BRA2Fog is now BRA2Cloud!

Welcome to the project website.

Our Team

Pergentino Araujo

Ph.D student at Department of Computer Science, University of Brasília, Brazil.

Donald Pianto

Adjunct Professor at Statistics Department, University of Brasília, Brazil.

Célia Ghedini

Member of the Department of Computer Science, University of Brasília, Brazil.

The Project

BRA2Cloud is a Brand new Resilient Agent-based Architecture for Cloud computing.

This project investigates the application of agent-based architectures to create a resilient environment using unsecured transient servers to offer trusted services or run applications using Cloud Computing idle resources. Exploring idle resources is an efficient way to save energy and money (e.g., reuse unused CPU and memory to provide services and run applications).

The BRA2Cloud architecture combines machine learning and a statistical model to predict instance survival time and helps to refine fault tolerance parameters to provide trusted services, reducing monetary cost. This model compiles and analyses Amazon EC2 Spot Instances’ historic price change data to predict revocation events.

Our agents pursue an efficient usage of Spot Instances, providing a novel resilient environment between users and cloud resources, through machine learning, to predict revocation events and define suitable Fault Tolerance mechanisms with their respective parameters. This is a key step toward successful and efficient usage of these instances to provide trusted services with minimal interruptions at cheapest prices.

Experiments indicates that this model can be used under realistic working conditions with better use of idle resources.

Agent-based Macro Architecture

An evolution of our agent-based architecture and their respective agents are presented as follows:

Repository

All collected data and source code are available at our public repository, hosted on GitLab.

Requirements

The BRA2Cloud framework has a few system requirements, as follows:

  • Java (8+) - A programming language that produces software for multiple platforms.
  • PostgreSQL (9.6+) - A powerful, open source object-relational database system.
  • MySQL (8+) - The world's most popular open source database (optional, as alternative to PostgreSQL).
  • MyCBR (3.1+) - An open-source similarity-based retrieval tool.
  • A Linux/OSX bash environment with Gnuplot (5+) installed.
  • A set of libraries available at lib folder.

Quickstart

How to start using our framework:

Clone our project using git clone https://gitlab.com/InfoKnow/CloudFogComputing/BRA2Cloud.git and create a project workspace using your preferential Java IDE.

Using our project can lead to excessive and expensive charges from cloud providers.

Our files and database are reaching approximately 65 GB of data (updated 02/19).

Licence

Copyright © 2017-19 BRA2Cloud. Licensed under Apache License Version 2.0.

Selected Publications

  • Araújo Neto, José Pergentino and Pianto, Donald M. and Ralha, Célia Ghedini, "Towards increasing reliability of Amazon EC2 spot instances with a fault-tolerant multi-agent architecture", Multiagent and Grid Systems Journal - vol. 15, no. 3, pp. 259-287, 2019.
  • José Pergentino de Araújo Neto and Donald M. Pianto and Célia Ghedini Ralha, "MULTS: A Multi-cloud Fault-tolerant Architecture to Manage Transient Servers in Cloud Computing", Journal of Systems Architecture, 2019.
  • J. P. Araujo Neto, D. M. Pianto and C. Ghedini Ralha, "A Resilient Agent-Based Architecture for Efficient Usage of Transient Servers in Cloud Computing", 2018 IEEE International Conference on Cloud Computing Technology and Science (CloudCom), Nicosia, Cyprus, 2018, pp. 218-225.
  • J. P. Araujo Neto, D. M. Pianto and C. G. Ralha, "An Agent-Based Fog Computing Architecture for Resilience on Amazon EC2 Spot Instances", 2018 7th Brazilian Conference on Intelligent Systems (BRACIS), São Paulo, SP, Brazil, 2018, pp. 360-365.
  • J. P. de Araujo Neto, D. M. Pianto and C. G. Ralha, "A Fault-Tolerant Agent-Based Architecture for Transient Servers in Fog Computing", 2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), Lyon, France, 2018, pp. 282-289.
  • Neto J. P. Araujo, Pianto D. M., Ralha C. G., "A Prediction Approach to Define Checkpoint Intervals in Spot Instances", In: The Cloud Computing Conference – CLOUD 2018, Seattle, WA, United States. Lecture Notes in Computer Science, vol 10967. Springer International Publishing. June 2018.
  • Neto J. P. Araujo, Pianto D. M., Ralha C. Ghedini. (2018) A Machine Learning Approach to Predict Revocation Failures on Transient Instances in Cloud Computing (Uma Abordagem Baseada em Aprendizagem de Máquina para Predição de Falhas de Revogação em Instâncias Transientes). In: XXIX Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, 2018, Campos do Jordão, SP. Anais do XXXVI SBRC - XVI WCGA, 2018. v. 1. p. 1-12.

Get in Touch

You're welcome to contribute to this project! Any help is appreciated!

Feel free to report issues and open merge requests.
There are several aspects you can help on:

  • Improving our code and sharing with us on our public repository.
  • Testing our solutions.
  • Sharing and helping other users to use this framework.
  • You can suggest your desired features.