基于混沌小波网络的交通流预测算法研究

Study of traffic flow forecast algorithms based on chaotic wavelet networks

实时准确的交通流量预测是实现智能交通诱导及控制的前提与关键,也是智能化交通管理的客观需要.结合交通流预测的特点,提出了一种基于小波网络的路段交通流预测方法,把混沌优化算法引入小波网络的拓扑构造,结合提出的相似时段的预测思想,给出了一种基于混沌优化算法的小波网络交通流量预测模型.实验结果表明,引入相似时段的预测思想可以有效提高交通流的预测精度。

Real-time and accurate traffic flow forecast is very important to the intelligent traffic guidance, control and management. According to the characteristics of traffic flow, this paper proposes a new model of traffic flow forecast based on wavelet networks and the forecast algorithm of comparable time intervals. The structures of wavelet networks are optimized by a modified chaos optimization algorithm. The experiment results show that this model is superior to the common BP neural networks in the aspects of flow forecasting precision and network convergence.