Electric Vehicle User Profiling and Spatiotemporal Charging Demand Forecasting Based on Monte Carlo Method

This paper addresses the challenge of limited understanding of current user behaviors by proposing an electric vehicle (EV) user profile method that encompasses a broad distribution range, large quantity, and diverse scale features. With the Gaussian Mixture Models (GMM), the study categorizes EV us...

Full description

Saved in:
Bibliographic Details
Published in2024 IEEE 25th China Conference on System Simulation Technology and its Application (CCSSTA) pp. 493 - 498
Main Authors Jiang, Weijie, Ameer, Hamza, Wang, Yujie
Format Conference Proceeding
LanguageEnglish
Published IEEE 21.07.2024
Subjects
Analytical models
cluster analysis
Demand forecasting
Electric vehicle charging
Estimation
Gaussian mixture model
Kernel
kernel density estimation
monte carlo method
Monte Carlo methods
Predictive models
Spatiotemporal phenomena
Systems simulation
user profile
Online AccessGet full text

Cover

More Information
Summary:This paper addresses the challenge of limited understanding of current user behaviors by proposing an electric vehicle (EV) user profile method that encompasses a broad distribution range, large quantity, and diverse scale features. With the Gaussian Mixture Models (GMM), the study categorizes EV users into 7 classes. Subsequently, employing kernel density estimation, we construct probability density functions(PDF) and perform Monte Carlo simulations to predict EV charging demands. This theoretical framework establishes a foundation for future advancements in managing and scheduling EV charging and discharging operations, aiming to optimize energy usage and improve overall system efficiency.
DOI:10.1109/CCSSTA62096.2024.10691711