Resource Constrained Neural Networks for 5G Direction-of-Arrival Estimation in Micro-controllers

TL;DR

This paper presents a low-complexity neural network algorithm for accurate direction-of-arrival estimation on microcontrollers, enabling efficient edge AI for 5G spectrum sensing with improved performance over traditional methods.

Contribution

It introduces a novel neural network-based DoA estimation method optimized for microcontroller constraints and demonstrates its implementation and validation on an STM32 MCU.

Findings

Outperforms conventional statistical spatial sensing methods.

Effective across various SNR levels and antenna configurations.

Validated on real hardware with a custom GUI.

Abstract

With the introduction of shared spectrum sensing and beam-forming based multi-antenna transceivers, 5G networks demand spectrum sensing to identify opportunities in time, frequency, and spatial domains. Narrow beam-forming makes it difficult to have spatial sensing (direction-of-arrival, DoA, estimation) in a centralized manner, and with the evolution of paradigms such as artificial intelligence of Things (AIOT), ultra-reliable low latency communication (URLLC) services and distributed networks, intelligence for edge devices (Edge-AI) is highly desirable. It helps to reduce the data-communication overhead compared to cloud-AI-centric networks and is more secure and free from scalability limitations. However, achieving desired functional accuracy is a challenge on edge devices such as microcontroller units (MCU) due to area, memory, and power constraints. In this work, we propose low complexity neural network-based algorithm for accurate DoA estimation and its efficient mapping on the off-the-self MCUs. An ad-hoc graphical-user interface (GUI) is developed to configure the STM32 NUCLEO-H743ZI2 MCU with the proposed algorithm and to validate its functionality. The performance of the proposed algorithm is analyzed for different signal-to-noise ratios (SNR), word-length, the number of antennas, and DoA resolution. In-depth experimental results show that it outperforms the conventional statistical spatial sensing approach.