ARCHES: Adaptive Real-Time Switching of AI Models for the RAN

TL;DR

ARCHES is a framework that enables real-time switching between AI and conventional models in the RAN to optimize performance and power efficiency based on current network conditions.

Contribution

It introduces a GPU-accelerated, real-time expert switching system with a novel control plane and switching kernel for adaptive RAN signal processing.

Findings

Achieves median throughput gains of 5.32% and 7.23% under different conditions.

Reduces GPU power consumption by 15.8 W (9.6%) when defaulting to traditional methods.

Maintains low control-loop latency of approximately 140 microseconds.

Abstract

Artificial Intelligence (AI) has become a powerful tool for model-free Radio Access Network (RAN) signal processing and optimization. However, designing a single model that generalizes across all radio environments is challenging. Specialized AI models outperform conventional algorithms only under specific conditions, while their higher compute and energy cost makes unconditional execution impractical at the base station. This creates a need for real-time expert switching: dynamically activating the most appropriate AI or conventional expert based on current network conditions. To address this, we propose ARCHES (Adaptive Real-time CUDA Hot-swapping of Experts in the RAN Stack), a framework hosting multiple AI-based and conventional signal processing experts within a GPU-accelerated PHY pipeline, dynamically selecting the most appropriate expert at slot-boundary granularity without dropping or corrupting in-flight data. ARCHES includes a lightweight CUDA switch kernel for zero-gap output selection, a dApp-based control plane that collects cross-layer telemetry and drives the switching policy, and a reusable process for policy design based on controlled perturbation, monotonicity filtering, and hierarchical clustering. We validate ARCHES on UL channel estimation, switching between an AI-based and a Minimum Mean Square Error (MMSE) estimator under changing propagation and interference conditions. Implemented on the X5G platform with NVIDIA Aerial and OpenAirInterface (OAI), ARCHES achieves median UL PHY throughput gains of 5.32% and 7.23% under good and poor conditions, with a control-loop latency of ~140 us and sub-microsecond decision inference. Under good conditions, defaulting to MMSE saves 15.8 W of GPU power (9.6%) and 17 percentage points of GPU utilization versus unconditional AI execution, validating the performance-per-watt tradeoff that motivates adaptive expert selection.