• Corpus ID: 14949672

Edge-Based Cloud Computing as a Feasible Network Paradigm

  title={Edge-Based Cloud Computing as a Feasible Network Paradigm},
  author={Joe Elizondo and Samuel Palmer},
The term edge based cloud computing refers to a network of edge systems that provide the services currently provided by data center clouds. In this paper we present modifications to MRPerf, an existing tool used to simulate MapReduce in data center clouds, enabling it to simulate Hadoop MapReduce jobs in edge networks. Our results indicate that the default Hadoop scheduler does not perform optimally in an edge environment and should be replaced. We also conclude that bandwidth is not a limiting… 

Figures and Tables from this paper

Exploiting Heterogeneity in Distributed Software Frameworks
DerbyhatS is designed, implemented, and evaluated, an applicationcharacteristics-aware resource manager for DSFs, which predicts the performance of the application under different hardware configurations and dynamically manage compute and storage resources as per the application needs.
Flow Inspection Router Assignment (FIRA) in Access/Aggregation Network Clouds
The NP-hardness of these two new problems related to Flow Inspection Router Assignment (FIRA) in ANCs are proved, the heuristic algorithms can perform close to their performance bounds, implying their near optimality and the tightness of the bounds.


Improving MapReduce Performance in Heterogeneous Environments
A new scheduling algorithm, Longest Approximate Time to End (LATE), that is highly robust to heterogeneity and can improve Hadoop response times by a factor of 2 in clusters of 200 virtual machines on EC2.
A simulation approach to evaluating design decisions in MapReduce setups
The resulting simulator, MRPerf, captures such aspects of MapReduce setups as node, rack and network configurations, disk parameters and performance, data layout and application I/O characteristics, among others, and uses this information to predict expected application performance and can serve as a tool for optimizing existing MapReduces setups as well as designing new ones.
CloudSim: A Novel Framework for Modeling and Simulation of Cloud Computing Infrastructures and Services
This paper proposes CloudSim: a new generalized and extensible simulation framework that enables seamless modelling, simulation, and experimentation of emerging Cloud computing infrastructures and management services.
Modeling and simulation of scalable Cloud computing environments and the CloudSim toolkit: Challenges and opportunities
This paper proposes CloudSim: an extensible simulation toolkit that enables modelling and simulation of Cloud computing environments and allows simulation of multiple Data Centers to enable a study on federation and associated policies for migration of VMs for reliability and automatic scaling of applications.
Using realistic simulation for performance analysis of mapreduce setups
The design of an accurate MapReduce simulator, MRPerf, is presented, which can serve as a design tool for Map Reduce infrastructure, and as a planning tool for making Map reduce deployment far easier via reduction in the number of parameters that currently have to be hand-tuned using rules of thumb.
Measuring ISP topologies with Rocketfuel
New Internet mapping techniques that have enabled us to measure router-level ISP topologies are presented, finding that these maps are substantially more complete than those of earlier Internet mapping efforts.
How to model an internetwork
This work considers the problem of efficiently generating graph models that accurately reflect the topological properties of real internetworks, and proposes efficient methods for generating topologies with particular properties, including a transit-stub model that correlates well with the internet structure.
BRITE: Universal Topology Generation from a User''s Perspective
The design, implementation and usage of the BRITE universal topology generation tool, a "universal topology generator", are discussed and the BRite Analysis Engine, BRIANA, is described, which is an independent piece of software designed and built upon BRITE design goals of flexibility and extensibility.
NDP2PSim: A NS2-Based Platform for Peer-to-Peer Network Simulations
The structure of NDP2PSim is described in detail, which can provide a realistic and generic simulation environment for almost all kinds of existing P2P protocols on large scales and is compared with other existing simulators.
MapReduce: simplified data processing on large clusters
This presentation explains how the underlying runtime system automatically parallelizes the computation across large-scale clusters of machines, handles machine failures, and schedules inter-machine communication to make efficient use of the network and disks.