Ponències/Comunicacions de congressos
Recent Submissions
-
Experimental demonstration of SDN-enabled reconfigurable disaggregated data center infrastructure
(Institute of Electrical and Electronics Engineers (IEEE), 2021)
Conference report
Restricted access - publisher's policyA 4-node prototype of SDN-controlled disaggregated data-center network is experimentally demonstrated based on the nanoseconds optical switch, enabling flexible hardware resource provisioning and dynamic resource reallocation. ... -
Desarrollo de un entorno de simulación para el aprendizaje de un algoritmo de navegación autónoma de un velero de 2 metros de eslora
(Universidade da Coruña. Servizo de Publicacións, 2021)
Conference lecture
Open AccessSe presenta el desarrollo de un entorno virtual de simulación basado en Python Turtle para el entrenamiento de un algoritmo de aprendizaje por refuerzo destinado a la navegación autónoma de un velero de 2 metros de eslora. ... -
Autonomous resource assignment for optimal utilization in optical data centre infrastructures
(Optica Publishing Group, 2021)
Conference report
Restricted access - publisher's policyWe present an architectural solution based on data analytics for self-organizing optical data centers. Thanks to a reinforcement learning-based cognitive layer, an adaptive and autonomous resource assignment to deployed ... -
A latency-aware real-time video surveillance demo: network slicing for improving public safety
(Institute of Electrical and Electronics Engineers (IEEE), 2021)
Conference report
Open AccessWe report the automated deployment of 5G services across a latency-aware, semi- disaggregated, and virtualized metro network. We summarize the key findings in a detailed analysis of end-to-end latency, service setup time, ... -
Lightweight optical constellation modeling by concatenating artificial neural networks
(Institute of Electrical and Electronics Engineers (IEEE), 2021)
Conference report
Open AccessA lightweight optical constellations modeling method based on concatenating ANNs is proposed. Statistical validation of the reproduced constellations is shown. The method accelerates data generation and facilitates detecting ... -
An autoencoder-based solution for IQ constellation analysis
(Institute of Electrical and Electronics Engineers (IEEE), 2021)
Conference report
Open AccessA method for IQ constellation analysis based on Autoencoders is proposed. Exhaustive numerical results show accurate physical metric prediction and large data compression, while providing useful model explainability. -
Implementing a machine learning function orchestration
(Institute of Electrical and Electronics Engineers (IEEE), 2021)
Conference report
Open AccessDeployment of Machine Learning (ML) applications require from an Orchestrator to create ML functions that are connected as ML pipelines. Orchestrator implementation and demonstration for the deployment and reconfiguration ... -
Reliable and accurate autonomous flow operation based on off-line trained reinforcement learning
(Institute of Electrical and Electronics Engineers (IEEE), 2021)
Conference report
Open AccessA RL agent trained offline for reliability and able to refine its policies during online operation is proposed. Results for three illustrative flow automation use cases show remarkable performance with extraordinary ... -
Combining long-short term memory and reinforcement learning for improved autonomous network operation
(Institute of Electrical and Electronics Engineers (IEEE), 2021)
Conference report
Open AccessA combined LSTM and RL approach is proposed for dynamic connection capacity allocation. The LSTM predictor anticipates periodical long-term sharp traffic changes and extends short-term RL knowledge. Numerical results show ... -
Experimental demonstration of widely tunable rate/reach adaptation from 80 km to 12,000 km using probabilistic constellation shaping
(2020)
Conference report
Open AccessWe experimentally demonstrate the rate/reach adaptability of probabilistically constellation-shaped quadrature amplitude modulation across from 80 km to 12,000 km using the same 32-GBaud transponder hardware and highlight ... -
On the benefits of probabilistic constellation shaping in Flex-Grid/MCF dynamic optical backbone networks
(Institute of Electrical and Electronics Engineers (IEEE), 2021)
Conference report
Open AccessIn this paper, we propose a novel methodology for estimating the worst-case spectral efficiency (b/s/Hz) of end-to-end paths across a Multi-Core Fiber (MCF)-enabled Flex-Grid optical network, accounting for physical link ... -
Adaptive and iterative QoT estimator retraining for launch power optimization
(Institute of Electrical and Electronics Engineers (IEEE), 2021)
Conference report
Open AccessWe dynamically optimize the transponders launch powers with iterative closed control loops. We close the loop after an adaptable number of algorithm’s intermediate calculations, to monitor and retrain the QoT estimator ...