LOLLA: Deep Reinforcement Learning for Closed-Loop Link Adaptation Towards a GPU-Accelerated AI-RAN
This work addresses the performance degradation of link adaptation in high-mobility 5G NR systems, offering a practical AI-native solution that can be deployed on GPU-accelerated RAN with sub-500 microsecond latency.
LOLLA replaces conventional outer-loop link adaptation in 5G NR with a deep reinforcement learning policy that learns a continuous SINR offset, achieving 15-92% throughput gains over OLLA across Doppler frequencies up to 400 Hz while maintaining tunable BLER targets from 1% to 15%.
Outer-loop link adaptation (OLLA) is widely deployed in 5G NR to track channel variations, yet its reliance on first-order, single-bit feedback degrades performance significantly under high-mobility and fast-varying channels. This paper presents LOLLA (Learned Outer-Loop Link Adaptation), a deep reinforcement learning framework that replaces the conventional OLLA staircase with a learned, continuous SINR offset conditioned on rich PHY/MAC telemetry inaccessible to OLLA. The offset modulates the SINR-to-MCS lookup table, preserving 3GPP-compliant MCS selection and provably subsuming the conventional OLLA update rule. A Proximal Policy Optimization (PPO) policy trained under a Lagrangian block error rate (BLER) constraint automatically enforces tunable reliability targets from 1% to 15% without manual penalty calibration. The framework is realized as the first closed-loop AI-native control dApp on a GPU-accelerated 5G NR stack, achieving end-to-end control latencies under 500 microseconds. Evaluations under 3GPP TDL channel models demonstrate 15% to 92% throughput gains over OLLA across Doppler frequencies up to 400 Hz, while attaining a Pareto frontier that strictly dominates OLLA across all evaluated reliability targets. The learned policy generalizes to unseen channel models and scales to eight concurrent UEs under shared-resource scheduling. In the uplink formulation, the gNB directly observes decoding outcomes, enabling simulation-to-deployment parity.