As digital infrastructure evolves, traditional monolithic applications are rapidly reaching their limits. With the rise of 5G/6G, virtualization, and optical networks, application design must adapt to meet increasing Quality of Service (QoS) demands. Enter the...
Lexicographic Optimization in Action: Prioritizing What Matters in Multi-Objective Problems
In our latest work on the Allegro project, we applied lexicographic optimization to tackle complex combinatorial problems involving conflicting objectives like cost, latency, and availability. Rather than optimizing all objectives at once, lexicographic optimization...
Allegro Project Update: Performance Evaluation of DRL-based Storage Allocation
As part of our ongoing work in intelligent distributed storage, we evaluated the performance of our Deep Reinforcement Learning (DRL) mechanism during the inference stage, comparing it against an optimal solver across various optimization objectives. 🧠Figure 26...
Allegro Project Update: Training Our Deep Reinforcement Learning Mechanism
Before deploying our DRL-powered distributed storage allocation system, we invested in an intensive training phase to ensure our agent’s efficiency and stability. 🎯 By carefully tuning the hyperparameters α (learning rate), β (latency weight), and γ (discount factor),...
Machine Learning Function Orchestrator (MLFO) in ALLEGRO
The ALLEGRO project introduces the MLFO, a dedicated orchestrator for managing distributed AI/ML pipelines across the network. Unlike traditional intent-based systems focused on single network entities, MLFO enables a global, scalable, and reconfigurable AI/ML...
AI/ML Agents in the ALLEGRO Project
In the ALLEGRO approach, AI/ML agents are designed as intelligent software entities responsible for managing and optimizing specific services. These agents are built with a modular architecture to ensure agility, security, and seamless integration. 🔍 Key Components:...
ALLEGRO Project: Transport Network Slicing for 5G & Beyond
As 5G services evolve and diversify, network slicing emerges as a foundational technology—enabling transport networks to deliver customized, on-demand, and performance-assured services across multiple domains and layers. In the ALLEGRO architecture, Transport Network...
ALLEGRO Project: Smart Orchestration for Multidomain Optical Networks
In today’s complex networking environments, efficient end-to-end service delivery demands multisegment and multidomain orchestration. Within the ALLEGRO project, we are pioneering a comprehensive framework to manage intent-based requests across multiple...
Dynamic Optical Line Control with the OMS Controller
In modern optical networks, real-time control and visibility of the Optical Multiplex Section (OMS) are crucial. Within the ALLEGRO architecture, the OMS Controller plays a pivotal role by managing amplifier operational settings and line performance between ROADMs. 🧠...
Automated Light path Deployment with LP-VE in ALLEGRO
As networks grow denser and more dynamic, automation becomes essential. In the Horizon Europe ALLEGRO project, we’ve developed the Lightpath Validation Engine (LP-VE) to enable fully automated, QoT-aware optical lightpath deployment using a Physical Layer Digital Twin...