Furht / Escalante Handbook of Cloud Computing

1. Auflage 2010
ISBN: 978-1-4419-6524-0
Verlag: Springer
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 634 Seiten

Cloud computing has become a significant technology trend. Experts believe cloud computing is currently reshaping information technology and the IT marketplace. The advantages of using cloud computing include cost savings, speed to market, access to greater computing resources, high availability, and scalability.Handbook of Cloud Computing includes contributions from world experts in the field of cloud computing from academia, research laboratories and private industry. This book presents the systems, tools, and services of the leading providers of cloud computing; including Google, Yahoo, Amazon, IBM, and Microsoft. The basic concepts of cloud computing and cloud computing applications are also introduced. Current and future technologies applied in cloud computing are also discussed. Case studies, examples, and exercises are provided throughout. Handbook of Cloud Computing is intended for advanced-level students and researchers in computer science and electrical engineering as a reference book. This handbook is also beneficial to computer and system infrastructure designers, developers, business managers, entrepreneurs and investors within the cloud computing related industry.

Borko Furht is a professor and chairman of the Department of Computer & Electrical Engineering and Computer Science at Florida Atlantic University (FAU) in Boca Raton, Florida. Professor Furht received his Ph.D. in electrical and computer engineering from the University of Belgrade. His current research is in multimedia systems, video coding and compression, 3D video and image systems, video databases, wireless multimedia, and Internet computing. He is a founder and editor-in-chief of the Journal of Multimedia Tools and Applications (Springer). He has received several technical and publishing awards, and has consulted for many high-tech companies including IBM, Hewlett-Packard, Xerox, General Electric, JPL, NASA, Honeywell, and RCA, and has been an expert witness for Cisco and Qualcomm. He has given many invited talks, keynote lectures, seminars, and tutorials, and served on the Board of Directors of several high-tech companies.Armando J. Escalante is SVP & Chief Technology Officer of Risk Solutions for the LexisNexis Group, a division of Reed Elsevier. In this position, Escalante is responsible for technology development, information systems and operations. Previously, Escalante was Chief Operating Officer for Seisint, a privately owned, Boca based company, which was purchased by LexisNexis in 2004. In this position, he was responsible for Technology, Development and Operations. Prior to 2001, Escalante served as Vice President of Engineering and Operations for Diveo Broadband Networks where he led world class Data Centers located in the U.S. and Latin America. Before Diveo Broadband Networks, Escalante was VP for one of the fastest growing divisions of Vignette Corporation, an eBusiness software leader. Escalante earned his bachelor's degree in electronic engineering at the USB in Caracas, Venezuela and a master's degree in computer science from Steven Institute of Technology as well as a master's in business administration from West Coast University.

Autoren/Hrsg.

Escalante, Armando

Furht, Borko

Inhaltsverzeichnis

1;Preface;4
2;Contents;6
3;Contributors;9
4;About the Editors;14
5;Part I Technologies and Systems;17
5.1;1 Cloud Computing Fundamentals;18
5.1.1;1.1 Introduction;18
5.1.1.1;1.1.1 Layers of Cloud Computing;19
5.1.1.2;1.1.2 Types of Cloud Computing;22
5.1.1.3;1.1.3 Cloud Computing Versus Cloud Services;23
5.1.2;1.2 Enabling Technologies;24
5.1.2.1;1.2.1 Virtualization;24
5.1.2.2;1.2.2 Web Service and Service Oriented Architecture;25
5.1.2.3;1.2.3 Service Flow and Workflows;25
5.1.2.4;1.2.4 Web 2.0 and Mashup;25
5.1.3;1.3 Cloud Computing Features;26
5.1.3.1;1.3.1 Cloud Computing Standards;26
5.1.3.2;1.3.2 Cloud Computing Security;27
5.1.4;1.4 Cloud Computing Platforms;28
5.1.4.1;1.4.1 Pricing;28
5.1.4.2;1.4.2 Cloud Computing Components and Their Vendors;30
5.1.5;1.5 Example of Web Application Deployment;31
5.1.6;1.6 Cloud Computing Challenges;32
5.1.6.1;1.6.1 Performance;32
5.1.6.2;1.6.2 Security and Privacy;32
5.1.6.3;1.6.3 Control;33
5.1.6.4;1.6.4 Bandwidth Costs;33
5.1.6.5;1.6.5 Reliability;33
5.1.7;1.7 Cloud Computing in the Future;33
5.1.8;References;34
5.2;2 Cloud Computing Technologies and Applications;35
5.2.1;2.1 Cloud Computing: IT as a Service;35
5.2.2;2.2 Cloud Computing Security;38
5.2.3;2.3 Cloud Computing Model Application Methodology;39
5.2.3.1;2.3.1 Cloud Computing Strategy Planning Phase;39
5.2.3.2;2.3.2 Cloud Computing Tactics Planning Phase;41
5.2.3.3;2.3.3 Cloud Computing Deployment Phase;41
5.2.4;2.4 Cloud Computing in Development/Test;42
5.2.5;2.5 Cloud-Based High Performance Computing Clusters;44
5.2.6;2.6 Use Cases of Cloud Computing;46
5.2.6.1;2.6.1 Case Study: Cloud as Infrastructure for an Internet Data Center (IDC);46
5.2.6.1.1;2.6.1.1 The Bottleneck on IDC Development;47
5.2.6.1.2;2.6.1.2 Cloud Computing Provides IDC with a New Infrastructure Solution;48
5.2.6.1.3;2.6.1.3 The Value of Cloud Computing for IDC Service Providers;48
5.2.6.1.4;2.6.1.4 The Value Brought by Cloud Computing for IDC Users;49
5.2.6.1.5;2.6.1.5 Cloud Computing Can Make Fixed Costs Variable;50
5.2.6.1.6;2.6.1.6 An IDC Cloud Example;51
5.2.6.1.7;2.6.1.7 The Influence of Cloud Computing in 3G Era;51
5.2.6.2;2.6.2 Case Study -- Cloud Computing for Software Parks;52
5.2.6.2.1;2.6.2.1 Cloud Computing Architecture;55
5.2.6.2.2;2.6.2.2 Outsourcing Software Research and Development Platform;55
5.2.6.3;2.6.3 Case Study -- an Enterprise with Multiple Data Centers;56
5.2.6.3.1;2.6.3.1 Overall Design of the Cloud Computing Platform in an Enterprise;57
5.2.6.4;2.6.4 Case Study: Cloud Computing Supporting SaaS;59
5.2.7;2.7 Conclusion;59
5.3;3 Key Enabling Technologies for Virtual Private Clouds;60
5.3.1;3.1 Introduction;60
5.3.2;3.2 Virtual Private Clouds;62
5.3.3;3.3 Virtual Data Centers and Applications;64
5.3.3.1;3.3.1 Virtual Data Centers;64
5.3.3.2;3.3.2 Virtual Applications;67
5.3.4;3.4 Policy-Based Management;68
5.3.4.1;3.4.1 Policy-Based Deployment;69
5.3.4.2;3.4.2 Policy Compliance;71
5.3.5;3.5 Service-Management Integration;73
5.3.6;3.6 Conclusions;75
5.3.7;References;76
5.4;4 The Role of Networks in Cloud Computing;77
5.4.1;4.1 Introduction;77
5.4.2;4.2 Cloud Deployment Models and the Network;78
5.4.2.1;4.2.1 Public Cloud;79
5.4.2.2;4.2.2 Private Cloud;79
5.4.2.3;4.2.3 Hybrid Cloud;80
5.4.2.4;4.2.4 An Overview of Network Architectures for Clouds;81
5.4.2.4.1;4.2.4.1 Data Center Network;81
5.4.2.4.2;4.2.4.2 Data Center Interconnect Network;84
5.4.3;4.3 Unique Opportunities and Requirements for Hybrid Cloud Networking;85
5.4.3.1;4.3.1 Virtualization, Automation and Standards -- The Foundation;86
5.4.3.2;4.3.2 Latency, Bandwidth, and Scale -- The Span;87
5.4.3.3;4.3.3 Security, Resiliency, and Service Management -- The Superstructure;88
5.4.4;4.4 Network Architecture for Hybrid Cloud Deployments;89
5.4.4.1;4.4.1 Cloud-in-a-Box;90
5.4.4.2;4.4.2 Network Service Node;91
5.4.4.3;4.4.3 Data Center Network and Data Center Interconnect Network;92
5.4.4.4;4.4.4 Management of the Network Architecture;92
5.4.5;4.5 Conclusions and Future Directions;93
5.4.6;References;93
5.5;5 Data-Intensive Technologies for Cloud Computing;95
5.5.1;5.1 Introduction;95
5.5.1.1;5.1.1 Data-Intensive Computing Applications;96
5.5.1.2;5.1.2 Data-Parallelism;97
5.5.1.3;5.1.3 The ''Data Gap'';98
5.5.2;5.2 Characteristics of Data-Intensive Computing Systems;98
5.5.2.1;5.2.1 Processing Approach;99
5.5.2.2;5.2.2 Common Characteristics;100
5.5.2.3;5.2.3 Grid Computing;101
5.5.2.4;5.2.4 Applicability to Cloud Computing;102
5.5.3;5.3 Data-Intensive System Architectures;103
5.5.3.1;5.3.1 Google MapReduce;104
5.5.3.2;5.3.2 Hadoop;107
5.5.3.3;5.3.3 LexisNexis HPCC;112
5.5.3.4;5.3.4 ECL;117
5.5.4;5.4 Hadoop vs. HPCC Comparison;121
5.5.4.1;5.4.1 Terabyte Sort Benchmark;121
5.5.4.2;5.4.2 Pig vs. ECL;123
5.5.4.3;5.4.3 Architecture Comparison;137
5.5.5;5.5 Conclusions;138
5.5.6;References;146
5.6;6 Survey of Storage and Fault Tolerance Strategies Used in Cloud Computing;149
5.6.1;6.1 Introduction;149
5.6.1.1;6.1.1 Theme 1: Voluminous Data;149
5.6.1.2;6.1.2 Theme 2: Commodity Hardware;150
5.6.1.3;6.1.3 Theme 3: Distributed Data;150
5.6.1.4;6.1.4 Theme 4: Expect Failures;150
5.6.1.5;6.1.5 Theme 5: Tune for Access by Applications;150
5.6.1.6;6.1.6 Theme 6: Optimize for Dominant Usage;151
5.6.1.7;6.1.7 Theme 7: Tradeoff Between Consistency and Availability;151
5.6.2;6.2 xFS;152
5.6.2.1;6.2.1 Failure Model;152
5.6.2.2;6.2.2 Replication;152
5.6.2.3;6.2.3 Data Access;152
5.6.2.4;6.2.4 Integrity;153
5.6.2.5;6.2.5 Consistency and Guarantees;153
5.6.2.6;6.2.6 Metadata;154
5.6.2.7;6.2.7 Data placement;154
5.6.2.8;6.2.8 Security;154
5.6.3;6.3 Amazon S3;154
5.6.3.1;6.3.1 Data Access and Management;154
5.6.3.2;6.3.2 Security;155
5.6.3.3;6.3.3 Integrity;155
5.6.4;6.4 Dynamo;155
5.6.4.1;6.4.1 Checkpointing;156
5.6.4.2;6.4.2 Replication;156
5.6.4.3;6.4.3 Failures;157
5.6.4.4;6.4.4 Accessing Data;157
5.6.4.5;6.4.5 Data Integrity;157
5.6.4.6;6.4.6 Consistency and Guarantees;158
5.6.4.7;6.4.7 Metadata;158
5.6.4.8;6.4.8 Data Placement;158
5.6.4.9;6.4.9 Security;159
5.6.5;6.5 Google File System;159
5.6.5.1;6.5.1 Checkpointing;159
5.6.5.2;6.5.2 Replication;160
5.6.5.3;6.5.3 Failures;160
5.6.5.4;6.5.4 Data Access;160
5.6.5.5;6.5.5 Data Integrity;161
5.6.5.6;6.5.6 Consistency and Guarantees;161
5.6.5.7;6.5.7 Metadata;161
5.6.5.8;6.5.8 Data Placement;161
5.6.5.9;6.5.9 Security Scheme;162
5.6.6;6.6 Bigtable;162
5.6.6.1;6.6.1 Replication;163
5.6.6.2;6.6.2 Failures;163
5.6.6.3;6.6.3 Accessing Data;164
5.6.6.4;6.6.4 Data Integrity;164
5.6.6.5;6.6.5 Consistency and Guarantees;164
5.6.6.6;6.6.6 Metadata;165
5.6.6.7;6.6.7 Data Placement;165
5.6.6.8;6.6.8 Security;165
5.6.7;6.7 Microsoft Azure;165
5.6.7.1;6.7.1 Replication;166
5.6.7.2;6.7.2 Failure;166
5.6.7.3;6.7.3 Accessing Data;167
5.6.7.4;6.7.4 Consistency and Guarantees;167
5.6.7.5;6.7.5 Data Placement;167
5.6.7.6;6.7.6 Security;167
5.6.8;6.8 Transactional and Analytics Debate;168
5.6.9;6.9 Conclusions;168
5.6.10;References;169
5.7;7 Scheduling Service Oriented Workflows Inside Clouds Using an Adaptive Agent Based Approach;171
5.7.1;7.1 Introduction;171
5.7.2;7.2 Related Work on DS Scheduling;173
5.7.3;7.3 Scheduling Issues Inside Service Oriented Environments;175
5.7.3.1;7.3.1 Estimating Task Runtimes and Transfer Costs;175
5.7.3.2;7.3.2 Service Discovery and Selection;177
5.7.3.3;7.3.3 Negotiation Between Service Providers;177
5.7.3.4;7.3.4 Overcoming the Internal Resource Scheduler;178
5.7.3.5;7.3.5 Trust in Multi-cloud Environments;179
5.7.4;7.4 Workflow Scheduling;180
5.7.5;7.5 Distributed Agent Based Scheduling Platform Inside Clouds;181
5.7.5.1;7.5.1 The Scheduling Platform;182
5.7.5.2;7.5.2 Scheduling Through Negotiation;186
5.7.5.3;7.5.3 Prototype Implementation Details;190
5.7.6;7.6 Conclusions;191
5.7.7;References;192
5.8;8 The Role of Grid Computing Technologies in Cloud Computing;195
5.8.1;8.1 Introduction;195
5.8.2;8.2 Basics of Grid and Cloud Computing;197
5.8.2.1;8.2.1 Basics of Grid Computing;197
5.8.2.2;8.2.2 Basics of Cloud Computing;197
5.8.2.3;8.2.3 Interaction Models of Grid and Cloud Computing;198
5.8.2.4;8.2.4 Distributed Computing in the Grid and Cloud;200
5.8.3;8.3 Layered Models and Usage patterns in Grid and Cloud;200
5.8.3.1;8.3.1 Infrastructure;201
5.8.3.2;8.3.2 Platform;203
5.8.3.2.1;8.3.2.1 Abstraction from Physical Resources;203
5.8.3.2.2;8.3.2.2 Programming API to Support New Services;203
5.8.3.3;8.3.3 Applications;205
5.8.4;8.4 Techniques;205
5.8.4.1;8.4.1 Service Orientation and Web Services;206
5.8.4.2;8.4.2 Data Management;207
5.8.4.3;8.4.3 Monitoring;209
5.8.4.4;8.4.4 Autonomic Computing;213
5.8.4.5;8.4.5 Scheduling, Metascheduling, and Resource Provisioning;214
5.8.4.6;8.4.6 Interoperability in Grids and Clouds;216
5.8.4.7;8.4.7 Security and User Management;219
5.8.4.8;8.4.8 Modeling and Simulation of Clouds and Grids;222
5.8.5;8.5 Concluding Remarks;223
5.8.6;References;225
5.9;9 Cloudweaver: Adaptive and Data-Driven Workload Manager for Generic Clouds;231
5.9.1;9.1 Introduction;231
5.9.2;9.2 System Overview;233
5.9.2.1;9.2.1 Components;234
5.9.2.1.1;9.2.1.1 Workload Manager;234
5.9.2.1.2;9.2.1.2 Cloud Monitor;235
5.9.2.1.3;9.2.1.3 Generic Cloud;235
5.9.3;9.3 Workload Manager;236
5.9.3.1;9.3.1 Terminology;237
5.9.3.2;9.3.2 Operator Parallelization Status;238
5.9.3.3;9.3.3 Job Execution Algorithm;239
5.9.3.4;9.3.4 Dynamic Parallelization for Job Execution;240
5.9.3.5;9.3.5 Balancing Pipelined Operators;242
5.9.3.6;9.3.6 Balancing Tiers;243
5.9.3.7;9.3.7 Scheduling Multiple Jobs;243
5.9.4;9.4 Related Work;244
5.9.4.1;9.4.1 Parallel Databases;244
5.9.4.2;9.4.2 Data Processing in Cluster;245
5.9.5;9.5 Conclusion;246
5.9.6;References;247
6;Part II Architectures;249
6.1;10 Enterprise Knowledge Clouds: Architecture and Technologies ;250
6.1.1;10.1 Introduction;250
6.1.2;10.2 Business Enterprise Organisation;251
6.1.3;10.3 Enterprise Architecture;253
6.1.4;10.4 Enterprise Knowledge Management;255
6.1.5;10.5 Enterprise Knowledge Architecture;258
6.1.6;10.6 Enterprise Computing Clouds;259
6.1.7;10.7 Enterprise Knowledge Clouds;260
6.1.8;10.8 Enterprise Knowledge Cloud Technologies;261
6.1.9;10.9 Conclusion: Future Intelligent Enterprise;263
6.1.10;References;264
6.2;11 Integration of High-Performance Computing into Cloud Computing Services;266
6.2.1;11.1 Introduction;266
6.2.2;11.2 NC State University Cloud Computing Implementation;268
6.2.3;11.3 The VCL Cloud Architecture;273
6.2.3.1;11.3.1 Internal Structure;275
6.2.3.1.1;11.3.1.1 Storage;276
6.2.3.1.2;11.3.1.2 Partner's Program;276
6.2.3.2;11.3.2 Access;277
6.2.3.2.1;11.3.2.1 Standard;277
6.2.3.2.2;11.3.2.2 Special needs;278
6.2.3.3;11.3.3 Computational/Data Node Network;278
6.2.4;11.4 Integrating High-Performance Computing into the VCL Cloud Architecture;280
6.2.5;11.5 Performance and Cost;283
6.2.6;11.6 Summary;286
6.2.7;References;286
6.3;12 Vertical Load Distribution for Cloud Computing via Multiple Implementation Options;288
6.3.1;12.1 Introduction;288
6.3.2;12.2 Overview;292
6.3.3;12.3 Scheduling Composite Services;294
6.3.3.1;12.3.1 Solution Space;294
6.3.3.2;12.3.2 Genetic algorithm;295
6.3.3.2.1;12.3.2.1 Chromosome Representation of a Solution;297
6.3.3.2.2;12.3.2.2 Chromosome Recombination;298
6.3.3.2.3;12.3.2.3 GA Evaluation Function;299
6.3.3.3;12.3.3 Handling Online Arriving Requests;299
6.3.4;12.4 Experiments and Results;301
6.3.4.1;12.4.1 Baseline Configuration Results;302
6.3.4.2;12.4.2 Effect of Service Types;304
6.3.4.3;12.4.3 Effect of Service Type Instances;305
6.3.4.4;12.4.4 Effect of Servers (Horizontal Balancing);307
6.3.4.5;12.4.5 Effect of Server Performance;308
6.3.4.6;12.4.6 Effect of Response Variation Control;310
6.3.4.7;12.4.7 Effect of Routing Against Conservative SLA;312
6.3.4.8;12.4.8 Summary of Experiments;314
6.3.5;12.5 Related Work;314
6.3.6;12.6 Conclusion;317
6.3.7;References;318
6.4;13 SwinDeW-C: A Peer-to-Peer Based Cloud Workflow System;320
6.4.1;13.1 Introduction;320
6.4.2;13.2 Motivation and System Requirement;323
6.4.2.1;13.2.1 Large Scale Workflow Applications;323
6.4.2.2;13.2.2 System Requirements;324
6.4.2.2.1;13.2.2.1 QoS Management;324
6.4.2.2.2;13.2.2.2 Data Management;325
6.4.2.2.3;13.2.2.3 Security Management;325
6.4.3;13.3 Overview of SwinDeW-G Environment;326
6.4.4;13.4 SwinDeW-C System Architecture;328
6.4.4.1;13.4.1 SwinCloud Infrastructure;328
6.4.4.2;13.4.2 Architecture of SwinDeW-C;329
6.4.4.3;13.4.3 Architecture of SwinDeW-C Peers;331
6.4.5;13.5 New Components in SwinDeW-C;332
6.4.5.1;13.5.1 QoS Management in SwinDeW-C;333
6.4.5.2;13.5.2 Data Management in SwinDeW-C;334
6.4.5.3;13.5.3 Security Management in SwinDeW-C;335
6.4.6;13.6 SwinDeW-C System Prototype;336
6.4.7;13.7 Related Work;337
6.4.8;13.8 Conclusions and Feature Work;339
6.4.9;References;340
7;Part III Services;344
7.1;14 Cloud Types and Services;345
7.1.1;14.1 Introduction;345
7.1.2;14.2 Cloud Types;347
7.1.2.1;14.2.1 Public Cloud;347
7.1.2.2;14.2.2 Private Cloud;348
7.1.2.3;14.2.3 Hybrid Cloud;349
7.1.2.4;14.2.4 Community Cloud;349
7.1.3;14.3 Cloud Services and Cloud Roles;349
7.1.4;14.4 Infrastructure as a Service;350
7.1.4.1;14.4.1 Amazon Elastic Compute Cloud (EC2);350
7.1.4.2;14.4.2 GoGrid;351
7.1.4.3;14.4.3 Amazon Simple Storage Service (S3);352
7.1.4.4;14.4.4 Rackspace Cloud;353
7.1.5;14.5 Platform as a Service;353
7.1.5.1;14.5.1 Google App Engine;353
7.1.5.2;14.5.2 Microsoft Azure;354
7.1.5.3;14.5.3 Force.com;355
7.1.6;14.6 Software as a Service;356
7.1.6.1;14.6.1 Desktop as a Service;356
7.1.6.2;14.6.2 Google Apps;357
7.1.6.3;14.6.3 Salesforce;357
7.1.6.4;14.6.4 Other Software as Service Examples;358
7.1.7;14.7 The Amazon Family;358
7.1.7.1;14.7.1 RightScale: IaaS Based on AWS;361
7.1.7.2;14.7.2 HeroKu: Platform as a Service Using Amazon Web Service;362
7.1.7.3;14.7.3 Animoto Software as Service Using AWS;362
7.1.7.4;14.7.4 SmugMug Software as Service Using AWS;362
7.1.8;14.8 Conclusion;363
7.1.9;References;363
7.2;15 Service Scalability Over the Cloud;366
7.2.1;15.1 Introduction;366
7.2.2;15.2 Foundations;368
7.2.2.1;15.2.1 History on Enterprise IT Services;368
7.2.2.2;15.2.2 Warehouse-Scale Computers;372
7.2.2.3;15.2.3 Grids and Clouds;374
7.2.2.4;15.2.4 Application Scalability;378
7.2.2.5;15.2.5 Automating Scalability;379
7.2.3;15.3 Scalable Architectures;381
7.2.3.1;15.3.1 General Cloud Architectures for Scaling;381
7.2.3.2;15.3.2 A Paradigmatic Example: Reservoir Scalability;383
7.2.4;15.4 Conclusions and Future Directions;384
7.2.5;References;385
7.3;16 Scientific Services on the Cloud;387
7.3.1;16.1 Introduction;387
7.3.1.1;16.1.1 Outline;388
7.3.2;16.2 Service Oriented Atmospheric Radiances (SOAR);388
7.3.3;16.3 Scientific Programming Paradigms;389
7.3.3.1;16.3.1 MapReduce;390
7.3.3.1.1;16.3.1.1 MapReduce Merge;392
7.3.3.2;16.3.2 Dryad;392
7.3.3.3;16.3.3 Remote Sensing Geo-Reprojection;394
7.3.3.3.1;16.3.3.1 Remote Sensing Geo-Reprojection with MapReduce;395
7.3.3.3.2;16.3.3.2 Remote Sensing Geo-reprojection with Dryad;396
7.3.3.4;16.3.4 K-Means Clustering;397
7.3.3.4.1;16.3.4.1 K-Means Clustering with MapReduce;398
7.3.3.4.2;16.3.4.2 K-Means Clustering with Dryad;399
7.3.3.5;16.3.5 Singular Value Decomposition;400
7.3.3.5.1;16.3.5.1 Singular Value Decomposition with MapReduce;401
7.3.3.5.2;16.3.5.2 Singular Value Decomposition with Dryad;402
7.3.4;16.4 Delivering Scientific Computing services on the Cloud;404
7.3.4.1;16.4.1 Service Requirements;404
7.3.4.2;16.4.2 Service Discovery;407
7.3.4.3;16.4.3 Service Negotiation;407
7.3.4.4;16.4.4 Service Composition;409
7.3.4.5;16.4.5 Service Consumption and Monitoring;409
7.3.5;16.5 Summary/Conclusions;411
7.3.6;References;412
7.4;17 A Novel Market-Oriented Dynamic Collaborative Cloud Service Platform;414
7.4.1;17.1 Introduction;414
7.4.2;17.2 Related Works;416
7.4.3;17.3 A Dynamic Collaborative Cloud Services Platform;417
7.4.4;17.4 Proposed Combinatorial Auction Based Cloud Market (CACM) Model to Facilitate a DC Platform;419
7.4.4.1;17.4.1 Market Architecture;419
7.4.4.2;17.4.2 Additional Components of a CP to Form a DC Platform in CACM;421
7.4.4.3;17.4.3 Formation of a DC Platform in CACM Model;422
7.4.4.4;17.4.4 System Model for Auction in CACM;424
7.4.4.4.1;17.4.4.1 Single and Group Bidding Functions of CPs;424
7.4.4.4.2;17.4.4.2 Payoff Function of the User/Consumer;426
7.4.4.4.3;17.4.4.3 Profit of the CPs to form a Group;426
7.4.5;17.5 Model for Partner Selection;427
7.4.5.1;17.5.1 Partner Selection Problem;427
7.4.5.2;17.5.2 MO Optimization Problem for Partner Selection;428
7.4.5.3;17.5.3 Multi-objective Genetic Algorithm;429
7.4.6;17.6 Evaluation;431
7.4.6.1;17.6.1 Evaluation Methodology;431
7.4.6.1.1;17.6.1.1 Simulation Examples;432
7.4.6.2;17.6.2 Simulation Results;434
7.4.6.2.1;17.6.2.1 Appropriate Approach to Develop the MOGA-IC;434
7.4.6.2.2;17.6.2.2 Performance comparison of MOGA-IC with MOGA-I in CACM Model;437
7.4.7;17.7 Conclusion and Future Work;438
7.4.8;References;439
8;Part IV Applications;442
8.1;18 Enterprise Knowledge Clouds:Applications and Solutions ;443
8.1.1;18.1 Introduction;443
8.1.2;18.2 Enterprise Knowledge Management;444
8.1.2.1;18.2.1 EKM Applications;445
8.1.3;18.3 Knowledge Management in the Cloud;447
8.1.3.1;18.3.1 Knowledge Content;447
8.1.3.2;18.3.2 Knowledge Users;448
8.1.3.3;18.3.3 Enterprise IT;449
8.1.3.3.1;18.3.3.1 Problem Solving;450
8.1.3.3.2;18.3.3.2 Monitoring, Tuning and Automation;451
8.1.3.3.3;18.3.3.3 Business Intelligence and Analytics;452
8.1.3.3.4;18.3.3.4 Decision Making;453
8.1.3.4;18.3.4 The Intelligent Enterprise;455
8.1.4;18.4 Moving KM Applications to the Cloud;456
8.1.5;18.5 Conclusions and Future Directions;456
8.1.6;References;458
8.2;19 Open Science in the Cloud: Towards a Universal Platform for Scientific and Statistical Computing;459
8.2.1;19.1 Introduction;459
8.2.2;19.2 An Open Platform for Scientific Computing, the Building Blocks;462
8.2.2.1;19.2.1 The Processing Capability;463
8.2.2.2;19.2.2 The Mathematical and Numerical Capability;464
8.2.2.3;19.2.3 The Orchestration Capability;464
8.2.2.4;19.2.4 The Interaction Capability;464
8.2.2.5;19.2.5 The Persistence Capability;465
8.2.3;19.3 Elastic-R and Infrastructure-as-a-Service;466
8.2.3.1;19.3.1 The Building Blocks of a Traceable and Reproducible Computational Research Platform;467
8.2.3.2;19.3.2 The Building Blocks of a Platform for Statistics and Applied Mathematics Education;468
8.2.4;19.4 Elastic-R, an e-Science Enabler;469
8.2.4.1;19.4.1 Lowering the Barriers for Accessing on-Demand Computing Infrastructures. Local/Remote Transparency;469
8.2.4.2;19.4.2 Dealing with the Data Deluge;469
8.2.4.3;19.4.3 Enabling Collaboration Within Computing Environments;470
8.2.4.4;19.4.4 Science Gateways Made Easy;471
8.2.4.5;19.4.5 Bridging the Gap Between Existing Scientific Computing Environments and Grids/Clouds;471
8.2.4.6;19.4.6 Bridging the Gap Between Mainstream Scientific Computing Environments;471
8.2.4.7;19.4.7 Bridging the Gap Between Mainstream Scientific Computing Environments and Workflow Workbenches;471
8.2.4.8;19.4.8 A Universal Computing Toolkit for Scientific Applications;472
8.2.4.9;19.4.9 Scalability for Computational Back-Ends;473
8.2.4.10;19.4.10 Distributed Computing Made Easy;474
8.2.5;19.5 Elastic-R, an Application Platform for the Cloud;475
8.2.5.1;19.5.1 The Elastic-R Plug-ins;475
8.2.5.2;19.5.2 The Elastic-R Spreadsheets;476
8.2.5.3;19.5.3 The Elastic-R extensions;477
8.2.6;19.6 Cloud Computing and Digital Solidarity;478
8.2.7;19.7 Conclusions and Future Directions;479
8.2.8;References;479
8.3;20 Multidimensional Environmental Data Resource Brokering on Computational Grids and Scientific Clouds;481
8.3.1;20.1 Introduction;481
8.3.2;20.2 Resource Discovery and Selection Using a Resource Broker Service;484
8.3.3;20.3 Anagram Based GrADS Data Distribution Service;485
8.3.4;20.4 Hyrax Based Five Dimension Distribution Data Service;486
8.3.5;20.5 Design and Implementation of an Instrument Service for NetCDF Data Acquisition;489
8.3.6;20.6 A Weather Forecast Quality Evaluation Scenario;492
8.3.7;20.7 Implementation of the Grid Application;494
8.3.8;20.8 Conclusions and Future Work;496
8.3.9;References;498
8.4;21 HPC on Competitive Cloud Resources;499
8.4.1;21.1 Introduction;499
8.4.2;21.2 Related Work;501
8.4.3;21.3 Background;502
8.4.3.1;21.3.1 Overview of Amazon EC2 Setup;503
8.4.3.2;21.3.2 Overview of HPL;505
8.4.4;21.4 Intranode Scaling;505
8.4.4.1;21.4.1 DGEMM Single Node Evaluation;506
8.4.4.2;21.4.2 HPL Single Node Evaluation;510
8.4.5;21.5 Internode Scaling;512
8.4.5.1;21.5.1 HPL Minimum Evaluation;513
8.4.5.2;21.5.2 HPL Average Evaluation;518
8.4.6;21.6 Conclusions;520
8.4.7;References;521
8.5;22 Scientific Data Management in the Cloud: A Survey of Technologies, Approaches and Challenges;523
8.5.1;22.1 Introduction;523
8.5.2;22.2 Data Management Issues Within Scientific Experiments;524
8.5.3;22.3 Data Clouds: Emerging Technologies;525
8.5.4;22.4 Case Studies: Harnessing the Data Cloud for Scientific Data Management;528
8.5.4.1;22.4.1 Pan-STARRS Data with GrayWulf;528
8.5.4.2;22.4.2 GEON Workflow with the CluE Cluster;529
8.5.4.3;22.4.3 SciDB;530
8.5.4.4;22.4.4 Astrophysical Data Analysis with Pig/Hadoop;530
8.5.4.5;22.4.5 Public Data Hosting by Amazon Web Services;531
8.5.5;22.5 A Gap Analysis of Data Cloud Capabilities;532
8.5.5.1;22.5.1 The Impedance Mismatch;532
8.5.5.2;22.5.2 Fault Tolerance;532
8.5.5.3;22.5.3 Scientific Data Format and Analysis Tools;532
8.5.5.4;22.5.4 Integration with the Object Oriented Programming Model;533
8.5.5.5;22.5.5 Working with Legacy Software;533
8.5.5.6;22.5.6 Real-Time Data;534
8.5.5.7;22.5.7 Programmable Interfaces to Performance Optimizations;534
8.5.5.8;22.5.8 Distributed Database Issues;535
8.5.5.9;22.5.9 Security and Privacy;535
8.5.6;22.6 Conclusions;535
8.5.7;References;535
8.6;23 Feasibility Study and Experience on Using Cloud Infrastructure and Platform for Scientific Computing;540
8.6.1;23.1 Introduction;540
8.6.2;23.2 Scientific Compute Tasks;541
8.6.3;23.3 Scientific Computing in the Cloud;544
8.6.3.1;23.3.1 Cloud Architecture as Foundation of Cloud-Based Scientific Applications;544
8.6.3.2;23.3.2 Emergence of Cloud-Based Scientific Computational Applications;547
8.6.4;23.4 Building Cloud Infrastructure for Scientific Computing;549
8.6.4.1;23.4.1 Setup and Experiment on Tiny Cloud Infrastructure and Platform;550
8.6.4.2;23.4.2 On Economical Use of the Enterprise Cloud;551
8.6.5;23.5 Toward Integration Of Private and Public Enterprise Cloud Environment;553
8.6.6;23.6 Conclusion;554
8.6.7;References;555
8.7;24 A Cloud Computing Based Patient Centric Medical Information System;557
8.7.1;24.1 Introduction;557
8.7.2;24.2 Potential Impact of Proposed Medical Informatics System;559
8.7.3;24.3 Background and Related Work;560
8.7.4;24.4 Brief Discussion of Medical Standards;563
8.7.5;24.5 Architecture Description and Research Methods;565
8.7.5.1;24.5.1 Objective 1: A Service Oriented Architecture for Interfacing Medical Messages;565
8.7.5.2;24.5.2 Objective 2: Lossless Accelerated Presentation Layer for Viewing DICOM Objects on Cloud;567
8.7.5.3;24.5.3 Objective 3: Web Based Interface for Patient Health Records;568
8.7.5.4;24.5.4 Objective 4: A Globally Distributed Dynamically Scalable Cloud Based Application Architecture;569
8.7.5.4.1;24.5.4.1 Distributed Data Consistency Across Clouds;571
8.7.5.4.2;24.5.4.2 Higher availability and application scalability;571
8.7.5.4.3;24.5.4.3 Concerning Low Level Security;573
8.7.6;References;575
8.8;25 Cloud@Home: A New Enhanced Computing Paradigm;578
8.8.1;25.1 Introduction;578
8.8.2;25.2 Why Cloud@Home?;582
8.8.2.1;25.2.1 Aims and Goals;583
8.8.2.2;25.2.2 Application Scenarios;585
8.8.3;25.3 Cloud@Home Overview;587
8.8.3.1;25.3.1 Issues, Challenges and Open Problems;587
8.8.3.2;25.3.2 Basic Architecture;588
8.8.3.3;25.3.3 Frontend Layer;588
8.8.3.4;25.3.4 Virtual Layer;589
8.8.3.5;25.3.5 Physical Layer;590
8.8.3.6;25.3.6 Management Subsystem;591
8.8.3.7;25.3.7 Resource Subsystem;593
8.8.4;25.4 Ready for CloudHome?;596
8.8.5;References;596
8.9;26 Using Hybrid Grid/Cloud Computing Technologies for Environmental Data Elastic Storage, Processing,and Provisioning;598
8.9.1;26.1 Introduction;598
8.9.2;26.2 Distributing Multidimensional Environmental Data;599
8.9.3;26.3 Environmental Data Storage on Elastic Resources;600
8.9.3.1;26.3.1 Amazon Cloud Services;601
8.9.3.2;26.3.2 Multidimensional Environmental Data Standard File Format;602
8.9.3.3;26.3.3 Enhancing the S3 APIs;603
8.9.3.4;26.3.4 Enabling the NetCDF Java Interface to S3;606
8.9.4;26.4 Cloud and Grid Hybridization: The NetCDF Service;608
8.9.4.1;26.4.1 The NetCDF Service Architecture;608
8.9.4.2;26.4.2 NetCDF Service Deployment Scenarios;611
8.9.5;26.5 Performance Evaluation;613
8.9.5.1;26.5.1 Parameter Selection for the S3-Enhanced Java Interface;613
8.9.5.2;26.5.2 Evaluation of S3- and EBS-Enabled NetCDF Java Interfaces;614
8.9.5.3;26.5.3 Evaluation of NetCDF Service Performance;616
8.9.6;26.6 Conclusions and Future Directions;618
8.9.7;References;620
8.10;Index;622