Dr. Roberto Rodrigues Filho

Assistant Professor

Department of Computing

Federal University of Santa Catarina

Araranguá, Santa Catarina, Brazil


Contact: roberto.filho [at] ufsc.br


Research Projects

SMART NEtworks and ServiceS for 2030 (SMARTNESS) (2024-current)

The SMARTNESS Engineering Research Center (ERC) targets developing cutting-edge advances in communication networks and digital application services scoped in strategic areas where significant scientific and technological impacts can be achieved towards 2030, in collaboration with the cloud and networking research communities. As 5G releases roll-out and the vision on 6G is being developed, SMARTNESS's main challenge is how to engineer (i.e., design and operate) cloud computing and network infrastructures with the adequate capabilities to empower next-generation Internet services and applications. The scope of end-to-end Internet-scale services is exceptionally broad and requires contributions from various disciplines along with large capital and human resource investments. However, the ongoing digital transformation in vertical industries and a shift towards open source network softwarization and disaggregation of infrastructures at multiple levels and protocol stack layers have opened well-scoped opportunities for accelerated innovation at unprecedented entry barriers for research enterprises based on academic and industrial partnerships. Cloud computing and network infrastructures are increasingly becoming more multidisciplinary, requiring system-oriented end-to-end views that leverage advances in hardware (HW) for computing and networking, modern software (SW) architectures, machine intelligence (AI/ML), user interfaces, "as a Service'' consumption and new business models, among other engineering disciplines (e.g., energy efficiency and design for security). SMARTNESS aims at exploiting well-thought-out opportunities through a proper methodology based on the confluence of parallel research strands (RS) tailored for successful impact research and innovation at world-class levels towards the realization of challenging use cases in Internet scenarios for industry and society with a 2030 horizon view.

Funding Agency: The São Paulo Research Foundation, FAPESP, Brazil.
Institution: University of Campinas (UNICAMP), Brazil.
Role: Research Associate.

Orchestrating Applications on Edge Computing (2022)

This pilot project aims to investigate a service placement orchestrator to explore the potential of the edge and cloud computing infrastructure. This project is divided into three main stages. The first is dedicated to investigating and assembling a testbed to simulate an edge-cloud infrastructure and define a use case for experiments. The second stage is dedicated to exploring technologies and concepts to help define and build the service orchestrator, a microservices-based video streaming application, and to conduct experiments in a controlled environment. Finally, the last stage is dedicated to conducting experiments with the orchestrator in the edge-cloud infrastructure considering user mobility. Also, as part of the last stage, we aim to explore ideas about a self-monitoring system and QoE composable model for applications running in the edge-cloud continuum.

Funding Agency: Ericsson Researcher, Sweden.
Institution: University of Campinas (UNICAMP), Brazil.
Role: Researcher (Postdoctoral Researcher).

Autonomous Composition of Software for Smart Cities (2020-2022)

Contemporary systems are often deployed in highly volatile and heterogeneous operating environments which make them greatly complex. Smart Cities are a notable example that illustrates all aspects of the complexity of contemporary systems. In the software development process of Smart Cities, we often use technologies that aim to mitigate problems related to the creation and management of modern systems, such as the application of microservices to construct the software platform that abstracts the device infrastructure spread throughout the city, and Software Defined Networks (SDN) for the Internet of Things (IoT) to provide more flexibility for interconnecting devices. However, these technologies, when used to support software adaptation at runtime, still demand the definition of the system's adaptation logic that determines when and to which software configuration the system must adapt. The manual definition of the adaptation logic is not desirable when considering large scale systems, for which it is hard to predict the events in the operating environment that impact the system's performance and require adaptation. A promising approach that enables systems in any application domain to learn at runtime their own adaptation logic, and thus deals with uncertainty in the operating environment, is named Emergent Software Systems (ESS). Therefore, this proposal aims to explore the ESS concept in tandem with microservices and SDN for IoT to autonomously compose software modules for Smart Cities, dealing with the high dynamicity and uncertainty of the operating environment that is characteristic of this application domain. At last, we aim to contribute to the advancement of the state-of-the-art of self-adaptive/autonomic systems and their role in managing the complexity in the current software ecosystem of Smart Cities.

Funding Agency: The São Paulo Research Foundation, FAPESP, Brazil.
Institution: Federal University of Goiás (INF-UFG), Brazil.
Role: Researcher (Postdoctoral Fellow).

The Emergent Self-Aware Data Centre (2017-2020)

This is a Leverhulme-funded project examining fully automated, continuous self-assembly of large distributed systems at scale. Our approach offers a strategy that generalises to software as a whole, but focuses on data centre infrastructures as a timely example for which enhanced efficiency will have very broad impact. This research takes a novel approach that inverts the software development process to put computers in the leading role. Using this approach, entire distributed software systems will autonomously self-assemble from a large set of small behaviours, to satisfy a given goal. Once assembled, these systems will continually discover their own capabilities by learning about the different ways in which they can assemble themselves and how those assemblies affect their performance under different conditions. This happens while a target software system is live, running in its normal production environment, so that everything is learned based on the reality to which the system is actually subjected. This work builds upon the EPSRC Deep Online Cognition project and its introduction of the emergent software systems concept. We use the Dana platform (http://www.projectdana.com/) to provide a highly-adaptive substrate for emergent software.

Funding Agency: The Leverhulme Trust, UK.
Institution: Lancaster University (SCC), UK.
Role: Researcher (Postdoctoral Research Associate).

Deep Online Cognition in Modular Software (2015-2017)

This research has developed the world's first approach to runtime emergent software - these are software systems which assemble themselves from small component models, and continually re-assemble themselves from other parts as they learn which combinations of behaviour work best in the current environment in which they are operating. We have developed both the fundamental software-building technology to enable this, and the broader machine learning / AI models to orchestrate it. We have demonstrated our work using data centre software such as web servers, showing that such software can rapidly learn how best to design itself in real-time to maximise its own efficiency, without any human guidance on how to do this. EPSRC Reference: EP/M029603/1.

Funding Agency: EPSRC, UK.
Institution: Lancaster University (SCC), UK.
Role: Researcher (PhD Student).