An Enhanced Predictive Cruise Control System Design With Data-Driven Traffic Prediction

The predictive cruise control (PCC) is a promising method to optimize energy consumption of vehicles, especially the heavy-duty vehicles (HDV). Due limited sensing range and computational capabilities available on-board, conventional PCC system can only obtain sub-optimal speed trajectory based on shorter prediction horizon. recently emerging information communication technologies such as vehicular communication, cloud computing, Internet Things provide huge potentials improve traditional system. In this paper, we propose general framework for enhanced cloud-based which integrates data-driven traffic model instantaneous algorithms. Specifically, introduce novel multi-view CNN deep learning algorithm predict situation historical real-time data collected from fields, time-varying adaptive (MPC) calculate optimal profile with aim minimizing consumption. We verified our approach via simulations in impact various condition PCC-enabled HDV has been fully evaluated.