• Home
  • About
    • Michele Polese logo

      Michele Polese

      I am a Research Assistant Professor and the Technical Director of the Institute for Intelligent Networked Systems (INSI), Northeastern University, Boston, working on Open RAN, AI-RAN, dApps, spectrum sharing, and 6G.

    • Learn More
    • Email
    • LinkedIn
    • Github
  • Research
  • Publications
  • Service
  • Projects
  • Travel

AI-RAN

AI-RAN brings AI and the radio access network onto shared, accelerated infrastructure: AI is used to improve the RAN (AI-for-RAN), AI workloads run alongside RAN workloads on the same compute (AI-and-RAN), and the RAN becomes a platform for AI services at the edge (AI-on-RAN). My work focuses on open and programmable architectures for this convergence, on how AI models are deployed, verified, and orchestrated in the RAN, and on testing all of this on real GPU-accelerated systems.

Community and industry

  • Chair of the AI-RAN Alliance AI-and-RAN Working Group (WG2), elected position (2025-2028), leading tasks on architecture and AI/ML workflows.
  • Co-founder of zTouch Networks, winner of the Deutsche Telekom/T-Mobile T-Challenge 2026 and an AI-RAN Alliance Innovation Award.
  • Keynote “Toward Open, Programmable, Intelligent, and Secure AI-RAN,” ACM WiseML 2026.

Code and testbeds

  • AgentRAN: open-source agentic AI framework for the autonomous control of Open RAN systems.
  • X5G: open, multi-vendor, end-to-end private 5G O-RAN testbed with NVIDIA ARC (Aerial) and OpenAirInterface. See also Open6G.

Key papers

  • M. Polese, N. Mohamadi, S. D’Oro, and T. Melodia, “Beyond Connectivity: An Open Architecture for AI-RAN Convergence in 6G,” IEEE Communications Magazine (to appear). arXiv
  • M. Elkael, S. D’Oro, L. Bonati, M. Polese, Y. Lee, K. Furueda, and T. Melodia, “AgentRAN: An Agentic AI Architecture for Autonomous Control of Open 6G Networks,” IEEE Communications Magazine (to appear). arXiv
  • M. Elkael, M. Polese, R. Prasad, S. Maxenti, and T. Melodia, “ALLSTaR: Automated LLM-Driven Scheduler Generation and Testing for Intent-Based RAN,” IEEE Transactions on Mobile Computing (to appear). arXiv
  • S. Maxenti, R. Shirkhani, M. Elkael, L. Bonati, S. D’Oro, T. Melodia, and M. Polese, “AutoRAN: Automated and Zero-Touch Open RAN Systems,” IEEE Transactions on Mobile Computing (to appear). arXiv
  • N. N. Santhi, D. Villa, M. Polese, S. D’Oro, Y. Lee, K. Furueda, and T. Melodia, “ARCHES: Adaptive Real-Time Switching of AI Models for the RAN,” 2026. arXiv
  • G. Gemmi, M. Polese, and T. Melodia, “A Techno-Economic Framework for Cost Modeling and Revenue Opportunities in Open and Programmable AI-RAN,” ICCCN 2026.
  • D. Villa, I. Khan, F. Kaltenberger, N. Hedberg, R. S. da Silva, S. Maxenti, L. Bonati, A. Kelkar, C. Dick, E. Baena, J. M. Jornet, T. Melodia, M. Polese, and D. Koutsonikolas, “X5G: An Open, Programmable, Multi-vendor, End-to-end, Private 5G O-RAN Testbed with NVIDIA ARC and OpenAirInterface,” IEEE Transactions on Mobile Computing, 2025. arXiv

See also: dApps and the E3 interface and the full publication list.