Recent Advances in LightConneuNet: Potential Analysis of Fuel Cell Vehicle-To-Grid System with Large-Scale Buildings: A Systematic Review

Abstract

The convergence of intelligent neural networks, renewable energy systems, and smart grid technologies is transforming modern building energy management. Fuel cell vehicle-to-grid (FCV2G) systems represent a promising paradigm for integrating hydrogen-powered vehicles as distributed energy resources within large-scale buildings. These systems enable bidirectional energy flow, supporting grid stability, renewable integration, and efficient energy utilization in complex and dynamic environments.  This paper presents a systematic review of LightConneuNet, a lightweight deep learning architecture designed to optimize FCV2G-based building energy systems. By combining depthwise separable convolutions, attention mechanisms, and residual connections, LightConneuNet achieves high predictive performance with reduced computational complexity, making it suitable for real-time and edge-based deployment. The framework incorporates multi-objective optimization to minimize energy costs, reduce emissions, and enhance renewable energy utilization while adapting to dynamic grid and vehicle conditions. Applications include peak load reduction, energy cost optimization, hydrogen energy management, and ancillary grid services such as frequency regulation. Empirical results demonstrate significant improvements in efficiency, scalability, and operational flexibility compared to traditional models. However, challenges related to hydrogen infrastructure, system integration, and regulatory frameworks persist. This review highlights the potential of combining deep learning and FCV2G systems to develop scalable, sustainable, and intelligent energy management solutions for future smart buildings.