Large-Scale Traffic Flow Forecast with Lightweight LLM in Edge Intelligence

Yi Rong, Yingchi Mao, Xiaoming He, Mingkai Chen

Abstract: Large-scale traffic flow forecasting affiliated with the time is valuable for the management in Intelligent Transportation Systems (ITS). Recently, Large Language Models (LLMs) have shown the prominence on this issue. Unfortunately, the existing LLMs cannot forecast the entire road network, including two problems, i.e., (1) training the large-scale data generated by a road network on the central cloud can impose computational pressure. (2) LLMs fail to capture the spatiotemporal correlations in the road network. To overcome the challenges, we propose a novel architecture named Light-weight Spatio-temporal Generative Large Language Model on Edges (LSGLLM-E). Specifically, we first decompose the entire large-scale road network into several subparts, and deploy the Rode-side Unit (RSU) as an edge on each subpart, thus avoiding the computational pressure on the central cloud. In addition, we design an LLM-based method named Light-weight Spatio-temporal Generative Large Language Model (LSGLLM) to extract the spatiotemporal correlations, which compensates for the lack of spatiotemporal features. Finally, the experimental results illustrate that the LSGLLM-E is superior to some advanced baselines in terms of the accuracy and efficiency of the prediction.