Smart Adaptive Streetlight

Inspiration

Spain faces one of the highest levels of light pollution in Europe, largely caused by inefficient public lighting. This is not only an environmental issue but also a public health and economic problem. We wanted to rethink how cities illuminate their streets—making them smarter, more efficient, and responsive to real human needs without compromising safety.

What it does

Smart Adaptive Streetlight dynamically adjusts lighting based on ambient light and human presence. It reduces unnecessary illumination during low-activity periods while maintaining a safe minimum brightness. The system also monitors environmental conditions such as noise and temperature, detects anomalies, and can activate a microclimate cooling system during extreme heat. Additionally, it sends real-time data to a central platform for urban analysis.

How we built it

We built the system using an Arduino-based platform running Zephyr. It integrates multiple sensors (LDR for light, PIR for presence, DHT22 for temperature and humidity, and KY-037 for sound). Local logic processes the data using filtering and rule-based decisions to control LED intensity and actuators. Data is transmitted via MQTT to a web-based control station built with Python, Eel, and SQLite for visualization and monitoring.

Challenges we ran into

One of the main challenges was dealing with sensor limitations, especially accurately interpreting sound levels using low-cost hardware. Another difficulty was balancing responsiveness and energy efficiency in the lighting logic. Integrating multiple components (hardware, MQTT communication, and web interface) into a stable system also required careful debugging and testing.

Accomplishments that we're proud of

We developed a fully functional prototype that combines real-time sensing, adaptive lighting, and environmental monitoring. The system works autonomously while also being connected to a central dashboard. We are especially proud of achieving a practical and scalable solution that addresses real urban problems rather than a purely conceptual idea.

What we learned

We gained hands-on experience in IoT system design, sensor integration, and real-time data processing. We also learned the importance of designing for real-world constraints, such as hardware limitations and environmental variability. Additionally, we improved our skills in system architecture, communication protocols like MQTT, and building full-stack prototypes.

What's next for Smart Adaptive Streetlight

Next steps include integrating machine learning models for sound classification and predictive lighting, improving sensor accuracy, and enabling communication between multiple streetlights for coordinated behavior. We also aim to test the system in real urban environments and refine the microclimate system to make it more efficient and sustainable.