A framework-based approach to support dynamic adaptation of web server clusters

Size: px
Start display at page:

Download "A framework-based approach to support dynamic adaptation of web server clusters"

Transcription

1 10th Brazilian Workshop on Real-Time and Embedded Systems 69 A framework-based approach to support dynamic adaptation of web server clusters Vinicius Petrucci 1, Orlando Loques 1 1 Instituto de Computação Universidade Federal Fluminense (UFF) Niterói RJ Brazil Abstract. Due to environmental and economic reasons, dynamic adaptation approaches to optimize the energy consumption of web server clusters are being intensively investigated. In this context, we present a framework-based solution, where adaptations are carried out in accordance with an adaptation logic specified in terms of high-level architectural contracts. The support infrastructure required for the contracts follows a standard implementation pattern, uses a set of reusable basic architectural configuration operators and shares monitoring functions common to this class of adaptive applications. 1. Introduction Due to environmental and economic reasons, dynamic adaptation approaches to optimize the energy consumption of web servers implemented by clusters of processors are being intensively investigated. This kind of optimization can be achieved by selecting the best processor set operational configuration that can fulfill other additional requirements of the web server application, such as requests response time or a given requests per second execution rate. A basic approach is to switch-off processors in periods of low server activity and switch-on them back when the demand increases. Additionally, one can take advantage of the (DVFS) Dynamic Voltage and Frequency Scaling capability of current processor architectures to further optimize the cluster energy consumption. The implementation of these approaches follows the autonomic computing closed loop control paradigm: monitor and collect system quality measures, process and evaluate them, execute a procedure to select the best configuration and impose the chosen configuration over the cluster architecture. The case of energy consumption in server clusters has been widely discussed and various policies and algorithms for cluster power management are being investigated [Elnozahy et al. 2002, Rusu et al. 2006, Bertini et al. 2008]. In the investigation stage, the main goals are to implement, refine and evaluate a particular optimization technique. Commonly, the required support mechanisms are implemented in an ad hoc fashion by members of the research team investigating the particular approach. As a consequence, the adaptation logic is mixed with the server implementation and the expertise about the implementation issues is retained in the team realm. This has some implications, e.g., (i) makes difficult to reuse the basic implementation to experiment with different optimization techniques; (ii) in the medium term, when the system goes to a real operational environment, hinders system maintenance and evolution activities. We are developing a framework-based solution for dynamic adaptation of web server clusters, where adaptations are carried out in accordance with an adaptation policy separately

2 70 10th Brazilian Workshop on Real-Time and Embedded Systems specified in terms of high-level architectural contracts. The support infrastructure required for the contracts follows a standard design pattern, uses a set of reusable basic architectural configuration operators and shares a standard infrastructure (including monitoring functions) common to this class of adaptive applications. By enabling reuse of significant parts of the adaptation infrastructure, besides facilitating the evaluation of different techniques, our framework may reduce the cost of development and improve the reliability of this class of adaptive applications. 2. Approach Our framework relies on an abstract architectural model to (i) specify and monitor run-time properties of an executing application configuration, (ii) evaluate the model for application s requirements violation and (iii) perform adaptations to maintain the application configuration within acceptable bounds of behavior. Dynamic adaptations of applications are carried out in accordance with an external adaptation logic specified in terms of a high-level architectural contract language, which has the following main elements [Loques et al. 2004]: Profiles represent conditions associated with architectural properties and define a predicate that determines whether one or more architectural properties (e.g., server s utilization) are valid (e.g., above some threshold). Typically, profiles are used to identify application conditions for triggering adaptations; Adaptation services specify the adaptation logic that should be applied to move an application away from an undesirable condition. For example, a cluster-based web application might have a performance profile (e.g., server s request response time bellow some threshold). Upon validating it, an adaptation service associated with this profile may increase the application s capacity by adding a new server. Adaptation services use abstract adaptation operators which are mapped to application-specific operators at run-time. Specifically, the application-level operators may be as primitive as operating system calls to stop and start processes, or may be specifically built using APIs provided by the application support level (in our case the Apache web server); Finally, a negotiation clause can be specified (by a transition system or by utility functions associated with the adaptation services) to explicitly establish a particular order to deploy the adaptation services [Petrucci and Loques 2007]. Our adaptation supporting infrastructure, depicted in Figure 1, is composed by a standard set of components: Contract Manager (CM) interprets the contracts and extracts from them the information regarding the adaptation services, respective profiles and the negotiation description. Periodically, profiles associated with adaptation services are evaluated and an adaptation service may be triggered if the respective profile is valid. In the case of two or more conflicting adaptation options, the decision of which adaptation service to use is guided by the negotiation specification; Contractor manages and mediates the monitoring process of the properties specified in the profiles. A Contractor interacts with Sensors to obtain and evaluate the measured values of the properties. Violations and validations of the profiles are notified to the CM. To deal with transient or stochastic properties, we rely on Filters components attached to Contractor. For example, a particular filter component can either adopt an exponential moving-average (EMA), which is a well-known technique to smooth measurement readings, or use a predictive filtering technique to identify trends in measurements. The latter intends to enable anticipatory adaptations [Poladian et al. 2007];

3 10th Brazilian Workshop on Real-Time and Embedded Systems 71 Configurator is the element responsible for mapping adaptation services into actions that configure the application architecture. Configurator interacts with Actuators that represent the individual mechanisms necessary to implement application-specific adaptation actions, e.g., allocation of a new server in a cluster. Translators entities are used to help with the mapping of information across the abstraction gap from the contract/architecture layer to the application layer. Contract/Architecture Layer adaptations Contract Manager notifications Configurator Translators profiles Contractor Filters Actuators API Sensors Application Layer Application Figure 1. Adaptation framework. 3. Clustered web application Our example application uses dynamic adaptation capabilities to maintain two correlated objectives. First, we aim to guarantee some quality of service requirements for the cluster (e.g., by controlling average cluster load or request response time). Second, to reduce energy costs, the set of currently active servers and their respective processor s speeds should be managed to achieve some goal related to power consumption Architecture description The architecture (shown in Figure 2) consists of a cluster of replicated web servers. The cluster presents a single view to the clients through a special component termed ServerCluster (also called front-end or load balancer), which distributes incoming requests among the actual Servers that process the requests (also known as back-ends or workers). Client 1... ServerCluster Server 1... Client N Server N Figure 2. Architecture of the web application. The architecture description is translated to an abstract representation of the current cluster configuration. Specifically, a cluster configuration is represented by a set of tuples,

4 72 10th Brazilian Workshop on Real-Time and Embedded Systems where each tuple is defined by (i, j) conf, where i N represents a server component reference, such as N is the number of total servers in the cluster, and j {0} F i represents the state of server i, where F i is the set of discrete frequencies (steps) available in the server processors. If j is equal to zero, then server i is inactive, otherwise server i is active and its processor is operating in frequency step j. We also consider the special case of server failure, when j is set to 1. We define an auxiliary function max_freq : i F i to return the maximum frequency step of server i, and function state : i j to return the current state of server i. One example of a cluster configuration, where N = 3, is conf = {(1, 0), (2, 3), (3, 2)}, which means that server 1 is turned off, server 2 is operating at frequency step 3, and server 3 at frequency step 2. In the architecture model, we represent the current cluster configuration as a property (termed currentconf ) of ServerCluster component Contracts In order to guarantee the application s quality requirements, we specify a set of adaptation services to be performed in response to changes in the execution environment of the application (e.g., workload variation, and resource availability). A simple and effective way to identify an undesirable state in which adaptations should be carried out is to define bounds for specific application properties, such as cluster utilization above X% or requests delay above Y seconds. The quality attributes are defined using profiles in the contracts. In the examples that we implemented, we measured the cluster quality in terms of what we call cluster utilization, which refers to the ratio of the actual number of requests per second (req/s) received by the cluster to the maximum number of requests that the current cluster configuration is able to process per second. In order to keep the request execution rate within acceptable levels, we define two thresholds low and high (corresponding to system under-utilization or saturation, respectively) for the cluster utilization using two profiles (see Figure 3). These profiles are then monitored at run-time by the supporting infrastructure (cf. Section 2). Note that we are not limited to any particular quality attribute. Our framework is designed to enable one to describe in profiles any quality attribute for which bounds can be defined, such as average response time or percentage of deadlines met. For each new profile the Contractor (that is a hot-spot) should be specialized and for each new quality attribute a specific Sensor module has to be developed. profile { webcluster.utilization < T_LOW; } util_low; profile { webcluster.utilization > T_HIGH; } util_high; Figure 3. The minimum and maximum thresholds for the cluster utilization. During the execution of the application, so as to respond to web requests properly when the cluster utilization is high, we have the option to (1) turn on servers to the cluster and (2) to increase the operating frequency of processors. As well, when the cluster utilization is low, to save energy, we can (3) turn off servers in the cluster and (4) reduce the operating frequency of the processors. A decision on the best adaptation will depend on a logic or policy that describes the objectives and expected effects on choice of each adaptation alternative. For example, when the cluster utilization is high, we have to decide the best choice between (a) turning on new servers or (b) increase the operating frequency of the currently active servers, or (c) an optimized combination of adaptations (e.g., turning off a particular server and turning on another with little higher capacity, but more energy efficient). In real cluster

5 10th Brazilian Workshop on Real-Time and Embedded Systems 73 of servers, processors can be heterogeneous adding to increase the number of configuration possibilities Simple contract The contract (described in Figure 4) adopts a simple policy which attempts to increase (or decrease) active servers frequencies up to a maximum (or minimum) and only then turn servers on (or off). It uses two adaptation services termed increasecapacity (lines 02-13) and decreasecapacity (lines 15-25), which are associated with profiles util_high (line 13) and util_low (line 25) to identify the precise conditions for adaptations. At run-time, the profiles are observed at every sampling_period (line 26), which value express a trade-off between responsiveness and overhead. In terms of our contract examples, values in the order of a few seconds were found suitable. 01 contract { 02 adaptation { 03 s = webcluster.nextservertoincfreq() 04 if s!= None: 05 curfreq = webcluster.state(s) 06 webcluster.adjustserverfreq(curfreq+1) 07 else: 08 s = webcluster.nextservertoadd() 09 if s!= None: 10 webcluster.turnserveron(s) 11 else: 12 warn("no more servers to turn on") 13 } increasecapacity with util_high settling_time 3000/*ms*/; 14 adaptation { 15 s = webcluster.nextservertodecfreq() 16 if s!= None: 17 curfreq = webcluster.state(s) 18 webcluster.adjustserverfreq(curfreq-1) 19 else: 20 s = webcluster.nextservertorem() 21 if s!= None: 22 webcluster.turnserveroff(s) 23 else: 24 warn("no more servers to turn off") 25 } decreasecapacity with util_low settling_time 3000/*ms*/; 26 } simplepolicy sampling_period 2000 /*ms*/; Figure 4. Contract expressing a simple dynamic power management policy. Another design issue addressed in the contract language is related to the proper time to perceive the adaptation effect to avoid oscillation between two (or more) competing adaptation services. Specifically, we assume that each adaptation service can be specified with a time window to indicate how long to wait before we could expect to observe the stabilized conditions of the executed adaptation (see settling_time operators in Figure 4 lines 13 and 25). If the time window value for the settling_time operator is well dimensioned, it would enable to achieve the desirable hysteresis (lag) effect between triggering adaptations. In [Cheng and Garlan 2007], a similar technique was adopted to address this particular aspect. Note that the thresholds used in the contract profiles should be selected based on an appropriate range to help prevent oscillatory behavior. This contract uses the following operations to query the state of the architecture model:

6 74 10th Brazilian Workshop on Real-Time and Embedded Systems nextservertoincfreq() / nextservertodecfreq(): These operations find and return a server reference in the current cluster configuration which has a frequency feasible to be increased (or decreased) discretely. In the case of not finding any server (i.e., all active servers are at maximum or minimum speed), None is returned; nextservertoadd() / nextservertorem(): These operations are used to find and return a server reference in the current cluster configuration available to be turned on (or off). In the case of not finding any server, None is returned. The above adaptation operators are based on a previously ordered list of servers. In particular, the servers are previously ordered by power efficiency, which is defined by the ratio of power consumption vs. performance, where power consumption is measured in watt and performance in requests per second (req/s). That is, the servers are increasingly ordered by those which consume less energy per request (i.e., joule / req). The information about power consumption of our cluster machines is the same used in [Bertini et al. 2008]. The operation nextservertoincfreq, for example, iterates over a list ordered in ascendent order to find a server reference which is turned on and is not operating at maximum frequency step. The next operations effect changes to the architectural model: turnserveron(server) / turnserveroff(server): These operations are used to turn machines on and off in the cluster. In practice, the load balancing mechanism must be aware of the new state of the servers in the cluster (i.e., booting or shutdown) so that it does not redirect requests to inoperable servers; adjustserverfreq(server, freq): This operation dynamically adjusts the frequencies of servers in the cluster. As we can dynamically change the computational power of servers, the load balancer must adopt a strategy to effectively balance the load among servers; for example, a dynamic weighted round robin (DWRR) scheme Contract using a general decision function Here, we describe a more complex contract based on a function used to dynamically choose the best cluster configuration, i.e., which processors should be active and their operating frequencies. As shown in Figure 5, alternatively to the simple contract presented previously, we define an unique adaptation service named adjustcapacity (lines 02-13), which joins the two adaptations increase/decreasecapacity into one. The profiles util_low and util_high used to identify when to trigger the adaptation based on cluster utilization are merged (by operator "or") and associated with the respective adaptation service (see line 13). In the specification of the adjustcapacity adaptation (lines in Figure 5), we first calculate the demand related to the current cluster load (line 03). In the case of the cluster utilization rises above the predefined quality bound (i.e., profile util_high is valid), we need to regulate the demand by a factor respecting to the maximum cluster utilization threshold. That is, we correct the demand value by normalizing it to the T_HIGH preset limit to archive the desired utilization bound (see line 04). Next, we execute the bestconfig function (line 05) to select the best cluster configuration, according to the load demand and a configuration model. Then, a loop (lines 06-12) is used to impose the chosen configuration over the application s architecture. More explicitly, the bestconfig operator implements a general configuration model (e.g., linear/integer optimization algorithm could be used) and returns a cluster configuration solution that handles the current workload (represented by demand parameter) and

7 10th Brazilian Workshop on Real-Time and Embedded Systems contract { 02 adaptation { 03 demand = webcluster.load; 04 if util_high: demand = demand / (T_HIGH / 100); 05 changeconf = webcluster.bestconfig(confmodel, demand); 06 for (server,freq) in changeconf: 07 if freq == 0: 08 webcluster.turnserveroff(server); 09 else: 10 if webcluster.state(server) == 0: 11 webcluster.turnserveron(server); 12 webcluster.adjustserverfreq(server,freq); 13 } adjustcapacity with util_low or util_high settling_time 3000/*ms*/; 14 } decisionpolicy sampling_period 2000/*ms*/; Figure 5. Decision-based policy for dynamic power management. minimizes the overall power consumption of the cluster based on active and baseline (or idle) power consumption cost of the set of servers [Bertini et al. 2008]. The solution is given by notation (server, f req) solutionconf, which represents a configuration of servers and their respective status (i.e., its operating frequency or inactive) cf. Section 3.1. Actually, the cluster configuration to be imposed is a difference between the two sets: current cluster configuration (associated with the webcluster architectural component) and the cluster configuration solution. For example, suppose the current configuration is currentconf = {(1, 0), (2, 2), (3, 1)} and the solution configuration is solutionconf = {(1, 0), (2, 1), (3, 4)}. Thus, we need to impose a configuration change given by solutionconf currentconf = changeconf = {(2, 1), (3, 4)}. That is, we need to decrease the frequency of server 2 to step 1, and increase the frequency of server 3 to step Discussion We can now examine how the two contracts reuse our monitoring and adaptation infrastructure. Although each contract captures a particular adaptation logic, they share common monitoring functions and adaptation operators. For instance, the two contracts use the same profiles, so it means that all elements for monitoring were reused. In the application-layer, we reused the sensor used to measure the cluster load (hence, the utilization) property associated with ServerCluster component type. The adaptation operators to query about current cluster configuration were designed specifically for each contract. For example, the operations nextservertoincfreq, nextservertodecfreq, nextservertoadd, and nextservertorem were used only in the simple contract. The bestconfig operator was used just in the decision-based contract. On the other hand, the adaptation operators to change the cluster configuration were reused in both contracts; that is, turnserveron, turnserveroff, and adjustserverfreq operations. 4. Conclusion and future work In previous works we developed a general contract-based framework for supporting adaptive systems [Loques et al. 2004]; other researchers have been experimenting with similar ideas, e.g., [Garlan et al. 2004, Bouchenak et al. 2006]. Here we described a specific use of the framework intended to provide dynamic adaptation support for web server clusters. We have implemented a prototype of our adaptation framework, which was used to implement the web application examples presented in Section 3. Based on these initial experiments,

8 76 10th Brazilian Workshop on Real-Time and Embedded Systems we believe that the approach can simplify the deployment of different energy management policies currently being proposed [Rusu et al. 2006, Bertini et al. 2008]. In other works, we used a set of autonomous contracts (working concurrently), respectively, to manage different aspects of a video conference system architecture [Cardoso et al. 2006] and of a web server architecture [Petrucci and Loques 2007]. Currently, following the separation of concerns paradigm, aiming to improve modularity, we are investigating the use of the same autonomy principle to cater for additional requirements of real web server architectures, such as: (i) Support of multi-layer servers; each layer can be managed by a specific contract. (ii) Processor fault management, required to meet availability requirements. (iii) In a data center [Chandra et al. 2003], several web server clusters each one associated to a different web service (and managed by its own individual contract) can be active at the same time. In this context, a higher level contract can manage the overall processor allocation over the set of web server clusters. Assuming that resource demands vary along time, this could lead to further performance and energy consumption optimizations. The specification and implementation of these autonomous contracts poses a great research challenge. For achieving consistent behavior, conflicts for the use of the shared resources and on the execution of conflicting adaptation policies have to be overcome. We think that the elements of our contract-based framework can help to solve these issues. Acknowledgement. This work has been partially supported by CNPq and Faperj. References Bertini, L., Leite, J., and Mossé, D. (2008). Optimal dynamic configuration in web server clusters. Technical Report RT-1/08, Instituto de Computação Universidade Federal Fluminense. Bouchenak, S., Palma, N. D., Hagimont, D., and Taton, C. (2006). Autonomic management of clustered applications. In Proceedings of the 2006 IEEE International Conference on Cluster Computing, Barcelona, Spain. IEEE Computer Society. Cardoso, L., Sztajnberg, A., and Loques, O. (2006). Self-adaptive applications using adl contracts. In SelfMan, pages Chandra, A., Gong, W., and Shenoy, P. (2003). Dynamic resource allocation for shared data centers using online measurements. In SIGMETRICS 03: Proceedings of the 2003 ACM SIGMETRICS international conference on Measurement and modeling of computer systems, pages , New York, NY, USA. ACM. Cheng, S.-W. and Garlan, D. (2007). Handling uncertainty in autonomic systems. In Proceedings of the International Workshop on Living with Uncertainties (IWLU 07) ASE 07, Atlanta, GA, USA. Elnozahy, E. N., Kistler, M., and Rajamony, R. (2002). Energy-efficient server clusters. In Falsafi, B. and Vijaykumar, T. N., editors, PACS, volume 2325 of Lecture Notes in Computer Science, pages Springer. Garlan, D., Cheng, S.-W., Huang, A.-C., Schmerl, B., and Steenkiste, P. (2004). Rainbow: Architecture-based self adaptation with reusable infrastructure. IEEE Computer, 37(10). Loques, O., Sztajnberg, A., Cerqueira, R. C., and Ansaloni, S. (2004). A contract-based approach to describe and deploy non-functional adaptations in software architectures. Journal of the Brazilian Computer Society, 10(1):5 18. Petrucci, V. and Loques, O. (2007). Suporte a adaptação dinâmica de aplicações usando funções de utilidade. In I Workshop on Pervasive and Ubiquitous Computing, WPUC SBAC-PAD Poladian, V., Garlan, D., Shaw, M., Schmerl, B., Sousa, J. P., and Satyanarayanan, M. (2007). Leveraging resource prediction for anticipatory dynamic configuration. In Proceedings of the First IEEE International Conference on Self-Adaptive and Self-Organizing Systems, SASO-2007, pages Rusu, C., Ferreira, A., Scordino, C., Watson, A., Melhem, R., and Mossé, D. (2006). Energy-efficient real-time heterogeneous server clusters. In RTAS 06: Proceedings of the 12th IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS 06), pages , Washington, DC, USA. IEEE Computer Society.

VINICIUS TAVARES PETRUCCI. A framework for supporting dynamic adaptation of power-aware web server clusters

VINICIUS TAVARES PETRUCCI. A framework for supporting dynamic adaptation of power-aware web server clusters VINICIUS TAVARES PETRUCCI A framework for supporting dynamic adaptation of power-aware web server clusters NITERÓI 2008 VINICIUS TAVARES PETRUCCI A framework for supporting dynamic adaptation of power-aware

More information

USING VIRTUAL MACHINE REPLICATION FOR DYNAMIC CONFIGURATION OF MULTI-TIER INTERNET SERVICES

USING VIRTUAL MACHINE REPLICATION FOR DYNAMIC CONFIGURATION OF MULTI-TIER INTERNET SERVICES USING VIRTUAL MACHINE REPLICATION FOR DYNAMIC CONFIGURATION OF MULTI-TIER INTERNET SERVICES Carlos Oliveira, Vinicius Petrucci, Orlando Loques Universidade Federal Fluminense Niterói, Brazil ABSTRACT In

More information

DEPLOYING QoS CONTRACTS IN THE ARCHITECTURAL LEVEL

DEPLOYING QoS CONTRACTS IN THE ARCHITECTURAL LEVEL Architecture Description Languages 19 DEPLOYING QoS CONTRACTS IN THE ARCHITECTURAL LEVEL Sidney Ansaloni 1, Alexandra Sztajnberg 2, Romulo C. Cerqueira 1, Orlando Loques 1 1 Institute de Computagdo - Universidade

More information

Adaptation Issues in Software Architectures of Remote Health Care Systems

Adaptation Issues in Software Architectures of Remote Health Care Systems Adaptation Issues in Software Architectures of Remote Health Care Systems Orlando Loques Instituto de Computação Universidade Federal Fluminense (UFF) Niterói, RJ, Brazil loques@ic.uff.br Alexandre Sztajnberg

More information

A dynamic optimization model for power and performance management of virtualized clusters

A dynamic optimization model for power and performance management of virtualized clusters A dynamic optimization model for power and performance management of virtualized clusters Vinicius Petrucci, Orlando Loques Univ. Federal Fluminense Niteroi, Rio de Janeiro, Brasil Daniel Mossé Univ. of

More information

Thesis Proposal: Dynamic optimization of power and performance for virtualized server clusters. Vinicius Petrucci September 2010

Thesis Proposal: Dynamic optimization of power and performance for virtualized server clusters. Vinicius Petrucci September 2010 Thesis Proposal: Dynamic optimization of power and performance for virtualized server clusters Vinicius Petrucci September 2010 Supervisor: Orlando Loques (IC-UFF) Institute of Computing Fluminense Federal

More information

Improving Response Time and Energy Efficiency in Server Clusters

Improving Response Time and Energy Efficiency in Server Clusters Improving Response Time and Energy Efficiency in Server Clusters Raphael Guerra, Luciano Bertini and J.C.B. Leite Instituto de Computação - Universidade Federal Fluminense Rua Passo da Pátria, 156, Bloco

More information

Comparison of Request Admission Based Performance Isolation Approaches in Multi-tenant SaaS Applications

Comparison of Request Admission Based Performance Isolation Approaches in Multi-tenant SaaS Applications Comparison of Request Admission Based Performance Isolation Approaches in Multi-tenant SaaS Applications Rouven Kreb 1 and Manuel Loesch 2 1 SAP AG, Walldorf, Germany 2 FZI Research Center for Information

More information

A Framework for Automatic Performance Monitoring, Analysis and Optimisation of Component Based Software Systems

A Framework for Automatic Performance Monitoring, Analysis and Optimisation of Component Based Software Systems A Framework for Automatic Performance Monitoring, Analysis and Optimisation of Component Based Software Systems Ada Diaconescu *, John Murphy ** Performance Engineering Laboratory Dublin City University,

More information

Architectural Design

Architectural Design Software Engineering Architectural Design 1 Software architecture The design process for identifying the sub-systems making up a system and the framework for sub-system control and communication is architectural

More information

CHAPTER 1 INTRODUCTION

CHAPTER 1 INTRODUCTION CHAPTER 1 INTRODUCTION 1.1 Background The command over cloud computing infrastructure is increasing with the growing demands of IT infrastructure during the changed business scenario of the 21 st Century.

More information

An Agent-based Middleware for Adaptive Systems

An Agent-based Middleware for Adaptive Systems An Agent-based Middleware for Adaptive Systems Nauman A. Qureshi, Anna Perini Software Engineering Research Group Fondazione Bruno Kessler - IRST Via Sommarive, 18, 38050 Trento, Italy {qureshi, perini}@fbk.eu

More information

Experimentation with virtual machine migration and replication mechanisms

Experimentation with virtual machine migration and replication mechanisms Fluminense Federal University CARLOS ROBERTO DE OLIVEIRA JUNIOR Experimentation with virtual machine migration and replication mechanisms NITEROI 2011 CARLOS ROBERTO DE OLIVEIRA JUNIOR Experimentation

More information

MODEL DRIVEN DEVELOPMENT OF BUSINESS PROCESS MONITORING AND CONTROL SYSTEMS

MODEL DRIVEN DEVELOPMENT OF BUSINESS PROCESS MONITORING AND CONTROL SYSTEMS MODEL DRIVEN DEVELOPMENT OF BUSINESS PROCESS MONITORING AND CONTROL SYSTEMS Tao Yu Department of Computer Science, University of California at Irvine, USA Email: tyu1@uci.edu Jun-Jang Jeng IBM T.J. Watson

More information

Jean Arnaud, Sara Bouchenak. Performance, Availability and Cost of Self-Adaptive Internet Services

Jean Arnaud, Sara Bouchenak. Performance, Availability and Cost of Self-Adaptive Internet Services Jean Arnaud, Sara Bouchenak Performance, Availability and Cost of Self-Adaptive Internet Services Chapter of Performance and Dependability in Service Computing: Concepts, Techniques and Research Directions

More information

A Symptom Extraction and Classification Method for Self-Management

A Symptom Extraction and Classification Method for Self-Management LANOMS 2005-4th Latin American Network Operations and Management Symposium 201 A Symptom Extraction and Classification Method for Self-Management Marcelo Perazolo Autonomic Computing Architecture IBM Corporation

More information

SERENITY Pattern-based Software Development Life-Cycle

SERENITY Pattern-based Software Development Life-Cycle SERENITY Pattern-based Software Development Life-Cycle Francisco Sanchez-Cid, Antonio Maña Computer Science Department University of Malaga. Spain {cid, amg}@lcc.uma.es Abstract Most of current methodologies

More information

Variabilities as First-Class Elements in Product Line Architectures of Homecare Systems

Variabilities as First-Class Elements in Product Line Architectures of Homecare Systems Variabilities as First-Class Elements in Product Line Architectures of Homecare Systems Sergio T. Carvalho, Leonardo Murta, Orlando Loques Instituto de Computação - Universidade Federal Fluminense, Niterói,

More information

Recommendations for Performance Benchmarking

Recommendations for Performance Benchmarking Recommendations for Performance Benchmarking Shikhar Puri Abstract Performance benchmarking of applications is increasingly becoming essential before deployment. This paper covers recommendations and best

More information

A Taxonomy and Survey of Energy-Efficient Data Centers and Cloud Computing Systems

A Taxonomy and Survey of Energy-Efficient Data Centers and Cloud Computing Systems A Taxonomy and Survey of Energy-Efficient Data Centers and Cloud Computing Systems Anton Beloglazov, Rajkumar Buyya, Young Choon Lee, and Albert Zomaya Present by Leping Wang 1/25/2012 Outline Background

More information

On the Placement of Management and Control Functionality in Software Defined Networks

On the Placement of Management and Control Functionality in Software Defined Networks On the Placement of Management and Control Functionality in Software Defined Networks D.Tuncer et al. Department of Electronic & Electrical Engineering University College London, UK ManSDN/NfV 13 November

More information

Impact of Control Theory on QoS Adaptation in Distributed Middleware Systems

Impact of Control Theory on QoS Adaptation in Distributed Middleware Systems Impact of Control Theory on QoS Adaptation in Distributed Middleware Systems Baochun Li Electrical and Computer Engineering University of Toronto bli@eecg.toronto.edu Klara Nahrstedt Department of Computer

More information

CHAPTER 5 WLDMA: A NEW LOAD BALANCING STRATEGY FOR WAN ENVIRONMENT

CHAPTER 5 WLDMA: A NEW LOAD BALANCING STRATEGY FOR WAN ENVIRONMENT 81 CHAPTER 5 WLDMA: A NEW LOAD BALANCING STRATEGY FOR WAN ENVIRONMENT 5.1 INTRODUCTION Distributed Web servers on the Internet require high scalability and availability to provide efficient services to

More information

Web Application Architectures

Web Application Architectures Web Engineering Web Application Architectures Copyright 2013 Ioan Toma & Srdjan Komazec 1 Where we are? # Date Title 1 5 th March Web Engineering Introduction and Overview 2 12 th March Requirements Engineering

More information

Dynamic Resource management with VM layer and Resource prediction algorithms in Cloud Architecture

Dynamic Resource management with VM layer and Resource prediction algorithms in Cloud Architecture Dynamic Resource management with VM layer and Resource prediction algorithms in Cloud Architecture 1 Shaik Fayaz, 2 Dr.V.N.Srinivasu, 3 Tata Venkateswarlu #1 M.Tech (CSE) from P.N.C & Vijai Institute of

More information

A Business Driven Cloud Optimization Architecture

A Business Driven Cloud Optimization Architecture A Business Driven Cloud Optimization Architecture Marin Litoiu York University, Canada mlitoiu@yorku.ca Murray Woodside Carleton University, Canada Johnny Wong University of Waterloo, Canada Joanna Ng,

More information

QoS Resource Management for Cloud Federations

QoS Resource Management for Cloud Federations QoS Resource Management for Cloud Federations Gaetano F. Anastasi National Council of Research (CNR), Pisa, Italy Pisa, June 16th, 2014 gaetano.anastasi@isti.cnr.it QoS Management for Cloud Federations

More information

Load Distribution in Large Scale Network Monitoring Infrastructures

Load Distribution in Large Scale Network Monitoring Infrastructures Load Distribution in Large Scale Network Monitoring Infrastructures Josep Sanjuàs-Cuxart, Pere Barlet-Ros, Gianluca Iannaccone, and Josep Solé-Pareta Universitat Politècnica de Catalunya (UPC) {jsanjuas,pbarlet,pareta}@ac.upc.edu

More information

PERFORMANCE ANALYSIS OF PaaS CLOUD COMPUTING SYSTEM

PERFORMANCE ANALYSIS OF PaaS CLOUD COMPUTING SYSTEM PERFORMANCE ANALYSIS OF PaaS CLOUD COMPUTING SYSTEM Akmal Basha 1 Krishna Sagar 2 1 PG Student,Department of Computer Science and Engineering, Madanapalle Institute of Technology & Science, India. 2 Associate

More information

Dynamism and Data Management in Distributed, Collaborative Working Environments

Dynamism and Data Management in Distributed, Collaborative Working Environments Dynamism and Data Management in Distributed, Collaborative Working Environments Alexander Kipp 1, Lutz Schubert 1, Matthias Assel 1 and Terrence Fernando 2, 1 High Performance Computing Center Stuttgart,

More information

Web Services Software Architecture

Web Services Software Architecture Web Services Software Architecture Syahrul Fahmy School of Informatics, The University of Manchester, PO Box 88, Manchester M60 1QD, United Kingdom S.Abdul-wahab@postgrad.manchester.ac.uk Abstract. Web

More information

Environments, Services and Network Management for Green Clouds

Environments, Services and Network Management for Green Clouds Environments, Services and Network Management for Green Clouds Carlos Becker Westphall Networks and Management Laboratory Federal University of Santa Catarina MARCH 3RD, REUNION ISLAND IARIA GLOBENET 2012

More information

Payment minimization and Error-tolerant Resource Allocation for Cloud System Using equally spread current execution load

Payment minimization and Error-tolerant Resource Allocation for Cloud System Using equally spread current execution load Payment minimization and Error-tolerant Resource Allocation for Cloud System Using equally spread current execution load Pooja.B. Jewargi Prof. Jyoti.Patil Department of computer science and engineering,

More information

Embedded Systems. 9. Low Power Design

Embedded Systems. 9. Low Power Design Embedded Systems 9. Low Power Design Lothar Thiele 9-1 Contents of Course 1. Embedded Systems Introduction 2. Software Introduction 7. System Components 10. Models 3. Real-Time Models 4. Periodic/Aperiodic

More information

IT Architecture Review. ISACA Conference Fall 2003

IT Architecture Review. ISACA Conference Fall 2003 IT Architecture Review ISACA Conference Fall 2003 Table of Contents Introduction Business Drivers Overview of Tiered Architecture IT Architecture Review Why review IT architecture How to conduct IT architecture

More information

A Management Tool for Component-Based Real-Time Supervision and Control Systems

A Management Tool for Component-Based Real-Time Supervision and Control Systems A Management Tool for Component-Based Real-Time Supervision and Control Systems Sandro Santos Andrade, Raimundo José de Araújo Macêdo Distributed Systems Laboratory (LaSiD) Post-Graduation Program on Mechatronics

More information

A Model-Driven Approach for Developing Self-Adaptive Pervasive Systems

A Model-Driven Approach for Developing Self-Adaptive Pervasive Systems A Model-Driven Approach for Developing Self-Adaptive Pervasive Systems Carlos Cetina, Pau Giner, Joan Fons and Vicente Pelechano Research Center on Software Production Methods Universidad Politécnica de

More information

Applying 4+1 View Architecture with UML 2. White Paper

Applying 4+1 View Architecture with UML 2. White Paper Applying 4+1 View Architecture with UML 2 White Paper Copyright 2007 FCGSS, all rights reserved. www.fcgss.com Introduction Unified Modeling Language (UML) has been available since 1997, and UML 2 was

More information

Objectives. Distributed Databases and Client/Server Architecture. Distributed Database. Data Fragmentation

Objectives. Distributed Databases and Client/Server Architecture. Distributed Database. Data Fragmentation Objectives Distributed Databases and Client/Server Architecture IT354 @ Peter Lo 2005 1 Understand the advantages and disadvantages of distributed databases Know the design issues involved in distributed

More information

Gaming as a Service. Prof. Victor C.M. Leung. The University of British Columbia, Canada www.ece.ubc.ca/~vleung

Gaming as a Service. Prof. Victor C.M. Leung. The University of British Columbia, Canada www.ece.ubc.ca/~vleung Gaming as a Service Prof. Victor C.M. Leung The University of British Columbia, Canada www.ece.ubc.ca/~vleung International Conference on Computing, Networking and Communications 4 February, 2014 Outline

More information

Locality Based Protocol for MultiWriter Replication systems

Locality Based Protocol for MultiWriter Replication systems Locality Based Protocol for MultiWriter Replication systems Lei Gao Department of Computer Science The University of Texas at Austin lgao@cs.utexas.edu One of the challenging problems in building replication

More information

Architecture Design & Sequence Diagram. Week 7

Architecture Design & Sequence Diagram. Week 7 Architecture Design & Sequence Diagram Week 7 Announcement Reminder Midterm I: 1:00 1:50 pm Wednesday 23 rd March Ch. 1, 2, 3 and 26.5 Hour 1, 6, 7 and 19 (pp.331 335) Multiple choice Agenda (Lecture)

More information

Efficient and Enhanced Load Balancing Algorithms in Cloud Computing

Efficient and Enhanced Load Balancing Algorithms in Cloud Computing , pp.9-14 http://dx.doi.org/10.14257/ijgdc.2015.8.2.02 Efficient and Enhanced Load Balancing Algorithms in Cloud Computing Prabhjot Kaur and Dr. Pankaj Deep Kaur M. Tech, CSE P.H.D prabhjotbhullar22@gmail.com,

More information

System Software Integration: An Expansive View. Overview

System Software Integration: An Expansive View. Overview Software Integration: An Expansive View Steven P. Smith Design of Embedded s EE382V Fall, 2009 EE382 SoC Design Software Integration SPS-1 University of Texas at Austin Overview Some Definitions Introduction:

More information

In: Proceedings of RECPAD 2002-12th Portuguese Conference on Pattern Recognition June 27th- 28th, 2002 Aveiro, Portugal

In: Proceedings of RECPAD 2002-12th Portuguese Conference on Pattern Recognition June 27th- 28th, 2002 Aveiro, Portugal Paper Title: Generic Framework for Video Analysis Authors: Luís Filipe Tavares INESC Porto lft@inescporto.pt Luís Teixeira INESC Porto, Universidade Católica Portuguesa lmt@inescporto.pt Luís Corte-Real

More information

Collaborative Open Market to Place Objects at your Service

Collaborative Open Market to Place Objects at your Service Collaborative Open Market to Place Objects at your Service D6.4.1 Marketplace integration First version Project Acronym COMPOSE Project Title Project Number 317862 Work Package WP6 Open marketplace Lead

More information

Performance evaluation of Web Information Retrieval Systems and its application to e-business

Performance evaluation of Web Information Retrieval Systems and its application to e-business Performance evaluation of Web Information Retrieval Systems and its application to e-business Fidel Cacheda, Angel Viña Departament of Information and Comunications Technologies Facultad de Informática,

More information

Middleware- Driven Mobile Applications

Middleware- Driven Mobile Applications Middleware- Driven Mobile Applications A motwin White Paper When Launching New Mobile Services, Middleware Offers the Fastest, Most Flexible Development Path for Sophisticated Apps 1 Executive Summary

More information

Semantic Search in Portals using Ontologies

Semantic Search in Portals using Ontologies Semantic Search in Portals using Ontologies Wallace Anacleto Pinheiro Ana Maria de C. Moura Military Institute of Engineering - IME/RJ Department of Computer Engineering - Rio de Janeiro - Brazil [awallace,anamoura]@de9.ime.eb.br

More information

Software Engineering Prof. N.L. Sarda Computer Science & Engineering Indian Institute of Technology, Bombay Lecture-4 Overview of Phases (Part - II)

Software Engineering Prof. N.L. Sarda Computer Science & Engineering Indian Institute of Technology, Bombay Lecture-4 Overview of Phases (Part - II) Software Engineering Prof. N.L. Sarda Computer Science & Engineering Indian Institute of Technology, Bombay Lecture-4 Overview of Phases (Part - II) We studied the problem definition phase, with which

More information

Titolo del paragrafo. Titolo del documento - Sottotitolo documento The Benefits of Pushing Real-Time Market Data via a Web Infrastructure

Titolo del paragrafo. Titolo del documento - Sottotitolo documento The Benefits of Pushing Real-Time Market Data via a Web Infrastructure 1 Alessandro Alinone Agenda Introduction Push Technology: definition, typology, history, early failures Lightstreamer: 3rd Generation architecture, true-push Client-side push technology (Browser client,

More information

Self-organizing Methods and Models for Software Development

Self-organizing Methods and Models for Software Development Self-organizing Methods and Models for Software Development Daniel J. Dubois Advisor: Prof. Elisabetta Di Nitto CoAdvisor: Prof. Raffaela Mirandola Tutor: Prof. Gianpaolo Cugola Milan February 17 th, 011

More information

Master Subagent Based Architecture to Monitor and Manage Nodes in Mobile Ad-hoc Networks

Master Subagent Based Architecture to Monitor and Manage Nodes in Mobile Ad-hoc Networks Vishalakshi Prabhu H / International Journal of Engineering Research and Applications (IJERA) Master Subagent Based Architecture to Monitor and Manage Nodes in Mobile Ad-hoc Networks Vishalakshi Prabhu

More information

DESIGN PATTERNS FOR SELF ADAPTIVE SYSTEMS ENGINEERING

DESIGN PATTERNS FOR SELF ADAPTIVE SYSTEMS ENGINEERING DESIGN PATTERNS FOR SELF ADAPTIVE SYSTEMS ENGINEERING ABSTRACT Yousef Abuseta and Khaled Swesi Computer Science Department, Faculty of Science Al-Jabal Al-Gharbi University, Libya Self adaptation has been

More information

GROUPWARE. Ifeoluwa Idowu

GROUPWARE. Ifeoluwa Idowu GROUPWARE Ifeoluwa Idowu GROUPWARE What is Groupware? Definitions of Groupware Computer-based systems that support groups of people engaged in a common task (or goal) and that provide an interface to a

More information

QoS EVALUATION OF CLOUD SERVICE ARCHITECTURE BASED ON ANP

QoS EVALUATION OF CLOUD SERVICE ARCHITECTURE BASED ON ANP QoS EVALUATION OF CLOUD SERVICE ARCHITECTURE BASED ON ANP Mingzhe Wang School of Automation Huazhong University of Science and Technology Wuhan 430074, P.R.China E-mail: mingzhew@gmail.com Yu Liu School

More information

Requirements Analysis Concepts & Principles. Instructor: Dr. Jerry Gao

Requirements Analysis Concepts & Principles. Instructor: Dr. Jerry Gao Requirements Analysis Concepts & Principles Instructor: Dr. Jerry Gao Requirements Analysis Concepts and Principles - Requirements Analysis - Communication Techniques - Initiating the Process - Facilitated

More information

Software Architecture

Software Architecture Software Architecture Lecture 2 Basic Concepts Rob Pettit George Mason University What is Software Architecture?! Definition:! A software system s architecture is the set of principal design decisions

More information

Bachelor Degree in Informatics Engineering Master courses

Bachelor Degree in Informatics Engineering Master courses Bachelor Degree in Informatics Engineering Master courses Donostia School of Informatics The University of the Basque Country, UPV/EHU For more information: Universidad del País Vasco / Euskal Herriko

More information

Performance Comparison of Assignment Policies on Cluster-based E-Commerce Servers

Performance Comparison of Assignment Policies on Cluster-based E-Commerce Servers Performance Comparison of Assignment Policies on Cluster-based E-Commerce Servers Victoria Ungureanu Department of MSIS Rutgers University, 180 University Ave. Newark, NJ 07102 USA Benjamin Melamed Department

More information

zen Platform technical white paper

zen Platform technical white paper zen Platform technical white paper The zen Platform as Strategic Business Platform The increasing use of application servers as standard paradigm for the development of business critical applications meant

More information

The Role of the Software Architect

The Role of the Software Architect IBM Software Group The Role of the Software Architect Peter Eeles peter.eeles@uk.ibm.com 2004 IBM Corporation Agenda Architecture Architect Architecting Requirements Analysis and design Implementation

More information

GAMES: Green Active Management of Energy in IT Service centres

GAMES: Green Active Management of Energy in IT Service centres GAMES: Green Active Management of Energy in IT Service centres Massimo Bertoncini 1, Barbara Pernici 2, Ioan Salomie 3, and Stefan Wesner 4 1 Engineering Ingegneria Informatica, Italy 2 Politecnico di

More information

Cluster Computing. ! Fault tolerance. ! Stateless. ! Throughput. ! Stateful. ! Response time. Architectures. Stateless vs. Stateful.

Cluster Computing. ! Fault tolerance. ! Stateless. ! Throughput. ! Stateful. ! Response time. Architectures. Stateless vs. Stateful. Architectures Cluster Computing Job Parallelism Request Parallelism 2 2010 VMware Inc. All rights reserved Replication Stateless vs. Stateful! Fault tolerance High availability despite failures If one

More information

Self-Manageable Replicated Servers

Self-Manageable Replicated Servers 1 Christophe Noël De aton1, alma3, Sara Daniel Bouchenak2, Hagimont1, Fabienne drian Mos1 Boyer2, SelfManageable eplicated Servers {Christophe.aton, Grenoble, INI France Sara.Bouchenak, Fabienne.Boyer,

More information

Information Technology Policy

Information Technology Policy Information Technology Policy Security Information and Event Management Policy ITP Number Effective Date ITP-SEC021 October 10, 2006 Category Supersedes Recommended Policy Contact Scheduled Review RA-ITCentral@pa.gov

More information

Power Consumption Based Cloud Scheduler

Power Consumption Based Cloud Scheduler Power Consumption Based Cloud Scheduler Wu Li * School of Software, Shanghai Jiaotong University Shanghai, 200240, China. * Corresponding author. Tel.: 18621114210; email: defaultuser@sjtu.edu.cn Manuscript

More information

Adaptation to Dynamic Resource Availability in Ad-hoc Grids through a Learning Mechanism

Adaptation to Dynamic Resource Availability in Ad-hoc Grids through a Learning Mechanism Adaptation to Dynamic Resource Availability in Ad-hoc Grids through a Learning Mechanism Behnaz Pourebrahimi, Koen Bertels Computer Engineering Laboratory, Delft University of Technology, The Netherlands

More information

A Dynamic Resource Management with Energy Saving Mechanism for Supporting Cloud Computing

A Dynamic Resource Management with Energy Saving Mechanism for Supporting Cloud Computing A Dynamic Resource Management with Energy Saving Mechanism for Supporting Cloud Computing Liang-Teh Lee, Kang-Yuan Liu, Hui-Yang Huang and Chia-Ying Tseng Department of Computer Science and Engineering,

More information

Cloud Management: Knowing is Half The Battle

Cloud Management: Knowing is Half The Battle Cloud Management: Knowing is Half The Battle Raouf BOUTABA David R. Cheriton School of Computer Science University of Waterloo Joint work with Qi Zhang, Faten Zhani (University of Waterloo) and Joseph

More information

INCREASING SERVER UTILIZATION AND ACHIEVING GREEN COMPUTING IN CLOUD

INCREASING SERVER UTILIZATION AND ACHIEVING GREEN COMPUTING IN CLOUD INCREASING SERVER UTILIZATION AND ACHIEVING GREEN COMPUTING IN CLOUD M.Rajeswari 1, M.Savuri Raja 2, M.Suganthy 3 1 Master of Technology, Department of Computer Science & Engineering, Dr. S.J.S Paul Memorial

More information

An Autonomic Auto-scaling Controller for Cloud Based Applications

An Autonomic Auto-scaling Controller for Cloud Based Applications An Autonomic Auto-scaling Controller for Cloud Based Applications Jorge M. Londoño-Peláez Escuela de Ingenierías Universidad Pontificia Bolivariana Medellín, Colombia Carlos A. Florez-Samur Netsac S.A.

More information

Software Development Under Stringent Hardware Constraints: Do Agile Methods Have a Chance?

Software Development Under Stringent Hardware Constraints: Do Agile Methods Have a Chance? Software Development Under Stringent Hardware Constraints: Do Agile Methods Have a Chance? Jussi Ronkainen, Pekka Abrahamsson VTT Technical Research Centre of Finland P.O. Box 1100 FIN-90570 Oulu, Finland

More information

Self-management as Support to an Advanced Traveler Information System

Self-management as Support to an Advanced Traveler Information System Self-management as Support to an Advanced Traveler Information System Marcia Pasin 1, Felipe Silvano Perini 1, Ana L. C. Bazzan 2 1 Centro de Tecnologia Universidade Federal de Santa Maria (UFSM) Av. Roraima

More information

Analysis of an Artificial Hormone System (Extended abstract)

Analysis of an Artificial Hormone System (Extended abstract) c 2013. This is the author s version of the work. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purpose or for creating

More information

Configuring Nex-Gen Web Load Balancer

Configuring Nex-Gen Web Load Balancer Configuring Nex-Gen Web Load Balancer Table of Contents Load Balancing Scenarios & Concepts Creating Load Balancer Node using Administration Service Creating Load Balancer Node using NodeCreator Connecting

More information

BUSINESS-ORIENTED MANAGEMENT OF WEB SERVICES

BUSINESS-ORIENTED MANAGEMENT OF WEB SERVICES By Fabio Casati, Eric Shan, Umeshwar Dayal, and Ming-Chien Shan BUSINESS-ORIENTED MANAGEMENT OF WEB SERVICES Using tools and abstractions for monitoring and controlling s. The main research and development

More information

Lecture 3: Scaling by Load Balancing 1. Comments on reviews i. 2. Topic 1: Scalability a. QUESTION: What are problems? i. These papers look at

Lecture 3: Scaling by Load Balancing 1. Comments on reviews i. 2. Topic 1: Scalability a. QUESTION: What are problems? i. These papers look at Lecture 3: Scaling by Load Balancing 1. Comments on reviews i. 2. Topic 1: Scalability a. QUESTION: What are problems? i. These papers look at distributing load b. QUESTION: What is the context? i. How

More information

An Architecture Model of Sensor Information System Based on Cloud Computing

An Architecture Model of Sensor Information System Based on Cloud Computing An Architecture Model of Sensor Information System Based on Cloud Computing Pengfei You, Yuxing Peng National Key Laboratory for Parallel and Distributed Processing, School of Computer Science, National

More information

REAL-TIME STREAMING ANALYTICS DATA IN, ACTION OUT

REAL-TIME STREAMING ANALYTICS DATA IN, ACTION OUT REAL-TIME STREAMING ANALYTICS DATA IN, ACTION OUT SPOT THE ODD ONE BEFORE IT IS OUT flexaware.net Streaming analytics: from data to action Do you need actionable insights from various data streams fast?

More information

Managed Virtualized Platforms: From Multicore Nodes to Distributed Cloud Infrastructures

Managed Virtualized Platforms: From Multicore Nodes to Distributed Cloud Infrastructures Managed Virtualized Platforms: From Multicore Nodes to Distributed Cloud Infrastructures Ada Gavrilovska Karsten Schwan, Mukil Kesavan Sanjay Kumar, Ripal Nathuji, Adit Ranadive Center for Experimental

More information

Associate Professor, Department of CSE, Shri Vishnu Engineering College for Women, Andhra Pradesh, India 2

Associate Professor, Department of CSE, Shri Vishnu Engineering College for Women, Andhra Pradesh, India 2 Volume 6, Issue 3, March 2016 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Special Issue

More information

Skyminer Big Data Solution Features Highlights. Company Proprietary Sensitive Information

Skyminer Big Data Solution Features Highlights. Company Proprietary Sensitive Information Skyminer Big Data Solution Features Highlights Purpose 1. Add value to the data by providing a unified archive and efficient analysis tools 2. Help using monitoring data to improve operations, detect and

More information

Ubiquitous, Pervasive and Mobile Computing: A Reusable-Models-based Non-Functional Catalogue

Ubiquitous, Pervasive and Mobile Computing: A Reusable-Models-based Non-Functional Catalogue Ubiquitous, Pervasive and Mobile Computing: A Reusable-Models-based Non-Functional Catalogue Milene Serrano 1 and Maurício Serrano 1 1 Universidade de Brasília (UnB/FGA), Curso de Engenharia de Software,

More information

Use Cases. Massimo Felici. Massimo Felici Use Cases c 2004 2011

Use Cases. Massimo Felici. Massimo Felici Use Cases c 2004 2011 Use Cases Massimo Felici Use Cases 1 Support requirements engineering activities and the requirement process Capture what a system is supposed to do, i.e., systems functional requirements Describe sequences

More information

Establishing Great Software Development Process(es) for Your Organization. By Dale Mayes DMayes@HomePortEngineering.com

Establishing Great Software Development Process(es) for Your Organization. By Dale Mayes DMayes@HomePortEngineering.com Establishing Great Software Development Process(es) for Your Organization By Dale Mayes DMayes@HomePortEngineering.com Class: ETP-410 Embedded Systems Conference San Francisco 2005 Abstract: There are

More information

Questions? Assignment. Techniques for Gathering Requirements. Gathering and Analysing Requirements

Questions? Assignment. Techniques for Gathering Requirements. Gathering and Analysing Requirements Questions? Assignment Why is proper project management important? What is goal of domain analysis? What is the difference between functional and non- functional requirements? Why is it important for requirements

More information

5 Performance Management for Web Services. Rolf Stadler School of Electrical Engineering KTH Royal Institute of Technology. stadler@ee.kth.

5 Performance Management for Web Services. Rolf Stadler School of Electrical Engineering KTH Royal Institute of Technology. stadler@ee.kth. 5 Performance Management for Web Services Rolf Stadler School of Electrical Engineering KTH Royal Institute of Technology stadler@ee.kth.se April 2008 Overview Service Management Performance Mgt QoS Mgt

More information

Building Web-based Infrastructures for Smart Meters

Building Web-based Infrastructures for Smart Meters Building Web-based Infrastructures for Smart Meters Andreas Kamilaris 1, Vlad Trifa 2, and Dominique Guinard 2 1 University of Cyprus, Nicosia, Cyprus 2 ETH Zurich and SAP Research, Switzerland Abstract.

More information

Energy Aware Consolidation for Cloud Computing

Energy Aware Consolidation for Cloud Computing Abstract Energy Aware Consolidation for Cloud Computing Shekhar Srikantaiah Pennsylvania State University Consolidation of applications in cloud computing environments presents a significant opportunity

More information

Tool Support for Inspecting the Code Quality of HPC Applications

Tool Support for Inspecting the Code Quality of HPC Applications Tool Support for Inspecting the Code Quality of HPC Applications Thomas Panas Dan Quinlan Richard Vuduc Center for Applied Scientific Computing Lawrence Livermore National Laboratory P.O. Box 808, L-550

More information

Autonomic computing: strengthening manageability for SOA implementations

Autonomic computing: strengthening manageability for SOA implementations Autonomic computing Executive brief Autonomic computing: strengthening manageability for SOA implementations December 2006 First Edition Worldwide, CEOs are not bracing for change; instead, they are embracing

More information

A Monitored Student Testing Application Using Cloud Computing

A Monitored Student Testing Application Using Cloud Computing A Monitored Student Testing Application Using Cloud Computing R. Mullapudi and G. Hsieh Department of Computer Science, Norfolk State University, Norfolk, Virginia, USA r.mullapudi@spartans.nsu.edu, ghsieh@nsu.edu

More information

The Requirements Compliance Matrix columns are defined as follows:

The Requirements Compliance Matrix columns are defined as follows: 1 DETAILED REQUIREMENTS AND REQUIREMENTS COMPLIANCE The following s Compliance Matrices present the detailed requirements for the P&I System. Completion of all matrices is required; proposals submitted

More information

Tracking the Impact of Design Changes During Software Development

Tracking the Impact of Design Changes During Software Development Tracking the Impact of Design Changes During Software Development Frank Padberg Fakultät für Informatik Universität Karlsruhe, Germany padberg@ira.uka.de Abstract Design changes occur frequently during

More information

Event based Enterprise Service Bus (ESB)

Event based Enterprise Service Bus (ESB) Event based Enterprise Service Bus (ESB) By: Kasun Indrasiri 128213m Supervised By: Dr. Srinath Perera Dr. Sanjiva Weerawarna Abstract With the increasing adaptation of Service Oriented Architecture for

More information

11 Tips to make the requirements definition process more effective and results more usable

11 Tips to make the requirements definition process more effective and results more usable 1 11 Tips to make the s definition process more effective and results more usable This article discusses what I believe are the key techniques for making s definition process repeatable from project to

More information

Software Active Online Monitoring Under. Anticipatory Semantics

Software Active Online Monitoring Under. Anticipatory Semantics Software Active Online Monitoring Under Anticipatory Semantics Changzhi Zhao, Wei Dong, Ji Wang, Zhichang Qi National Laboratory for Parallel and Distributed Processing P.R.China 7/21/2009 Overview Software

More information