1 Applications and Developments in Grid, Cloud, and High Performance Computing Emmanuel Udoh Sullivan University, USA Information Science REFERENCE
2 Detailed Table of Contents Preface xvii Section 1 Introduction Chapter 1 Risk Assessment for CloudBased IT Systems 1 Yuyu Chou, Berlin Institute of Technology, Germany Jan Oetting, Consileon Business Consultancy GmbH, Germany The use of Cloud Computing services is an attractive option to improve IT systems to achieve rapidly and elastically provisioned capability, and also to offer economic benefits. However, companies see security as a major concern in migrating to the Cloud. To bring clarity in Cloud security, this paper presents a systematic approach to manage the risks and analyzes the full range of risk in Cloud Computing solu tions. Furthermore, as a study case, Google App Engine Platform is assessed based on ISO/IEC and OWASPTop 10 Risk List in this paper. Knowing the risks of Cloud solutions, companies can execute wellinformed decisions on going into the Cloud and build their Cloud solutions in a secure way, relying on a robust etrust relationship. Section 2 Scheduling Chapter 2 A Computational Grid Scheduling Model to Maximize Reliability Using Modified GA 16 ZahidRaza, Jawaharlal Nehru University, India Deo Prakash Vidyarthi, Jawaharlal Nehru University, India This paper presents a grid scheduling model to schedule a job on the grid with the objective of ensuring maximum reliability to the job under the current grid state. The model schedules a modular job to those resources that suit the job requirements in terms of resources while offering the most reliable environ ment. The reliability estimates depict true grid picture and considers the contribution of the computational resources, network links and the application awaiting allocation. The scheduling executes the interac tive jobs while considering the looping structure. As scheduling on the grid is an NP hard problem, soft computing tools are often applied. This paper applies Modified Genetic Algorithm (MGA), which is an elitist selection method based on the two threshold values, to improve the solution. The MGA works on
3 the basis of partitioning the current population in three categories: the fittest chromosomes, average fit chromosomes and the ones with worst fitness. The worst are dropped, while the fittest chromosomes of the current generation are mated with the average fit chromosomes of the previous generation to produce offspring. The simulation results are compared with other similar grid scheduling models to study the performance of the proposed model under various grid conditions. Chapter 3 A Novel System Oriented Scheduler for Avoiding Haste Problem in Computational Grids 36 Ahmed I. Saleh, Mansoura University, Egypt Scheduling is an important issue that must be handled carefully to realize the "Just login to compute" principle introduced by computational grids. Current grid schedulers sufferfrom the haste problem, which is the inability to schedule all tasks successfully. Accordingly, some tasks fail to complete execution as they are allocated to unsuitable workers. Others may not start execution as suitable workers are previ ously allocated to other tasks. This paper introduces the scheduling haste problem and presents a novel high throughput grid scheduler. The proposed scheduler selects the most suitable worker to execute an input grid task. Hence, it minimizes the turnaround time for a set of grid tasks. Moreover, the scheduler is system oriented and avoids the scheduling haste problem. Experimental results show that the proposed scheduler outperforms traditional grid schedulers as it introduces better scheduling efficiency. Chapter 4 Dynamic Dependent Tasks Assignment for Grid Computing 58 Meriem Meddeber, University ofmascara, Algeria Belahbas Yagoubi, University of Oran, Algeria Acomputational grid is a widespread computingenvironmentthatprovides huge computational powerfor largescale distributed applications. One ofthe most important issues in such an environment is resource management. Task assignment as a part of resource management has a considerable effect on the grid middleware performance. In grid computing, task execution time is dependent on the machine to which it is assigned, and task precedence constraints are represented by a directed acyclic graph. This paper proposes a hybrid assignment strategy of dependent tasks in Grids which integrate static and dynamic assignment technologies. Grid computing is considered a set of clusters formed by a set of computing elements and a cluster manager. The main objective is to arrive at a method of task assignment that could achieve minimum response time and reduce the transfer cost, inducing by the tasks transfer respecting the dependency constraints. Section 3 Algorithms and Optimization Chapter 5 An Algorithm for Task Scheduling in Heterogeneous Distributed Systems Using Task Duplication 75 Amrit Agrawal, Jaypee University ofinformation Technology, India Pranay Chaudhuri, Jaypee University ofinformation Technology, India Task scheduling in heterogeneous parallel and distributed computing environment is a challenging problem. Applications identified by parallel tasks can be represented by directedacyclic graphs (DAGs). Scheduling refers to the assignment ofthese parallel tasks on a set of bounded heterogeneous processors
4 connected by high speed networks. Since task assignment is an NPcomplete problem, instead of find ing an exact solution, scheduling algorithms are developed based on heuristics, with the primary goal of minimizing the overall execution time of the application or schedule length. In this paper, the overall execution time (schedule length) of the tasks is reduced using task duplication on top of the Critical PathOnaProcessor (CPOP) algorithm. Chapter 6 ACO Based Dynamic Scheduling Algorithm for RealTime Multiprocessor Systems 85 Apurva Shah, GHPatel College ofengg & Tech, India Ketan Kotecha, Nirma University, India The Ant Colony Optimization (ACO) algorithms are computational models inspired by the collective foraging behavior of ants. The ACO algorithms provide inherent parallelism, which is very useful in multiprocessor environments. They provide balance between exploration and exploitation along with robustness and simplicity of individual agent. In this paper, ACO based dynamic scheduling algorithm for homogeneous multiprocessor realtime systems is proposed. The results obtained during simulation are measured in terms of Success Ratio (SR) and Effective CPU Utilization (ECU) and compared with the results of Earliest Deadline First (EDF) algorithm in the same environment. It has been observed that the proposed algorithm is very efficient in underloaded conditions and it performs very well dur ing overloaded conditions also. Moreover, the proposed algorithm can schedule some typical instances successfully which are not possible to schedule using EDF algorithm. Chapter 7 Performance Analysis of Sequential and Parallel Neural Network Algorithm for Stock Price Forecasting 97 Rashedur M. Rahman, North South University, Bangladesh Ruppa K. Thulasiram, University ofmanitoba, Canada Parimala Thulasiraman, University ofmanitoba, Canada The neural network is popular and used in many areas within the financial field, such as credit authoriza tion screenings, regularities in security price movements, simulations of market behaviour, and so forth. In this research, the authors use a neural network technique for stock price forecasting of Great West Life, an insurance company based in Winnipeg, Canada. The Backpropagation algorithm is a popular algorithm to train a neural network. However, one drawback of traditional Backpropagation algorithm is that it takes a substantial amount of training time. To expedite the training process, the authors design and develop different parallel and multithreaded neural network algorithms. The authors implement parallel neural network algorithms on both shared memory architecture using OpenMP and distributed memory architecture using MPI and analyze the performance of those algorithms. They also compare the results with traditional autoregression model to establish accuracy. Chapter 8 Dynamic Rightsizing with QualityControlled Algorithms in Virtualization Environments 122 MingJeng Yang, Mackay Medical College, Taiwan ChinLin Kao, National Taiwan Normal University, Taiwan YaoMing Yeh, National Taiwan Normal University, Taiwan Virtual ization and partitioning are the means by which multiple application instances can share and run multiple virtual machines supported by a platform. In a Green Cloud environment, the goal is consolidate multiple applications onto virtual machines associated by fewer servers, and reduce cost to
5 Mahabad, Saghez, and complexity, increase agility, and lower power and cooling costs. To make Cloud center greener, it is beneficial to limit the amount of active servers to minimize energy consumption. This paper presents a precise model to formulate the rightsizing and energysaving mechanism, which not only minimizes energy consumption of the server but also maintains a service quality through the Mt/M/Vt strategy of queuing theory. The authors map the complicated formula of the energysaving mechanism to an ap proximation equation and design the fast decidable algorithms for calculating the right size of virtual machines in constant time complexity for power management systems. Chapter 9 Location Update Improvement Using Fuzzy Logic Optimization in Location Based Routing Protocols in MANET Amjad Osmani, Islamic Azad University Iran Abolfazl Toroghi Haghighat, Islamic Azad University Qazvin, Iran Shirin Khezri, Islamic Azad University Iran Several positionbased routing protocols have been developed for mobile ad hoc networks. Many of these protocols assume that a location service is available which provides the network. This paper introduces a new schema in management of mobile nodes location in mobile ad hoc networks. Fuzzy logic optimization is applied to a better management of location update operation in hierarchical location services. Update management overhead is decreased without significant loss of query success probability. Onehopchaintechnique is used for Auto compensation. A new composed method can update mobile nodes location when the nodes cross a grid boundary. The proposed method 138 location information on the nodes in uses a dynamic grid area that solves the pingpong problem between grids. Simulation results show that these methods are effective. The algorithms are distributed and can keep scalability in the scenario of increasing nodes density. The described solutions are not limited to a special network grid ordering, and can be used in every hierarchical ordering like GLS if the ordering can be mappable on these methods. Chapter 10 Performance Evaluation of Reactive Routing in Mobile Grid Environment 159 L. Shrivastava, Madhav Institute of Technology and Science, Gwalior, India G. S. Tomar, Machine Intelligence Research Labs, India S. S. Bhadanria, Madhav Institute oftechnology and Science, India Grid computing came into existence as a manner of sharing heavy computational loads among multiple computers to be able to compute highly complex mathematical problems. The grid topology is highly flexible and easily scalable, allowing users to join and leave the grid without the hassle of time and resourcehungry identification procedures, having to adjust their devices or install additional software. The goal of grid computing is described as "to provide flexible, secure and coordinated resource sharing among dynamic collections of individuals, institutions and resources". AODV is an ondemand (reac tive) algorithm capable of both unicast and multicast routing. In this paper, AODV has been modified by varying some of the configuration parameters used in this algorithm to improve its performance. This modified protocol i.e. AAODV (advanced ad hoc on demand distance vector) has been compared with AODV in grid environment. The simulations have shown that AAODV is able to achieve high throughput and packet delivery ratio and average endtoend delay is reduced.
6 Universite Universite Saghez, Chapter 11 An Intelligent Sensor Placement Method to Reach a High Coverage in Wireless Sensor Networks 168 Shirin Khezri, Islamic Azad University Mahabad, Iran Karim Faez, Amirkabir University of Technology, Iran Amjad Osmani, Islamic Azad University Iran Adequate coverage is one of the main problems for Sensor Networks. The effectiveness of distributed wireless sensor networks highly depends on the sensor deployment scheme. Optimizing the sensor deployment provides sufficient sensor coverage and saves cost of sensors for locating in grid points. This article applies the modified binary particle swarm optimization algorithm for solving the sensor placement in distributed sensor networks. PSO is an inherent continuous algorithm, and the discrete PSO is proposed to be adapted to discrete binary space. In the distributed sensor networks, the sensor placement is an NPcomplete problem for arbitrary sensor fields. One of the most important issues in the research fields, the proposed algorithms will solve this problem by considering two factors: the complete coverage and the minimum costs. The proposed method on sensors surrounding is examined in different area. The results not only confirm the successes of using the new method in sensor place ment, also they show that the new method is more efficiently compared to other methods like Simulated Annealing(SA), PBIL and LAEDA. Section 4 High Performance Computing Chapter 12 High Performance Computing Design by Code Migration for Distributed Desktop Computing Grids 185 Makoto Yoshida, Okayama University ofscience, Japan Kazumine Kojima, Okayama University ofscience, Japan Large scale loosely coupled PCs can organize clusters and form desktop computing grids on sharing each processing power; power of PCs, transaction distributions, network scales, network delays, and code migration algorithms characterize the performance of the computing grids. This article describes the design methodologies ofworkload management in distributed desktop computing grids. Based on the code migration experiments, transfer policy for computation was determined and several simulations for location policies were examined, and the design methodologies for distributed desktop computing grids are derived from the simulation results. The language for distributed desktop computing is designed to accomplish the design methodologies. Chapter 13 Parallelization of LittlewoodRichardson Coefficients Computation and its Integration into the BonjourGrid MetaDesktop Grid Middleware 204 Heithem Abbes, University of Tunis, Franck Butelle, LIPN/UMR 7030 Christophe Cerin, LIPN/UMR 7030 Tunisia Paris 13, France Paris 13, France This paper shows how to parallelize a compute intensive application in mathematics (Group Theory) for an institutional Desktop Grid platform coordinated by a metagrid middleware named BonjourGrid. The paper is twofold: it shows how to parallelize a sequential program for a multicore CPU which partici
7 pates in the computation; and it demonstrates the effort for launching multiple instances of the solutions for the mathematical problem with the BonjourGrid middleware. BonjourGrid is a fully decentralized Desktop Grid middleware. The main results of the paper are: a) an efficient multithreaded version of a sequential program to compute LittlewoodRichardson coefficients, namely the MultiLR program and b) a proofof concept, centered around the user needs, for the BonjourGrid middleware dedicated to coordinate multiple instances ofprogramsfor Desktop Grids and with the help of MultiLR. In this paper, the scientific work consists in starting from a model for the solution of a compute intensive problem in mathematics, to incorporate the concrete model into a middleware and running it on commodity PCs platform managed by an innovative meta Desktop Grid middleware. Chapter 14 Structural Outlooks for the OTISArrangement Network 221 AhmadAwwad, Fahad Bin Sultan University, Saudi Arabia JehadAiSadi, Arab Open University, Jordan Bassam Haddad, University ofpetra, Jordan Ahmad Kayed, Fahad Bin Sultan University, Saudi Arabia Recent studies have revealed that the Optical Transpose Interconnection Systems (OTIS) are promising candidates for future highperformance parallel computers. This paper presents and evaluates a general method for algorithm development on the OTISArrangement network (OTISAN) as an exampleofotis network. The proposed method can be used and customized for any other OTIS network. Furthermore, it allows efficient mapping of a wide class of algorithms into the OTISAN. This method is based on grids and pipelines as popular structures that support a vast body of parallel applications including linear algebra, divideandconquer types of algorithms, sorting, and FFT computation. This study confirms the viability of the OTISAN as an attractive alternative for largescale parallel architectures. Chapter 15 Energy Efficient Packet Data Service in Wireless Sensor Network in Presence of Rayleigh Fading 232 Amah Nandi, National Institute of Technology Durgapur, India Sumit Kimdu, National Institute of Technology Durgapur, India Energy level performances of three packet delivery schemes in Wireless Sensor Networks (WSN) are evaluated in presence of Rayleigh fading. Three different information delivery mechanisms are investigated using regenerative relays with or without error correction capability. Energy consumption for successful delivery of a data packet for each mechanism is evaluated and compared under several conditions of node density, bit rate, transmit power, and channel fading. Energy efficiencies of different retransmission schemes are also evaluated. Further, an optimal packet length based on energy efficiency is derived. Impact of optimal packet size on average number of retransmission and total energy expen diture is analyzed for each delivery scheme. Chapter 16 Cost Efficient Implementation of Multistage Symmetric Repackable Networks 246 Amitabha Chababarly, Dublin City University, Ireland Martin Collier, Dublin City University, Ireland Symmetric rearrangeable networks (SRN)(Chakrabarty, Collier, & Mukhopadhyay, 2009) make efficient use of hardware, but they have the disadvantage of momentarily disrupting the existing communications during reconfiguration. Path continuity is a major issue in some application of rearrangeable networks.
8 Using repackable networks (Yanga, Su, & Pin, 2008) is a solution to the path continuity problem in SRN. These networks provide functionality comparable to that of strict sense no blocking networks (SNB) but with minimum increase in the hardware than SRN. This paper proposes an efficient implementa tion of multistage symmetric repackable networks requiring optimum hardware cost than the method proposed in the literature. Cost optimization is achieved through the use of minimum number of bypass link(s). Investigated method works for networks built with more than three switching stages and shows promise of scalability. Chapter 17 Using Machine Learning Techniques for Performance Prediction on MultiCores 259 Jitendra Kumar Rai, ANURAG, Hyderabad, India Atul Negi, University of Hyderabad, India Rajeev Wankar, University ofhyderabad, India Sharing of resources by the cores of multicore processors brings performance issues for the system. Majority of the shared resources belong to memory hierarchy subsystem of the processors such as last level caches, prefetches and memory buses. Programs corunning on the cores of a multicore processor may interfere with each other due to usage of such shared resources. Such interference causes corunn ing programs to suffer with performance degradation. Previous research works include efforts to character ize and classify the memory behaviors of programs to predict the performance. Such knowledge could be useful to create workloads to perform performance studies on multicore processors. It could also be utilized to form policies at system level to mitigate the interference between corunning programs due to use of shared resources. In this work, machine learning techniques are used to predict the performance on multicore processors. The main contribution of the study is enumeration of solorun program attributes, which can be used to predict concurrentrun performance despite change in the number of corunning programs sharing the resources. The concurrentrun involves the interference between corunning pro grams due to use of shared resources. Chapter 18 Performance Evaluation of Full Diversity QOSTBC MIMO Systems with Multiple Receive Antenna Hardip K. Shah, Dharmsinh Desai University, India Tejal N. Parmar, Dharmsinh Desai University, India Nikhil Kothari, Dharmsinh Desai University, India 274 K. S. Dasgupta, Indian Institute of Space Science and Technology, India Multipath fading is inherent in wireless communication systems. Diversity is the technique which takes advantage of multipath to mitigate the effect of fading and increase signal strength. Space Time Block codes (STBC) are used in MIMO systems to improve the performance by maximizing transmit and/or receive diversity. Among different schemes based on STBC, Quasi Orthogonal Space Time Block Code (QOSTBC) is able to achieve full rate transmission for more than two transmit antennas. Constellation Rotation QOSTBC (CRQOSTBC) achieves full diversity and improves performance further along with full rate, to overcome the limitation of QOSTBC, which is unable to maintain orthogonality amongst the codes transmitted by different antennas. Higher diversity can be achieved by increasing uncorrelated paths between transmitter and receivers using higher number of receive antennas. This paper examines improvement in BER with reference to a number ofreceive antennas. Simulations were carried out under ideal as well as realistic environments, using least square technique with four antennas at transmitter side and variable receive antennas. Results of simulations presented in this paper indicate performance improvement of CRQOSTBC over QOSTBC in flat fading channel environment. Simulation results also show performance degradation in BER when channel is estimated at the receiver.
9 Section 5 Applications Chapter 19 On Construction of Cluster and Grid Computing Platforms for Parallel Bioinformatics Applications 286 ChaoTiing Yang, Timghai University, WenChung Shih, Asia University, Taiwan Taiwan Biology databases are diverse and massive. As a result, researchers must compare each sequence with vast numbers of other sequences. Comparison, whether of structural features or protein sequences, is vital in bioinformatics. These activities require highspeed, highperformance computing powerto search through and analyze large amounts of data and industrialstrength databases to perform a range of dataintensive computing functions. Grid computing and Cluster computing meet these requirements. Biological data exist in various web services that help biologists search for and extract useful information. The data formats produced are heterogeneous and powerful tools are needed to handle the complex and difficult task of integrating the data. This paper presents a review of the technologies and an approach to solve this problem using cluster and grid computing technologies. The authors implement an experimental distributed computing application for bioinformatics, consisting of basic highperformance computing environments (Grid and PC Cluster systems), multiple interfaces at user portals that provide useful graphical interfaces to enable biologists to benefit directly from the use of highperformance technology, and a translation tool for converting biology data into XML format. Chapter 20 Migrating Android Applications to the Cloud 307 ShihHao Hung, National Taiwan University, Taiwan JengPeng Shieh, National Taiwan University, Taiwan ChenPang Lee, National Taiwan University, Taiwan Recently, smartphone technologies have evolved quickly and offered end users the computing power and networking capabilities required to perform useful network and multimedia applications. However, due to limited physical sizes and battery capacities, the current generation of smartphones cannot yet fulfill the requirements of sophisticated applications ofwhich personal computers are capable. One way to solve this problem is to minimize the workload on a smartphone as much as possible by offloading portions of an application to a server. The solution is particularly attractive today as cloud computing provides the needed server resources at relatively low costs. This paper proposes a novel, lightweight application migration mechanism for the users of smartphones to suspend the execution of applications and offload them to the cloud. The authors also developed a framework to perform Android applications efficiently with virtual phones in the cloud with a virtual storage. This paper discusses the migration mechanism and evaluates its effectiveness on the Android smartphone. This approach may effectively offload workload for Android applications even with lowspeed mobile network.
10 Chapter 21 A Grid and Cloud Based System for Data Grouping Computation and Online Service 323 WingNingLi, University ofarkansas, USA Donald Hayes, University ofarkansas, USA, Jonathan Bar an, University ofarkansas, USA Cameron Porter, Acxiom Corporation, USA Tom Schweiger, Acxiom Corporation, USA Record linkage deals with finding records that identify the same real world entity, such as an individual or a business, from a given file or set of files. Record linkage problem is also referred to as the entity resolution or record recognition problem. To locate those records identifying the same real world entity, in principle, pairwise record analyses have to be performed among all records. Analytical operations between two records vary from comparing correspondingfields to enhancing records through large knowl edge bases and querying large databases. Hence, these operations are complex and take time. To reduce the number of pairwise record comparisons, blocking techniques are introduced to partition the records into blocks. After that records in each block are analyzed against one and another. One of the effective blocking methods is the closure approach, where a "related" equivalence relation is used to partition the records into equivalence classes. This paper introduces the closure problem and describes the design and implementation ofa parallel and distributed closure prototype system running in an enterprise grid. Compilation of References 337 About the Contributors 362 Index 368
Green-Cloud: Economics-inspired Scheduling, Energy and Resource Management in Cloud Infrastructures Rodrigo Tavares Fernandes firstname.lastname@example.org Instituto Superior Técnico Avenida Rovisco
Institut für Technische Informatik und Kommunikationsnetze Kirila Adamova Anomaly Detection with Virtual Service Migration in Cloud Infrastructures Master Thesis 263-8-L October 22 to March 23 Tutor: Dr.
IEEE COMMUNICATIONS SURVEYS ACTIVE NETWORKS: APPLICATIONS, SECURITY, SAFETY, AND ARCHITECTURES KONSTANTINOS PSOUNIS STANFORD UNIVERSITY ABSTRACT Active networks represent a new approach to network architecture.
Journal of Computer and System Sciences 78 (2012) 1330 1344 Contents lists available at SciVerse ScienceDirect Journal of Computer and System Sciences www.elsevier.com/locate/jcss Cloud federation in a
Escola Tècnica Superior d Enginyeria Departamento d Arquitectura de Computadors i Sistemas Operatius P2P-VoD on Internet: Fault Tolerance and Control Architecture Thesis submitted by Rodrigo Godoi under
Energy-aware joint management of networks and cloud infrastructures Bernardetta Addis 1, Danilo Ardagna 2, Antonio Capone 2, Giuliana Carello 2 1 LORIA, Université de Lorraine, France 2 Dipartimento di
Resource Management for Scientific Application in Hybrid Cloud Computing Environments Dissertation by Simon Ostermann submitted to the Faculty of Mathematics, Computer Science and Physics of the University
Cost aware real time big data processing in Cloud Environments By Cristian Montero Under the supervision of Professor Rajkumar Buyya and Dr. Amir Vahid A minor project thesis submitted in partial fulfilment
Journal of Computing and Information Technology - CIT 19, 2011, 1, 25 55 doi:10.2498/cit.1001864 25 A Review on Cloud Computing: Design Challenges in Architecture and Security Fei Hu 1, Meikang Qiu 2,JiayinLi
Masaryk University Faculty of Informatics Master Thesis Database management as a cloud based service for small and medium organizations Dime Dimovski Brno, 2013 2 Statement I declare that I have worked
SOFTWARE ENGINEERING Key Enabler for Innovation NESSI White Paper Networked European Software and Services Initiative July 2014 Executive Summary Economy and industry is experiencing a transformation towards
A METHOD FOR MINIMIZING COMPUTING CORE COSTS IN CLOUD INFRASTRUCTURES THAT HOST LOCATION-BASED ADVERTISING SERVICES A Thesis Presented to the Faculty of San Diego State University In Partial Fulfillment
Analysis of server utilization and resource consumption of the Google data centre trace log Robert Mugonza MSc Advanced Computer Science 2012/2013 The candidate confirms that the work submitted is their
JANUARY 2013 REPORT OF THE DEFENSE SCIENCE BOARD TASK FORCE ON Cyber Security and Reliability in a Digital Cloud JANUARY 2013 Office of the Under Secretary of Defense for Acquisition, Technology, and Logistics
Network Monitoring with Software Defined Networking Towards OpenFlow network monitoring Vassil Nikolaev Gourov Master of Science Thesis Network Architectures and Services Faculty of Electrical Engineering,
J. Parallel Distrib. Comput. 64 (2004) 238 253 A new fuzzy-decision based load balancing system for distributed object computing $ Yu-Kwong Kwok and Lap-Sun Cheung Department of Electrical and Electronic
JAVA-BASED INTELLIGENT NETWORK MONITORING by Haifeng Xi Thesis submitted to the Faculty of the Graduate School of the University of Maryland at College Park in partial fulfillment of the requirements for
February 2009 Seeding the Clouds: Key Infrastructure Elements for Cloud Computing Page 2 Table of Contents Executive summary... 3 Introduction... 4 Business value of cloud computing... 4 Evolution of cloud
Customer Cloud Architecture for Big Data and Analytics Executive Overview Using analytics reveals patterns, trends and associations in data that help an organization understand the behavior of the people
MASARYK UNIVERSITY FACULTY OF INFORMATICS Best Practices in Scalable Web Development MASTER THESIS Martin Novák May, 2014 Brno, Czech Republic Declaration Hereby I declare that this paper is my original
HP Performance Engineering Best Practices Series for Performance Engineers and Managers Performance Monitoring Best Practices Document Release Date: 201 Software Release Date: 2014 Legal Notices Warranty
HP Performance Engineering Best Practices Series for Performance Engineers and Managers Performance Monitoring Best Practices Document Release Date: May 2009 Software Release Date: May 2009 Legal Notices
Enhancing Data Center Sustainability Through Energy Adaptive Computing Krishna Kant, George Mason University Muthukumar Murugan, University of Minnesota David H.C. Du, University of Minnesota The sustainability
Monitoring Services in a Federated Cloud - The RESERVOIR Experience Stuart Clayman, Giovanni Toffetti, Alex Galis, Clovis Chapman Dept of Electronic Engineering, Dept of Computer Science, University College
The Definitive Guide tm To Cloud Computing Ch apter 10: Key Steps in Establishing Enterprise Cloud Computing Services... 185 Ali gning Business Drivers with Cloud Services... 187 Un derstanding Business