GenAI for Energy-Efficient and Interference-Aware Compressed Sensing of GNSS Signals on a Google Edge TPU

2026-05-14

AI Summary

This work addresses the challenge of real-time GNSS interference classification on resource-constrained devices, where conventional approaches rely on cloud-based processing and thus fail to meet latency and energy efficiency requirements. The authors propose an edge intelligence framework leveraging generative AI, deploying for the first time an 8-bit quantized Variational Autoencoder (VAE) on a Google Edge TPU. By integrating conditional and disentangled representation learning (FactorVAE), the model processes raw IQ samples, FFT spectra, and handcrafted features directly at the edge, achieving over 42× high-fidelity signal compression. This approach significantly reduces data transmission overhead and power consumption while maintaining strong classification performance—attaining an F2-score of 0.915 across 72 interference classes, closely approaching the 0.923 score obtained with uncompressed signals—and simultaneously ensuring real-time operation, energy efficiency, and model interpretability.

Abstract

Traditional methods for classifying global navigation satellite system (GNSS) jamming signals typically involve post-processing raw or spectral data streams, requiring complex and costly data transmission to cloud-based interference classification systems. In contrast, our proposed approach efficiently compresses GNSS data streams directly at the hardware receiver while simultaneously classifying jamming and spoofing attacks in real time. Given the growing prevalence of GNSS jamming, there is a critical need for real-time solutions suitable for power-constrained environments. This paper introduces a novel method for compressing and classifying GNSS jamming threats using generative artificial intelligence (GenAI), specifically variational autoencoders (VAEs), deployed on Google Edge tensor processing units (TPUs). The study evaluates various autoencoder (AE) architectures to compress and reconstruct GNSS signals, focusing on preserving interference characteristics while minimizing data size near the receiver hardware. The pipeline adapts large-scale AE models for Google Edge TPUs through 8-bit quantization to ensure energy-efficient deployment. Tests on raw in-phase and quadrature-phase (IQ) data, Fast Fourier Transform (FFT) data, and handcrafted features show the system achieves significant compression (>42x) and accurate classification of approximately 72 interference types on reconstructed signals (F2-score 0.915), closely matching the original signals (F2-score 0.923). The hardware-centric GenAI approach also substantially reduces jammer signal transmission costs, offering a practical solution for interference mitigation. Ablation studies on conditional and factorized VAEs (i.e., FactorVAE) explore latent feature disentanglement for data generation, enhancing model interpretability and fostering trust in machine learning (ML) solutions for sensitive interference applications.

Problem

• GNSS interference
• compressed sensing
• energy-efficient edge computing
• real-time classification
• generative AI

Innovation

• Generative AI
• Variational Autoencoder
• Edge TPU
• Compressed Sensing
• GNSS Interference Classification