Online Scheduling With Trajectory Prediction for Collaborative DNN Inference in Vehicular Networks

In recent years, deep neural networks (DNNs) have been extensively utilized to provide vehicular intelligent services. Given the limited computing capabilities of vehicles, collaborative vehicle-edge DNN inference has emerged as a promising approach. This method partitions the DNN, then distributes parts to the vehicle or the edge, e.g., roadside unit (RSU), for sequential inferences. However, determining the optimal DNN partition is challenging due to the uneven load distribution of DNN models and varying road traffic conditions. Moreover, vehicle movement can cause loss of inference results if vehicles leave the RSU signal coverage. To this end, we propose a novel online learning-based collaborative DNN Inference framework MCI. MCI utilizes multiple RSUs to assist vehicles with sequential inference and ensure reliable data transmission. To reduce learning cost, MCI designs a trajectory prediction to analyze vehicle context before making decisions. Then, MCI combines the classical EXP4 and LinUCB algorithms to learn system dynamics and make effective scheduling decisions. We prove that MCI achieves a sublinear regret bound of $O(T^{3/4} \sqrt {\log T})$ . Extensive experimental results show that MCI reduces latency by up to 68% and has a lower failure rate, compared to state-of-the-art algorithms.