profile_picture
Andrea Lacava
Research Scientist, Institute for Intelligent Networked Systems
a.lacava@northeastern.edu

I am a Research Scientist at the Institute for Intelligent Networked Systems (INSI) at Northeastern University. I designed the E3 interface and the architecture of dApps, the real-time controllers for the Open RAN (O-RAN) architecture. dApps bring sub-millisecond, AI-driven decision-making to the edge of the cellular network, and E3 is the interface that connects them to disaggregated RAN nodes. I built the open-source dApp framework and the libe3 library, and I partnered on their adoption into OpenAirInterface, OCUDU, and the NVIDIA Aerial framework. I am also a collaborator of the OpenAirInterface (OAI) project. Today my work extends this line toward agentic AI: LLM-driven frameworks, RAG pipelines, and MCP interfaces that let agents reason about and control the RAN, plus AI-powered sensing dApps that turn the RAN into a distributed spectrum sensor. I have presented this demo at many venues, including MWC 2026. I am also a member of the AI-RAN Alliance, where I contribute actively in building the 6th generation of the cellular networks and I lead the research Work Item 6 in WG 1 (AI-on-RAN).

I completed a dual PhD in Computer Engineering (Northeastern University) and Internet and Communication Technologies (Sapienza University of Rome) in 2025, graduating with honors, advised by Tommaso Melodia and Francesca Cuomo. My thesis, on enabling intelligent nextG cellular networks through the Open RAN architecture, includes the dApp architecture and ns-O-RAN, a framework that connects a real-world near-real-time RIC to ns-3 to generate large-scale realistic datasets for deep reinforcement learning xApps. The dApp concept and the E3 interface are currently gaining momentum among industry players such as NVIDIA, DeepSig, and Nokia, while ns-O-RAN is now part of the O-RAN Software Community and has been adopted by companies such as Mavenir and Orange.

My work has been recognized with the Best Paper Award at IEEE Globecom 2024, the Best Demo Award Runner-Up at IEEE CCNC 2024, and induction into Northeastern’s Laurel and Scroll 100 Honor Society. I serve on program committees (INFOCOM, VTC, WCNC), am on the organizing committee of the OAI Foundation Hands-on Workshop, and served as Technical Chair of the RESTART Tech Camp on 5G and Open RAN. I am passionate about turning open, programmable networks into intelligent ones, and I would love to hear about projects at the intersection of AI and next-generation wireless.

Selected honors:

  • Inducted into Northeastern University’s Laurel and Scroll 100 Honor Society (2025)
  • Best Paper Award, IEEE Globecom 2024 (TwiNet)
  • Best Demo Award Runner-Up, IEEE CCNC 2024 (Energy Saving in Open RAN)

You can find a detailed list about my publications at my Google Scholar profile.

Please also refer to my LinkedIn profile for the recent activities.

Interests

  • Open RAN (O-RAN) Architecture and AI-RAN
  • Agentic AI for Cellular Networks
  • 5G and beyond cellular networks
  • Security of the Cellular Networks

Academia

Northeastern University
2020 - 2025
Ph.D. Computer Engineering
supervised by Prof. Tommaso Melodia
Sapienza, University of Rome
2020 - 2025
Ph.D. Information and Communication Technology (ICT)
supervised by Prof. Francesca Cuomo
Sapienza, University of Rome
2018 - 2020
M.Sc. Cybersecurity

News

News about projects and research I am involved in
  • Invited speaker and organizing committee member at the OAI Foundation Hands-on Workshop on AI-native wireless systems and ISAC, North Carolina State University, Raleigh, NC, USA, Oct. 2026.
  • Presented the AI-Based Spectrum Sensing and Sharing in the RAN demo at MWC 2026, Barcelona, Spain, Mar. 2026.
  • Presented dApps at the Annual INSI Industry Day, Northeastern University, Feb. 2026.
  • Presented the AI-Based Spectrum Sensing and Sharing in the RAN demo at the Brooklyn 6G Summit 2025, NYU Tandon, Fall 2025.
  • Technical Chair at the 3rd RESTART Tech Camp on 5G and Open RAN, Palermo University, Oct. 2025.
  • Joined the AI-RAN Alliance (WG 1 – AI-on-RAN), 2025.
  • I’ve been selected for the Laurel and Scroll Honor Society – Class of 2025 (induction ceremony), Northeastern University, May 2025.
  • Best Demo Award Runner-Up at IEEE CCNC 2024 for Enabling Deep Reinforcement Learning Research for Energy Saving in Open RAN, Las Vegas, NV, USA, Jan. 2025.

Publications

This list is indicative and does not fully reflect the latest status of my works, which is shown in my Google Scholar and my Scopus profiles.
How to Poison an xApp: Dissecting Backdoor Attacks to Deep Reinforcement Learning in Open Radio Access Networks, 2025, Computer Networks, vol. 273, doi: 10.1016/j.comnet.2025.111727
Andrea Lacava , Stefano Maxenti , Leonardo Bonati , Salvatore D'Oro , Alina Oprea , Tommaso Melodia , Francesco Restuccia
dApps: Enabling real-time AI-based Open RAN control, 2025, Journal of Computer Networks, doi: 10.1016/j.comnet.2025.111342
Andrea Lacava , Leonardo Bonati , Niloofar Mohamadi , Rajeev Gangula , Florian Kaltenberger , Pedram Johari , Salvatore D’Oro , Francesca Cuomo , Michele Polese , Tommaso Melodia
Enabling Intelligent nextG Cellular Networks through the Open RAN Architecture, 2025, Ph.D. Thesis, Sapienza University of Rome & Northeastern University
Andrea Lacava
Enabling Online Reinforcement Learning Training for Open RAN, 2024, 2024 IFIP Networking Conference (IFIP Networking), pp. 577-582
Andrea Lacava , Tommaso Pietrosanti , Michele Polese , Francesca Cuomo , Tommaso Melodia
ns-O-RAN: Simulating O-RAN 5G Systems in ns-3, 2023, Proceedings of the 2023 Workshop on ns-3 (WNS3 '23) — ACM Artifacts Available, doi: 10.1145/3592149.3592161
Andrea Lacava , Matteo Bordin , Michele Polese , Rajarajan Sivaraj , Tommaso Zugno , Francesca Cuomo , Tommaso Melodia
Programmable and customized intelligence for traffic steering in 5G networks using Open RAN architectures, 2022, IEEE Transactions on Mobile Computing, doi: 10.1109/TMC.2023.3266642
Andrea Lacava , Michele Polese , Rajarajan Sivaraj , Rahul Soundrarajan , Bhawani Shanker Bhati , Tarunjeet Singh , Tommaso Zugno , Francesca Cuomo , Tommaso Melodia
GENESIS: Harnessing AI Agents for Autonomous 6G RAN Synthesis, Research, and Testing, 2026, Submitted to IEEE Transactions on Mobile Computing (under review)
Tamerlan Aghayev , Maxime Elkael , Michele Polese , Minh Dat Nguyen , Gabriele Gemmi , Andrea Lacava , Ali Saeizadeh , Reshma Prasad , Paolo Testolina , Angelo Feraudo , Soumendra Nanda , Pedram Johari , Salvatore D'Oro , Tommaso Melodia
Research Report on dApp Architecture and Interfaces, 2026, O-RAN next Generation Research Group (nGRG) Contributed Research Report (nGRG-RR-2025-05)
Northeastern University , SoftBank , NVIDIA
xDevSM: An Open-Source Framework for Portable, AI-Ready xApps Across Heterogeneous O-RAN Deployments, 2026, Submitted to IEEE Transactions on Network and Service Management (under review)
Angelo Feraudo , Stefano Maxenti , Andrea Lacava , Leonardo Bonati , Paolo Bellavista , Michele Polese , Tommaso Melodia
Method and System for Sub-Millisecond Radio Resource Management and Monitoring in Open RAN, 2025, U.S. Provisional Patent Application No. 63/868,906 (Northeastern University)
Salvatore D'Oro , Tommaso Melodia , Michele Polese , Leonardo Bonati , Rajeev Gangula , Niloofar Mohamadi , Andrea Lacava
LibIQ: Toward Real-Time Spectrum Classification in O-RAN dApps, 2025, 2025 23rd Mediterranean Communication and Computer Networking Conference (MedComNet), doi: 10.1109/MedComNet65822.2025.11100289
Filippo Olimpieri , Noemi Giustini , Andrea Lacava , Salvatore D'Oro , Tommaso Melodia , Francesca Cuomo
Demo: Enabling Deep Reinforcement Learning Research for Energy Saving in Open RAN, 2025, 2025 IEEE 22nd Consumer Communications & Networking Conference (CCNC) — Best Demo Award Runner-Up, doi: 10.1109/CCNC54725.2025.10975928
Matteo Bordin , Andrea Lacava , Michele Polese , Francesca Cuomo , Tommaso Melodia
Design and Evaluation of Deep Reinforcement Learning for Energy Saving in Open RAN, 2025, 2025 IEEE 22nd Consumer Communications & Networking Conference (CCNC), doi: 10.1109/CCNC54725.2025.10976108
Matteo Bordin , Andrea Lacava , Michele Polese , Sai Satish , Manoj AnanthaSwamy Nittoor , Rajarajan Sivaraj , Francesca Cuomo , Tommaso Melodia
TwiNet: Connecting Real World Networks to their Digital Twins Through a Live Bidirectional Link, 2024, GLOBECOM 2024 - 2024 IEEE Global Communications Conference — Best Paper Award, doi: 10.1109/GLOBECOM52923.2024.10901203
Clifton Paul Robinson , Andrea Lacava , Pedram Johari , Francesca Cuomo , Tommaso Melodia
dApps for Real-Time RAN Control: Use Cases and Requirements, 2024, O-RAN next Generation Research Group (nGRG) Contributed Research Report (RR-2024-10)
Northeastern University , NVIDIA , Mavenir , MITRE , Qualcomm
Listen-While-Talking: Toward dApp-based Real-Time Spectrum Sharing in O-RAN, 2024, MILCOM 2024 - 2024 IEEE Military Communications Conference (MILCOM), doi: 10.1109/MILCOM61039.2024.10773685
Rajeev Gangula , Andrea Lacava , Michele Polese , Salvatore D'Oro , Leonardo Bonati , Florian Kaltenberger , Pedram Johari , Tommaso Melodia

Projects

Current and past projects of mine
dApps: Real-Time AI-Based Open RAN Control
ns-O-RAN: Open Source Open RAN Simulation Platform
Colosseum: The World’s Most Powerful Wireless Network Emulator