Massive MIMO Channel Path Detection Under Ultra-Low SNR
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for channel path detection and parameter estimation in mmWave/THz massive multi-antenna systems are limited by spatial wideband effects and ultra-low Signal-to-Noise Ratio (SNR), leading to inaccurate path detection and DoA-ToA estimation.
Innovation Solution
An AI-enabled mixed signal processing framework using Deep Learning (DL) for channel response denoising, Local Gravitation-based Clustering (LGC) for path identification, and a low-complexity rotation-based fine-tuning mechanism to mitigate off-grid measurement errors and handle spatial wideband effects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional on-grid methods are used for path parameter estimation, then computational efficiency is improved, but measurement precision deteriorates due to off-grid input signatures
Solution Approach 1:
The patent introduces an intermediary AI-based processing layer between the traditional on-grid estimation method and the final path parameter output. This AI intermediary learns to map off-grid measurements to accurate parameters while maintaining computational efficiency, resolving the contradiction between speed and precision
2Measurement precision
If Deep Learning assisted denoising is applied to recover channel paths under ultra-low SNR, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent implements preliminary action by pre-training the AI denoising model offline using simulated channel data. During actual operation, only the pre-trained model inference is needed, which significantly reduces the computational complexity and hardware requirements compared to training complex denoising networks in real-time
3Measurement precision
If rotation-based fine-tuning mechanism is used to mitigate off-grid errors, then measurement precision is improved, but computational complexity increases
Solution Approach 1:
The patent applies partial action by implementing rotation-based fine-tuning only in the angular dimension rather than performing exhaustive grid search in both angular and temporal dimensions. This selective approach achieves significant accuracy improvement while keeping computational complexity manageable
Data Source
AI summary
The present invention discloses an automated AI-enabled mixed signal processing-based method for suitable channel path characterization in a radio propagation environment for a multi-antenna-based communication system comprising capturing dual wideband spreading of channel paths, recovering the channel paths under extremely low SNR scenario via Deep Learning (DL) assisted channel response denoising, identifying the number of unknown channel path clusters and their respective 2D spreads through a robust clustering mechanism and estimating Direction of Arrival (DoA) and Time of Arrival (ToA) of the channel paths with low computational complexity, accounting for spatial wideband effects to mitigate off-grid measurement errors via a rotation-based fine-tuning approach.