摘要
针对目前城市轨道交通短时客流量预测模型在构建特征时容易忽略客流变化周期依赖性的不足,提出一种考虑多时间尺度特征的混合深度学习模型(GRU-Transformer),该模型由添加注意力机制的GRU(Gate Recurrent Unit)神经网络(Attention-GRU)和改进的Transformer(Conv-Transformer)两模块并行构成。首先,对周周期、日周期及相邻时段这3种时间尺度下的客流数据分别进行建模,并合并各周期数据作为模型输入。其次,搭建Attention-GRU和Conv-Transformer模块分别挖掘数据连续性与周期性特征,融合特征后输出预测值。最后,采集上海市地铁2号线两站点AFC(Automatic Fare Collection)客流数据,预测5 min时间粒度下的进出站客流量。为分析各模型参数对预测结果的影响,开展模型精细化调参实验,基于所得最优参数组合验证和评估模型。结果表明,相较于5个基线模型(BPNN(Back Propagation Neural Network)、CNN(Convolutional Neural Network)、GRU、CNN-GRU及Transformer)和4个GRU-Transformer消融模型,本文提出的GRU-Transformer模型预测精度最高,具有较好的实用性。
Current prediction models on short-time passenger flow of urban rail transits always ignore the period dependence of data in feature construction.To address this problem,a hybrid deep learning model(GRU-Transformer)considering multi-timescale temporal features is proposed.The model consists of two blocks in parallel,a GRU neural network with added attention mechanism(Attention-GRU)and an improved Transformer(Conv-Transformer).First,passenger flow data at three time scales,namely weekly periodic,daily periodic,and recent time segment,are modeled separately and combined as model inputs.Second,the Attention-GRU and Conv-Transformer blocks are built to mine the continuity and periodicity features respectively and the prediction values are output after feature fusion.Finally,the AFC passenger flow data of two stations of Shanghai Metro Line 2 were collected for the prediction of inbound and outbound passenger flow under the 5-minute time granularity.To analyze the influence of parameters,tuning experiments are carried out and the model is evaluated based on the optimal parameter combination.The results show that compared with five baseline models(BPNN,CNN,GRU,CNN-GRU,Transformer)and four GRU-Transformer ablation models,the GRU-Transformer model has the highest prediction accuracy and good practicability.
作者
张文娟
杨皓哲
张彬
李秀杰
ZHANGWen-juan;YANG Hao-zhe;ZHANG Bin;LI Xiu-jie(School of Mechanical Engineering,Tongji University,Shanghai 201804,China)
出处
《交通运输系统工程与信息》
EI
CSCD
北大核心
2022年第6期212-223,共12页
Journal of Transportation Systems Engineering and Information Technology
基金
上海市科技创新行动计划(21DZ1203700)。
