A Smart Vehicle-to-Grid Energy Management System Using IOT and Machine Learning

The increasing adoption of electric vehicles (EVs) is creating new challenges and opportunities for modern power systems. One promising approach to manage this growing demand is the Vehicle-to-Grid (V2G) technology, which allows electric vehicles not only to consume energy from the grid but also to supply energy back when needed. This paper presents the design and implementation of an IoT-based V2G system with a simple demand prediction mechanism using machine learning. The proposed system uses an ESP32 microcontroller to monitor electrical parameters such as voltage, current, and power during both Grid-to-Vehicle (G2V) and Vehicle-to-Grid (V2G) modes. The collected data is transmitted to a cloud database using Firebase, which enables real-time monitoring through a dashboard interface. A machine learning model based on the Random Forest algorithm is implemented to predict power demand based on voltage, current, and operational mode of the system. The predicted demand helps in understanding the future power requirements and possible energy exchange between electric vehicles and the grid. The system also includes relay-based switching to simulate bidirectional energy flow between the grid and the vehicle battery. Experimental results show that the proposed system is able to monitor energy parameters in real time and provide reasonable demand prediction. This work demonstrates how IoT and machine learning techniques can be combined to support smarter and more flexible energy management in future EV charging infrastructure. .