基于马尔柯夫过程的城市交叉口车辆到达模型

提出在城市交叉口多相位实时控制过程中,采用马尔柯夫方法对各相位内进入交叉口车辆数的可能性进行预估。基于交叉口车辆运行的强随机特征,交叉口车辆到达预测的准确性是控制策略准确制定的关键。根据马尔柯夫过程预测结果,系统可进行交通信号的延时和相位变化,从而使整个交叉口的平均时延得到优化。通过实例验证了马尔柯夫分析模型用于多相位交叉口短时交通流占有率预测的可用性,并将预测得到的交通流占有率与观测值进行了对比,同时对两者之间的误差进行了分析。结果表明,预测结果有助于制定实时的交通控制策略。

Modal of vehicles arrival in intersections based on Markov process

Markov analysis method was used to construct an intersection traffic situation prediction model to accurately estimate the forthcoming traffic conditions of the multi-phase intersection. Intersection traffic controlling is an important aspect in urban traffic controlling system, the controlling policy depends on the forecasting results of the vehicles arrived and distributed in signalized intersections. The time delay of the whole intersection was optimized based on the predicted results. A numerical example applying the Markov analysis model to forecast the short period traffic flow occupancy probability distribution at the multi-phase intersection was given. The predicted traffic flow occupancy probability distribution was compared with the observed results, and the errors between them were analyzed. The predicted results could help to decide the real-time controlling strategies.