Sell your books and get cash! Enter to win $500 daily! Click here for more info.

Buy it Used or New Buy it New or Used

Other buying options Other buying options

Authorized Marketplace Sellers:
4 new from $72.83
Have one to sell? We'll buy it!
Cloud-Computing
view larger

Cloud-Computing

Magoules, Frederic; Pan, Jie; Teng, Fei
ISBN-10: 1466507829
ISBN-13: 9781466507821

Our Price: $87.20
Free standard shipping
or $4.99 3-day shipping
In our Marketplace:
4 new from $72.83
This practical book delves into new cloud computing technologies and indicates the main challenges for their development in the future, especially for resource management problems. By systematizing cloud resource management problems, it helps knowledgeable readers who are not subject matter experts in a topic but want to have an in-depth analysis.
It provides a parallel programming model, MapReduce, to parallelize multidimensional analytical query processing. The text includes how to master the fundamental concepts and programming models and apply them successfully to reach objectives. The authors discuss how to maximize the value of existing scheduling algorithms from a theoretical point of view.
show more show less
List of figures
List of tables
Foreword
Preface
Warranty
Overview of cloud computing
Introduction
Cloud definitions
System architecture
Deployment models
Cloud characteristics
Cloud evolution
Getting ready for the cloud
Brief history
Comparison with related technologies
Cloud services
Cloud projects
Commercial products
Research projects
Cloud challenges
MapReduce programming model
Data management
Resource scheduling
Concluding remarks
Resource scheduling for cloud computing
Introduction
Cloud service scheduling hierarchy
Economic models for resource-allocation scheduling
Market strategies
Auction strategies
Economic schedulers
Heuristic models for task-execution scheduling
Static strategies
Dynamic strategies
Heuristic schedulers
Real-time scheduling in cloud computing
Fixed priority strategies
Dynamic priority strategies
Real-time schedulers
Concluding remarks
Game theoretical allocation in a cloud datacenter
Introduction
Game theory
Normal formulation
Payoff choice and utility function
Strategy choice and Nash equilibrium
Cloud resource allocation model
Bid-shared auction
Non-cooperative game
Nash equilibrium allocation algorithms
Bid functions
Parameters estimation
Equilibrium price
Implementation in a cloud datacenter
Cloudsim toolkit
Communication among entities
Bidding algorithms
Comparison of forecasting methods
Concluding remarks
Multi-dimensional data analysis in a cloud datacenter
Introduction
Pre-computing
Data cube
Sparse cube
Reuse of previous query results
Data compressing
Data indexing
Data partitioning
Data partitioning methods
Horizontal partitioning of a multi-dimensional dataset
Vertical partitioning of a multi-dimensional dataset
Data replication
Query processing parallelism
Inter-and intra-operators
Exchange operator
SQL operator parallelization
Concluding remarks
Data intensive applications with MapReduce
Introduction
MapReduce: New parallel computing model in cloud computing
Dataflow model
Two frameworks: GridGain versus Hadoop
Communication cost analysis
Distributed data storage underlying MapReduce
Google file system
Distributed cache memory
Data accessing
Large-scale data analysis based on MapReduce
Data query languages
Data analysis applications
Comparison with shared-nothing parallel databases
SimMapReduce: Simulator for modeling MapReduce framework
Multi-layer architecture
Input and output of simulator
Implementation details of simulator
Modeling process
Concluding remarks
Large-scale multi-dimensional data aggregation
Introduction
Data organization
Computations in data explorations
Multiple group-by query
Choosing a right MapReduce framework
Advantages of GridGain
Combiner support in Hadoop and GridGain
Realizing MapReduce applications with GridGain
Workflow analysis of GridGain procedure
Parallelizing single group-by query with MapReduce
Parallelizing multiple group-by query with MapReduce
Data partitioning and data placement
MapReduce model-based implementation
MapCombineReduce model-based implementation
Cost estimation
MapReduce model-based implementation
MapCombineReduce model-based implementation
Comparison of implementations
Concluding remarks
Multi-dimensional data analysis optimization
Introduction
Data-locating based job-scheduling
Job-scheduling implementation
Two-level scheduling
Alternative job-scheduling schemes
Improvements by speed-up measurements
Horizontal partitioning
Vertical partitioning
Improvements by affecting factors
Query selectivity
Side effects
Improvement by cost estimation
Horizontal partitioning
Vertical partitioning
Comparison of partitioning
Compressed data structures
Data structure description
Data structures for storing recordId-list
Compressed data structures for different dimensions
Bitmap sparcity and compressing
Concluding remarks
Real-time scheduling with MapReduce
Introduction
Real-time scheduling problem
Real-time task
Processing resource
Scheduling algorithms
Schedulability test in the cloud datacenter
Pseudo-polynomial complexity
Polynomial complexity
Constant complexity
Utilization bounds for schedulability testing
Classical bound
Closer periods
Harmonic chains
Hyperbolic bound
Real-time task scheduling with MapReduce
System model
MapReduce segmentation
Worst pattern for a schedulable task set
Reliability indication methods
Reliability indicator
Schedulability test conditions
Comparison of rate monotonic conditions
Comparison of deadline monotonic conditions
Concluding remarks
Future for cloud computing
Bibliography
Index

Edition: 2012
Publisher: Taylor & Francis Group
Binding: Trade Cloth
Pages: 231
Size: 6.50" wide x 9.50" long x 1.00" tall
Weight: 1.03 lbs.
Language: English

100% Money Back Guarantee: Wrong item? No problem! Our hassle-free returns policy has you covered. We'll also process your order within 1-2 business days. Learn more about our shipping policy.