Optical wireless receiver detects faults using on-device AI

Fault Detection and Bit-Error Rate Diagnostics in Optical Wireless Links Using Edge-AI

Machine Learning

Summary

Optical wireless communication can send data very fast without radio interference but is easily disrupted by things like blocking the signal or bright lights. The authors built a tiny computer inside the receiver that watches the signal and uses a small AI model to quickly figure out if something is wrong. This AI runs directly on a low-power chip and can tell different issues like bad alignment or too much light without needing a cloud computer. This helps make optical wireless devices smarter and able to fix problems by themselves in real time.

What this means in practice

  • For wireless network engineers: Integrate on-device AI to diagnose and classify faults in optical wireless links in real time without external processing.
  • For iot device developers: Build self-monitoring optical wireless nodes that maintain communication quality by detecting and reporting physical channel issues on device.

Authors

Sarthak Bhattarai, Sheshadri Shikhar Bandyopadhyay, Suprabh Dhakal, Jitendra Kumar Manandhar

Abstract

Optical Wireless Communication (OWC) systems provide high-bandwidth, spatially secure, and RF-interference-free digital transmission. However, direct free-space optical links suffer from extreme sensitivity to line-of-sight disruptions, optical attenuation, high ambient light saturation, and transmitter-receiver misalignment. Traditional channel diagnostic frameworks rely on external computing nodes or cloud-based processing, which introduces severe diagnostic latency and reduces edge node autonomy. This paper presents an autonomous, self-diagnosing optical wireless receiver node that integrates physical-layer signal telemetry extraction with an on-device TinyML classification engine. Built around an ESP32-S3 microcontroller, the receiver recovers 1000 bit/s On-Off Keying (OOK) digital payloads using a 5-sample majority voting mechanism while concurrently extracting real-time channel features: Bit Error Rate (BER), received signal voltage (Vsignal), Signal-to-Noise Ratio (SNRdB), and ambient light baseline (Lambient). Evaluated against a Random Forest baseline (77.22% accuracy) and a floating-point neural network (78.48% accuracy), a post-training INT8 quantized TensorFlow Lite Micro model occupying only 3.32 kB of SRAM runs directly on the receiver firmware. The quantized model achieves 74.68% overall accuracy across four distinct operational conditions: normal transmission, optical filter attenuation, ambient light interference, and severe obstruction/misalignment. On-device deployment tests confirm real-time, deterministic fault classification, establishing a practical approach for self-aware optical IoT nodes.