InterfO-RAN: Real-Time In-band Cellular Uplink Interference Detection with GPU-Accelerated dApps

2025-07-30

AI Summary

Unpredictable uplink co-channel interference in ultra-dense 5G/6G networks—particularly at cell edges and in mmWave scenarios—degrades SINR, distorts RSRP/RSSI measurements, and disrupts higher-layer protocols (e.g., scheduling, HARQ). Method: This paper proposes a real-time interference detection framework built on the O-RAN architecture, deploying a lightweight CNN model directly on the NVIDIA Aerial GPU-accelerated platform to process gNB physical-layer I/Q samples, enabling sub-millisecond inference co-located with 5G NR baseband processing. Contribution/Results: Evaluated on over 7 million real-world uplink time slots from a private 5G network, the solution achieves >91% detection accuracy with <650 μs per-inference latency—significantly surpassing conventional detection latency bottlenecks—and establishes a deployable, intelligent RAN interference-awareness paradigm for O-RAN ecosystems.

Technology Category

• Machine Learning: Hardware-aware ML
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Ultra-dense fifth generation (5G) and beyond networks leverage spectrum sharing and frequency reuse to enhance throughput, but face unpredictable in-band uplink (UL) interference challenges that significantly degrade Signal to Interference plus Noise Ratio (SINR) at affected Next Generation Node Bases (gNBs). This is particularly problematic at cell edges, where overlapping regions force User Equipments (UEs) to increase transmit power, and in directional millimeter wave systems, where beamforming sidelobes can create unexpected interference. The resulting signal degradation disrupts protocol operations, including scheduling and resource allocation, by distorting quality indicators like Reference Signal Received Power (RSRP) and Received Signal Strength Indicator (RSSI), and can compromise critical functions such as channel state reporting and Hybrid Automatic Repeat Request (HARQ) acknowledgments. To address this problem, this article introduces InterfO-RAN, a real-time programmable solution that leverages a Convolutional Neural Network (CNN) to process In-phase and Quadrature (I/Q) samples in the gNB physical layer, detecting in-band interference with accuracy exceeding 91% in under 650 us. InterfO-RAN represents the first O-RAN dApp accelerated on Graphics Processing Unit (GPU), coexisting with the 5G NR physical layer processing of NVIDIA Aerial. Deployed in an end-to-end private 5G network with commercial Radio Units (RUs) and smartphones, our solution was trained and tested on more than 7 million NR UL slots collected from real-world environments, demonstrating robust interference detection capabilities essential for maintaining network performance in dense deployments.

Problem

• Detects real-time in-band uplink interference in 5G networks
• Addresses SINR degradation from unpredictable interference at cell edges
• Uses GPU-accelerated CNN for accurate interference detection

Innovation

• GPU-accelerated O-RAN dApp for real-time interference detection
• CNN processes I/Q samples with over 91% accuracy
• Deployed in private 5G network with commercial RUs