As Beyond 5G (B5G) networks evolve toward zero-touch automation, one critical question emerges:  When should AI/ML models be retrained to keep up with dynamic traffic and avoid SLA violations?  🚨 The CLEVER Project introduces a predictive retraining approach—using unsupervised learning to decide when to retrain AI/ML models deployed in Open RAN (O-RAN) systems. The goal:…

CLEVER-project is at #ICTON2025, with partners from #CNIT.   Come to our talk or exploit the breaks to share a fruitful discussion about our most recent developments!  

In an era of real-time data and rapidly evolving urban dynamics, concept drift is a silent killer of AI accuracy. As patterns shift (think lockdowns, weather anomalies, or energy crises), traditional models fail.  As part of the CLEVER Project, we introduce a resilient, containerized edge computing architecture (EMDC) that automatically detects and adapts to concept…

CLEVER’s layered middleware is the answer! It automates orchestration, connecting compute/storage across cloud & edge for smart deployments & max resource use.Here’s CLEVER in Action:1- Request lands at Frontend (specs included).2- Where to run it? Global Scheduler + Knowledge Graph pick the best spot.3- Off it goes to the perfect edge node (like Far Edge) for execution.4-…

Introducing our flexible forecasting platform for Zero Touch Networking and Digital Twinning, developed as part of the CLEVER Project 🔍  In today’s dynamic 5G and beyond environments, reactivity is not enough. Network automation must evolve into proactivity — where systems anticipate failures, forecast traffic, and autonomously optimize performance.  📶 Our platform uses real-time and historical…