Cloud Computing: Data-Intensive Computing and Scheduling

Cloud Computing: Data-Intensive Computing and Scheduling

by Frederic Magoules, Jie Pan, Fei Teng


Choose Expedited Shipping at checkout for guaranteed delivery by Wednesday, February 27

Product Details

ISBN-13: 9781466507821
Publisher: Taylor & Francis
Publication date: 09/21/2012
Series: Chapman & Hall/CRC Numerical Analysis and Scientific Computing Series , #18
Pages: 231
Product dimensions: 6.20(w) x 9.20(h) x 0.80(d)

About the Author

Frédéric Magoulès is a professor at École Centrale Paris, where he leads the high performance computing research group. His research focuses on the algorithmic interface between parallel computing and the numerical analysis of PDEs and algebraic differential equations. He earned a Ph.D. in applied mathematics from Université Pierre et Marie Curie.

Jie Pan is a Java developer at the Klee Group Company. She earned a Ph.D. in applied mathematics. During her doctoral work, she focused on large-scale data analysis on distributed systems.

Fei Teng is a researcher in the Key Lab of Cloud Computing and Intelligent Technology at Southwest Jiaotong University. Her research interests are mainly in cloud computing, data mining, resource allocation, and distributed scheduling algorithms.

Table of Contents

Overview of Cloud Computing
Cloud evolution
Cloud services
Cloud projects
Cloud challenges
Concluding remarks

Resource Scheduling for Cloud Computing
Cloud service scheduling hierarchy
Economic models for resource-allocation scheduling
Heuristic models for task-execution scheduling
Real-time scheduling in cloud computing
Concluding remarks

Game Theoretical Allocation in a Cloud Datacenter
Game theory
Cloud resource allocation model
Nash equilibrium allocation algorithms
Implementation in a cloud datacenter
Concluding remarks

Multidimensional Data Analysis in a Cloud Datacenter
Data indexing
Data partitioning
Data replication
Query processing parallelism
Concluding remarks

Data-Intensive Applications with MapReduce
MapReduce: a new parallel computing model in cloud computing
Distributed data storage underlying MapReduce
Large-scale data analysis based on MapReduce
SimMapReduce: a simulator for modeling MapReduce framework
Concluding remarks

Large-Scale Multidimensional Data Aggregation
Data organization
Choosing a right MapReduce framework
Parallelizing single group-by query with MapReduce
Parallelizing multiple group-by query with MapReduce
Cost estimation
Concluding remarks

Multidimensional Data Analysis Optimization
Data-locating-based job-scheduling
Improvements by speed-up measurements
Improvements by affecting factors
Improvement by cost estimation
Compressed data structures
Concluding remarks

Real-Time Scheduling with MapReduce
A real-time scheduling problem
Schedulability test in the cloud datacenter
Utilization bounds for schedulability testing
Real-time task scheduling with MapReduce
Reliability indication methods
Concluding remarks

Future for Cloud Computing



Customer Reviews

Most Helpful Customer Reviews

See All Customer Reviews