Enabling Programmable Inference and ISAC at the 6GR Edge with dApps

2026-03-30

AI Summary

This work addresses the limitations of existing O-RAN and 3GPP architectures in supporting dynamic AI inference, integrated sensing and communication (ISAC), and real-time resource scheduling. To overcome these challenges, the authors propose an open radio access network architecture based on programmable decentralized applications (dApps), enabling intelligent inference and ISAC at the 5G/6G edge. By extending the user plane to provide open access to I/Q samples and RAN telemetry data, and integrating a hierarchical controller with AI pipelines, the framework supports plug-and-play model deployment and closed-loop control. Experimental validation on an open-source RAN testbed demonstrates that the proposed approach breaks through the traditional RAN bottleneck in accommodating dynamic AI tasks, effectively delivering low-latency sensing and inference services.

Abstract

The convergence of communication, sensing, and Artificial Intelligence (AI) in the Radio Access Network (RAN) offers compelling economic advantages through shared spectrum and infrastructure. How can inference and sensing be integrated in the RAN infrastructure at a system level? Current abstractions in O-RAN and 3GPP lack the interfaces and capabilities to support (i) a dynamic life cycle for inference and Integrated Sensing and Communication (ISAC) algorithms, whose requirements and sensing targets may change over time and across sites; (ii) pipelines for AI-driven ISAC, which need complex data flows, training, and testing; (iii) dynamic device and stack configuration to balance trade-offs between connectivity, sensing, and inference services. This paper analyzes the role of a programmable, software-driven, open RAN in enabling the intelligent edge for 5G and 6G systems. We identify real-time user-plane data exposure, open interfaces for plug-and-play inference and ISAC models, closed-loop control, and AI pipelines as elements that evolutions of the O-RAN architecture can uniquely provide. Specifically, we describe how dApps - a real-time, user-plane extension of O-RAN - and a hierarchy of controllers enable real-time AI inference and ISAC. Experimental results on an open-source RAN testbed demonstrate the value of exposing I/Q samples and real-time RAN telemetry to dApps for sensing applications.

Problem

• Integrated Sensing and Communication
• AI Inference
• Radio Access Network
• 6G
• Programmable RAN

Innovation

• programmable RAN
• dApps
• Integrated Sensing and Communication (ISAC)
• AI inference at the edge
• open interfaces