Automatic Street Light using IOT and M L

This abstract introduces an innovative project that seamlessly combines Internet of Things (IoT) technology with machine learning, specifically leveraging the random forest and Linear regression algorithm, to create an advanced automatic street light system with predictive capabilities. The system incorporates various IoT components, including a Light Dependent Resistor (LDR) for ambient light detection, an air quality sensor, a humidity sensor, an ESP32 microcontroller for data processing, and a motion sensor for vehicle detection. The primary goal of this system is twofold: to optimize energy consumption and to ensure proper illumination. During daylight hours, the street lights remain off as the LDR senses sufficient natural light, conserving energy. As darkness sets in, the system automatically triggers the street lights to turn on, thereby providing efficient lighting when needed. Furthermore, the project implements a motion sensor to further enhance energy efficiency. When no vehicles are detected on the road, the street lights are dimmed, minimizing energy usage. However, as a vehicle approaches, the motion sensor identifies its presence and brightens the lights, ensuring adequate visibility and safety. Beyond lighting control, the system employs machine learning techniques for predictive analytics. Data from various sensors, including the LDR, air quality, and humidity sensors, are collected and analyzed using the Random forest and linear regression algorithm, enabling accurate predictions of power consumption, air quality, and humidity levels. These predictive capabilities facilitate efficient energy management, inform urban planning, and support resource allocation. To facilitate seamless integration and real-time monitoring of sensor data, the project utilizes Python Flask, a micro web framework, for building the web interface. Flask’s versatility enables easy data visualization and management, making it a suitable choice for this application.