Research
Overview
Research at the LRC Lab encompasses various topics in computer science and networking. Our team is dedicated to exploring innovative approaches to solving complex problems and creating solutions that have practical applications. Some of our current research areas include:
Federated learning over PONs: We are investigating using federated learning techniques over passive optical networks (PONs) to improve data privacy and efficiency in distributed machine learning.
Reinforcement learning for SDN: Our team is developing new algorithms and methods for using reinforcement learning in software-defined networking (SDN) to optimize network performance and resource allocation.
Mobile fronthauling: We are exploring ways to improve mobile fronthauling, which involves transmitting data between the cell tower and the central processing unit, to reduce latency and increase network capacity.
Drones: We are investigating the use of drones in various applications, including environmental monitoring, disaster response, and delivery services.
Fog computing: Our team is exploring the potential of fog computing, which involves processing data at the network’s edge, to improve distributed systems’ performance and efficiency.
Multimedia services: We are developing new techniques for improving the quality and reliability of multimedia services, including video streaming, online gaming, and virtual reality.
6G: As the next generation of wireless technology, 6G promises to deliver unprecedented speeds and capabilities. Our team is exploring the potential of 6G and developing new techniques for optimizing its performance.
State-of-the-art facilities, equipment, and collaborations with leading institutions and industry partners support our research. We welcome students and researchers with a passion for innovation and a desire to make a real-world impact to join our team. Please contact us to learn more about current research opportunities
FL over PON Networks
Federated Learning over Next-Generation Ethernet Passive Optical Networks
Description:
Federated Learning (FL) is a distributed machine learning type of processing that preserves the privacy of user data, sharing only the parameters of ML models with a common server. The processing of FL requires specific latency and bandwidth demands that must be fulfilled by the operation of the communication network. This paper introduces two Dynamic Wavelength and Bandwidth Allocation algorithms for TWDM-PONs: one based on bandwidth reservation and the other on statistical multiplexing for the Quality of Service provisioning for FL traffic over 50 Gb/s Ethernet Passive Optical Networks.
Publication(s):
Team members:
Oscar Ciceri, Carlos A. Astudillo, Nelson L.S. da Fonseca
FL in CAVs
FLEXE: Investigating Federated Learning in Connected Autonomous Vehicle Simulations
Description:
Due to the increased computational capacity of Connected and Autonomous Vehicles (CAVs) and worries about transferring private information, it is becoming more and more appealing to store data locally and move network computing to the edge. This trend also extends to Machine Learning (ML) where Federated learning (FL) has emerged as an attractive solution for preserving privacy. Today, to evaluate the implemented vehicular FL mechanisms for ML training, researchers often disregard the impact of CAV mobility, network topology dynamics, or communication patterns, all of which have a large impact on the final system performance. To address this, this work presents FLEXE, an Open Source extension to Veins that offers researchers a simulation environment to run FL experiments in realistic scenarios. FLEXE combines the popular Veins framework with the OpenCV library. Using the example of traffic sign recognition, we demonstrate how FLEXE can support investigations of FL techniques in a vehicular environment.
Publication(s):
Team members:
Wellington Lobato, Joahannes B. D. Da Costa, Allan M. de Souza, Denis Rosário, Christoph Sommer, Leandro A. Villas