Hierarchical Stochastic Models for Performance, Availability, and Power Consumption Analysis of IaaS Clouds

Ataie, Ehsan; Entezari‐Maleki, Reza; Rashidi, Leila; Trivedi, Kishor S.; Ardagna, Danilo; Movaghar, Ali

doi:10.1109/tcc.2017.2760836

Cited by 42 publications

(27 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…But the differences between PMs are not considered. In [19], a hierarchical model based on Stochastic Reward Networks is constructed to analyze performance, availability, and power consumption; in [17] [18] the authors studied the impact of failures on IaaS availability, when failure is typically dealt with through migration of VMs; Chilwan et al [20] investigated the effect of dynamic load in a cloud cluster on the service availability using analytical models; Ghosh et al [7] researched the impact of I/O on availability. In those models, the PMs are classified into three types: hot, warm (hot standby), cold (cold standby), since different types of machines may need different times to deploy a VM with noticeable effects on availability.…”

Section: Iaas and Availabilitymentioning

confidence: 99%

An Attribute-Based Availability Model for Large Scale IaaS Clouds with CARMA

Hillston

Piho

et al. 2020

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

High availability is one of the core properties of Infrastructure as a Service (IaaS) and ensures that users have anytime access to on-demand cloud services. However, significant variations of workflow and the presence of super-tasks, mean that heterogeneous workload can severely impact the availability of IaaS clouds. Although previous work has investigated global queues, VM deployment, and failure of PMs, two aspects are yet to be fully explored: one is the impact of task size and the other is the differing features across PMs such as the variable execution rate and capacity. To address these challenges we propose an attribute-based availability model of large scale IaaS developed in the formal modeling language CARMA. The size of tasks in our model can be a fixed integer value or follow the normal, uniform or log-normal distribution. Additionally, our model also provides an easy approach to investigating how to arrange the slack and normal resources in order to achieve availability levels. The two goals of our work are providing an analysis of the availability of IaaS and showing that the use of CARMA allows us to easily model complex phenomena that were not readily captured by other existing approaches.

show abstract

Section: Iaas and Availabilitymentioning

confidence: 99%

An Attribute-Based Availability Model for Large Scale IaaS Clouds with CARMA

Hillston

Piho

et al. 2020

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

show abstract

“…where Y (n + 1) is the upper neighboring level performance, X n is the lower neighboring level performance, and n is the number of level. Advanced Energy Management, Modelling and Control for Intelligent and Efficient Transport... 6 The coefficients R 21 -R 65 are used to calculate the required indicators of various levels of the MLHRM within the design of electric vehicles with the specified reliability and fault tolerance parameters.…”

Section: Structure Of Mlhrmmentioning

confidence: 99%

“…In turn, solving the secondary models allows the primary model to be solved and all of the customer interruption information to be computed. An interesting approach to solving the complex problem of performance, availability, and power consumption analysis of infrastructure as a service (IaaS) clouds, based hierarchical stochastic reward nets (SRN), is presented in [6]. In order to use the resources of an IaaS cloud efficiently, several important factors such as performance, availability, and power consumption need to be considered and evaluated carefully.…”

Section: Introductionmentioning

confidence: 99%

Reliability-Oriented Design of Vehicle Electric Propulsion System Based on the Multilevel Hierarchical Reliability Model

Bolvashenkov¹,

Kammermann²,

Frenkel³

et al. 2020

Intelligent and Efficient Transport Systems - Design, Modelling, Control and Simulation

View full text Add to dashboard Cite

This chapter describes a methodology of evaluation of the various sustainability indicators, such as reliability, availability, fault tolerance, and reliability-associated cost of the electric propulsion systems, based on a multilevel hierarchical reliability model (MLHRM) of the life cycles of electric vehicles. Considering that the vehicle propulsion systems are safety-critical systems, to each of their components, the strict requirements on reliability indices are imposed. The practical application of the proposed technique for reliability-oriented development of the icebreaking ship's electric propulsion system and the results of computation are presented. The opportunities of improvement of reliability and fault tolerance are investigated. The results of the study, allowing creating highly reliable electric vehicles and choosing the most appropriate traction electric drive design, are discussed.Advanced Energy Management, Modelling and Control for Intelligent and Efficient Transport... 2 that the maximum number of factors affects the amount of sustainable functioning criterion of the traction drive. Accordingly, the above criterion has the maximum potential to increase the value of the level of excellence of the traction electric drive and an electric vehicle as a whole. In addition, the most stringent requirements are imposed on reliability, fault tolerance, and survivability of electric vehicles, which are safety-critical systems.In this way, reliability-oriented design of the vehicle electric propulsion system and, accordingly, all its subsystems, units, and components is a very urgent and complex task while considering their interactions. In recent years, a multilevel approach in the development, design, and optimization of various technical systems and their particular parameters has become quite widespread. In addition, when using a multilevel approach in most cases, the various levels are interconnected hierarchically. Depending on the complexity of the system being developed, the multilevel hierarchical reliability model (MLHRM) may consist of a different number of levels. In the simplest case, it can consist of three levels.Attempts to develop the methods for solving such a problem were undertaken by various research groups. The first group of scientists, whose works are presented in [1][2][3][4], uses the method of hierarchical decomposition of the technical system, better known as analytic hierarchy process (AHP). It was developed by Thomas L. Saaty in the 1970s and represents a structured technique to organize and analyze complex decisions, described in detail in [1]. This approach has significant advantages when important components of the decision are difficult to quantify or to compare or when communication between team members is made difficult by their different specializations, terminology, or perspectives. Due to the relatively simple mathematical formula, as well as the easy data collection, AHP has been widely applied by many researchers. The integral shortcoming of the AHP is the fact t...

show abstract

“…The insertion sub-model (Figure 2a) models the arrival of user requests to the system, the migration sub-model (Figure 2b) addresses the migration of VMs between VMMs, the service and green computing sub-model ( Figure 2c) models serving VMs and termination of lightly loaded VMMs with the aim of green computing goals, the rejuvenation sub-model ( Figure 2d) addresses rejuvenation of the aged VMMs, and the failure sub-model (Figure 2e) models the failure of VMMs. We assumed that the times assigned to all timed activities follow an exponential distribution [36][37][38][39]. In Figure 2a, the arrival of new requests to the system and selection of appropriate VMM to handle them are modeled.…”

Section: The Proposed Modelmentioning

confidence: 99%

Modeling and Evaluation of Power-Aware Software Rejuvenation in Cloud Systems

2018

Self Cite

View full text Add to dashboard Cite

Long and continuous running of software can cause software aging-induced errors and failures. Cloud data centers suffer from these kinds of failures when Virtual Machine Monitors (VMMs), which control the execution of Virtual Machines (VMs), age. Software rejuvenation is a proactive fault management technique that can prevent the occurrence of future failures by terminating VMMs, cleaning up their internal states, and restarting them. However, the appropriate time and type of VMM rejuvenation can affect performance, availability, and power consumption of a system. In this paper, an analytical model is proposed based on Stochastic Activity Networks for performance evaluation of Infrastructure-as-a-Service cloud systems. Using the proposed model, a two-threshold power-aware software rejuvenation scheme is presented. Many details of real cloud systems, such as VM multiplexing, migration of VMs between VMMs, VM heterogeneity, failure of VMMs, failure of VM migration, and different probabilities for arrival of different VM request types are investigated using the proposed model. The performance of the proposed rejuvenation scheme is compared with two baselines based on diverse performance, availability, and power consumption measures defined on the system.

show abstract

Hierarchical Stochastic Models for Performance, Availability, and Power Consumption Analysis of IaaS Clouds

Cited by 42 publications

References 46 publications

An Attribute-Based Availability Model for Large Scale IaaS Clouds with CARMA

An Attribute-Based Availability Model for Large Scale IaaS Clouds with CARMA

Reliability-Oriented Design of Vehicle Electric Propulsion System Based on the Multilevel Hierarchical Reliability Model

Modeling and Evaluation of Power-Aware Software Rejuvenation in Cloud Systems

Contact Info

Product

Resources

About