Erica Sousa

A Modeling Approach for Cloud Infrastructure Planning Considering Dependability and Cost Requirements

Cloud computing is a model in which resources such as storage, applications, and networking infrastructures can be offered as services over the internet. Cloud applications are becoming even bigger and more complex with a high availability requirement. This paper presents a modeling strategy based on a hierarchical and heterogeneous modeling for cloud infrastructure planning. This modeling strategy allows the selection of cloud infrastructures according to dependability and cost requirements. Additionally, a stochastic model generator for cloud infrastructure planning provides automatic generation of dependability and cost models for representing cloud infrastructures. A case study based on Moodle hosted on a Eucalyptus platform is adopted to demonstrate the feasibility of the proposed solution (modeling strategy and tooling).

Performance Modeling for Evaluation and Planning of Electronic Funds Transfer Systems with Bursty Arrival Traffic

As business enterprisers are increasingly becoming dependent on using online transactions, the demand for high-end and efficient transaction monitor systems becomes a serious issue. Hence, the performance evaluation of Electronic Funds Transfer (EFT) systems has an enormous importance for companies that implement this service, since the computing resources must be used efficiently in order to ensure high availability, reliability, scalability and security. This paper presents a stochastic model for performance evaluation and planning EFT systems computational resources in the course of demonstrating that the effect of the traffic variations mechanism in computational resources is magnified when the interarrivals are highly bursty and correlated. At the end, a real case study is presented in order to describe the adequacy of presented approach and results.

Performability modeling of electronic funds transfer systems

Dependability is a paramount requirement for computer systems, since failures can cause a serious economic impact and jeopardize profitability. This paper considers electronic funds transfer (EFT) systems, where computing resources must be used efficiently in order to achieve high availability and reliability for a high quality of the offered service. The design of fault-tolerant computer systems requires their model-based performability evaluation. A stochastic Petri net model of EFT architecture and behavior is presented to evaluate the impact of availability and reliability issues on computational resources. An industrial case study shows the practical usability of the proposed models and techniques.

Cloud infrastructure planning considering different redundancy mechanisms

Cloud computing has been established as a remarkable business model that allows the outsourcing of processing, memory, storage, and networking provided by cloud infrastructures. Cloud applications require computing resources being promptly available to serve the on-demand load. If resources are not available to meet user requests, service dependability and performance may be considerably impacted. Thus redundancy mechanisms are a suitable solution for rapidly providing resources to recover the failure in service delivery. However, one of the main difficulties in cloud infrastructures are related to the selection of redundancy mechanisms that can provide a high availability with acceptable costs. This paper provides a methodology, stochastic models and an optimization approach for assisting the planning of private cloud infrastructures, which are selected according to the availability, downtime and cost constraints. Two case studies based on cloud platform are adopted to demonstrate the feasibility of the proposed work.

Performance and Cost Modeling Strategy for Cloud Infrastructure Planning

Cloud computing is a computational paradigm in which resources such as storage, applications and networking infrastructures can be offered as services over the internet. Due to dynamic and virtualized nature of cloud environments and diversity of client requests, providing the expected service quality while avoiding over-provisioning is not a simple task. To ensure that the provisioned service is acceptable, providers must exploit techniques and mechanisms that guarantee a minimum level of service quality. This performance evaluation of cloud infrastructures has been receiving considerable attention by providers as a prominent activity for improving service quality. This paper presents a modeling strategy for cloud infrastructure planning with different software and hardware configurations, according to performance and cost requirements. A case study based on Moodle hosted on Eucalyptus platform is adopted to demonstrate the feasibility of the proposed modeling strategy.

Development Risk Assessment in Software Projects Using Dependability Models

Risk management is a prominent activity, which aims the mitigation of undesirable issues during a project lifetime. In this context, techniques have been proposed to evaluate the impact of risks, but probability estimates are usually neglected, affecting a proper evaluation of such issues. This work presents an approach based on dependability models (e.g., stochastic Petri nets) for probabilistic evaluation of risks regarding the turnover of team members and requirement implementation in software development projects. Two case studies are adopted to demonstrate the feasibility of the proposed technique.

Video Conferencing Evaluation Considering Scalable Video Coding and SDN Network

Video conferencing is very common nowadays, and it may contemplate heterogenous devices (e.g., smartphones, notebooks, game consoles) and networks in the same session. Developing video conferencing systems for this myriad of devices with different capabilities requires special attention from system designer. Scalable video coding (SVC) is a prominent option to mitigate this heterogeneity issue, but traditional Internet protocol (IP) networks may not fully benefit from such a technology. In contrast, software-defined networking (SDN) may allow better utilization of SVC and improvements on video conferencing components. This paper evaluates the performance of video conferencing systems adopting SVC, SDN and ordinary IP networks, taking into account throughput, delay and peak signal-to-noise ratio (PSNR) as the metrics of interest. The experiments are based on Mininet framework and distinct network infrastructures are also considered. Results indicate SDN with SVC may deliver better video quality with reduced delay and increased throughput.

Virtual network mapping considering energy consumption and availability

Network virtualization is widely considered as a mainstay for overcoming the Internet’s ossification problem, and virtual network embedding (VNE) is a critical issue. Over recent years, growing energy costs and increased ecological awareness have stimulated the interest in reducing energy consumption by Internet service providers (ISP). Dependability is also an important requirement, as it involves metrics such as reliability and availability, which directly impact quality of service (QoS). Prior works on virtual network embedding have focused mainly on maximizing revenue for Internet service providers (ISPs), and they did not consider energy consumption and dependability metrics jointly in the mapping. This paper presents an energy-efficient mapping of dependable virtual networks. The approach considers a problem formulation that concomitantly takes into account energy consumption and availability constraints for virtual network embedding problem, and an algorithm based on Greedy Randomized Adaptive Search Procedure (GRASP) metaheuristic is adopted. The algorithm utilizes a sensitivity analysis based on availability importance to achieve the QoS required by each virtual network, and models based on reliability block diagrams (RBD) and stochastic Petri nets (SPN) are utilized to estimate availability. Results demonstrate the feasibility of the proposed approach, and they show the trade-off between availability, energy consumption, cost and revenue.

Performance Evaluation of Mobile Applications in Mobile Cloud Environments

The current society lives in the era of the mobile devices (especially smarthphones). These devices are used to execute various tasks: send mail, access internet bank, payments and so on. However, mobile device faces with an issue of availability because the battery autonomy is limited. To extend the battery autonomy, one emerging solution is to use the cloud and offload tasks to save energy. One existing issue in this context is related to the decision of which applications are better candidates to this approach, and this issue can be mitigated by the use of performance evaluation techniques. However there is a lack in the literature about how to carry performance evaluation activities in the context of mobile cloud computing. Based on that, this work presents a methodology to realize studies of performance evaluation on mobile cloud computing environments considering measurement approaches. To evaluate the proposed methodology, a case study was developed and the results shows how to compare the impact of executing an application in the device in comparison to execute it in the cloud through the use of offload techniques.

Performability Assessment of a Government Process in the Cloud

Governments can take advantage of cloud computing to deal with the pressures as well as challenges to reduce costs and improve service performance. In this context, the joint evaluation of performance and dependability (i.e., Performability) is very important, and stochastic modeling provides a prominent mechanism for assessing government services in the cloud and evaluation of distinct scenarios. This work proposes an approach based on stochastic Petri nets (SPN) for performability evaluation of Taxpayer Assistance Center (TAC) in the cloud. Performability techniques are considered, as failures in the process are taken into account and the respective impact in performance is analyzed. Results are presented to demonstrate the feasibility of the proposed approach, and they indicate that failures should not be neglected.