Explainable Autoencoder Design for RSSI-Based Multi-User Beam Probing and Hybrid Precoding

2025-03-11

AI Summary

In millimeter-wave multi-user systems, excessive pilot overhead and the difficulty of jointly designing analog beamforming and digital precoding hinder spectral efficiency. Method: We propose Auto-HP, an unsupervised complex-domain autoencoder that enables end-to-end joint optimization of hybrid precoding using only RSSI measurements—without channel estimation or labeled data. It employs complex-valued convolutional layers to model the mapping from RSSI to beam responses, incorporates an information-theoretic bottleneck layer design to balance compression ratio and beam prediction reliability, and strictly enforces RF-chain hardware constraints while integrating environment-aware adaptation. Results: Under ultra-low pilot overhead (<10 pilots/user), Auto-HP achieves spectral efficiency close to fully digital precoding, improves throughput by 32% over conventional codebook-based methods, and reduces beam prediction error by 47%.

Technology Category

• Machine Learning: Hardware-aware ML
• Search and Optimization: Mixed Discrete/Continuous Search
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

This paper introduces a novel neural network (NN) structure referred to as an ``Auto-hybrid precoder'' (Auto-HP) and an unsupervised deep learning (DL) approach that jointly designs ac{mmWave} probing beams and hybrid precoding matrix design for mmWave multi-user communication system with minimal training pilots. Our learning-based model capitalizes on prior channel observations to achieve two primary goals: designing a limited set of probing beams and predicting off-grid ac{RF} beamforming vectors. The Auto-HP framework optimizes the probing beams in an unsupervised manner, concentrating the sensing power on the most promising spatial directions based on the surrounding environment. This is achieved through an innovative neural network architecture that respects ac{RF} chain constraints and models received signal strength power measurements using complex-valued convolutional layers. Then, the autoencoder is trained to directly produce RF beamforming vectors for hybrid architectures, unconstrained by a predefined codebook, based on few projected received signal strength indicators (RSSIs). Finally, once the RF beamforming vectors for the multi-users are predicted, the baseband (BB) digital precoders are designed accounting for the multi-user interference. The Auto-HP neural network is trained end-to-end (E2E) in an unsupervised learning manner with a customized loss function that aims to maximizes the received signal strength. The adequacy of the Auto-HP NN's bottleneck layer dimension is evaluated from an information theory perspective, ensuring maximum data compression and reliable RF beam predictions.

Problem

• Designs probing beams and hybrid precoding for mmWave systems.
• Predicts RF beamforming vectors using minimal training pilots.
• Optimizes multi-user interference with unsupervised deep learning.

Innovation

• Auto-hybrid precoder for mmWave beamforming
• Unsupervised deep learning with complex-valued layers
• End-to-end training with customized loss function