Logo image
Back
Advancing electric vehicle ecosystems: a survey of generative artificial intelligence and distributed machine learning applications
Journal article - Review   Open access   Peer reviewed

Advancing electric vehicle ecosystems: a survey of generative artificial intelligence and distributed machine learning applications

Seyed Mahmoud Sajjadi Mohammadabadi, Aidin Karimi Moghaddam, Mahmoudreza Entezami, Mirali Seyedrezaei, Dorsa Charkhian, Behzad Moghaddami and Mohammad Sassani
Global Energy Interconnection, v 9(2), pp 315-336
Apr 2026
DOI: https://doi.org/10.1016/j.gloei.2025.10.010
Featured in Collection :   Drexel's Newest Publications
url
https://doi.org/10.1016/j.gloei.2025.10.010View
Published, Version of Record (VoR) Open CC BY-NC-ND V4.0

Abstract

ChatGPT Distributed machine learning Energy forecasting Fault detection Generative artificial intelligence Resource optimization Electric Vehicles Optimization
The growing popularity of Electric Vehicles (EVs) necessitates advanced systems capable of managing the increasing complexity of EV-generated data. However, the exponential expansion of data streams poses significant challenges to existing network infrastructure, potentially limiting EV performance and scalability. This survey investigates the synergistic potential of Generative Artificial Intelligence (GenAI) and Distributed Machine Learning (DML) to address key challenges and enhance EV efficiency across diverse domains. DML facilitates collaborative learning across decentralized devices, enabling optimized resource allocation, strengthened privacy, and improved EV operations without data centralization. Meanwhile, GenAI techniques, such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), offer transformative capabilities, including synthetic data generation for energy forecasting, data compression for efficient transmission, and resource-efficient task offloading. This paper explores the applications of GenAI and DML in several key areas of the EV ecosystem. These include battery lifecycle management, energy optimization, fault detection, and workload balancing. Furthermore, it highlights the primary advantages and challenges of implementing these technologies, such as addressing computational demands, algorithmic complexity, and mitigating biases in generated content. By advancing the integration of GenAI and DML, this study lays a foundation for a more sustainable, intelligent, and efficient transportation future.

Metrics

1 Record Views

Details

Logo image