Velocity and Density-Aware RRI Analysis and Optimization for AoI Minimization in IoV SPS
Maoxin Ji, Tong Wang, Qiong Wu, Pingyi Fan, Nan Cheng, Wen Chen
TL;DR
This work addresses AoI minimization in IoV SPS by jointly optimizing vehicle speed, density, and Resource Reservation Interval under speed- and density-induced channel uncertainties. It presents a dual-path optimization framework that leverages a pretrained Large Language Model (LLM) for rapid, exemplar-driven solutions and a Deep Deterministic Policy Gradient (DDPG) agent for stable online optimization. The AoI model captures collisions, Doppler-induced losses, and retransmission effects through a Markov-channel-based analysis, and the optimization is formulated as an MDP with detailed state, action, and reward definitions. Simulation results indicate that the LLM approach can significantly reduce AoI with few exemplars and no online training, while DDPG achieves stable performance after training; together, they highlight the potential of combining data-driven and learning-to-optimize strategies for real-time vehicular communications.
Abstract
Addressing the problem of Age of Information (AoI) deterioration caused by packet collisions and vehicle speed-related channel uncertainties in Semi-Persistent Scheduling (SPS) for the Internet of Vehicles (IoV), this letter proposes an optimization approach based on Large Language Models (LLM) and Deep Deterministic Policy Gradient (DDPG). First, an AoI calculation model influenced by vehicle speed, vehicle density, and Resource Reservation Interval (RRI) is established, followed by the design of a dual-path optimization scheme. The DDPG is guided by the state space and reward function, while the LLM leverages contextual learning to generate optimal parameter configurations. Experimental results demonstrate that LLM can significantly reduce AoI after accumulating a small number of exemplars without requiring model training, whereas the DDPG method achieves more stable performance after training.