基于混沌搜索的人工蜂群优化神经网络交通流预测方法

Li Xue, Li Yang, Zheng Xuan

摘要:

为了提高长时交通流的预测精度,提出一种改进的人工蜂群优化BP神经网络分时段预测交通流的方法。利用Tent混沌映射采蜜蜂放弃的新解,实现具有混沌搜索策略的人工蜂群算法,然后优化BP神经网络的权值和阈值,最终训练BP神经网络以求得最优值。利用该预测方法对合肥市黄天路全天的交通流分时段预测,实现了对长时交通流的准确预测,与传统的人工蜂群优化BP神经网络预测对比,能有效改善预测精度,降低预测误差。

Abstract:

In order to improve the prediction accuracy of long-term traffic flow. A method for predicting long-term traffic flow in different time periods based on BP neural network is proposed, which is optimized by Artificial Bee Colony Algorithm. The new solution is improved by Tent chaotic, to realize the chaotic search strategy. Then artificial bee colony algorithm is used to optimize the weights and thresholds of the BP neural network, to obtain the optimal value by BP neural network. This forecasting method was applied to Huangtian Road in Hefei the accurate prediction of long-term traffic flow is realized. Compared with the traditional artificial bee colony optimization BP neural network prediction, it can effectively improve the prediction accuracy and reduce the prediction error.