Airborne Base Stations (ABSs) allow for flexible geographical allocation of network resources with dynamically changing load as well as rapid deployment of alternate connectivity solutions during natural disasters. Since the radio infrastructure is carried by unmanned aerial vehicles (UAVs) with limited flight time, it is important to establish the best location for the ABS without exhaustive field trials. This paper proposes a digital twin (DT)-guided approach to achieve this goal through the following key contributions: (i) Implementation of an interactive software bridge between two open-source DTs such that the same scene is evaluated with high fidelity across NVIDIA's Sionna and Aerial Omniverse Digital Twin (AODT), highlighting the unique features of each of these platforms for this allocation problem, (ii) Design of a back- propagation-based algorithm in Sionna for rapidly converging on the physical location of the UAVs, orientation of the antennas and transmit power to ensure efficient coverage across the swarm of the UAVs, and (iii) numerical evaluation in AODT for large network scenarios (50 UEs, 10 ABS) that identifies the environmental conditions in which there is agreement or divergence of performance results between these twins. Finally, (iv) we propose a resilience mechanism to provide consistent coverage to mission-critical devices and demonstrate a use case for bi-directional flow of information between the two DTs.

Industry adoption of Artificial Intelligence (AI)-native wireless receivers, or even modular, Machine Learning (ML)-aided wireless signal processing blocks, has been slow. The main concern is the lack of explainability of these trained ML models and the significant risks posed to network functionalities in case of failures, especially since (i) testing on every exhaustive case is infeasible and (ii) the data used for model training may not be available. This paper proposes ATLAS, an AI-guided approach that generates a battery of tests for pre-trained AI-native receiver models and benchmarks the performance against a classical receiver architecture. Using gradient-based optimization, it avoids spanning the exhaustive set of all environment and channel conditions; instead, it generates the next test in an online manner to further probe specific configurations that offer the highest risk of failure. We implement and validate our approach by adopting the well-known DeepRx AI-native receiver model as well as a classical receiver using differentiable tensors in NVIDIA’s Sionna environment. ATLAS uncovers specific combinations of mobility, channel delay spread, and noise, where fully and partially trained variants of AI-native DeepRx perform suboptimally compared to the classical receivers. Our proposed method reduces the number of tests required per failure found by 19% compared to grid search for a 3-parameters input optimization problem, demonstrating greater efficiency. In contrast, the computational cost of the grid-based approach scales exponentially with the number of variables, making it increasingly impractical for high-dimensional problems.

5G and beyond cellular networks promise remarkable advancements in bandwidth, latency, and connectivity. The emergence of Open Radio Access Network (O-RAN) represents a pivotal direction for the evolution of cellular networks, inherently supporting machine learning (ML) for network operation control. Within this framework, RAN Intelligence Controllers (RICs) from one provider can employ ML models developed by third-party vendors through the acquisition of key performance indicators (KPIs) from geographically distant base stations or user equipment (UE). Yet, the development of ML models hinges on the availability of realistic and robust datasets. In this study, we embark on a two-fold journey. First, we collect a comprehensive 5G dataset, harnessing real-world cell phones across diverse applications, locations, and mobility scenarios. Next, we replicate this traffic within a full-stack srsRAN-based O-RAN framework on Colosseum, the world's largest radio frequency (RF) emulator. This process yields a robust and O-RAN compliant KPI dataset mirroring real-world conditions. We illustrate how such a dataset can fuel the training of ML models and facilitate the deployment of xApps for traffic slice classification by introducing a CNN based classifier that achieves accuracy > 95% offline and 92% online. To accelerate research in this domain, we provide open-source access to our toolchain and supplementary utilities, empowering the broader research community to expedite the creation of realistic and O-RAN compliant datasets.

Open Radio Access Network (O-RAN) is positioned to play a pivotal role in shaping the future of telecommunications networks through open interfaces and virtualization, allowing interoperability between different vendors. As a key departure from single-operator managed RAN, a remote RAN intelligence controller (RIC) queries the gNB for the Key Performance Indicators (KPIs) that are required for making RAN control decisions, often leveraging advanced machine learning (ML) models. However, this repeated querying increases control traffic overhead on the so called E2 interface connecting the gNB to the RIC. To address this challenge, we utilize a method from Explainable Artificial Intelligence (XAI), specifically SHapley Additive exPlanations (SHAP), which quantifies the contribution of each requested KPI to a model's prediction. Furthermore, we explore two different methods of choosing the most discriminative KPIs influencing model's performance, so that a smaller subset of KPIs may be queried, thus lowering the overhead on the E2 interface. Our analysis reveals that a model trained for the task of traffic classification using as input only the fraction of the top contributing KPIs identified by SHAP reduces control traffic overhead by up to 33% with only 7% reduction in ML classification accuracy.

Spectrum sharing allows different protocols of the same standard (e.g., 802.11 family) or different standards (e.g., LTE and DVB) to coexist in overlapping frequency bands. As this paradigm continues to spread, wireless systems must also evolve to identify active transmitters and unauthorized waveforms in real time under intentional distortion of preambles, extremely low signal-to-noise ratios and challenging channel conditions. We overcome limitations of correlation-based preamble matching methods in such conditions through the design of T-PRIME: a Transformer-based machine learning approach. T-PRIME learns the structural design of transmitted frames through its attention mechanism, looking at sequence patterns that go beyond the preamble alone. The paper makes three contributions: First, it compares Transformer models and demonstrates their superiority over traditional methods and state-of-the-art neural networks. Second, it rigorously analyzes T-PRIME’s real-time feasibility on DeepWave’s AIR-T platform. Third, it utilizes an extensive 66 GB dataset of over-the-air (OTA) WiFi transmissions for training, which is released along with the code for community use. Results reveal nearly perfect (i.e. > 98%) classification accuracy under simulated scenarios, showing 100% detection improvement over legacy methods in low SNR ranges, 97% classification accuracy for OTA single-protocol transmissions and up to 75% double-protocol classification accuracy in interference scenarios.

Massive MIMO (mMIMO) technology is considered as a key enabler for 5G and beyond cellular networks, which allows formation of highly directional radiation beams in the millimeter-wave (mmWave) band. Specifically, considering the 5G new radio (NR) standard, a codebook-based approach is used that allows setting the antenna weights, so that both transmission and reception can be achieved in the desired angle. However, when a fixed codebook is used, these angular directions may not be exactly aligned along the optimal path that maximizes the SINR between the transmitter-receiver pair, depending on the granularity of the beam and the codebook size. To address these issues, we propose selection of the analog parameters of the transceiver chain through Deep Reinforcement Learning (DRL). Simulation results show that our approach allows fine-grained beam refinement to the coarse initial estimates of Angle-of-Arrival and Angle-of-Departures in mmWave Frequency Range 2 (FR2) for the 5G NR standard obtained during the a reduced initial beam establishment procedure (P-1). We observe our approach consistently improves the Reference Signal Received Power (RSRP) perceived at the UE side up to 15% while allowing a reduction in the number of Synchronization Signal Blocks (SSBs) up to a factor of$\times 64$compared to the equivalent number used in P-1 to obtain comparable steering accuracy. Finally, once the trained DRL agent is implemented, it eliminates 100% of control signals needed for the beam refinement procedures, namely P-2 for transmitter beam refinement and P-3 for receiver.

Perfect alignment in chosen beam sectors at both transmit- and receive-nodes is required for beamforming in mmWave bands. Current 802.11ad WiFi and emerging 5G cellular standards spend up to several milliseconds exploring different sector combinations to identify the beam pair with the highest SNR. In this paper, we propose a machine learning (ML) approach with two sequential convolutional neural networks (CNN) that uses out-of-band information, in the form of camera images, to (i) rapidly identify the locations of the transmitter and receiver nodes, and then (ii) return the optimal beam pair. We experimentally validate this intriguing concept for indoor settings using the NI 60GHz mmwave transceiver. Our results reveal that our ML approach reduces beamforming related exploration time by 93% under different ambient lighting conditions, with an error of less than 1% compared to the time-intensive deterministic method defined by the current standards.

This paper describes the architecture and performance of ORACLE, an approach for detecting a unique radio from a large pool of bit-similar devices (same hardware, protocol, physical address, MAC ID) using only IQ samples at the physical layer. ORACLE trains a convolutional neural network (CNN) that balances computational time and accuracy, showing 99% classification accuracy for a 16-node USRP X310 SDR testbed and an external database of >100 COTS WiFi devices. Our work makes the following contributions: (i) it studies the hardware-centric features within the transmitter chain that causes IQ sample variations; (ii) for an idealized static channel environment, it proposes a CNN architecture requiring only raw IQ samples accessible at the front-end, without channel estimation or prior knowledge of the communication protocol; (iii) for dynamic channels, it demonstrates a principled method of feedback-driven transmitter-side modifications that uses channel estimation at the receiver to increase differentiability for the CNN classifier. The key innovation here is to intentionally introduce controlled imperfections on the transmitter side through software directives, while minimizing the change in bit error rate. Unlike previous work that imposes constant environmental conditions, ORACLE adopts the `train once deploy anywhere' paradigm with near-perfect device classification accuracy.

Radio fingerprinting provides a reliable and energy-efficient IoT authentication strategy by leveraging the unique hardware-level imperfections imposed on the received wireless signal by the transmitter's radio circuitry. Most of existing approaches utilize hand-tailored protocol-specific feature extraction techniques, which can identify devices operating under a pre-defined wireless protocol only. Conversely, by mapping inputs onto a very large feature space, deep learning algorithms can be trained to fingerprint large populations of devices operating under any wireless standard.