Build a Federated Anomaly Detection System with ESP32 Mesh & Pi 5

Every part needed, pre-tested for compatibility, with an AI build companion trained on this exact project. Shipped from Bengaluru in 3-5 days.

In a world where data privacy matters, this kit lets you build a network of 5 ESP32 sensor nodes that detect anomalies locally, sharing only encrypted model gradients to a central Raspberry Pi 5 aggregator. Ideal for real-world IoT security monitoring, industrial sensor fault detection, or a standout college project. No cloud, no centralized data — true federated learning at the edge, right on your desk.

What You'll Build

You'll assemble a wireless mesh of five ESP32 microcontrollers, each equipped with a DHT22 temperature/humidity sensor and three nodes with ADXL345 accelerometers. They train individual anomaly detection models on locally sensed data, then collaboratively improve a global model on the Pi 5 without exposing raw data. The final dashboard on the Pi shows detected anomalies across the mesh.

What You'll Learn

• Implementing federated averaging on resource-constrained ESP32 devices
• Training on-device anomaly detection using TinyML frameworks
• Building an ESP-NOW mesh network for low-latency gradient sharing
• Deploying a secure aggregator node on Raspberry Pi 5 with NVMe storage for model checkpoints

Kit Contents

Why Buy This Kit Instead of Sourcing Parts Separately

Who This Kit Is For

Ideal for B.Tech ECE/EEE students tackling privacy-aware IoT projects, Smart India Hackathon teams exploring federated edge AI, and advanced CBSE Class 11-12 makers in ATL Tinkering Labs. Perfect for anyone moving from simple sensor tutorials to real distributed machine learning at IIT, NIT, VIT, or BITS Pilani.

Built and Backed by Compoden

Every Compoden kit ships with an AI build companion trained on this exact project — accessible via a QR code on the box, with WhatsApp and email backup. We've spent 10 years building projects for makers, schools, and institutions across India. If a part fails because of a manufacturing defect, replace it free within 7 days.