LITE: Lightweight Channel Gain Estimation with Reduced X-Haul CSI Signaling in O-RAN

TL;DR

LITE is a novel lightweight channel gain estimation method for O-RAN that significantly reduces bandwidth and computational requirements while maintaining high accuracy and throughput.

Contribution

It introduces a combined autoencoder and SE-BiLSTM pipeline with 50% CSI compression, achieving 83.39% model complexity reduction and 5% accuracy improvement.

Findings

LITE reduces model complexity by 83.39%.

LITE achieves 147k QPS throughput with TensorRT.

LITE maintains accuracy with only 6% loss after compression-aware training.

Abstract

Cell-Free Massive Multiple-Input Multiple-Output (CF-MaMIMO) in Open Radio Access Network (O-RAN) promises high spectral efficiency but is limited by frequent Channel State Information (CSI) exchanges, which strain fronthaul/midhaul/backhaul (X-haul) bandwidth and exceed the capabilities of existing approaches relying on uncompressed CSI or heavy predictors. To overcome these constraints, we propose LITE, a lightweight pipeline combining a 1-D convolutional Autoencoder (AE) at the O-RAN Distributed Unit (O-DU) with a Squeeze-and-Excitation (SE)-enhanced Bidirectional Long Short-Term Memory (BiLSTM) predictor at the Near-Real-Time RAN Intelligent Controller (Near-RT-RIC), enabling short-horizon trajectory-unaware forecasting under strict transport and processing budgets. LITE applies 50% CSI compression and an asymmetric SE-BiLSTM, reducing model complexity by 83.39% while improving accuracy by 5% relative to a baseline BiLSTM. With compression-aware training, the Lightweight Intelligent Trajectory Estimator (LITE) incurs only 6% accuracy loss versus the BiLSTM baseline, outperforming independent and end-to-end strategies. A TensorRT-optimized implementation achieves 147k Queries per Second (QPS), a 4.6x throughput gain. These results demonstrate that LITE delivers X-haul-efficient, low-latency, and deployment-ready channel-gain prediction compatible with O-RAN splits.