Motion sensors are a cheap way to control lighting, but they are blind: lights turn on with delay, turn off when someone is still in the room, and ignore daylight. The result — 30% of energy is wasted. We, a team with over 5 years of experience in ML building automation (more than 50 completed projects), solve this problem differently: we train a model to predict occupancy and smoothly adjust brightness to real conditions. The system pays for itself in 2–4 years, and staff comfort increases — no harsh switching or flicker.
In one project for an office building of 2500 m², we implemented a system based on Edge ML. We installed 12 Raspberry Pi 4 units connected to a DALI network. The Random Forest model was trained on 3 months of historical data and achieved 94% occupancy accuracy. Energy consumption dropped by 45%.
How AI Solves Blind Lighting
Classic PIR sensors provide a binary signal: "motion/no motion." They cannot distinguish a person from a cat, do not remember history, and do not know that at 3:00 PM the meeting room is usually occupied. Our approach — an ML model on time series — collects data from sensors (PIR, ultrasound, CO2, lux) and builds a probabilistic forecast. The Random Forest model yields 95% occupancy accuracy — 1.5 times more accurate than typical PIR (70%). Daylight harvesting based on autoregression reduces brightness when natural light reaches 500 lux — an extra 15% savings.
System Architecture
- Sensor layer: PIR/ultrasonic presence sensors (accuracy 90–95%), lux sensors for daylight harvesting, CO2 sensors for indirect occupancy estimation, optionally cameras with people counting.
- Edge ML: On a DALI controller or local Raspberry Pi: occupancy prediction (Random Forest on temporal patterns), daylight model (AutoRegressive on historical lux + weather forecast), adaptive dimming (RL agent maintains target illuminance of 300–500 lux).
- Control Layer: DALI (Digital Addressable Lighting Interface) — standard protocol for lighting control. Group and individual luminaire control.
What the System Does
- Turns off lighting when no people are present after N minutes (adaptive timeout per zone, considering return probability).
- Reduces brightness when daylight is sufficient — the model predicts illuminance one hour ahead.
- Pre-lights before people arrive (based on calendar/patterns).
- Emergency lighting when motion is detected in dark periods — with smooth ramp-up to 20%.
- Automatic calibration: the model retrains every week on new data, adapting to seasonality.
Why Choose ML Over Simple Timers?
Timers are inflexible: on Friday evening the office is empty, but lights stay on until 11:00 PM. An ML model analyzes occupancy over the last 8 weeks and predicts empty zones with probability 0.97 — lights turn off 40 minutes earlier. The "last person leaves" scenario saves up to 8% of total consumption. Plus, the model suppresses false triggers from drafts and animals — detection accuracy does not drop. The ML model cuts energy consumption by 30–50%, which is 2–3 times more than timers (10–20%).
Impact Metrics
| Indicator | Value | Comment |
|---|---|---|
| Electricity savings | 30–50% | Depending on zone and season |
| System payback period | 2–4 years | For objects from 500 m² |
| Occupancy detection accuracy | 92–96% | On labeled data from 10 zones |
| Employee comfort improvement | – | Discomfort complaints reduced by 70% |
Comparison of Lighting Control Approaches
| Parameter | Timers | PIR Sensors | ML Approach |
|---|---|---|---|
| Schedule flexibility | Low | Medium | High |
| Daylight harvesting | No | No | Yes |
| Occupancy accuracy | – | 70% | 95% |
| Energy savings | 10–20% | 20–30% | 30–50% |
| Seasonal adaptation | No | No | Yes |
What's Included in the Work
- Site survey: audit of current lighting system, zone diagrams, illuminance measurements, historical sensor data collection.
- ML solution design: model selection (Random Forest, LSTM, Prophet), hyperparameter tuning, simulation on synthetic data.
- Installation and integration: edge controller setup, connection via DALI/Modbus, model deployment through ONNX Runtime. Integration with BMS via BACnet, Modbus, KNX is possible.
- Calibration and A/B test: 2–3 weeks of parallel operation, comparison with existing logic.
- Staff training and documentation: handover of dashboard (Grafana), API for BMS integration.
Ready to estimate savings for your building? Contact us for a preliminary calculation.
Timeline: 4–8 weeks
Leave a request for a savings calculation — we will assess your facility in 2 days and calculate payback. We guarantee at least 30% reduction in energy consumption.
DALI — standard IEC 62386 for digital lighting control.