基于Kriging遗传算法的高速公路应急车道管控优化

Optimization of Highway Emergency Lane Control Based on Kriging Genetic Algorithm

针对如何在不同交通流状况下有效提高高速公路运行效率和降低安全风险的问题,提出基于Kriging代理模型的遗传算法优化应急车道管控策略。结合应急车道开放策略的时空特性设计数学优化模型,通过引入Kriging代理模型,结合遗传算法搭建优化框架,采用仿真软件获取数据训练代理模型,以此求解带有开放时间和开放空间双重约束的总行程时间与总碰撞暴露时间最小化问题。对车道控制时间与空间变量的变化频次进行了约束,并对目标函数中效率与安全指标权重变化对优化结果的影响进行了分析。实验表明:该优化方法使路网总行程时间减小14.9%,碰撞暴露时间减小44.2%,控制效果提升。

To address the issue of how to effectively improve the highway operational efficiency and reduce the safety risks under different traffic flow conditions,this study proposed a genetic algorithm based on Kriging agent model is proposed to optimize the emergency lane control strategy.A mathematical optimization model is designed by combining the spatial and temporal characteristics of the emergency lane opening strategy.By introducing Kriging agent model,combining the genetic algorithm to build the optimization framework,and using simulation software to obtain data to train the agent model,the problem of minimizing the total travel time and the total exposed time-to-collision with both time and space constraints is solved.The change frequency of the emergency lane control at time and space dimension is constrained.The effect of the change of weights for efficiency and safety indicators in the objective function on the optimization results.Comparison in experiments show that the proposed optimization method reduces the total travel time of the road network by 14.9%and the total time exposed time-to-collision by 44.2%.