Auto-Scaling Web Applications in Clouds

Qu, Chenhao; Calheiros, Rodrigo N.; Buyya, Rajkumar

doi:10.1145/3148149

Cited by 217 publications

(166 citation statements)

References 99 publications

Supporting

Mentioning

152

Contrasting

Unclassified

Order By: Relevance

“…Grey-box models are hybrid approaches that use models in combination with machine learning (Gandhi et al, 2012). (Qu et al, 2016) Rule-based approaches are used in commercial auto-scaling systems such as (Amazon AWS AutoScaling service,2018) or (RightScale, 2018). An advantage of this approach is that a DevOps user can relatively easily create and understand them.…”

Section: Adaptation Implementationmentioning

confidence: 99%

“…The above mentioned special characteristics of each mode of adaptation indicate that research is required by application developers in order to formulate the correct criteria to trigger adaptations. A relevant survey, which examines many scaling techniques used by dedicated software (auto-scaling) has been compiled by (Qu et al, 2016) …”

Section: Scale Up -Scale Downmentioning

confidence: 99%

See 1 more Smart Citation

Challenges and Research Directions in Big Data-driven Cloud Adaptivity

Τσαγκαρόπουλος

Papageorgiou

Apostolou

et al. 2018

Proceedings of the 8th International Conference on Cloud Computing and Services Science

View full text Add to dashboard Cite

Abstract:Mainstream cloud technologies are challenged by real-time, big data processing requirements or emerging applications. This paper surveys recent research efforts on advancing cloud computing virtual infrastructures and real-time big data technologies in order to provide dynamically scalable and distributed architectures over federated clouds. We examine new methods for developing cloud systems operating in a real-time, big data environment that can sense the context of the application environment and can adapt the infrastructure accordingly. We describe research topics linked to the challenge of adaptivity such as situation awareness, context detection, service-level objectives, and the capability to predict extraordinary situations requiring remedying action. We also describe research directions for realising adaptivity in cloud computing and we present a conceptual framework that represents research directions and shows interrelations.

show abstract

Section: Adaptation Implementationmentioning

confidence: 99%

Section: Scale Up -Scale Downmentioning

confidence: 99%

Challenges and Research Directions in Big Data-driven Cloud Adaptivity

Τσαγκαρόπουλος

Papageorgiou

Apostolou

et al. 2018

Proceedings of the 8th International Conference on Cloud Computing and Services Science

View full text Add to dashboard Cite

show abstract

“…Similarly, the optimal methodologies such as MPC and LLC based approaches are also blamed for their computationally expensive nature due to solving complex optimization models [103] despite their ability of producing optimal results. For example, Ali-Eldin et al [33] reported that for the LLC based solution proposed in [34], it takes half an hour for computing the elasticity decision for a system consist of 60 virtual machines hosted by 15 physical servers.…”

Section: Discussion Issues and Challengesmentioning

confidence: 99%

“…On the other hand, knowledge-based control solutions utilizing machine learning [67,106,107] or neural networks [99,108] provide high levels of flexibility and adaptivity. However, such flexibility and adaptivity come at the cost of long training delays, poor scalability, slower convergence rate, and the impossibility of deriving stability proof [7,18,103,109].…”

Section: Discussion Issues and Challengesmentioning

confidence: 99%

“…Such methodologies provide flexibility and adaptivity. However, they are also criticized for their long training delays and slower convergence rate [7,18,103,109] because they are required to learn the system behaviour at runtime. The existing research works that have utilised such methods are often lack on providing details regarding the associated computational overhead.…”

Section: Discussion Issues and Challengesmentioning

confidence: 99%

See 1 more Smart Citation

A control theoretical view of cloud elasticity: taxonomy, survey and challenges

Ullah

Shen

et al. 2018

Cluster Comput

View full text Add to dashboard Cite

The lucrative features of cloud computing such as pay-as-you-go pricing model and dynamic resource provisioning (elasticity) attract clients to host their applications over the cloud to save up-front capital expenditure and to reduce the operational cost of the system. However, the efficient management of hired computational resources is a challenging task. Over the last decade, researchers and practitioners made use of various techniques to propose new methods to address cloud elasticity. Amongst many such techniques, control theory emerges as one of the popular methods to implement elasticity. A plethora of research has been undertaken on cloud elasticity including several review papers that summarise various aspects of elasticity. However, the scope of the existing review articles is broad and focused mostly on the highlevel view of the overall research works rather than on the specific details of a particular implementation technique. While considering the importance, suitability and abundance of control theoretical approaches, this paper is a step forward towards a stand-alone review of control theoretic aspects of cloud elasticity. This paper provides a detailed taxonomy comprising of relevant attributes defining the following two perspectives, i.e., control-theory as an implementation technique as well as cloud elasticity as a target application domain. We carry out an exhaustive review of the literature by classifying the existing elasticity solutions using the attributes of control theoretic perspective. The summarized results are further presented by clustering them with respect to the type of control solutions, thus helping in comparison of the related control solutions. In last, a discussion summarizing the pros and cons of each type of control solutions are presented. This discussion is followed by the detail description of various open research challenges in the field.

show abstract

Applying queue theory for modeling of cloud computing: A systematic review

Ghomi

Rahmani

Qader

2019

Concurrency and Computation

View full text Add to dashboard Cite

The cloud computing paradigm is an important service in the Internet for sharing and providing resources in a cost-efficient way. Modeling of a cloud system is not an easy task because of the complexity and large scale of such systems. Cloud reliability could be improved by modeling the various aspects of cloud systems, including scheduling, service time, wait time, and hardware and software failures. The aim of this study is to survey research studies done on the modeling of cloud computing using the queuing system in order to identify where more emphasis should be placed in both current and future research directions. This paper follows the goal by investigating the articles published between 2008 and January 2017 in journals and conferences. A systematic mapping study combined with a systematic literature review was performed to find the related literature, and 71 articles were selected as primary studies that were classified in relation to the focus, research type, and contribution type. We classified the modeling techniques of cloud computing using the queuing theory in seven categories based on their focus area: (1) performance, (2) quality of service, (3) workflow scheduling, (4) energy savings, (5) resource management, (6) priority-based servicing, and (7) reliability. A majority of the primary articles focus on performance (37%), 15% of them focus on resource management, 14% of them focus on quality of service, 13% of them focus on workflow scheduling, 13% of them focus on energy savings, 4% of them focus on priority-based servicing for requests, and 4% of them focus on reliability. This work summarizes and classifies the research efforts conducted on applying queue theory for modeling of cloud computing (AQTMCC), providing a good starting point for further research in this area. KEYWORDScloud computing, cloud modeling, queuing systems, queuing theory, systematic review INTRODUCTIONCloud computing is the recent evolution in the information technology and is growing very fast due to the extensive use of mobile devices, such as PDAs, cell phones, and tablets. 1 To emphasize the goals of cloud computing, we refer to the definition of NIST (National Institute of Standards and Technology); a cloud model is composed of five characteristics, three service models, and four deployment models. 2 Service models of cloud computing are as follows: (1) Software as a Service (SaaS), such as CRM (Customer Relationship Management), virtual desktop, communications, and games; (2) Platform as a Service (PaaS), such as databases, web servers, and deployment tools; and (3) Infrastructure as a Service (IaaS), such as virtual machines (VMs), storages, servers, and load balancers. Deployment models include private clouds, public clouds, community clouds, and hybrid clouds. The characteristics of a cloud are on-demand self-servicing, elasticity, broad network access, resource pooling, and measured service. 1 A data center in cloud computing consists of several servers that are organized in racks and connected through communicati...

show abstract

Auto-Scaling Web Applications in Clouds

Cited by 217 publications

References 99 publications

Challenges and Research Directions in Big Data-driven Cloud Adaptivity

Challenges and Research Directions in Big Data-driven Cloud Adaptivity

A control theoretical view of cloud elasticity: taxonomy, survey and challenges

Applying queue theory for modeling of cloud computing: A systematic review

Contact Info

Product

Resources

About