Centro de Informática · UFPE

Intelligence inside the network

We investigate how a mobile network can observe its own state, decide and act without human intervention. We research 5G and beyond (NextG), from the Open RAN to the core.

Mission

Putting the decision inside the network: allocating resources, choosing routes, and performing handover through AI-assisted decision-making and AI-native intelligence embedded in network operations.

The group is led by Kelvin Lopes Dias, a full professor at Centro de Informática, UFPE, where he has been since 2010. He is a CNPq research productivity fellow.

AI agents operating the core, optimized routing for critical traffic, handover in aerial networks. Published in leading journals such as IEEE Network and IEEE Transactions on Network and Service Management.

Since
2003, researching mobile networks
Graduated
Dozens of PhD and master's graduates
Output
Papers in the field's leading journals and conferences
Experiments
Simulation, analytical modeling and testbeds

Where we work

We work across the whole stack

The network is a stack, and every layer of it has its own decision to make.

  1. Radio

    Open RAN

    Open interfaces and xApps deciding on handover, energy and spectrum inside the RIC.

  2. Transport

    Transport network

    The path between the antenna and the core, with the route chosen by software.

  3. Core

    AI-orchestrated core

    The core as a system that learns, observes and acts on its own functions.

  4. Edge

    Edge computing

    Processing close to the user, with hard deadlines to meet.

  5. Application

    What the network sustains

    Services that only exist if the network delivers: vehicles, healthcare and instrumented cities.

See the five layers in detail

Admissions

We are looking for master's and doctoral students

There are open topics in 5G and beyond (NextG): Open RAN, AI-orchestrated 6G core, aerial networks and network observability. Scholarships through CNPq, CAPES and FACEPE.

See the open topics