Charging Station Usage Prediction

The "Charging Station Usage Prediction" project aims to predict the occupancy status (occupied or not occupied) of charging stations using machine learning models, specifically Random Forest and Gradient Boosting. The system is developed with a Python backend, using Flask as the framework, and integrates a MySQL database to store station data. The dataset, sourced from Kaggle, provides historical data about charging station usage, including factors such as time, weather, location, and demand. By analyzing these parameters, the system predicts whether a charging station will be occupied or not, optimizing the station's operations and improving user convenience. The front-end of the application is developed using HTML, CSS, and JavaScript for a seamless user experience. The proposed system offers an efficient, scalable solution for managing charging station availability, ultimately enhancing the user experience and supporting better resource utilization.

Keywords: Charging station, occupancy prediction, Random Forest, Gradient Boosting, Flask, MySQL, Kaggle dataset, machine learning.