Toward Sustainable Residential Energy Use: A Simulated IoT Prototype with Cloud Storage and AI Analysis

Abstract

This paper presents an Internet of Things prototype for residential energy monitoring and basic automation. The system was developed with an ESP32 in Wokwi, a PIR motion sensor, an ultrasonic sensor, an LED, a buzzer, and an OLED display. The PIR sensor controls a bedroom light according to detected movement. The ultrasonic sensor is placed in front of the refrigerator door, and the system compares each measured distance with a reference distance recorded when the door is closed to determine whether the door is open or closed. If the door remains open longer than a defined limit, the system generates an alert. Sensor events are sent through a Flask proxy to Oracle APEX and stored in an Oracle database. A mobile application developed in MIT App Inventor allows users to review the event history and change sensor status. Gemini analyzes recent events and produces a short report describing a pattern, a possible waste condition, and one recommendation. Functional tests confirmed communication between Wokwi, Flask, Oracle APEX, App Inventor, and Gemini. The prototype shows that a simple, low-cost IoT architecture can support monitoring, remote control, and energy-saving decisions in a residential environment.