基于SAE-ConvLSTM深度学习模型的多站城轨短时客流预测  

Prediction of short-time passenger flow on multi-station urban rail based on SAE-ConvLSTM deep learning model

作　　者：李莎 王秋雯 陈彦如[1] 秦娟[1] Li Sha;Wang Qiuwen;Chen Yanru;Qin Juan(College of Economics&Management,Southwest Jiaotong University,Chengdu 610031,China;College of Economics&Management,West Yunnan University,Lincang Yunnan 677000,China)

机构地区：[1]西南交通大学经济管理学院,成都610031 [2]滇西科技师范学院管理与经济学院,云南临沧677000

出　　处：《计算机应用研究》2022年第7期2025-2031,共7页Application Research of Computers

基　　金：国家重点研发计划资助项目(2018YFC0705000);西南交通大学经济管理学院资助项目(JGSF06)。

摘　　要：为准确预测多个站点城轨交通短时客流,提出卷积长短时记忆网络(ConvLSTM)与栈式自编码器(SAE)相结合的深度学习模型SAE-ConvLSTM。考虑了13个影响客流量的外部因素,并通过SAE对其进行逐层提取,获得更具代表性的外部特征。通过ConvLSTM充分提取客流量的时间与空间特征,并融合所获得的外部特征对轨道交通网络中多个站点的短时客流量进行同步预测。同时设计了隐动作蒙特卡罗树搜索方法(LA-MCT),对SAE进行参数寻优。为了验证寻优效果,与遗传算法、粒子群算法、模拟退火算法以及禁忌搜索算法进行对比。结果表明,LA-MCTS在寻优时间和寻优效果方面均具有优势。此外,以深圳地铁为例进行大量的数值实验,结果显示在预测均方根误差、绝对误差均值、平均绝对百分比误差以及拟合优度方面,所构建的SAE-ConvLSTM模型预测结果均优于浅层机器学习模型—反向传播神经网络、支持向量回归模型、整合移动平均自回归模型,及深度学习模型—长短时记忆网络、卷积神经网络、以及不加入外部特征的ConvLSTM、加外部特征无SAE的ConvLSTM、长短时记忆网络+卷积神经网络(CNN+LSTM)和加外部特征的CNN+LSTM。In order to accurately predict the short-term passenger flow of urban rail transit for multiple stations,this paper proposed a deep learning model,SAE-ConvLSTM,combining convolutional long short-term memory(ConvLSTM)and stack autoencoder(SAE).This paper considered thirteen external factors related to passenger flow,whose features would be extracted by SAE with successive layers and thus obtain more representative features.It proposed ConvLSTM to extract spatiotemporal features of passenger flow,which was combined with the resulting external factors to predict short-term passenger flow of multiple stations simultaneously.And it developed latent action Monte Carlo tree search(LA-MCTS)to optimize the parameters of SAE.Compared with genetic algorithm(GA),particle swarm optimization(PSO),simulated annealing algorithm(SA)and tabu search(TS),LA-MCTS performed best in terms of effect and efficiency.This paper conducted extensive experiments.The results show that SAE-ConvLSTM works better than shallow machine learning model—back propagation neural network(BPNN),support vector regression mode(SVR),autoregressive integrated moving average model(ARIMA),and deep learning model—long and short time memory network(LSTM),convolutional neural network(CNN)and ConvLSTM without external features,ConvLSTM external features without SAE,CNN+LSTM and CNN+LSTM with external features,in terms of root mean square errors(RMSE),mean absolute errors(MAE)and mean absolute percentage errors(MAPE),and the goodness of fit(R 2).

关 键 词：城轨交通短时客流 时空特征 多站点 外部特征 卷积长短时记忆网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] U121[自动化与计算机技术—控制科学与工程]