在电动车辆路径优化问题中,考虑驾驶员个性化驾驶习惯能够有效提升路径规划的适用性与用户满意度。不同驾驶员在加速、减速、速度选择及路线偏好方面存在显著差异,而这些驾驶习惯直接影响到电动车的能耗、行驶时间及充电需求。为了实现个性化的路径优化,本文提出了一种基于改进最大最小蚂蚁系统(Min Max Ant System)的求解方法,将驾驶员的驾驶特征(如急加速频率、平均速度、路线偏好等)融入优化模型中,从而更加准确地预测能耗和最佳路径。以自适应大邻域搜索算法(Adaptive Large Neighborhood Search)为改进方法的IMMAS算法来求解该车辆路径规划模型,通过随机破坏贪心修补,多次试验来确保算法的稳定性。实验结果表明,改进后的最大最小蚂蚁系统在电动车辆个性化路径优化问题上表现出较好的求解效率和适应性,与传统算法相比,在能耗、行驶时间和驾驶员偏好方面均表现出显著优势。该研究为电动车辆智能路径优化提供了新的方法和思路,有助于未来智能交通系统的个性化发展。In the optimization problem of electric vehicle paths, considering the personalized driving style of drivers can effectively improve the applicability and user satisfaction of path planning. There are significant differences in acceleration, deceleration, speed selection, and route preferences among different drivers, and these driving styles directly affect the energy consumption, travel time, and charging requirements of electric vehicles. In order to achieve personalized path optimization, this paper proposes a solution method based on the improved Min Max Ant System, which integrates the driving style characteristics of the driver (such as acceleration frequency, average speed, route preference, etc.) into the optimization model to more accurately predict energy consumption and optimal path. The IMMAS algorithm, improved by the Adaptive Large Neighborhood Search algorithm, is used to solve the vehicle path planning model. The stability of the algorithm is ensured through random damage greedy repair and multiple experiments. The experimental results show that the improved maximum minimum ant system exhibits good efficiency and adaptability in solving personalized path optimization problems for electric vehicles. Compared with traditional algorithms, it shows significant advantages in energy consumption, travel time, and driver preferences. This study provides new methods and ideas for intelligent path optimization of electric vehicles, which will contribute to the personalized development of future intelligent transportation systems
暂无评论