关键词: 预测性节能巡航, 云控分层架构, 动态规划算法, 空挡滑行, 动力系统与车速协同规划

Abstract:

With the continuous development of vehicle-road-cloud integration systems， cloud-controlled energy-saving technologies for intelligent connected vehicles have become a key focus for industrial application. However， the existing energy-saving control technologies for electric heavy-duty trucks exhibit two primary deficiencies. On the one hand， there is lack of cloud-controlled hierarchical architecture design specifically tailored for energy-efficient driving application. On the other hand， current energy-saving speed optimization research based on road gradient information does not fully consider the characteristics of electric heavy-duty truck power systems， such as regenerative braking energy recovery and coasting， constraining the energy-saving performance of such systems. To address these challenges， in this study a predictive energy-saving cruise control system for electric heavy-duty trucks based on the cloud-controlled hierarchical architecture is proposed. Firstly， the system architecture for energy-efficient driving application is designed based on the principles of cloud control system， and a rolling optimization control method for vehicle-cloud collaboration is proposed. Secondly， leveraging cloud-based gradient information and the energy consumption model of electric heavy-duty trucks， an energy-saving cruise control algorithm is developed that integrates economic speed， coasting， and regenerative braking energy recovery into coordinated planning. The algorithm constructs a state space under heterogeneous hierarchical densities and employs state-point approximation to solve the dynamic programming problem. Finally， the planning performance of the proposed algorithm is analyzed and validated under typical uphill and downhill conditions， demonstrating significant predictive energy-saving driving characteristics. Additionally， comparative simulation using real road gradient data is conducted against traditional energy-saving cruise control algorithms. The results show that the proposed algorithm achieves a 4.29% improvement in energy-saving efficiency by incorporating coasting operation， highlighting the potential of coasting in energy-saving control for electric heavy-duty trucks. A cloud-controlled hierarchical platform is constructed to comprehensively validate the system architecture and energy-saving performance. The results from 200 km of effective testing show that the proposed system achieves a maximum energy-saving efficiency of 8% compared to constant-speed cruise control， and an energy-saving rate of 1.62%-3.40% compared to manual driving. The above findings show that the cloud-controlled predictive energy-saving cruise control system has significant energy-saving potential and can comprehensively enhance the energy-efficient driving capabilities of vehicles and drivers， providing substantial value for industrial application.

Key words: predictive energy-saving cruise control, cloud-controlled hierarchical architecture, dynamic programming algorithm, coasting in neutral, power system and speed collaborative planning