Artificial Intelligence Optimization for User Prediction and Efficient Energy Distribution in Electric Vehicle Smart Charging Systems

Siow Jat Shern, Md Tanjil Sarker (), Mohammed Hussein Saleh Mohammed Haram, Gobbi Ramasamy (), Siva Priya Thiagarajah and Fahmid Al Farid
Additional contact information
Siow Jat Shern: Centre for Electric Energy and Automation, Faculty of Engineering, Multimedia University, Cyberjaya 63100, Malaysia
Md Tanjil Sarker: Centre for Electric Energy and Automation, Faculty of Engineering, Multimedia University, Cyberjaya 63100, Malaysia
Mohammed Hussein Saleh Mohammed Haram: Centre for Electric Energy and Automation, Faculty of Engineering, Multimedia University, Cyberjaya 63100, Malaysia
Gobbi Ramasamy: Centre for Electric Energy and Automation, Faculty of Engineering, Multimedia University, Cyberjaya 63100, Malaysia
Siva Priya Thiagarajah: Centre for Electric Energy and Automation, Faculty of Engineering, Multimedia University, Cyberjaya 63100, Malaysia
Fahmid Al Farid: Centre for Digital Home, Faculty of Engineering, Multimedia University, Cyberjaya 63100, Malaysia

Energies, 2024, vol. 17, issue 22, 1-25

Abstract: This paper presents an advanced AI-based optimization framework for Electric Vehicle (EV) smart charging systems, focusing on efficient energy distribution to meet dynamic user demand. The study leverages machine learning models such as Random Forest, Support Vector Regression (SVR), Gradient Boosting Regressor, XGBoost, LightGBM, and Long Short-Term Memory (LSTM) to forecast user demand and optimize energy allocation. Among the models, XGBoost demonstrated superior predictive performance, achieving the lowest Mean Absolute Error (MAE) and Root Mean Square Error (RMSE), making it the most effective for real-time user demand prediction in smart charging scenarios. The framework introduces proportional and priority-based allocation strategies to distribute available energy effectively, with a focus on minimizing energy shortfalls and balancing supply with user demand. Results from the XGBoost model reduced prediction error by 15% compared to other models, significantly improving the station’s ability to meet user demand efficiently. The proposed AI framework enhances charging station operations, supports grid stability, and promotes sustainability in the context of increasing EV adoption.

Keywords: electric vehicle (EV) charging; artificial intelligence (AI) optimization; energy distribution; XGBoost; machine learning; smart charging system; demand forecasting; proportional allocation; priority-based allocation; sustainable energy management; grid stability (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/17/22/5772/pdf (application/pdf)
https://www.mdpi.com/1996-1073/17/22/5772/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:17:y:2024:i:22:p:5772-:d:1523919

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().