An approach to predict emergent behaviors in systems-of-systems in the big data context

• Grant number: 17/22237-3
• Support Opportunities: Scholarships in Brazil - Master
• Start date: April 01, 2018
• End date: March 31, 2019
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Agreement: Coordination of Improvement of Higher Education Personnel (CAPES)
• Principal Investigator: Elisa Yumi Nakagawa
• Grantee: Bruno Sena da Silva
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

Systems-of-Systems (SoS) are composed of heterogeneous, independent, and software-intensive constituent systems, which work together towards a common goal. SoS are mainly found in critical domains, such as health, transportation, and military. A main characteristic of these systems is the emergent behavior (i.e., the desired and non-desired behaviors that emerge at runtime as result of the behaviors of their constituents). In parallel, it is observed the increasingly growth of data created by software-intensive systems, characterizing the Big Data scenario, and machine learning techniques have been explored to extract knowledge from such data. The set of data from constituents of SoS also characterizes the Big Data. However, although this set of data contains knowledge that could predict emergent behaviors in SoS, this has not been explored, yet. Besides that, the inability of SoS to predict emergent behaviors (before they occur) could cause failures resulting in problems, e.g., injury or even death caused by an ehealth SoS. The main objective of this Master's project is to establish an approach to predict emergent behaviors in SoS and also predict the ones unexpected at runtime, supporting SoS stakeholders to better react by beforehand knowing that new behaviors will emerge. This approach will be implemented using machine learning techniques applied over the set of data from constituent systems. In order to evaluate this approach, a case study and also an experiment will be conducted by applying it in a real ehealth SoS. As main results, we intend to contribute to SoS community, providing a means to predict emergent behavior and also helping stakeholders to prevent systems failures. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

ALLIAN, ANA PAULA; SENA, BRUNO; NAKAGAWA, ELISA YUMI; ASSOC COMP MACHINERY. Evaluating variability at the software architecture level: An Overview. SAC '19: PROCEEDINGS OF THE 34TH ACM/SIGAPP SYMPOSIUM ON APPLIED COMPUTING, v. N/A, p. 8-pg., 2019-01-01. (16/15634-3, 17/22237-3, 18/20882-1, 16/05919-0, 17/06195-9)

ALLIAN, ANA PAULA; DUCHIEN, L; KOZIOLEK, A; MIRANDOLA, R; MARTINEZ, EMN; QUINTON, C; SCANDARIATO, R; SCANDURRA, P; TRUBIANI, C; WEYNS, D. Promoting Trust in Interoperability of Systems-of-Systems. 13TH EUROPEAN CONFERENCE ON SOFTWARE ARCHITECTURE (ECSA 2019), VOL 2, v. N/A, p. 4-pg., 2019-01-01. (17/22237-3, 18/20882-1, 18/21517-5, 16/05919-0, 17/06195-9)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

SILVA, Bruno Sena da. KnowSoS: A Software Architecture for Knowledge Discovery in Systems-of-Systems. 2020. Master's Dissertation - Universidade de São Paulo (USP). Instituto de Ciências Matemáticas e de Computação (ICMC/SB) São Carlos.