The invention discloses an intelligent network connection vehicle power demand online prediction method based on space-time cooperation. The method comprises the following steps: in an intelligent network connection environment, dividing vehicle target travel into a plurality of space road sections according to space distances; extracting vehicle feature information of each space road section at atypical moment through V2I communication to form a feature parameter space matrix; constructing a feature parameter recombination model; and further determining an optimal node matrix set. In actualdriving, vehicle feature information of each space road section at a current moment is firstly extracted, a power demand of the target vehicle in the space road section is calculated through the optimal node matrix set determined by the model, and then the power demand of the space road section is compensated through a time deviation coefficient matrix so as to determine the final power demand. According to the method, power demand prediction precision of the target vehicle under the target travel can be improved, and space-time collaboration is ensured so that a foundation is laid for implementation of an energy management strategy and planning of an optimal path of the intelligent network connection vehicle.
本发明公开了一种基于时空协同的智能网联汽车功率需求在线预测方法,是在智能网联环境下,按空间距离将车辆目标行程划分为多个空间路段,通过V2I通信提取典型时刻各空间路段车辆特征信息,形成特征参数空间矩阵,并构建特征参数重组模型,进而确定最优节点矩阵集合;在实际行驶中,车辆先提取当前时刻各个空间路段的车辆特征信息,并通过模型确定的最优节点矩阵集合去计算目标车辆在空间路段的功率需求,然后通过时间偏差系数矩阵对空间路段的功率需求进行补偿,确定最终的功率需求。本发明能提高目标车辆在目标行程下的功率需求预测精度,并保证了时空的协同性,从而为智能网联汽车在能量管理策略的实施以及最优路径的规划奠定基础。
Intelligent network connection vehicle power demand online prediction method based on space-time coordination
一种基于时空协同的智能网联汽车功率需求在线预测方法
2020-06-23
Patent
Electronic Resource
Chinese
European Patent Office | 2023
|European Patent Office | 2024
|Demand response bus real-time scheduling method and system based on intelligent network connection
European Patent Office | 2023
|Intelligent network connection vehicle searching navigation method
European Patent Office | 2022
|