Urban Road Short-term Traffic Flow Forecasting Based on the Delay and Nonlinear Grey Model

Concerning the delay and nonlinear properties of traffic flow in urban road systems, this paper forecasts the short-term traffic flow based on the grey GM(1,1|τ,r). Firstly, the delay factor τ is determined by the speed-flow relationship when volume is greater than it capacity. Then, the nonlinear parameter r is determined by a particle swarm optimization algorithm, where the prediction effect is unsurpassed. Finally, verification of this model is done by collecting traffic flow data on one section of Youyi Avenue and comparing the prediction value of GM(1,1|τ,r) with GM(1,1) and SVM. The results show that the prediction effect of GM(1,1|τ,r) model for short-term traffic flow is significantly improved, which plays an important role in intelligent traffic systems.

摘要充分考虑城市道路交通系统中交通流存在的延迟性和非线性, 本文基于灰色GM(1,1|τ,r)模型对城市道路短时交通流进行建模预测. 首先, 通过建立城市交通路段上交通流量大于通行能力时的速度–流量关系, 得到交通系统延迟时间 τ 的计算模型. 再针对交通流存在的非线性特征, 以模型的预测效果最优为目标, 建立关于非线性因子的优化模型并利用粒子群算法寻找最佳的非线性参数 r 最后对武汉市友谊大道某一路段进行交通实验, 将灰色GM(1,1|τ,r)模型的预测结果与灰色 GM(1,1) 模型和支持向量机进行比较.结果表明, GM(1,1|τ,r) 模型的预测精度有明显的提高, 能为智能交通系统的管理和控制提供及时可靠的信息资源.