Cloud Computing Vision Tools Technologies for Delivering Computing

Cloud Computing: Vision, Tools, Technologies for Delivering Computing as the 5 th Utility 1

Cloud Computing: Vision, Tools, and Technologies for Delivering Computing as the 5 th Utility Dr. Rajkumar Buyya Cloud Computing and Distributed Systems (CLOUDS) Lab Dept. of Computer Science and Software Engineering The University of Melbourne, Australia www. gridbus. orgcloudbus. org www. buyya. com www. manjrasoft. com Major Sponsors/Supporters

Outline n “Computer Utilities” n n Cloud Computing and Related Paradigms n n n 3 Trends, Definition, Cloud Benefits and Challenges Market-Oriented Cloud Architecture n n Vision and Promising IT Paradigms/Platforms SLA-oriented Resource Allocation Global Cloud Exchange Emerging Cloud Platforms Cloudbus: Melbourne Cloud Computing Project Summary and Thoughts for Future

“Computer Utilities” Vision: Implications of the Internet n 1969 – Leonard Kleinrock, ARPANET project n n “As of now, computer networks are still in their infancy, but as they grow up and become sophisticated, we will probably see the spread of ‘computer utilities’, which, like present electric and telephone utilities, will service individual homes and offices across the country” Computers Redefined n 1984 – John Gage, Sun Microsystems n n 2008 – David Patterson, U. C. Berkeley n n 4 “The network is the computer” “The data center is the computer. There are dramatic differences between of developing software for millions to use as a service versus distributing software for millions to run their PCs” 2008 – “The Cloud is the computer” – Buyya!

Computing Paradigms and Attributes: Realizing the ‘Computer Utilities’ Vision n n n n } ? Web Data Centres Utility Computing Service Computing Grid Computing P 2 P Computing Market-Oriented Computing Cloud Computing … Paradigms 5 + -Ubiquitous -Reliable -Scalable -Autonomic -Dynamic discovery - Composable -Qo. S -SLA -… -Trillion $ business Attributes/Capabilities

Outline n “Computer Utilities” n n Cloud Computing and Related Paradigms n n n 6 Trends, Definition, Cloud Benefits and Challenges Market-Oriented Cloud Architecture n n Vision and Promising IT Paradigms/Platforms SLA-oriented Resource Allocation Global Cloud Exchange Emerging Cloud Platforms Cloudbus: Melbourne Cloud Computing Project Summary and Thoughts for Future

Gold rush: Too many people are “In Search” of Cloud Computing! Legend: Cluster computing, Grid computing, Cloud computing 7

2009 Gartner IT Hype Cycle of Emerging Technologies 8

Defining Clouds: There are many views for what is cloud computing? n Over 20 definitions: n n Buyya’s definition n n 9 http: //cloudcomputing. sys-con. com/read/612375_p. htm "A Cloud is a type of parallel and distributed system consisting of a collection of inter-connected and virtualised computers that are dynamically provisioned and presented as one or more unified computing resources based on service-level agreements established through negotiation between the service provider and consumers. ” Keywords: Virtualisation (VMs), Dynamic Provisioning (negotiation and SLAs), and Web 2. 0 access interface

Cloud Services n Infrastructure as a Service (Iaa. S) n n Google App Engine, Microsoft Azure, Manjrasoft Aneka. . Platform as a Service (Paa. S) Software as a Service (Saa. S) n 10 Software as a Service (Saa. S) Platform as a Service (Paa. S) n n CPU, Storage: Amazon. com, Nirvanix, Go. Grid…. Sales. Force. Com Infrastructure as a Service (Iaa. S)

Clouds based on Ownership and Exposure Public/Internet Clouds 3 rd party, multi-tenant Cloud infrastructure & services: * available on subscription basis (pay as you go) 11 Private/Enterprise Clouds Hybrid/Mixed Clouds Cloud computing model run within a company’s own Data Center / infrastructure for internal and/or partners use. Mixed usage of private and public Clouds: Leasing public cloud services when private cloud capacity is insufficient

(Promised) Benefits of (Public) Clouds n No upfront infrastructure investment n n On demand access n n n Parallelism for large-scale data analysis, what-if scenarios studies… Highly Availability, Scalable, and Energy Efficient Supports Creation of 3 rd Party Services & Seamless offering n 12 Based on Usage, Qo. S, Supply and Demand, Loyalty, … Application Acceleration n n Globally shared infrastructure, can always be kept busy by serving users from different time zones/regions. . . Nice Pricing n n Lease what you need and when you need. . Efficient Resource Allocation n n No procuring hardware, setup, hosting, power, etc. . Builds on infrastructure and follows similar Business model as Cloud

Cloud opportunity in short term 13

When will Cloud spending become 50% of IT spending or reach to a several trillion $ business/year? 600? 30% 120? 2016 14 1000? 15% 2020? Buyya’s Estimate! 2020? 50%

Cloud Computing Challenges: Dealing with too many issues ng Prici zat uali ion Scalability Res Virt our ce M Qo. S el v Le nts e e c vi em r Se gre A Privacy st Tru Programming Env. & Application Dev. Software Eng. Complexity 15 Reliability Ene r l & ry a g to Le ula g Re Sec ing Billing Provisionin g on Deman d y urit eter gy E Utility & Risk Management Uhm, I am not quite clear…Yet another complex IT paradigm? ffici enc y

Outline n “Computer Utilities” n n Cloud Computing and Related Paradigms n n n 16 Trends, Definition, Cloud Benefits and Challenges Market-Oriented Cloud Architecture n n Vision and Promising IT Paradigms/Platforms SLA-oriented Resource Allocation Global Cloud Exchange Emerging Cloud Platforms Cloudbus: Melbourne Cloud Computing Project Summary and Thoughts for Future

Realizing the ‘Computer Utilities’ Vision: What Consumers and Providers Want? n Consumers – minimize expenses, meet Qo. S n n n n Providers – maximise Return On Investment (ROI) n n n n How do I decide service pricing models? How do I specify prices? How do I translate prices into resource allocations? How do I assign and enforce resource allocations? How do I advertise and attract consumers? How do I perform accounting and handle payments? … Mechanisms, tools, and technologies n 17 How do I express Qo. S requirements to meet my goals? How do I assign valuation to my applications? How do I discover services and map applications to meet Qo. S needs? How do I manage multiple providers and get my work done? How do I outperform other competing consumers? … value expression, translation, and enforcement

Market-based Systems = Selfmanaged and self-regulated systems. n Manage n n n 1 Complexity Supply and Demand Enhance Utility 2 3 penalty 18

Market-oriented Cloud Architecture: Qo. S negotiation and SLAbased Resource Allocation 19

A (Layered) Cloud Architecture User level Apps Hosting Platforms Core Middleware Qo. S Negotiation, Admission Control, Pricing, SLA Management, Monitoring, Execution Management, Metering, Accounting, Billing Virtual Machine (VM), VM Management and Deployment Cloud resources System level 20 Autonomic / Cloud Economy Cloud programming: environments and tools Web 2. 0 Interfaces, Mashups, Concurrent and Distributed Programming, Workflows, Libraries, Scripting Adaptive Management User-Level Middleware Cloud applications Social computing, Enterprise, ISV, Scientific, CDNs, . . .

Outline n 21 st Century Vision of Computing n n Cloud Computing and Related Paradigms n n n 21 Trends, Definition, Characteristics, Architecture Market-Oriented Cloud Architecture n n Promising Computing Paradigms SLA-oriented Resource Allocation Global Cloud Exchange Emerging Cloud Platforms Cloudbus: Melbourne Cloud Computing Project Summary and Thoughts for Future

Some Commercial-Oriented Cloud platforms/technologies System Property 22 Amazon EC 2 & S 3 Google App Engine Microsoft Azure Manjrasoft Aneka Focus Iaa. S/Paa. S Service Type Compute (EC 2), Storage (S 3) Web apps Web and non-web apps Compute/Data Virtualisation OS Level: Xen Apps container OS level/Hyper-V Resource Manager and Scheduler Dynamic Negotiation of Qo. S None SLA-oriented/ Resource Reservation User Access Interface EC 2 Command-line Tools Web-based Administration Console Windows Azure portal Workbench, Tools Web APIs Yes Yes Value-added Service Providers Yes No Programming Framework Amazon Machine Image (AMI) Python . NET framework Multiple App models in. NET languages

Many Cloud Offerings: Good, but new issues“vendor lock in”, “scaling” across clouds en ix X o ix van M Nir r rve Se s os Am e zur ro Mic er ne ngi G vi r-V so e yp rs … n re Wa M V Complex decisions to make? ud d lou C brid Hy 23 H Xe loud Private Clo Manjrasoft Aneka Iaa. S Pub lic C pp. E le A oog Saa. S Paa. S Hy p on E C 2 azo Citr t. A sof Am az 3 n. S

Inter. Cloud: Global Cloud Exchange and Market Maker Compute Cloud Storage Cloud Broker 1 Request Negotiate/Bid Capacity Enterprise Resource Manager (Proxy) . . Broker N Publish Offers Directory Bank Auctioneer Compute Cloud Global Cloud Exchange Enterprise IT Consumer Storage Cloud 24

Outline n “Computer Utilities” n n Cloud Computing and Related Paradigms n n n 25 Trends, Definition, Cloud Benefits and Challenges Market-Oriented Cloud Architecture n n Vision and Promising IT Paradigms/Platforms SLA-oriented Resource Allocation Global Cloud Exchange Emerging Cloud Platforms Cloudbus: Melbourne Cloud Computing Project Summary and Thoughts for Future

Cloudbus@CLOUDS Lab: Melbourne Cloud Computing Initiative n Market-Oriented Clouds n n n Aneka –. NET-based Cloud Computing n n Energy Efficiency and Qo. S Oriented Resource Allocation Cloud. Sim: Toolkit for Simulation of Clouds n 26 Building Content Delivery Networks using different “vendors” Storage Clouds Green Clouds / Data Centers n n Federation of clouds for application scaling across distributed resources 3 rd Party Cloud Services (e. g. , Meta. CDN) – Harnessing Storage resources n n Paa. S for Enterprise and Public Clouds Scaling Across Clouds (Meta Brokering) – Harnessing Compute resources n n SLA-based Resource Management Global Cloud Exchange Elements: Brokers Design and evaluation for resource management policies & algorithms

Aneka: . NET-based Cloud Computing n n n SDK containing APIs for multiple programming models and tools Runtime Environment for managing application execution management Suitable for n n n Portability for Customer Apps: n n 27 Development of Enterprise Cloud Applications Cloud enabling legacy applications Enterprise ↔ Public Clouds . NET/Win ↔ Mono/Linux

Qo. S Negotiation in Aneka Meta Negotiation Registry … 3. Matching DB DB Registries DB 2. Publishing, Querying 1. Publishing MN Middelware 4. Session Establishment Gridbus Broker Amadeus Workflow Alternate Offers Negotiation Strategy Meta. Negotiation Local SLA Template Handshaking 5. Negotiation Party 1 API Service Consumer Aneka Meta. Negotiation Local SLA Template Party 2 Service Provider 6. Service Invocation 28 WSDL MN Middelware Alternate Offers Negotiation Strategy

Aneka: components public Dumb. Task: ITask { … public void Execute() { for(int …… i=0; i<n; i++) { } }… Dumb. Task task = new Dumb. Task(); app. Submit. Execution(task); } Aneka enterprise Cloud Executor work units Executor Client Agent Executor internet work units Scheduler internet Aneka Worker Service Aneka Manager Executor Client Agent Programming / Deployment Model Aneka User Agent 29

Aneka & Virtual Resource Pools Integration n Xen. Server Pool n n VMWare Pool n n Allows resource provisioning over private Cloud infrastructure managed by VMWare Amazon EC 2 Pool n 30 Allows resource provisioning over private Cloud infrastructure managed by Xen Server Allows resource provisioning over public Cloud provider : Amazon EC 2

Aneka Cloud Request (5 resources, $0) Completed Xen Server - Capacity : 10 VMs Aneka Provision Service VMWare - Capacity : 5 VMs Process (5) Amazon Clouds Enterprise Desktops/Servers Cloud 31

Aneka+Xen Request (5 resources, $0) Request (20 resources, $0) Completed Aneka Start VM (10) Suspend VM (10) Xen Server - Capacity : 10 VMs Provision (14) Join Network(14) Provision Service Process (14) Suspend VM (4) Start VM (4) VMWare - Capacity : 5 VMs Process (5) Process (6) Release (14) Amazon Clouds Enterprise Desktops/Servers Cloud 32

Aneka+Xen+EC 2 Request (5 resources, $0) Request (30 resources, $5) Completed ($3. 2) Start VM (10) Suspend VM (10) Xen Server - Capacity : 10 VMs Aneka Provision (24) Join Network(24) Provision Service Process (24) Suspend VM (5) Start VM (5) VMWare - Capacity : 5 VMs Process (5) Process (6) Release (24) Release VM (9) Start VM (9) Amazon Clouds - Cost : 20 cents per instance Enterprise Desktops/Servers Cloud 33

Aneka Case Studies

User scenario: Go. Front (unit of China Southern Railway Group) Application: Locomotive design CAD rendering Aneka Maya Renderer Go. Front Private Aneka Cloud Use private Aneka Cloud LAN network (Running Maya Batch Mode on demand) Case 2: Aneka Enterprise Cloud Time (in hrs) Case 1: Single Server Raw Locomotive Design Files (Using Auto. Desk Maya) Using Maya Graphical Mode Directly Single Server 4 cores server 35 Aneka Cloud Aneka utilizes idle desktops (30) to decrease task time from days to hours

Providing a scalable architecture for Titan. Strike on-line Gaming Portal Aneka-based Game. Controller Titan. Strike Private Aneka Cloud The local scheduler interacts with Aneka and distributes the load in the cloud. Case 2: Aneka Enterprise Cloud = Scalability Gamers profiles Players statistics Team playing Multiple games Distributed log parsing LAN network (Running Game plugins on Demand) logs Titan Strike On Line Gaming Portal Case 1: Single Server = Huge Overload logs Centralized log parsing 36 Single Game. Controller Single scheduler controlling the execution of all the matches. logs Game Servers

DNA Micro. Array Data Analysis for BRCA (Brain Cancer gene profiles) Aneka on Public Cloud – Amazon EC 2 37

Gene Expression Profiling Classification on Public Clouds Aneka distribution engine: dispatches Co. XCS tasks in the Aneka Cloud. Offspring Development and execution environment of composable workflows that are run on top of distributed middleware via plug-in based engines. Aneka deployment on EC 2 public Compute Cloud 38 Cloud Co. XCS Co-XCS Model: multiple Co. XCS Classifiers evolve separately on a different partition and exchange individuals at predefined stages

Experiments on Amazon EC 2 n n Master image: Aneka container with scheduling and task model file staging services deployed on Windows Server 2003 Worker image: Aneka Container with task execution services deployed on Red. Hat Linux c 1. medium n 39 Execution time (in minutes)

Building 3 rd Party Cloud Services – Harnessing Storage Clouds Building Next-Gen “Content Delivery Networks”

Motivations n Content Delivery Networks (CDNs) such as Akamai place web server clusters in numerous geographical locations – ”huge upfront investment” n n n 41 to improve the responsiveness and locality of the content it hosts for end-users. However, their services are priced out of reach for all but the largest enterprise customers. Hence, we have developed an alternative approach to content delivery by leveraging infrastructure ‘Storage Cloud’ providers at a fraction of the cost of traditional CDN providers – “pay as you go”

Commercial Storage Clouds & Pricing 42

Meta. CDN: Harnessing Storage Clouds for Content Delivery (Broberg, Buyya, Tari, JNCA 2009) 43

Meta Brokering – Harnessing Compute Clouds for Application Scaling Extending market-oriented Grid Ideas with Cloud computing

Building a Grid of Clouds Global Utility Computing Grid Information Service Grid Resource Broker R 2 R 3 R 5 Application database R 4 RN Grid Resource Broker R 6 Grid Information Service 45 R 1 Resource Broker

Gridbus Service Broker (GSB) n n n A resource broker for scheduling task farming dataintensive applications with static or dynamic parameter sweeps on global Grids and Clouds. It uses computational economy paradigm for optimal selection of computational and data services depending on their quality, cost, and availability, and users’ Qo. S requirements (deadline, budget, & T/C optimisation) Key Features n n n n 46 A single window to manage & control experiment Programmable Task Farming Engine Resource Discovery and Resource Trading Optimal Data Source Discovery Scheduling & Predications Generic Dispatcher & Grid Agents Transportation of data & sharing of results Accounting

workload Gridbus User Console/Portal/Application Interface App, T, $, Optimization Preference Gridbus Broker Gridbus Farming Engine Schedule Advisor Trading Manager Record Keeper Dispatcher Core Middleware Grid Explorer TM $ TS GE GIS, NWS Grid Info Server RM & TS $ 47 G U G Globus enabled node. $ L Amazon EC 2/S 3 Cloud. Data Node Data Catalog C A

Gridbus Broker: Separating “applications” from “different” remote service access enablers and schedulers Application Development Interface Home Node/Portal Scheduling Interfaces Algorithm 1 Algorithm. N Gridbus Broker Single-sign on security batch() fork() -PBS -Condor -SGE -Aneka -XGrid Data Catalog Plugin Actuators Aneka Globus Data Store Job manager Amazon EC 2 Access Technology fork() batch() -PBS -Condor -SGE 48 Gridbus agent Grid FTP SRB AMI SSH fork() batch() -PBS -Condor -SGE -XGridbus agent

s 49

Market-Oriented Scheduling Experiments

Experiment Setup: DBC Scheduling with Optimize for (1) Time & (2) Cost n Workload: n n n A parameter sweep “synthetic” application (100 jobs), each job is modeled to execute ~5 minute with variation of (+/-20 sec. ). Qo. S Constraints: Deadline: 40 min. and Budget: $6 Resources: n n n US Europe Australia R* Information Service R 2 R 1 R 4, 5 51 Resource Broker

Resources & Price (multiplier for clarity) Rate Total Jobs Organization Resource Details (Cents per second*1000 ) Time-Opt Cost-Opt Georgia State University, US snowball. cs. gsu. edu 8 Intel 1. 90 GHz CPU, 3. 2 GB RAM, 152 GB HD, Linux 90 (0. 09) 32 11 H. Furtwangen University, Germany unimelb. informatik. hs-furtwangen. de 1 Athlon XP 1700+ CPU, 767 MB RAM, 147 GB HD 3 4 5 University of California. Irvine, US harbinger. calit 2. uci. edu 2 Intel P III 930 MHz CPU, 503 MB RAM, 32 GB HD 2 8 10 University of Melbourne, Australia billabong. csse. unimelb. edu. au 2 Intel(R) 2. 40 GHz CPU, 1 GB RAM, 35 GB HD 6 8 10 University of Melbourne, Australia gieseking. csse. unimelb. edu. au 2 Intel(R) 2. 40 GHz CPU, 1 GB RAM, 71 GB HD 6 8 10 Amazon EC 2 * ec 2 -Medium instance 5 EC 2 Compute Units*, 1. 7 GB RAM, 350 GB HD 60 14 16 Amazon EC 2 * ec 2 -Medium instance 5 EC 2 Compute Units, 1. 7 GB RAM, 350 GB HD 60 13 16 Amazon EC 2 * ec 2 -Small instance 1 EC 2 Compute Unit, 1. 7 GB RAM, 160 GB HD 30 7 11 Amazon EC 2 * ec 2 -Small instance 1 EC 2 Compute Unit, 1. 7 GB RAM, 160 GB HD 30 6 11 Total Price / Budget Consumed 5. 04$ 3. 71$ Time to Complete Execution 28 min 35 min * Amazon charges for 1 hour even if you use VM for 1 sec. We should force Amazon to change Charging Policy from 1 hr block to actual usage! Or invent a 3 rd party service that manages this by leasing smaller slots. 52

Execution Console: Setting Qo. S 53

Results of Execution on Cloud and other Distributed Resources 54 Rate Total Jobs Organization Resource Details (Cents per second*1000 ) Time-Opt Cost-Opt Georgia State University, US snowball. cs. gsu. edu 8 Intel 1. 90 GHz CPU, 3. 2 GB RAM, 152 GB HD, Linux 90 (0. 09) 32 11 H. Furtwangen University, Germany unimelb. informatik. hs-furtwangen. de 1 Athlon XP 1700+ CPU, 767 MB RAM, 147 GB HD 3 4 5 University of California. Irvine, US harbinger. calit 2. uci. edu 2 Intel P III 930 MHz CPU, 503 MB RAM, 32 GB HD 2 8 10 University of Melbourne, Australia billabong. csse. unimelb. edu. au 2 Intel(R) 2. 40 GHz CPU, 1 GB RAM, 35 GB HD 6 8 10 University of Melbourne, Australia gieseking. csse. unimelb. edu. au 2 Intel(R) 2. 40 GHz CPU, 1 GB RAM, 71 GB HD 6 8 10 Amazon EC 2 * ec 2 -Medium instance 5 EC 2 Compute Units*, 1. 7 GB RAM, 350 GB HD 60 14 16 Amazon EC 2 * ec 2 -Medium instance 5 EC 2 Compute Units, 1. 7 GB RAM, 350 GB HD 60 13 16 Amazon EC 2 * ec 2 -Small instance 1 EC 2 Compute Unit, 1. 7 GB RAM, 160 GB HD 30 7 11 Amazon EC 2 * ec 2 -Small instance 1 EC 2 Compute Unit, 1. 7 GB RAM, 160 GB HD 30 6 11 Total Price / Budget Consumed 5. 04$ 3. 71$ Time to Complete Execution 28 min 35 min * Amazon charges for 1 hour even if you use VM for 1 sec. Qo. S Constraints: Deadline: 40 min. and Budget: $6

Scheduling for DBC Cost Optimization 55

Resource Scheduling for DBC Time Optimization 56

Resources Consumed by Cost and Time Opt. Strategies Cost-Opt Time-Opt Uni. Melb: . 006 EC 2 -m: . 06 Uni. Melb: . 006 EC 2 -m : . 06 UCi: . 002 EC 2 -s : . 03 EU: . 003 EC 2 -s: . 03 Georgia: . 09 (most expensive) Qo. S Constraints: Deadline: 40 min. and Budget: $6 Time 57 Cost Budget Consumed 5. 04$ 3. 71$ Time to Complete 28 min 35 min

Experimental Evaluation is too much of work and “expensive” for computing researchers? Cloud. Sim: Performance Evaluation Made Easy *Repeatable, scalable, controllable environment for modelling and simulation of Clouds * No need to worry about paying Iaa. S provides + Cloud. Sim is FREE!

Outline n “Computer Utilities” n n Cloud Computing and Related Paradigms n n n 60 Trends, Definition, Cloud Benefits and Challenges Market-Oriented Cloud Architecture n n Vision and Promising IT Paradigms/Platforms SLA-oriented Resource Allocation Global Cloud Exchange Emerging Cloud Platforms Cloudbus: Melbourne Cloud Computing Project Summary and Thoughts for Future

Summary n Several Computing Platforms/Paradigms are promising to deliver “Computing Utilities” vision n n Market Oriented Clouds are getting real n n Need to move from static pricing to dynamic pricing Need strong support for SLA-based resource management 3 rd party Composed Cloud services starting to emerge Building Grids using Clouds is much more realistic. n 61 Cloud Computing is the most recent kid in the block promising to turn vision into reality Clouds built on: SOA, VMs, Web 2. 0 technologies Many exciting business and consumer applications enabled. Extension of idea can lead to “Global Cloud Exchange”

Dozens of Open Research Issues n n n (Application) Software Licensing Seamless integration of private and Cloud resources Security, Privacy and Trust Cloud “Lock-In” worries and Interoperability Application Scalability Across Multiple Clouds Federation and Cooperative Sharing Global Cloud Exchange and Market Maker Dynamic Pricing Dynamic Negotiation and SLA Management Energy Efficient Resource Allocation and User Qo. S Power-Cost and CO 2 emission issues n 62 n Use renewable energy: follow Sun and wind? Regulatory and Legal Issues

Convergence of Competing Paradigms/Communities Needed n n n n n } ? Web Data Centres Utility Computing Service Computing Grid Computing P 2 P Computing Cloud Computing Market-Oriented Computing … Paradigms 63 + • Ubiquitous access • Reliability • Scalability • Autonomic • Dynamic discovery • Composability • Qo. S • SLA • … -Trillion $ business - Who will own it? Attributes/Capabilities

References n Blueprint Paper! n n Aneka Documents: n n 64 R. Buyya, D. Abramson, S. Venugopal, “The Grid Economy”, Proceedings of the IEEE, No. 3, Volume 93, IEEE Press, 2005. Meta. CDN Paper: n n http: //www. manjrasoft. com/ The Grid Economy Paper: n n R. Buyya, C. S. Yeo, S. Venugopal, J. Broberg, I. Brandic, “Cloud Computing and Emerging IT Platforms: Vision, Hype, and Reality for Delivering Computing as the 5 th Utility”, Future Generation Computer Systems (FGCS) Journal, June 2009. James Broberg, Rajkumar Buyya, and Zahir Tari, Meta. CDN: Harnessing 'Storage Clouds' for High Performance Content Delivery, Journal of Network and Computer Applications, ISSN: 1084 -8045, Elsevier, Amsterdam, The Netherlands, 2009. Cloudbus Keynote Paper: n R. Buyya, S. Pandey, and C. Vecchiola, Cloudbus Toolkit for Market -Oriented Cloud Computing, Proceeding of the 1 st International Conference on Cloud Computing (Cloud. Com 2009, Springer, Germany), Beijing, China, December 1 -4, 2009.

Thanks for your attention! n Are there any n n Questions? Comments/ Suggestions We Welcome Cooperation in R&D and Business! http: /www. gridbus. org | www. manjrasoft. com rbuyya@unimelb. edu. au | raj@manjrasoft. com 65

Solutions for Cloud Computing 66