Collaborative edge-cLoud continuum and Embedded AI for a Visionary industry of thE futuRe

How do you run faster apps while using less energy? 

That’s the million-dollar question in edge-cloud systems!  CLEVER Project is tackling it with a blend of engineering smarts and intelligent orchestration.  📢 Our new research which was presented at CLOSER 2025, shows how to deploy microservice-based apps more efficiently by dynamically adjusting the processing speed (frequency) of each computing core across the edge-cloud continuum using…

Continue Reading

⚙️ Deploying Deep Neural Networks directly into network switches? Now it’s possible! 🚀 

The CLEVER Project presents a novel way to embed AI into programmable data planes — with zero arithmetic logic, zero stateful memory, and zero loss in performance.  🔍 Our latest innovation introduces a lookup table distillation technique that transforms complex DNNs into cascaded, stateless, P4-compatible flow tables, unlocking true in-network AI at wirespeed.  💡 Why…

Continue Reading

Newsletter 3.2. is out: Big strides in Edge AI from the CLEVER Project! 

Newsletter D3.2 marks a major milestone in accelerating hardware innovation at the edge, and it’s anything but ordinary.  🔍 What’s inside:  Neuromorphic processors (Innatera): Ultra-low power SNPs inspired by the brain, running PyTorch models for digital twins & AR retail.  Optical Neural Networks (TU Eindhoven): Light-speed inference with 100× better energy efficiency.  AI SoCs (Synopsys):…

Continue Reading

Boosting Data Trust with Efficient Annotations in Alvarium DCF!

Did you know that Data Confidence Fabrics (DCFs) are revolutionizing how we ensure trust in distributed systems? The Alvarium framework (backed by the Linux Foundation) is leading the charge by decoupling security metadata (“annotations”) from data, enabling scalable, transparent trust evaluation across heterogeneous networks.🛑 MYTH: Secure, trusted data pipelines must come with high overhead.✅ FACT:…

Continue Reading

🧠Smart AI, Smarter Networks: Predicting Retraining in Real-Time for 6G! 

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:…

Continue Reading