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

Abstract

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.

6 pages, 4 figures, 2 tables