Federated learning over next-generation ethernet passive optical networks
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 privacy of user data, sharing only the parameters of ML models with a common server …
Applying cognitive dynamic learning strategies for margins reduction in operational optical networks
Today's optical transport networks are complex already and the support of the new arising
services will further increase such complexity. Traditional deterministic network procedures …
services will further increase such complexity. Traditional deterministic network procedures …
Efficient queue based dynamic bandwidth allocation scheme for Ethernet PONs
PK Choudhury, P Saengudomlert - IEEE GLOBECOM 2007 …, 2007 - ieeexplore.ieee.org
We propose an optical line terminal (OLT) centric dynamic bandwidth allocation (DBA)
scheme based on individual requests from service queues in optical network units (ONUs) …
scheme based on individual requests from service queues in optical network units (ONUs) …
Self-Adaptive Bandwidth Allocation to Address Dynamic Traffic Concept Drift in Optical Access Networks
In this invited talk, we will review our recent work on online reinforcement learning-based
dynamic bandwidth allocation (ORL-DBA) scheme that addresses concept drift in ML …
dynamic bandwidth allocation (ORL-DBA) scheme that addresses concept drift in ML …
Demand assigned capacity management (DACM) in IP over optical (IPO) networks
DO Awduche, B Jabbari - IEEE/ACM Transactions on …, 2006 - ieeexplore.ieee.org
The demand assigned capacity management (DACM) problem in IP over optical (IPO)
network aims at devising efficient bandwidth replenishment schedules from the optical …
network aims at devising efficient bandwidth replenishment schedules from the optical …
Multiconstraints fuzzy-logic-based scheduling algorithm for passive optical networks
R Razavi, K Guild - Journal of Optical Networking, 2009 - opg.optica.org
Presented is a fuzzy-logic-based scheduling algorithm for passive optical networks (PONs)
that considers four different metrics to allocate an upstream bandwidth to optical network …
that considers four different metrics to allocate an upstream bandwidth to optical network …
From 5G to beyond: Passive optical network and multi-access edge computing integration for latency-sensitive applications
A recent paradigm shift in support of 5G-and-beyond (5GB), Human-to-Machine/Robot
(H2M/R), and the Tactile Internet has resulted in a surge of latency-sensitive applications …
(H2M/R), and the Tactile Internet has resulted in a surge of latency-sensitive applications …
Experimental evaluation of a latency-aware routing and spectrum assignment mechanism based on deep reinforcement learning
C Hernández-Chulde, R Casellas… - Journal of Optical …, 2023 - opg.optica.org
The introduction of futuristic and challenging use cases of 5G and 6G communications will
demand strict requirements in terms of high bandwidth and low latency. Optical backbone …
demand strict requirements in terms of high bandwidth and low latency. Optical backbone …
Combining long-short term memory and reinforcement learning for improved autonomous network operation
Combining Long-Short Term Memory and Reinforcement Learning for Improved Autonomous
Network Operation Page 1 Combining Long-Short Term Memory and Reinforcement Learning …
Network Operation Page 1 Combining Long-Short Term Memory and Reinforcement Learning …