Queue Analysis for Probabilistic Cloud Workflows

Abstract

Cloud applications can be modeled as workflows. These workflows are represented by Directed Acyclic Graphs (DAGs) or non-DAGs. The graph shows the relationship between tasks that compose a workflow and the dependencies between these tasks. in our previous work, we presented a method for transforming a workflow into an equivalent graph that shows all possible paths that a workflow will take. In this paper, we use the results of that method for multiple workflows coming to a queue and use the famous pollaczek–khintchine formula to estimate the average waiting and completion time for submitted workflows. Then, we use different scheduling algorithms, namely, Shortest Job First (SJF) and Longest Job First (LJF) and compare them with First Come First Serve (FCFS).