Smart Building Energy Management System Using Machine Learning And IOT

This abstract describes the development of an integrated system for smart energy management using a Raspberry Pi interfaced with multiple sensors. The system incorporates a Passive Infrared (PIR) motion sensor, a gas sensor, a DHT11 temperature and humidity sensor, and an atmospheric pressure sensor. These sensors collectively enable the measurement of motion, temperature, humidity, and atmospheric pressure within a given environment. The gathered sensor data is then processed through a machine learning algorithm, which plays a pivotal role in decision-making for energy optimization. The primary objective of this system is to enhance energy efficiency by automating the control of electrical loads such as fans and lights. If the machine learning algorithm detects an absence of people in the vicinity, it triggers a relay-based mechanism to power off these loads.

The implementation of this system serves as an intelligent solution to minimize energy consumption when it is not required, thereby contributing to effective energy management. By utilizing sensor data and machine learning, it ensures a more responsive and dynamic approach to control electrical appliances, ultimately leading to reduced energy usage and associated cost savings. This integration aligns with the broader goals of creating sustainable and environmentally responsible smart spaces. And those values will upload to a webserver for remote monitoring and analysis.