Empirical prediction models for adaptive resource provisioning in the cloud

Islam, Sadeka; Keung, Jacky; Lee, Kevin; Liu, Anna

doi:10.1016/j.future.2011.05.027

Cited by 548 publications

(267 citation statements)

References 8 publications

Supporting

Mentioning

263

Contrasting

Unclassified

Order By: Relevance

“…Lastly, they are also criticized more often for their associated unwanted behaviour, termed as bumpy transition, that could lead the system to an oscillatory state [27,104,105]. 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%

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

Section: Discussion Issues and Challengesmentioning

confidence: 99%

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

show abstract

“…Islam et al [24] propose resource prediction approaches based on machine learning. More specifically, they propose and experiment with Linear Regression and an Error Correction Neural Network.…”

Section: Related Workmentioning

confidence: 99%

Tackling uncertainty in long-term predictions for host overload and underload detection in cloud computing

2017

View full text Add to dashboard Cite

Dynamic workloads in cloud computing can be managed through live migration of virtual machines from overloaded or underloaded hosts to other hosts to save energy and/or mitigate performance-related Service Level Agreement (SLA) violations. The challenging issue is how to detect when a host is overloaded to initiate live migration actions in time. In this paper, a new approach to make long-term predictions of resource demands of virtual machines for host overload detection is presented. To take into account the uncertainty of long-term predictions, a probability distribution model of the prediction error is built. Based on the probability distribution of the prediction error, a decision-theoretic approach is proposed to make live migration decision that take into account live migration overheads. Experimental results using the CloudSim simulator and PlanetLab workloads show that the proposed approach achieves better performance and higher stability compared to other approaches that do not take into account the uncertainty of long-term predictions and the live migration overhead.

show abstract

“…Islam et al [12] present an approach for predicting the aggregated percentage of CPU utilisation of VMs running a distributed web benchmark, using both error correction neural networks (ECNN) and linear regression (LR). Their results suggest that although using ECNN yields better prediction results than, the need to retrain the neural network might be a disadvantage compared to the use of LR.…”

Section: Time Series Predictionmentioning

confidence: 99%

Simulation of SLA-based VM-scaling algorithms for cloud-distributed applications

Antonescu

Braun

2016

Future Generation Computer Systems

View full text Add to dashboard Cite

Cloud Computing has evolved to become an enabler for delivering access to large scale distributed applications running on managed network-connected computing systems. This makes possible hosting Distributed Enterprise Information Systems (dEISs) in cloud environments, while enforcing strict performance and quality of service requirements, defined using Service Level Agreements (SLAs). SLAs define the performance boundaries of distributed applications, and are enforced by a cloud management system (CMS) dynamically allocating the available computing resources to the cloud services. We present two novel VM-scaling algorithms focused on dEIS systems, which optimally detect most appropriate scaling conditions using performance-models of distributed applications derived from constant-workload benchmarks, together with SLA-specified performance constraints. We simulate the VMscaling algorithms in a cloud simulator and compare against trace-based performance models of dEISs. We compare a total of three SLA-based VMscaling algorithms (one using prediction mechanisms) based on a real-world application scenario involving a large variable number of users. Our results show that it is beneficial to use autoregressive predictive SLA-driven scaling algorithms in cloud management systems for guaranteeing performance invariants of distributed cloud applications, as opposed to using only reactive SLA-based VM-scaling algorithms.

show abstract

Empirical prediction models for adaptive resource provisioning in the cloud

Cited by 548 publications

References 8 publications

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

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

Tackling uncertainty in long-term predictions for host overload and underload detection in cloud computing

Simulation of SLA-based VM-scaling algorithms for cloud-distributed applications

Contact Info

Product

Resources

About