In July 2026, the TRANS research group published its latest finding—titled “Large Language Models for Transportation Energy Integration: A Functional Framework and Future Directions“—in Renewable and Sustainable Energy Reviews, a top-tier (JCR Q1) journal in the energy sector with an impact factor of 18. The transportation and building sectors currently account for approximately 55% of global energy consumption and nearly 50% of carbon emissions. With the advancement of electric mobility, Vehicle-to-Grid technology, and renewable energy, the deep coupling of transportation networks with power grids and building systems—known as Transportation-Energy Integration (TEI)—has emerged as a critical pathway toward global decarbonization. However, traditional computational models face significant bottlenecks when dealing with massive heterogeneous data, complex non-linear coupling, and the high uncertainty of human behavior. Addressing the frontier needs of low-carbon transportation transitions, the synergistic optimization of energy systems, and the integration of AI technologies, this paper systematically reviews research progress on LLMs in the field of TEI. It proposes a three-layer functional framework—”Perception & Understanding,” “Prediction & Reasoning,” and “Decision-Making & Optimization”—providing a systematic reference for future research on smart transportation-energy systems.
CITAION: Chen, Y., Ou, S. S., Lv, Z., Yang, Z., Gu, L., & Ma, W. (2026). Large language models for transportation energy integration: A functional framework and future directions. Renewable and Sustainable Energy Reviews, 241, 117243. doi:10.1016/j.rser.2026.117243