achieved by different strategies for selecting VM-sizes for handling increasing load and we propose a cost-benefit based approach to determine when to (partly) replace a current set of VMs with a different set. We evaluate our repacking approach in combination with different auto-scaling strategies. Our results show a range of 7% up to 60% cost saving in total resource utilization cost of our sample applications and workloads.

show abstract

A game theoretical method for auto-scaling of multi-tiers web applications in cloud

Cited by 7 publications

References 15 publications

Virtual machines migration game approach for multi‐tier application in infrastructure as a service cloud computing

Virtual machines migration game approach for multi‐tier application in infrastructure as a service cloud computing

A Survey and Taxonomy of Self-Aware and Self-Adaptive Cloud Autoscaling Systems

A virtual machine re-packing approach to the horizontal vs. vertical elasticity trade-off for cloud autoscaling

Contact Info

Product

Resources

About