Model transformations of MapReduce Design Patterns for automatic development and verification

Mapping MapReduce frameworks to Cloud Architecture became a must in last years because of the need of managing large data sets and Big Data in fast, reliable (and as cheap as possible) way. Scientific Literature proposes many works about new architectures, frameworks and algorithms improving and opt...

Full description

Saved in:
Bibliographic Details
Published in:Journal of parallel and distributed computing Vol. 110; pp. 52 - 59
Main Authors: Amato, Flora, Moscato, Francesco
Format: Journal Article
Language:English
Published: Elsevier Inc 01.12.2017
Subjects:
Cloud computing
Cloud patterns
Formal verification
MapReduce
Model driven engineering
Cloud computing
Model driven engineering
Cloud patterns
Formal verification
MapReduce
ISSN:0743-7315, 1096-0848
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Mapping MapReduce frameworks to Cloud Architecture became a must in last years because of the need of managing large data sets and Big Data in fast, reliable (and as cheap as possible) way. Scientific Literature proposes many works about new architectures, frameworks and algorithms improving and optimizing performances while performing MapReduce operations. Anyway, MapReduce framework is only the starting point for building a plethora of services based on different analyses. This is the reason for recent application of Design Patterns methodologies to develop MapReduce applications. Here we propose a Model Driven Engineering methodology to design, verify and develop MapReduce applications on Cloud Systems. The methodology is driven by MapReduce Design Patterns and is used to analyse soundness and reliability of services based on MapReduce from early design stage to runtime. •A methodology to develop and verify QoS of MapReduce services driven.•The methodology is based on MapReduce Design Patterns and Model Transformation.•It enables formal verification of properties like availability or real-time constraints.•It improves state of the art on MapReduce Design and development based on workflows and Design Patterns.
ISSN:0743-7315
1096-0848
DOI:10.1016/j.jpdc.2016.12.017