Model-based sensitivity analysis of IaaS cloud availability

Abstract

The increasing shift of various critical services towards Infrastructure-as-a-Service (IaaS) cloud data centers (CDCs) creates a need for analyzing CDCs' availability, which is affected by various factors including repair policy and system parameters. This paper aims to apply analytical modeling and sensitivity analysis techniques to investigate the impact of these factors on the availability of a large-scale IaaS CDC, which (1) consists of active and two kinds of standby physical machines (PMs), (2) allows PM moving among active and two kinds of standby PM pools, and (3) allows active and two kinds of standby PMs to have different mean repair times. Two repair policies are considered: (P1) all pools share a repair station and (P2) each pool uses its own repair station. We develop monolithic availability models for each repair policy by using Stochastic Reward Nets and also develop the corresponding scalable two-level models in order to overcome the monolithic model's limitations, caused by the large-scale feature of a CDC and the complicated interactions among CDC components. We also explore how to apply differential sensitivity analysis technique to conduct parametric sensitivity analysis in the case of interacting submodels. Numerical results of monolithic models and simulation results are used to verify the approximate accuracy of interacting sub-models, which are further applied to examine the sensitivity of the large-scale CDC availability with respect to repair policy and system parameters.

Reliability and high availability in cloud computing environments: a reference roadmap

“…In addition, the review results show that 'Experiment' approach is used more than other approaches for evaluating the HA solutions. However, the paper proposed some research questions and tried to answer these questions, but the study results are more similar to the study [46] applied an analytical modeling and sensitivity analysis for investigating the effective factors on cloud infrastructure availability such as repair policy and system parameters. In this study, the replication method was used to provide physical machine availability.…”

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

“…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. Furthermore, other models investigate concepts related to the availability of IaaS, such as capacity planning [21], VM migration [22] [23], sensitivity analysis [3], performance [24]. In those works, the effects of VM scheduling and PM management are considered in ways similar to previous availability models.…”

“…Similarly, a receiver also uses a predicate to identify accepted sources. An interaction will occur only when the sender satisfies the [5] PM &VM deployment (PM & VM) super-task no [12] queuing (PM & VM) super-task no [11] availability (PM & VM) super-task no [13] failure of PM (PM & VM) super-task no [15] heterogeneous VM (VM) only vcpu cores no [9] heterogeneous workload (PM & VM) only VM size no [30] performance [29] availability (container) no no [3] sensitivity analysis (PM & VM) no - [32] heterogeneous workload (VM) Constant/burst/periodic task no our work availability (PM & VM) both yes '-' means this item is not involved. predicate used by the receiver, and the receiver satisfies the predicate used by the sender.…”

“…99.9% system availability means 42 minutes of downtime per month) the IaaS availability may not be satisfactory. From the provider's perspective, any availability violation may cause the loss of revenue and damage business reputations [3]. Hence, maintaining the availability of IaaS is of significant interest.…”

Computation of the Insurance Premium for Cloud Services Based on Fourth-Order Statistics

“…In order to avoid significant losses, the provider may act in two ways (also concurrently):  improving the reliability of its infrastructure (see, e.g. [23], [24], [25], [26], [27]),  protecting itself through an insurance policy. The latter approach has been pursued, e.g., in [28], where a formula based on the expected utility paradigm has been proposed to set the insurance premium.…”