Carlos Natalino Da Silva
Carlos Natalino is a Researcher with the Optical Networks Unit. His research focuses on network automation and on the challenges and opportunities for application of machine learning in the network automation context. In particular, over the past years, he has been researching how to leverage machine learning for optical network design and operation, in problems such as resource efficiency (e.g., spectrum) and physical layer security. Carlos has been involved in several national and international projects funded by research bodies in EU and Brazil. He has also been involved in teaching computer programming courses in Brazil and Sweden. He is an IEEE and Optica member.
Showing 69 publications
Programmable Filterless Optical Networks: Architecture, Design and Resource Allocation
Towards Explainable Reinforcement Learning in Optical Networks: The RMSA Use Case
AI/ML-as-a-Service for optical network automation: use cases and challenges [Invited]
Analysis and Mitigation of Unwanted Biases in ML-based QoT Classification Tasks
TAPI-based Telemetry Streaming in Multi-Domain Optical Transport Network
P5: Event-driven Policy Framework for P4-based Traffic Engineering
Demonstrating the Benefits of Service-Aware Pod Autoscaling with Shared Resources
Machine-Learning-as-a-Service for Optical Network Automation
Cascading-failure-Aware Disaster Recovery in Optical Cloud Networks
Machine-Learning-as-a-Service for Optical Networks: Use Cases and Benefits
P4-based Telemetry Processing for Fast Soft Failure Recovery in Packet-Optical Networks
Scalable and Efficient Pipeline for ML-based Optical Network Monitoring
DRL-based RMSCA for SDM Networks with Core Switching in Multi-Core Fibres
Optical Network Automation and Programmability for 6G: State-of-the-Art, Vision, and Challenges
Proactive Spectrum Defragmentation Leveraging Spectrum Occupancy State Information
Benefits of Pod dimensioning with best-effort resources in bare metal cloud native deployments
A Flexible and Scalable ML-Based Diagnosis Module for Optical Networks: A Security Use Case
Root Cause Analysis for Autonomous Optical Network Security Management
Machine learning for network security management, attacks, and intrusions detection
Microservice-Based Unsupervised Anomaly Detection Loop for Optical Networks
Linear Regression vs. Deep Learning for Signal Quality Monitoring in Coherent Optical Systems
Feedforward Neural Network-Based EVM Estimation: Impairment Tolerance in Coherent Optical Systems
DeepDefrag: A deep reinforcement learning framework for spectrum defragmentation
Deep Learning Assisted Pre-Carrier Phase Recovery EVM Estimation for Coherent Transmission Systems
Fast signal quality monitoring for coherent communications enabled by CNN-based EVM estimation
Spectrum Anomaly Detection for Optical Network Monitoring using Deep Unsupervised Learning
Scalable Physical Layer Security Components for Microservice-Based Optical SDN Controllers
Storage Protection with Connectivity and Processing Restoration for Survivable Cloud Services
A GPU-assisted NFV framework for intrusion detection system
Autonomous Security Management in Optical Networks
Network automation: challenges, enablers, and benefits
Machine Learning for Optical Network Security Management
The Optical RL-Gym: an open-source toolkit for applying reinforcement learning in optical networks
Structural Methods to Improve the Robustness of Anycast Communications to Large-Scale Failures
Machine Learning for Cognitive Optical Network Security Management
Availability-Guaranteed Service Function Chain Provisioning with Optional Shared Backups
Forecasting power load curves from spatial and temporal mobile data
Network Slicing Automation: Challenges and Benefits
Design of Programmable Filterless Optical Networks
Content placement in 5G-enabled edge/core data center networks resilient to link cut attacks
Root Cause Analysis for Autonomous Optical Networks: A Physical Layer Security Use Case
A Heuristic Approach for the Design of UAV-Based Disaster Relief in Optical Metro Networks
Machine Learning for Optical Network Security Monitoring: A Practical Perspective
Content placement in 5G‐enabled edge/core datacenter networks resilient to link cut attacks
Network-wide localization of optical-layer attacks
Functional Metrics to Evaluate Network Vulnerability to Disasters
Enhancing optical network security with machine learning
Reinforcement Learning for Slicing in a 5G Flexible RAN
Infrastructure upgrade framework for content delivery networks robust to targeted attacks
Demonstration of Machine-Learning-Assisted Security Monitoring in Optical Networks
Energy- and fatigue-aware RWA in optical backbone networks
Cost Benefits of Centralizing Service Processing in 5G Network Infrastructures
Machine Learning Methods for Slice Admission in 5G Networks
One-Shot Learning for Modulation Format Identification in Evolving Optical Networks
Microservice-Based Unsupervised Anomaly Detection Loop for Optical Networks
Download publication list
You can download this list to your computer.
Filter and download publication list
As logged in user (Chalmers employee) you find more export functions in MyResearch.
You may also import these directly to Zotero or Mendeley by using a browser plugin. These are found herer:
Zotero Connector
Mendeley Web Importer
The service SwePub offers export of contents from Research in other formats, such as Harvard and Oxford in .RIS, BibTex and RefWorks format.
Showing 7 research projects
“Efficient Confluent Edge Networks (ECO-eNET),” EU HORIZON project
Photonic-Assisted Hardware for Reservoir Computing (BRAIN)
Secured autonomic traffic management for a Tera of SDN flows (TeraFlow)
Automation of Network edge Infrastructure & Applications with aRtificiAl intelligence, ANIARA
Smart City Concepts in Curitiba - low-carbon transport and mobility in a digital society