Cloud simulation under fault constraints

Abstract

As Cloud Computing offers support to more and more complex applications, the need to verify and validate computing models under fault constraints becomes more important, aiming to ensure applications performance. Doing this experimental validation in the early development phase and with small costs require a cloud simulation tool. An extensible framework for Cloud simulation and modeling is CloudSim. This paper proposes a new module for CloudSim consisting of a fault injector based on a specification language. The aim is to assist simulation to be more realistic and includes concrete conditions and constraints. The impact is on testing Cloud applications and help test fault tolerant applications by specifying defect patterns and failing components. The evaluation of the fault injection module is done by measuring the behavior and performance of a tool based on CloudSim, named CloudAnalyst. Several metrics are determined and measured for experimental validation, and conclusions are drawn.

Aggressive Fault Tolerance in Cloud Computing Using Smart Decision Agent

“…It has a forward and backward recovery mechanism and it can calculate the reliability of node and takes decision based on reliability. Bosilca et al [27] propose a fault injection module that can inject fault in cloud environment. Zhang et al [28] propose a heuristic ant colony algorithm that VMs are placed by the ant colony algorithms.…”

“…The different types of faults are injected randomly and their effects are observed in Table 2. We have used the Poisson's distribution for different types of injected faults based on fixed time interval and different locations [24,27,34].…”