Welcome Cloud Technologies

This Chapter aims to create an interest group focused on the creation of a Software Platform of Cloud Technologies that will enable Future Internet Services delivery. Through the Chapter we will develop our vision of Clouds as a large pool of easily usable and accessible virtualized resources (such as hardware, development platforms and/or services). These resources can be dynamically reconfigured to adjust to a variable load (scale), allowing also for optimum resource utilization. This pool of resources will be typically exploited using a pay-per-use model in which guarantees are offered by the Infrastructure Providers by means of customized SLAs.
This Chapter provides a critical view and promotion of these technologies, to separate facts from hype, and to identify key challenges that will help to understand and apply these systems in real scenarios like Clouds, Green IT or Enterprise Grids.

Provisioning Data Analytic Workloads in a Cloud

Future Generation Computer Systems has published our work entitled “Provisioning Data Analytic Workloads in a Cloud”, which is the result of the collaboration with Prof. Patrick Martin’s group from Queen’s University.

Data analytics applications are well-suited for a cloud environment. In this paper we examine the problem of provisioning resources in a public cloud to execute data analytic workloads. The goal of our provisioning method is to determine the most cost-effective configuration for a given data analytic workload. Provisioning a workload in a public cloud environment faces several challenges: it is difficult to develop accurate performance prediction models using standard methods; the space of possible configurations is very large so exact solutions cannot be efficiently determined, and the mix and intensity of query classes in a workload vary dynamically over time.

We provide a formulation of the provisioning problem and then define a framework to solve the problem. Our framework contains a cost model to predict the cost of executing a workload on a configuration and a method of selecting configurations. The cost model balances resource costs and penalties from SLAs. The specific resource demands and frequencies are accounted for by queueing network models of the Virtual Machines (VMs), which are used to predict performance. We evaluate our approach experimentally using sample data analytic workloads on Amazon EC2.

You can access the full paper here.

J.L. Vázquez-Poletti

Workshop MEDIANET 2013

The Workshop MEDIANET 2013 will be held next April 19, 2013 at University Carlos III of Madrid (Leganes Campus, room 4.1.S08 of the Rey Pastor library). The aim  of the Workshop is to demonstrate the main results of the project. All talks will be conducted in English, and the event is open to the public, but registration is required by using a web registration form http://goo.gl/cuAvB

Program
10:00-10:10 Welcome and Introduction Jaime García Reinoso (UC3M)
10:10-10:30 Quid Pro Quo: auction mechanisms without payments Agustín Santos Méndez (IMDEA Networks)
10:30-10:45 Evaluation results of All-Path protocols with OMNET++ simulator. Guidelines for improvement of protocol mechanisms Elisa Rojas (UAH)
10:45-11:00 Evaluation results of All-Path protocols with flow simulator: results and next steps Juan A. Carral (UAH)
11:00-11:20 BREAK
11:20-11:40 Cloud Computing for on-Demand Provisioning of Resources Carlos Martín Sánchez (UCM)
11:40-12:00 Cloud Computing Federation and Interoperability Daniel Molina Aranda (UCM)
12:00-12:30 Multimedia over Content-Centric Networking Jaime García Reinoso (UC3M)
12:30-13:00 New challenges and paradigms in the Internet for multimedia, Data Centers and Cloud Computing Ignacio M. Llorente (UCM), Guillermo Ibáñez (UAH), Jaime García (UC3M),

Cloud 4CaaSt’ing in Madrid

This week our project held its General Assembly in Madrid, at IMDEA Software headquarters. In fact, we are very happy to announce that this partner is the latest addition to our consortium.

The IMDEA Software Institute is part of IMDEA, the Madrid Institute of Advanced Studies, a network of international research centers in the Madrid region for research of excellence in areas of high economic impact. Its main focus is to perform the research of excellence required to devise methods that will allow the cost-effective development of software products with sophisticated functionality and high quality.

After 3 days of hard work, surely inspired by the huge amount of clouds that invaded Madrid, we have set a very solid roadmap for the next 6 months.

J.L. Vázquez-Poletti

Student Cloud Computing Projects against the Financial Crisis

The Master Thesis project is an important stage in which students tackle a specific problem and do so using all available technologies and methodologies learned during their studies.

One of the best features of cloud computing is its high accessibility. In this way, it opens up a world of research possibilities and engenders a fast learning process, allowing the students to develop outstanding projects in a very reasonable time.

This time the effects of the financial crisis turned to be the center of gravity of this year’s Master Thesis projects with I advise, which are always proposed by the students themselves. This year’s projects provide sustainable solutions for Computer Science teaching, Research and High-Tech SMEs.

HPC in the Cloud has featured an article on my students and their awesome projects. Click here to access it.

Also, Cadena SER, one of the major radio stations in Spain, interviewed us in prime time. You can access the audio (in Spanish) here.

J.L. Vázquez-Poletti

IaaS Cloud Architecture: From Virtualized Datacenters to Federated Cloud Infrastructures

“IaaS Cloud Architecture: From Virtualized Datacenters to Federated Cloud Infrastructures” is the title of our last article published in the December 2012 issue of the IEEE Computer Magazine that presents an architecture reference model for IaaS clouds. The article introduces the cloud OS (Operating System) platform as the core component of this architecture that is responsible for managing the physical and virtual infrastructure, orchestrating and commanding service provisioning and deployment, and providing federation capabilities for accessing and deploying virtual resources in remote cloud infrastructures. The article ends with a description of different architectures for cloud federation. OpenNebula is also mentioned as an open-source reference implementation of the cloud OS platform.

Enjoy the article!

4CaaSt Passes its Second Year Review!

Last week the 4CaaSt project has been evaluated by the European Commission after its second year.

These 29 months of hard work have produced solid presentations, high quality deliverables and even more important, the integration of components developed within the project. Obviously, the integration of the whole platform is not at 100% (we are just in our second year) but the reviewers were satisfied with the current level.

So long Brussels! We’ll see you next year and we at 4CaaSt promise to bring you something even cooler.

J.L. Vázquez-Poletti

Curiosity, Phobos and Cloud Computing

The Monthly Notices of the Royal Astronomical Society journal has just published our paper entitled “Opportunities to observe solar eclipses by Phobos with the Mars Science Laboratory”. In this contribution a series of predictions for observing solar eclipses by Mars’ biggest moon within NASA’s Mars Science Laboratory (Curiosity) Mission.

The application is a result of the great collaboration that lasts for two years within the MEIGA-MetNet Project, part of the Finnish-Russian-Spanish Mars MetNet Mission which will deploy several meteorological probes on the Martian surface. Phobos shadow trace could be used for the localization of the probes and due to its computing requirements, cloud computing is a “must use” technology.

We already published some papers on this topic, specially on the efficient infrastructure deployment by means of performance and cost. This time, the news are not only that the contribution with proposed observation dates/times for Curiosity was published but also that the Martian rover has confirmed the predictions with the incredible precision of 1 second.

One example of the observations made by Curiosity on Sol 37 (13th September 2012) can be found here.

Summarizing, the application for the next generation of Martian probes has been successfully validated by Curiosity. And of course, cloud computing has become an essential tool for Space exploration.

The complete reference for this journal paper is:

G. Barderas, P. Romero, L. Vazquez, J.L. Vazquez-Poletti and I.M. Llorente: Opportunities to observe solar eclipses by Phobos with the Mars Science Laboratory. Monthly Notices of the Royal Astronomical Society, 2012, Volume 426, Number 4, pp. 3195–3200. Wiley.

J.L. Vázquez-Poletti