IWFCC 2019 Abstracts

Full Papers Short Papers
Full Papers
Paper Nr: 1
Title:

Medical Imaging Processing Architecture on ATMOSPHERE Federated Platform
Authors:

Ignacio Blanquer, Ángel Alberich-Bayarri, Fabio García-Castro, George Teodoro, André Meirelles, Bruno Nascimento, Wagner Meira Jr. and Antonio P. Ribeiro
Abstract: This paper describes the development of applications in the frame of the ATMOSPHERE platform. ATMOSPHERE provides means for developing container-based applications over a federated cloud offering measuring the trustworthiness of the applications. In this paper we show the design of a transcontinental application in the frame of medical imaging that keeps the data at one end and uses the processing capabilities of the resources available at the other end. The applications are described using TOSCA blueprints and the federation of IaaS resources is performed by the Fogbow middleware. Privacy guarantees are provided by means of SCONE and intensive computing resources are integrated through the use of GPUs directly mounted on the containers.
Download
Paper Nr: 2
Title:

DistributedFaaS: Execution of Containerized Serverless Applications in Multi-Cloud Infrastructures
Authors:

Adbys Vasconcelos, Lucas Vieira, Ítalo Batista, Rodolfo Silva and Francisco Brasileiro
Abstract: The adoption of cloud computing is continuously increasing due to the attractiveness of low costs of infrastructure acquisition and maintenance, as well as having virtually infinite resources available for scaling applications based on demand. Due to the increasing interest in this topic, there is a continuos search for better, more cost-effective ways to manage such infrastructures. One of the most recent steps was taken by the definition and development of Serverless computing, a.k.a. Function-as-a-Service (FaaS). FaaS is a cloud computing service model where developers can deploy functions to a cloud platform and have them executed based either on the triggering of events by other services, or by making requests directly to an HTTP(S) gateway, without having to worry about setting up the underlying infrastructure. In this paper, we propose an architecture for deploying FaaS platforms in hybrid clouds that can be composed by multiple cloud providers. This architecture aims at enabling privately deployed FaaS platforms to perform auto-scaling of resources (virtual machines) in a distributed infrastructure, while considering the scenario where the users of such platform are scattered around the globe. This allows the execution of requests in servers geographically located as close as possible from the client, with benefits to both the clients and the service providers.
Download
Paper Nr: 4
Title:

Easing the Deployment and Management of Cloud Federated Networks Across Virtualised Clusters
Authors:

Ivan A. Castañeda, Ignacio Blanquer and Carlos de Alfonso
Abstract: Cloud federation, in the last years, has grown rapidly in literature because to its multiple advantages to coordinate and re-use different services across multiple sites, different geographic locations or cloud providers. This article presents a federated network architecture and focuses on the multi-tenant overlay networks creation across different sites, as well as, the inter-site migration of virtual machines, introducing a framework that allows us to manage our federate cloud environment in three scenarios: distribution of Virtual Machines, resource management, and network management.
Download
Paper Nr: 5
Title:

Gray-Box Models for Performance Assessment of Spark Applications
Authors:

Marco Lattuada, Eugenio Gianniti, Marjan Hosseini, Danilo Ardagna, Alexandre Maros, Fabricio Murai, Ana P. Couto da Silva and Jussara M. Almeida
Abstract: Big data applications are among the most suitable applications to be executed on cluster resources because of their high requirements of computational power and data storage. Correctly sizing the resources devoted to their execution does not guarantee they will be executed as expected. Nevertheless, their execution can be affected by perturbations which can change the expected execution time. Identifying when these types of issue occurred by comparing their actual execution time with the expected one is mandatory to identify potentially critical situations and to take the appropriate steps to prevent them. To fulfill this objective, accurate estimates are necessary. In this paper, machine learning techniques coupled with a posteriori knowledge are exploited to build performance estimation models. Experimental results show how the models built with the proposed approach are able to outperform a reference state-of-the-art method (i.e., Ernest method), reducing in some scenarios the error from the 221.09-167.07% to 13.15-30.58%.
Download
Short Papers
Paper Nr: 3
Title:

Immediate Mobility Number Portability: Cloud Database Appliance Platform to Provide Central Portability
Authors:

Katelaris Leonidas, Themistocleous Marinos and Brasca Fabrizio
Abstract: The ongoing “era of data” arise challenges and issues on analysing huge volumes of data in an efficient way, developing applications and services that leverage the benefits of cloud infrastructures alongside with fast data processing services. Despite, the large number of different applications migrated in cloud, there still applications that are not frequently met on cloud infrastructures. Applications defined as time critical or data-intensive are applications of this kind. The need of high resilience alongside with high performance lead these types of applications to run on mainframes, than in cloud infrastructures, as cloud is not able to satisfy them under strict Service Level Agreements (SLAs) and without predictable performance. The aim of this paper is to report research issues around time critical and data-intensive applications deployed in cloud and present Immediate Mobile Number Portability (MNP) Use-Case migration to cloud infrastructure, which aim to provide portability nation-wide.
Download