Back to Case Studies
IoT & IndustrialEnergy
PowerIntel
AI Smart Energy Monitor based on nRF9160
Clip-on energy monitor that identifies individual appliance usage from aggregate mains power using edge AI.
Disaggregation Accuracy
93%
Sampling Rate
1 MHz
PowerIntel
Client
An energy analytics company providing residential energy monitoring that breaks down electricity usage by individual appliance without per-appliance sensors.
Challenge
Sampling mains current at sufficient resolution (1MHz) to capture appliance electrical signatures, then classifying them on-device with consumer-grade privacy.
Product Concept & Architecture
A Rogowski coil clamps around the mains feed. A 24-bit ADS131M04 ADC samples at 1MHz. The Nordic nRF9160 processes 1-second current windows through a neural network for appliance identification.
Engineering Solution
The nRF9160's Cortex-M33 runs a 1D-CNN + LSTM hybrid model (150KB, INT8 quantized) that processes the 1MHz current waveform and extracts appliance-level signatures. The model identifies 12 appliance types with 93% accuracy. Only the appliance-level breakdown is transmitted via LTE-M.
Result
93% appliance disaggregation accuracy across 12 common appliances. Instant clip-on installation. Zero raw data leaves the home.
Deep Tech FAQ
What makes the AI Smart Energy Monitor based on nRF9160 unique?+
The AI Smart Energy Monitor based on nRF9160 leverages custom hardware and edge AI to deliver industry-leading performance and efficiency.
What are the core technical benefits?+
Key benefits include low power consumption, real-time processing, robust connectivity, and a compact form factor tailored for deployment.
Can this architecture be adapted for other use cases?+
Absolutely. The underlying methodology is modular and can be retargeted for various applications with minimal redesign.
Project Profile
Services Delivered
Hardware DesignEmbedded SoftwareRF Design
Core Technologies
LTE-M/NB-IoTTinyMLRTOS
Silicon & Vendors
NordicTI
Need similar outcomes?
Let's discuss how ChipTalk can deliver results for your next project.
Tell us about your project.
Fast Response — Initial feedback within 48 hours
Full R&D Lifecycle — From feasibility to mass production
Extensive Experience — 500+ projects across 15 verticals
Rapid MVP Validation — Prototype in as fast as 12 weeks
Portfolio
