城市轨道交通规划线网的拥堵点预测与分流仿真

Congestion Point Prediction and Shunting Simulation of Urban Rail Transit Planning Network

依据拥堵时的交通流量序列,估测城市轨道交通规划线网拥堵客流量区域,通过小波分解及重构的Mallat算法与改进ARMA预测模型相结合,在拥堵客流量区域预测城市轨道交通规划线网客流拥堵点;针对预测出的拥堵点,利用Dijkstra算法求解城市轨道交通乘客出行的最短路径,通过考虑最短路径上的综合阻抗构建城市轨道交通客流分流模型,并采用改进Logit算法,实现城市轨道交通客流的分流.结果表明:该方法预测流量数据与真实数据结果相差较小;该方法客流分流后增加三条有效路径,可有效分担部分的客流量,缓解交通拥堵.

According to the traffic flow sequence during congestion,the congested passenger flow area of urban rail transit planning network was estimated.By combining Mallat algorithm of wavelet decomposition and reconstruction with improved ARMA prediction model,the congestion point of urban rail transit planning network was predicted in the congested passenger flow area.Aiming at the predicted congestion point,Dijkstra algorithm was used to solve the shortest path of urban rail transit passengers.By considering the comprehensive impedance on the shortest path,the passenger flow diversion model of urban rail transit was constructed,and the improved Logit algorithm was adopted to realize the passenger flow diversion of urban rail transit.The experimental results show that the difference between the predicted traffic data and the real data is small.This method adds three effective paths after passenger flow diversion,which can effectively share part of passenger flow and alleviate traffic congestion.