Bruno Guazzelli Batista

Performance Evaluation of Resource Management in Cloud Computing Environments.

Cloud computing is a computational model in which resource providers can offer on-demand services to clients in a transparent way. However, to be able to guarantee quality of service without limiting the number of accepted requests, providers must be able to dynamically manage the available resources so that they can be optimized. This dynamic resource management is not a trivial task, since it involves meeting several challenges related to workload modeling, virtualization, performance modeling, deployment and monitoring of applications on virtualized resources. This paper carries out a performance evaluation of a module for resource management in a cloud environment that includes handling available resources during execution time and ensuring the quality of service defined in the service level agreement. An analysis was conducted of different resource configurations to define which dimension of resource scaling has a real influence on client requests. The results were used to model and implement a simulated cloud system, in which the allocated resource can be changed on-the-fly, with a corresponding change in price. In this way, the proposed module seeks to satisfy both the client by ensuring quality of service, and the provider by ensuring the best use of resources at a fair price.

A QoS-driven approach for cloud computing addressing attributes of performance and security

Abstract In recent years, cloud computing has been one of the most widely discussed topics in the field of Information Technology. Owing to the popularity of services offered by cloud environments, several critical aspects of security have aroused interest in the academic and industrial world, where there is a concern to provide efficient mechanisms to combat a wide range of threats. As is well known, the application of security techniques and methodologies has a direct influence on the performance of the system, since security and performance are two quantities that are inversely proportional. This means that if the service providers fail to manage their computing infrastructure efficiently, the demand for services may not be met with the quality required by clients, including security and performance requirements, and the computational resources may be used inefficiently. The aim of this paper was to define QoS-driven approaches for cloud environments on the basis of the results of a performance evaluation of a service in which different security mechanisms are employed. These mechanisms impose additional overhead on the performance of the service, and to counter this, an attempt was made to change computational resources dynamically and on-the-fly. On the basis of the results, it could be shown that in a cloud environment, it is possible to maintain the performance of the service even with the overhead imposed by the security mechanisms, through an alteration in the virtualized computational resources. However, this change in the amount of resources had a direct effect on the response variables.

Performance Evaluation in a Cloud with the Provisioning of Different Resources Configurations

Cloud computing is a computing style where resource providers can offer on-demand services in a transparent way and clients usually pay as they go. It introduces a new level of flexibility and scalability for IT users addressing challenges such as the rapid change in IT and the need to reduce cost and time of infrastructure management. However, to be able to offer QoS guarantees without limiting the number of accepted requests, providers must be able to dynamically adjust the available resources to serve requests. This dynamic resource management is not a trivial task, bringing its own challenges related to workload and performance modelling, and deployment and monitoring of applications on virtualised IT resources. An efficient mapping between resources and applications ensures workload balancing and good resource utilization and allows to meet the QoS levels required by clients. This paper presents a performance evaluation that considers different resource configurations in a cloud environment to define which dimension of resource scaling has real impact on client applications.

Scheduling algorithms for opportunistic computational grid based on television digital receiver

This paper reports on the development and evaluation of scheduling algorithms that allow an adequate distribution of applications in opportunistic computational grid elements. This grid can group computing resources of any equipment, including digital receivers, into a federation and it allows a better use of resources. Experiments were carried out using the GridSim simulator, where digital receivers available in the market and some interactive applications were classified and characterized, modeling and simulating opportunistic computational grid environments. The policy that examines the information of applications and resources information presented a better performance in the scheduling of applications to resources that compose the simulated grid.

A low cost workload generation approach through the cloud for capacity planning in service-oriented systems

This paper presents a cloud approach for low cost capacity planning evaluations. To perform these evaluations we have to specify and measure the workload on the target system to discover issues and make the necessary adjustments. However, due to high costs, these evaluations are usually done using simulations, which does not consider stochastic effects. We propose to use a tool named PEESOS, a generic and flexible approach to apply real workloads and measure used resources on these real systems. As a proof of concept, our case study use a real ticket sales service to evaluate the influence of scalability in the resource provisioning to show how PEESOS can lower the cost of such real evaluations. The results show the efficiency and savings that we can obtain using PEESOS for large-scale capacity planning evaluations before the real services are deployed. This approach can avoid several problems that real services faces when they launch.

The influence of resource allocation on cloud computing performance

This paper makes experimental evaluations that involve the allocation of virtual machines in a cloud environment. Virtual machine allocation is an open research field in cloud, which can lead to the best performance for clients. However, the allocations are made by estimating the number of resources that need to be allocated to the virtual machines in the host without taking account of the possible workload required for these virtual machines. In carrying out this, we set up a cloud prototype, together with virtual machines with the same configuration as that for Amazon and Microsoft providers, so that our prototype could be validated. After this, we allocated as many virtual machines as possible in a single host based on our own infrastructure and involving homogeneous workloads and heterogeneous workloads. The results showed that the benefits obtained from heterogeneous sets of virtual machines were better than the homogeneous sets.

A Performance Evaluation of an Automatic Web Services Composition System

The automatic composition of Web Services has been explored in the literature from different standpoints. It aims to create an execution plan for the flow of Web Services based on requests made and sent by the client, by following the stages necessary for the generation of composite services and then carrying out the execution of the workflow that has been designed. However, no research studies have been found that undertake the whole process of an automatic composition and execution, from the users request to the execution of the services chosen as a solution. Therefore, the goal of this paper is to evaluate the performance of an automatic Web Service composition, since the request made by the client, to the delivery of the results of the executed composition. This article examines the integration between two tools, the automatic web service composition system and the extensible platform to evaluate semantic web services with the aim of conducting a performance evaluation of an entire process of automatic composition of Web services.

A GRASP Heuristic in the Choice of Clusterheads for Wireless Sensor Networks Provided as a Service

In Wireless Sensor Networks (WSNs), the efficient use of sensor energy is a crucial point to extend the network lifetime and has been the focus of many industrial and academic researchers, since it is not a trivial task. Several methodologies for clustering, routing and energy saving in WSNs are available in the literature. However, the lack of detailed and crucial information from the analyzed studies made it possible to propose and develop a new approach. In this way, in this paper we propose and develop a new strategy to choose clusterheads in WSNs, based on the GRASP metaheuristic, in order to increase the energy autonomy and, consequently, the system lifetime. Based on experiments and comparative analyzes, it was verified that the application of our algorithm in the process of choices of clusterheads allowed to obtain a longer life and a lower energy consumption when compared to other algorithms such as LEACH and LEACH-C.

Gap Filling of Missing Streaming Data in a Network of Intelligent Surveillance Cameras

The growth of video surveillance devices increases the rate of streaming data. However, even working in the Fog Computing environment, these smart devices may fail collecting information, producing missing or invalid data. This issue can affect the user quality of experience, because the PTZ-controller may lose the target object tracking. Therefore, this paper presents the Singular Spectrum Analysis - (SSA), as the method to replace missing values in this complex environment of intelligent surveillance cameras. SSA is characterized within time series field by performing a non-parametric spectral estimation with spatial-temporal correlations. The values not correctly monitored, were estimated by SSA with accuracy, allowing the tracking of a suspect object.

CM Cloud Simulator: A Cost Model Simulator Module for Cloudsim

The vast cloud computing environment holds out good prospects for researchers in the computing technology field. However, with several Cloud providers offering different pricing models, the evaluation and modeling of Cloud environments and applications are getting harder because there is a lack of tools for this task. We propose the CM Cloud Simulator to fill this gap since it provides a comprehensive and dynamic simulation of applications with various deployment configurations and incurs the cost it would require when implemented in a Cloud Provider, according to the cost model of any service provider. The CM Cloud Simulator also provides custom-built cost models through the XML file.