基于免疫遗传算法的OD矩阵反推模型与算法

OD-matrix Estimation Model and Algorithm Based on Immune Genetic Algorithm

针对在反推OD矩阵的非结构化方法中,各模型都将路段流量一次观测得到的样本值作为路段流量的真实值来推算OD矩阵,导致推算结果出现偏差的问题,在熵极大化模型的基础上,引入了路段流量真实值参数,对模型进行了修正。在反推过程中,利用免疫遗传算法良好的全局搜索能力,提出了基于免疫遗传算法的OD矩阵反推模型。算例表明,免疫遗传算法在进行OD矩阵反推时,能够快速、有效地搜索出最优OD矩阵。

In the unstructured methods of OD-matrix Estimation,because almost every models take once observed samples of traffic flows as the true values to project OD-matrix,it results in the deviation of the projected results.In this paper,based on the entropy maximization model,the true values of traffic flow parameters are used to amend the model.Meanwhile,this paper presents an OD-matrix estimation model based on Immune Genetic Algorithm due to the well global search capability of the Immune Genetic Algorithm.Examples show that the immune genetic algorithm can efficiently search out the optimal OD-matrix during estimating OD-matrices.