arXiv subjects

Joseph Boccuzzi

Publications and source records attributed to Joseph Boccuzzi.

4 recordsLinked to original sources

arXiv2026

AtlasRAN: Timing-Aware Evaluation of Open-source 5G Platforms for Integrated Wireless Testbeds

Open-source fifth-generation (5G) and Open Radio Access Network (O-RAN) experiments span simulation, host operating system (host-OS) emulation, software-defined radio hardware-in-the-loop testing, Open Radio Unit fronthaul deployments, wireless digital twins, and accelerator-backed radio access network (RAN) runtimes. These environments may expose similar interfaces while preserving different timing, input/output, synchronization, buffering, transport, and observability; functional compatibility is therefore not timing fidelity. This paper presents AtlasRAN, a claim-to-capability framework for deciding what an open-source 5G platform can credibly measure. It combines two reference paths, an execution-regime matrix, and a measurement-backed case study comparing OpenAirInterface (OAI) radio-frequency simulator (RFSim) with the Sionna Research Kit (Sionna-RK), which offloads low-density parity-check (LDPC) decoding to CUDA while retaining the surrounding OAI host-OS path. From one to six users, aggregate uplink goodput falls from 114.59 to 35.09 Mb/s for OAI and from 103.34 to 35.01 Mb/s for Sionna-RK. At six users, both RFSim real-time factors are approximately 0.55, despite estimated cumulative LDPC work of 1.09~ms per transport block for OAI and 0.37 ms for Sionna-RK. Timing-normalized service remains 60.7-63.6~Mb per emulated second across complete runs, while falling host and accelerator utilization is consistent with an under-fed decoder. A twelve-user run is retained only as failure-region evidence because end-of-test traffic summaries are absent. The practical takeaway is that integrated wireless testbeds, edge platforms, artificial-intelligence-enabled RANs, and digital twins should report timing discipline, transport path, memory movement, and observability as first-class experimental variables.

cs.NI↗

arXiv2026

Six Times to Spare: Characterizing GPU-Accelerated 5G LDPC Decoding for Edge-RSU Communications

Ultra-reliable low-latency vehicular communications (URLLC) require sufficient physical-layer (PHY) compute headroom at the network edge, where roadside units (RSUs) and compact next-generation base stations (gNBs) must meet strict timing constraints while co-hosting higher-layer services. In 5G New Radio (5G NR), low-density parity-check code (LDPC) decoding is a latency-sensitive iterative PHY workload whose cost scales with both workload parallelism and decoder iteration budget, making it a potential bottleneck on general-purpose central processing units (CPUs). This paper presents a reproducible, telemetry-backed microbenchmark derived from the Sionna LDPC5G baseline to characterize the compute headroom obtained through graphics processing unit (GPU) offload on compact heterogeneous edge platforms. We evaluate decoder behavior across multiple processor architectures and a wide range of batch sizes and iteration counts, with emphasis on dense operating regimes relevant to edge provisioning. Results show that GPU acceleration substantially increases LDPC throughput, reduces amortized decode service time, and shifts compute pressure away from the CPU, thereby improving the feasibility of meeting edge-RSU timing budgets under heavy parallel workloads. These findings indicate that GPU offload can provide substantial spare PHY compute margin for compact vehicular edge platforms, making dense decode workloads more practical within realistic edge power and timing constraints.

cs.DC↗

arXiv2025

NVIDIA AI Aerial: AI-Native Wireless Communications

6G brings a paradigm shift towards AI-native wireless systems, necessitating the seamless integration of digital signal processing (DSP) and machine learning (ML) within the software stacks of cellular networks. This transformation brings the life cycle of modern networks closer to AI systems, where models and algorithms are iteratively trained, simulated, and deployed across adjacent environments. In this work, we propose a robust framework that compiles Python-based algorithms into GPU-runnable blobs. The result is a unified approach that ensures efficiency, flexibility, and the highest possible performance on NVIDIA GPUs. As an example of the capabilities of the framework, we demonstrate the efficacy of performing the channel estimation function in the PUSCH receiver through a convolutional neural network (CNN) trained in Python. This is done in a digital twin first, and subsequently in a real-time testbed. Our proposed methodology, realized in the NVIDIA AI Aerial platform, lays the foundation for scalable integration of AI/ML models into next-generation cellular systems, and is essential for realizing the vision of natively intelligent 6G networks.

cs.LG↗

arXiv2025

Spectral Efficiency Considerations for 6G

As wireless connectivity continues to evolve towards 6G, there is an ever-increasing demand to not only deliver higher throughput, lower latency, and improved reliability, but also do so as efficiently as possible. To this point, the term efficiency has been quantified through applications to Spectral Efficiency (SE) and Energy Efficiency (EE). In this paper we introduce a new system metric called Radio Resource Utilization Efficiency (RUE). This metric quantifies the efficiency of the available radio resources (Spectrum, Access Method, Time Slots, Data Symbols, etc.) used to deliver future 6G demands. We compare the system performance of Typical Cellular and Cell-Free Massive MIMO deployments as a vehicle to demonstrate the need for this new metric. We begin by providing a concise treatment of items impacting SE by introducing three categories: 5G Radio Resources, Practical Limitations (such as channel matrix rank deficiency) and Implementation Losses (SINR degradation). For the example Radio Access Technology configuration analyzed, we show 5G yields an RUE of 47% (revealing significant room for improvement when defining 6G). Practical limitation assumptions are compared to 5G Multi-User MIMO (MU-MIMO) measurements conducted in a commercialized deployment. SE losses are characterized to offer guidance to advanced algorithms employing Machine Learning (ML) based techniques. We present the benefits of increasing the transmission Bandwidth (BW) from 100MHz to 1.6GHz. We describe a Next Generation RAN architecture that can support 6G and AI-RAN.

eess.SP↗