Blog
TOSSI · JOURNAL
Blog
Announcements, release notes, and project updates from TOSSI — the open, vendor-neutral RAN integration project.
ReleasesNTN E2E Testbed Release: GEO NTN with OCUDU RAN and OAI UE Simulator
Validating NTN behaviour has traditionally required satellite capacity, RF equipment or specialised channel emulators. This release is an end-to-end GEO NTN testbed that runs a complete 5G Standalone network over a simulated geostationary satellite link, on a single machine, with no radio hardware and no satellite: OCUDU RAN with 3GPP Release 17 NTN, an OAI UE Simulator over ZMQ, a sample-exact GEO delay relay, and a 5G core, under a genuine 240 ms round trip.
OCUDU Closed-Loop rApp for Cell Congestion OptimizationThe real test of Open RAN is whether a live RAN, an SMO, a Non-RT RIC and an rApp can complete an end-to-end control loop through standardized O-RAN interfaces. Using the OCUDU RAN ecosystem and the coRAN LABS Cell Congestion Optimization rApp, this demonstration closes that loop: detect PRB congestion from O1 telemetry, verify a signal-audible neighbour, and relieve the cell with a management-driven inter-gNB handover.Read more →
ML-Based CSI Prediction for Intelligent 5G SchedulingA 5G scheduler is only as effective as the channel information available when it makes a decision, and for downlink that information is often already stale. ML-based CSI prediction replaces the conventional hold-last-CQI assumption with a per-UE forecast of the next report, so the scheduler can act on where the channel is heading, not only where it was last measured. Two prediction engines, one framework, built on the OCUDU AI-RAN foundation.Read more →
NVIDIA Sionna RT Integration in OCUDU: Deterministic Digital Twins for 6G and AI-RANStatistical channel models represent an average radio environment; they cannot reproduce the multipath signature of a specific site. Integrating NVIDIA Sionna RT with OCUDU RAN connects a 3D digital representation of the physical world to a live cellular stack, streaming deterministic ray-traced channels into a running RAN without a restart, a foundation for site-specific AI-RAN and 6G digital twins.Read more →
NVIDIA Aerial, OCUDU, and xFAPI: Building the Future of Open AI-RANMost AI-RAN discussions begin with computing power. The harder question is how much engineering effort it takes to make independently developed RAN components work together. The NVIDIA Aerial, OCUDU, and Duranta integrations through coRAN LABS xFAPI show a different way to design the Layer 1 to Layer 2 boundary, and reframe openness as replaceability.Read more →
India's 5G Decade: Big Intent, Repeated Initiatives, and the Road to 6G OutcomesIndia's 5G journey from 2018 to 2026 moved through the Indigenous 5G Testbed, the BSNL/DoT ecosystem push, Bharat RAN 1 and 2, IOS-MCN, and 100 5G Use Case Labs, plus the 5Gi standards contribution. The intent and capability are real; the open question for 6G is conversion, turning testbeds, consortiums, and declared patents into deployed, operator-demanded products.Read more →
OCUDU AI-RAN: Building an Open Framework for Per-UE IntelligenceOCUDU AI-RAN brings intelligence natively into the Open RAN stack: data collection, model training, runtime inference, and standards-based deployment as reusable capabilities. The first application is adaptive per-UE Buffer Status Report (BSR) configuration, where the DU scheduler learns each UE's uplink traffic and tunes the periodicBSR-Timer over standard F1AP and RRC.Read more →
OCUDU RAN Advances Open RAN Mobility with Standards-Based Inter-gNB Handover and O-RAN O1 IntegrationTOSSI demonstrates standards-based inter-gNB handover and O-RAN O1 integration in a real Open RAN deployment built with OCUDU RAN, SD-Core, LiteON Radio Units, and commercial UEs. It validates both network-triggered and Event A3 measurement-based mobility, and exposes handover events and RSRP/RSRQ/SINR telemetry over O1 for xApps, rApps, and AI-RAN.Read more →
CNTC: Building Trust in Open Telecom, Beginning with 5G User Plane CertificationThe TOSSI Foundation introduces Cloud Native Telecom Certification (CNTC), an open, standards-driven certification framework for cloud-native telecom software. It begins with the UPF Certification Module: PFCP conformance, N3 robustness, performance, and load, graded by a Verdict Engine that issues a certificate only on a strict essential-test pass.Read more →
OCUDU AI-RAN Release 1: An Open Framework for Intelligent Link AdaptationAn open, end-to-end AI-RAN framework: live data collection, dataset generation, training, runtime inference in the DU scheduler, online learning, and OLLA fallback. The first application is ML-based uplink link adaptation, built on 900k+ real over-the-air transmissions.Read more →
From Kernel-Locked to Cloud-Native: Rebuilding Magma's 5G User Plane with eBPFMoving GTP-U processing into three compact eBPF programs makes the Magma 5G Core user plane portable across Linux kernels, with Open vSwitch left completely unmodified and the control plane untouched.Read more →
Building an End-to-End Open Network Slicing Ecosystem with OCUDUThe latest TOSSI release delivers a complete open-source network slicing platform: multi-UE orchestration, slice-aware OCUDU scheduling, Magma Core integration, O1-based live configuration, and an rApp development environment, all unified into a single ecosystem.Read more →
Building the AI-RAN Data Path in OCUDU: Inline GPU Processing for PRACH and SRSNVIDIA GPUDirect RDMA delivers fronthaul packets directly into GPU memory, with no host copies and no PCIe bottleneck. PRACH detection latency drops 70%, SRS achieves 20× acceleration at 256 UEs, all on a workstation-class RTX A4000.Read more →
Bridging Open RAN Ecosystems: OAI L1 with OCUDU L2 via xFAPIOAI Layer 1 (v2.4) and OCUDU Layer 2 (v26.04) interoperate through xFAPI Release 2.2 with no source changes to either project. All the integration logic lives inside xFAPI, validating Open RAN's core promise: independently developed components working together while preserving their native implementations.Read more →
Scaling RAN Testing: From Single UE to Multi-UE SimulationOCUDU India extends OAI's new ZMQ-capable nr-uesoftmodem into a multi-UE testbed: N OAI UEs against a single OCUDU gNB, joined by a Python IQ-superposition proxy, per-UE Linux network namespaces, wave admission into the 5G CN, and a live Rust/ratatui dashboard.Read more →
xFAPI: A FAPI L1/L2 Split for Open, Vendor-Neutral AI-RANOCUDU moves from a monolithic gNB to a fully operational FAPI L1/L2 split: odu_high and odu_low run as independent processes across the Small Cell Forum FAPI boundary, bridged by coRAN LABS' xFAPI translator. The boundary becomes open, portable, and vendor-neutral, a foundation for AI-RAN.Read more →
Hardware-Accelerated PRACH Detection: CUDA-Graph GPU OffloadA second hardware-acceleration path lands in OCUDU's upper-PHY: PRACH detection captured as a single CUDA graph on an NVIDIA GPU, with the IDFT running device-side via cuFFTDx. Two acceleration paths, two vendors, one binary.Read more →
Offloading LDPC in PDSCH & PUSCH to Hardware AcceleratorsA BBDEV-based execution path for hardware-accelerated LDPC lands in OCUDU's upper-PHY, with a first reference backend on Intel ACC100 and a HAL designed to extend cleanly to next-generation accelerators.Read more →