改进蛙跳算法的小波神经网络短时交通流预测

Short-term Traffic Flow Prediction of Wavelet Neural Network Based on the Improved Shuffled Flog Leaping Algorithm

为改进小波神经网络模型对短时交通流的预测效果,提出一种基于改进混合蛙跳算法的短时交通流预测模型用以优化小波神经网络。该算法使用交叉分组法对子群进行划分,再利用具有自适应因子的局部搜索策略平衡混合蛙跳算法局部与全局搜索能力,最后把得到的最优解用于优化小波神经网络模型初始值,并对短时交通流进行预测。实验结果表明,该方法对短时交通流预测精确度达到97.43%,比传统方法提高1.016 1%,均方根误差比传统方法降低了5.587 9%,具有较高的应用价值。

In order to improve the prediction effect of wavelet neural network model on short-time traffic flow,a short time traffic flow prediction model based on improved shuffled frog leaping algorithm is proposed to optimize wavelet neural network.The algorithm uses cross grouping method to divide the subgroups,and then uses the local search strategy with adaptive factors to balance the local and global search ability of the hybrid frog jump algorithm.Finally the optimal solution is used to optimize the initial value of the wavelet neural network model and predict the short-time traffic flow.The experimental results show that the accuracy of this method for short-term traffic flow prediction is 97.43%,which is 1.0161%higher than the traditional method,and the root mean square error is 5.5879%lower than the traditional method,which has high application value.