基于互补型集成经验模态分解和遗传最小二乘支持向量机的交通流量预测模型

交通流是智能交通系统中的关键组成部分,也是交通规划的重要依据。为了提高道路交通流量预测的精确性,提出一种基于互补型集成经验模态分解(complete ensemble empirical mode decomposition,CEEMD)后,采用遗传算法(genetic algorithm,GA)优化参数的最小二乘支持向量机(least square support vector machine,LSSVM)的交通流量预测模型。该模型使用互补型集成经验模态分解原始数据,将分解后的本征模态函数(intrinsic mode function,IMF)分量分别用遗传算法优化参数后的最小二乘支持向量机进行预测,叠加全部IMF分量值作为模型最终的预测结果。通过对美国加利福利亚州某高速公路一个月的交通流量数据进行训练预测,结果表明,该模型平均相对误差仅为6.51%,相较于其他模型拥有更好的预测效果,可为交通流的预测提供一定的参考。

Traffic Flow Forecasting Model Based on CEEMD and GA-LSSVM

Traffic flow is a key component of intelligent transportation system and an important basis for traffic planning. In order to improve the accuracy of road traffic flow forecasting, a traffic flow forecasting model based on complementary integrated empirical mode decomposition (CEEMD)and least squares support vector machine (LSSVM) with optimized parameters by genetic algorithm was proposed. This model used CEEMD to decompose the original data, and used LSSVM to predict the decomposed Intrinsic Mode Function (IMF) components. The prediction parameters of LSSVM was optimized by genetic algorithm (GA), integrated all predicted IMFs for the ensemble result as the final prediction. By training and forecasting the traffic flow data of a California freeway in a month. The results show that the average relative error of the model is only 6.51%. Compared with other models, the model has better prediction effect, provides some reference for traffic flow forecasting in the future.