Integration of LLM and Human-AI Coordination for Power Dispatching With Connected Electric Vehicles Under SAGVNs

Xingchi Chen, Xiaoyang Lu, Qing Li, Dazhou Li, Fa Zhu

Abstract: Advanced artificial intelligence (AI) solutions deployed in the environment of space-air-ground integrated vehicular networks (SAGVNs) are instrumental in achieving efficient coordination between connected electric vehicles (EVs) and distributed networks. This study addresses this challenge by leveraging a Large Language Model (LLM) based hybrid dispatching framework for formulating dispatching strategies, where the need for commonsense understanding by EV drivers is paramount. This paper proposes a framework LLM-D3PG, LLM-guided dual Deep Deterministic Policy Gradient, which empowers EV drivers to articulate their expectations for AI-generated dispatching strategies using natural language instructions. These instructions serve as guidance for the generation of dispatching strategies within complex distributed network scenarios. According to this strategy, the proposed framework seamlessly integrates the decision-making capabilities of LLM with multiple D3PG models to generate a large number of candidate dispatching strategies and then uses the whale optimization algorithm to optimize these strategies to achieve better dispatching results. Comprehensive experimental results demonstrate the effectiveness of the proposed framework and show outperformance in comparison to some existing methods for power dispatching tasks with the random connection of EVs in SAGVNs.

External IDs:dblp:journals/tvt/ChenLLLZ25