Northeastern University Wireless Networks and Embedded Systems Lab

Intent-based and Automated Control of 5G Networks

O-RAN Colosseum Integration

Existing wireless networks rely on closed and inflexible architectures that impose significant challenges into adopting new wireless networking technologies. The notion of software defined networking (SDN) has therefore been recently introduced to simplify network control and to make it easier to introduce and deploy new applications and services.

However, to date, existing SDN architecture are far from fulfilling the requirements of next-generation wireless networks because (i) the separate-then-centralize architecture of most existing SDNs requires high backhaul network capacity that can exceed the currently available capacity in large-scale and densely-deployed wireless networks; (ii) network engineers are typically required to have a thorough, expert understanding of the wireless network protocol stack, including the lower layers, to be able to dene complex control behaviors.

We propose and explore a radically different approach to SDN for next-generation wireless networks, studying the core building principles of a "Wireless Network Operating System" that provides the network designer with an intent-based and automated control of NextG networks.


The Wireless Network Operating System (WNOS) investigates the basic design principles for a new optimization-based operating system for ad hoc networks, with a radically different approach to SDN for infrastructure-less wireless networks. Departing from well-understood approaches inspired by OpenFlow, WNOS provides the network designer with an abstraction hiding (i) the lower-level details of the wireless protocol stack and (ii) the distributed nature of the network operations. Based on this abstract representation, the WNOS takes network control programs written on a centralized, high-level view of the network and automatically generates distributed cross-layer control programs based on distributed optimization theory that are executed by each individual node on an abstract representation of the radio hardware.

We have first identify the main architectural principles of WNOS. Then, we propose a new approach to automatically generate solution algorithms for each of the resulting subproblems in an automated fashion. Finally, we illustrate a prototype implementation of WNOS on software-defined radio devices and we have tested its effectiveness by considering specific cross-layer control problems. Experimental results indicate that, based on the automatically generated distributed control programs, WNOS can achieve 18%, 56% and 80.4% utility gain in networks with low, medium and high levels of interference; more importantly, we have illustrated how the global network behavior can be controlled by modifying a few lines of code on a centralized abstraction.


We built Arena, a wireless testing platform based on a grid of 64 antennas mounted on the ceiling of a 2240 square feet office-space environment. Each antenna is connected to programmable software-defined radios enabling sub-6 GHz 5G-and-beyond spectrum research. With 12 computational servers, 24 software defined radios synchronized at the symbol level, Arena provides the computational power and the scale to foster new technology development in some of the most crowded spectrum bands, and ensures a reconfigurable, scalable, and repeatable real-time experimental evaluation in a real wireless indoor environment. We showcase some of Arena capabilities in providing a testing ground for key wireless technologies, including synchronized MIMO transmission schemes, multi-hop ad hoc networking, multi-cell LTE networks, and spectrum sensing for cognitive radios.

Network Slicing Enforcement in 5G Networks

Radio access network (RAN) slicing refers to a vision where multiple mobile network operators (MNOs) are assigned virtual networks, i.e., the slices, instantiated on top of the same physical infrastructure. Existing work has addressed RAN slicing at different levels of network abstraction, but has often neglected a multitude of constraints of practical slicing systems. In this project, we aim at developing a novel framework for operator-to-waveform 5G RAN slicing. In the proposed framework, slicing operations are treated holistically, including MNO's selection of base stations (BSs) and maximum number of users, down to the waveform-level scheduling of resource blocks.

First, we show that the RAN slicing problem is NP-hard. Then, we design a variety of optimization algorithms that render the solution scalable as the size of the RAN increases. We extensively evaluate their performance through simulations and experiments on a testbed made up of 8 software-defined radio peripherals. Experimental results revealed that not only do our algorithms enforce the slicing policies, but can also double the total network throughput. Moreover, they also show that the proposed RAN slicing framework (i) generates RAN slices where 95% of allocated resources can be used to perform coordination-based 5G transmission technologies, and (ii) facilitates the coexistence of multiple RAN slices providing up to 120% improvement in terms of SINR experienced by mobile users.


We study an essential yet challenging problem in 5G wireless networks: Is it possible to enable spectrally-efficient spectrum sharing for heterogeneous wireless networks with different, possibly incompatible, spectrum access technologies on the same spectrum bands; without modifying the protocol stacks of existing wireless networks? To answer this question, we explore the system challenges that need to be addressed to enable a new spectrum sharing paradigm based on beamforming.

We propose CoBeam, a novel framework where a newly-deployed wireless network is allowed to access a spectrum band based on cognitive beamforming without mutual temporal exclusion, i.e., without interrupting the ongoing transmissions of coexisting wireless networks on the same bands; and without cross-technology communication. We describe the main components of CoBeam, including programmable physical layer driver, cognitive sensing engine, beamforming engine, and scheduling engine. Then, we showcase the potential of the CoBeam framework by designing a practical coexistence scheme between Wi-Fi and LTE on unlicensed bands. We implement a prototype of the resulting coexisting Wi-Fi/U-LTE network built on off-the-shelf software radios. Experimental performance evaluation results indicate that CoBeam can achieve significant throughput gain, while requiring no signaling exchange between the coexisting wireless networks.

Low-complexity Distributed Network Slicing

RAN slicing is an effective methodology to dynamically allocate networking resources in 5G networks. One of the main challenges of RAN slicing is that it is provably an NP-Hard problem. In this project, we investigate the challenging problem of designing privacy-preserving, low-complexity, near-optimal distributed algorithms for RAN network slicing, where the MVNOs selfishly compete with each other to acquire slices from the telecom operators while minimizing their cost.

First, we model the slicing problem as a congestion game, and demonstrate that such game admits a unique Nash equilibrium (NE). Then, we evaluate the Price of Anarchy (PoA) of the NE (i.e., the efficiency of the NE as compared to the social optimum), and demonstrate that the PoA is upper-bounded by 3/2. Next, we propose two fully-distributed algorithms that provably converge to the unique NE without revealing privacy-sensitive parameters from the slice tenants. Moreover, we introduce an adaptive pricing mechanism of the wireless resources to improve the network owner's profit. We evaluate the performance of our algorithms through simulations and an experimental testbed deployed on the Amazon EC2 cloud, both based on a real-world dataset of base stations from the OpenCelliD project. Results conclude that our algorithms converge to the NE rapidly and achieve near-optimal performance, while our pricing mechanism effectively improves the profit of the network owner.


Wireless networks are extremely vulnerable to a plethora of security threats, e.g., eavesdropping, jamming, and spoofing. Recently, a number of next-generation cross-layer attacks have been unveiled, which leverage small changes on one network layer to stealthily and significantly compromise another target layer. Since cross-layer attacks are unpredictable in nature, novel learning-based security techniques are needed.

We propose FORMAT, a novel framework to tackle cross-layer security attacks in wireless networks. FORMAT is based on Bayesian learningand made up by a detection and a mitigation component. On one hand, the attack detection component constructs a model of observed evidence to identify stealthy attack activities. On the other hand, the mitigation component uses optimization theory to achieve the desired trade-off between security and performance. The proposed FORMAT framework has been extensively evaluated and compared with existing work by simulations and experiments obtained with a real-world testbed made up by NI USRP software-defined radios. Results demonstrate the effectiveness of the proposed methodology as FORMAT is able to effectively detectand mitigate the considered cross-layer attacks.


The Cellular Operating System (CellOS) proposes a network operating system for automatic self-optimization of softwarized cellular networks aimed at bridging the gap between Software-Defined Networking (SDN) and cross-layer distributed optimization. Unlike state-of-the-art SDN-inspired solutions for cellular networking, CellOS (i) hides low-level network details through a general virtual network abstraction; (ii) allows Telco Operators to define high-level control objectives on multiple network slices without requiring knowledge of optimization techniques or of the network specifics, and (iii) automatically generates distributed control programs for the simultaneous optimization of different control objectives on different network slices at the same base station.

We prototype CellOS on an LTE-compliant testbed where optimization algorithms are automatically generated and solved over OpenAirInterface/srsLTE wireless links. Our results show that power control and scheduling policies computed by CellOS can be effectively implemented and enforced on real cellular networks showing that CellOS remarkably outperforms current solutions for cellular networks over key performance metrics, including throughput (up to 75%), energy efficiency (up to 84%) and user fairness (up to 29%).


Network slicing and Multi-access Edge Computing (MEC) are emerging as pivotal technologies for the success of 5G networks and beyond. Among others, MEC-enabled edge nodes are expected to revolutionize the way mobile users access Internet services. Given the limited availability of resources, how to efficiently instantiate networking and MEC slices on multiple MEC-enabled edge nodes without incurring in resource over-provisioning is a core problem that stands out with respect to traditional resource allocation problems. Sl-EDGE proposes a slicing framework for MEC-enabled 5G systems that allows network operators to instantiate heterogeneous slice services (e.g., video streaming, 5G network access) on edge devices.

We propose centralized and distributed algorithms to efficiently instantiate slices, and assess their performance both numerically and experimentally on a 64-antenna testbed with 24 software-defined radios. Results show that Sl-EDGE avoids over-provisioning granting cellular connectivity, wireless video streaming and video transcoding, where other approaches allocates up to 6x more resources than the available ones.


Virtualization and softwarization technologies will allow Infrastructure Providers (IPs) to create virtual networks on top of their physical infrastructure, each assigned to a different mobile virtual operator. This project leverages RAN softwarization and network slicing to realize Private Cellular Connectivity as a Service, allowing the IP to instantiate and deploy private network slices sharing the virtualized infrastructure with other (public) slices. Such private slices, only known to selected users, can exchange sensitive data in a secure manner, embedding it covertly and undetectably into primary traffic, used as decoy.

We propose SteaLTE as the first realization of a Private Cellular Connectivity as a Service (PCCaaS)-enabling system for cellular networks. At its core, SteaLTE utilizes wireless steganography to disguise data as noise to adversarial receivers. Differently from previous work, however, it takes a full-stack approach to steganography, contributing an LTE-compliant steganographic protocol stack for PCCaaS-based communications, and packet schedulers and operations to embed covert data streams on top of traditional cellular traffic (primary traffic). SteaLTE balances undetectability and performance by mimicking channel impairments so that covert data waveforms are almost indistinguishable from noise. We implement SteaLTE through srsLTE and evaluate its the performance on an indoor LTE-compliant testbed under different traffic profiles, distance and mobility patterns. We further test it on the outdoor PAWR POWDER platform over long-range cellular links. Results show that in most experiments SteaLTE imposes little loss of primary traffic throughput in presence of covert data transmissions (< 6%), making it suitable for undetectable PCCaaS networking.

Data-driven O-RAN-compliant NextG Networks

Future, "NextG" cellular networks will be natively cloud-based and built upon programmable, virtualized, and disaggregated architectures. The separation of control functions from the hardware fabric and the introduction of standardized control interfaces will enable the definition of custom closed-control loops, which will ultimately enable embedded intelligence and real-time analytics, thus effectively realizing the vision of autonomous and self-optimizing networks. This project explores the NextG disaggregated architecture proposed by the O-RAN Alliance and provides the first large-scale demonstration of a the integration of O-RAN-compliant software components with an open-source full-stack softwarized cellular network, controlled by a data-driven machine learning agent.

We provide the first large-scale demonstration of a the integration of O-RAN-compliant software components with an open-source full-stack softwarized cellular network. Experiments conducted on Colosseum, the world's largest wireless network emulator, demonstrate closed-loop integration of real-time analytics and control through deep reinforcement learning agents. We also demonstrate for the first time Radio Access Network (RAN) control through xApps running on the near real-time RAN Intelligent Controller (RIC), to optimize the scheduling policies of co-existing network slices, leveraging O-RAN open interfaces to collect data at the edge of the network.


  • Z. Guan, L. Bertizzolo, E. Demirors, and T. Melodia, "WNOS: Enabling Principled Software-Defined Wireless Networking," in IEEE/ACM Transactions on Networking, 2021.

  • L. Bonati, S. D'Oro, F. Restuccia, S. Basagni, and T. Melodia, "SteaLTE: Private 5G Cellular Connectivity as a Service with Full-stack Wireless Steganography," in Proc. of IEEE Intl. Conf. on Computer Communications (INFOCOM), Vancouver, BC, Canada, May 2021. [pdf] [bibtex]

  • L. Bonati, S. D'Oro, M. Polese, S. Basagni, and T. Melodia, "Intelligence and Learning in O-RAN for Data-driven NextG Cellular Networks", IEEE Communications Magazine, vol. 59, no. 10, pp. 21–27, October 2021. [pdf] [bibtex]

  • L. Bonati, M. Polese, S. D'Oro, S. Basagni, and T. Melodia, "Open, Programmable, and Virtualized 5G Networks: State-of-the-Art and the Road Ahead," Computer Networks, vol. 182, December 2020. [pdf] [bibtex]

  • L. Bertizzolo, L. Bonati, E. Demirors, A. Al-Shawabka, S. D'Oro, F. Restuccia, and T. Melodia, "Arena: A 64-antenna SDR-based Ceiling Grid Testing Platform for Sub-6 GHz 5G-and-Beyond Radio Spectrum Research," Computer Networks, vol. 181, November 2020. [pdf] [bibtex]

  • S. D'Oro, L. Bonati, F. Restuccia, M. Polese, M. Zorzi and T. Melodia, "Sl-EDGE: Network Slicing at the Edge", in Proc. of ACM Intl. Symp. on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc), October 2020. [pdf] [bibtex]

  • L. Bonati, S. D'Oro, L. Bertizzolo, E. Demirors, Z. Guan, S. Basagni, and T. Melodia, "CellOS: Zero-touch Softwarized Open Cellular Networks," Computer Networks, vol. 180, October 2020. [pdf] [bibtex]

  • L. Bertizzolo, E. Demirors, Z. Guan, and T. Melodia, "CoBeam: Beamforming-based Spectrum Sharing With Zero Cross-Technology Signaling for 5G Wireless Networks," in Proc. of IEEE Intl. Conference on Computer Communications (INFOCOM), July 2020 (AR: 20%). [pdf] [bibtex]

  • S. D'Oro, L. Bonati, F. Restuccia and T. Melodia, "Coordinated 5G Network Slicing: How Constructive Interference Can Boost Network Throughput," submitted for publication, IEEE/ACM Transactions on Networking, 2020. [pdf] [bibtex]

  • S. D'Oro, F. Restuccia, and T. Melodia, "Toward Operator-to-Waveform 5G Radio Access Network Slicing," under review, IEEE Communications Magazine. [pdf] [bibtex]

  • L. Bertizzolo, L. Bonati, E. Demirors, and T. Melodia, "Arena: A 64-antenna SDR-based Ceiling Grid Testbed for Sub-6 GHz Radio Spectrum Research," in Proc. of ACM Workshop on Wireless Network Testbeds, Experimental evaluation & CHaracterization (WiNTECH), Los Cabos, Mexico, October 2019. Best Paper Award [pdf] [bibtex]

  • L. Bertizzolo, L. Bonati, E. Demirors, and T. Melodia, "Demo: Arena: A 64-antenna SDR-based Ceiling Grid Testbed for Sub-6 GHz Radio Spectrum Research," in Proc. of ACM Workshop on Wireless Network Testbeds, Experimental evaluation & CHaracterization (WiNTECH), Los Cabos, Mexico, October 2019. [pdf] [bibtex]

  • Z. Guan, L. Bertizzolo, E. Demirors, and T. Melodia, "WNOS: An Optimization-based Wireless Network Operating System," in Proc. of ACM Intl. Symp. on Mobile Ad Hoc Networking and Computing (MobiHoc), Los Angeles, USA, June 2018. [pdf] [bibtex]

  • Z. Guan, L. Bertizzolo, E. Demirors, and T. Melodia, "Demo Abstract: WNOS: Software-defined Generation of Distributed Optimal Control Programs for Wireless Networks," in Proc. of IEEE Intl. Conference on Computer Communications (INFOCOM), Honolulu, HI, April 2018. [pdf] [bibtex] [source]

Patent Applications

  • WNOS: An Optimization-based Wireless Network Operating System
  • CoBeam: Beamforming-based Spectrum Sharing With Zero Cross-Technology Signaling for 5G Wireless Networks
  • CellOS: A Network Operating System for Softwarized and Self-Optimizing Cellular Networks
  • Methods for the Enforcement of Network Slicing Policies in Virtualized Cellular Networks
  • SteaLTE: Private 5G Cellular Connectivity as a Service Through Full-Stack Wireless Steganography
  • A unified framework for multi-access edge computing (MEC) network slicing in 5G networks
  • Intelligence and Learning in O-RAN for 5G and 6G Cellular Networks

Educational Activities

Materials developed in this project have impacted and influenced a number of educational activities conducted by the PI. First, the PI has transitioned research materials developed in this project into lectures offered in the classroom, including in a graduate class on the topic of Wireless Sensor Networks and the Internet of Things, as well as classes on Fundamental of Networks offered at the graduate and undergraduate levels. Second, slides of materials developed in this project have been made available through the PI's webpage. Research topics on softwarized network control developed in this project have made it into a large number of seminars, keynote speeches, and lectures offered by the PI in the last two years.