基于深度残差长短记忆网络交通流量预测算法  

Traffic flow prediction algorithm based on deep residual long short-term memory network

作　　者：刘世泽 秦艳君 王晨星 苏琳[3] 柯其学 罗海勇[4] 孙艺 王宝会[1] LIU Shize;QIN Yanjun;WANG Chenxing;SU Lin;KE Qixue;LUO Haiyong;SUN Yi;WANG Baohui(College of Software,Beihang University,Beijing 100191,China;School of Computer Science,Beijing University of Posts and Telecommunications,Beijing 100876,China;College of Information Engineering,Capital Normal University,Beijing 100048,China;Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China)

机构地区：[1]北京航空航天大学软件学院,北京100191 [2]北京邮电大学计算机学院,北京100876 [3]首都师范大学信息工程学院,北京100048 [4]中国科学院计算技术研究所,北京100190

出　　处：《计算机应用》2021年第6期1566-1572,共7页journal of Computer Applications

基　　金：国家自然基金资助项目(61872046);北京邮电大学提升科技创新能力行动计划项目(2019XD-A06)。

摘　　要：针对多步交通流量预测任务中时间空间特征提取效果不佳和预测未来时间交通流量精度低的问题,提出一种基于长短时记忆(LSTM)网络、卷积残差网络和注意力机制的融合模型。首先,利用一种基于编解码器的架构,通过在编解码器中加入LSTM网络来挖掘不同尺度的时间域特征;其次,构建基于注意力机制挤压激励(SE)模块的卷积残差网络嵌入到LSTM网络结构中,从而挖掘交通流量数据中的空间域特征;最后,将编码器中获得的隐状态下的信息输入到解码器中,实现高精度多步交通流量的预测。基于真实交通数据进行实验测试和分析,实验结果表明,相较于原始的基于图卷积的模型,所提模型在北京和纽约两个交通流量公开数据集上的均方根误差(RMSE)分别获得了1.622和0.08的下降。所提模型能够高效且精确地对交通流量作出预测。In the multi-step traffic flow prediction task,the spatial-temporal feature extraction effect is not good and the prediction accuracy of future traffic flow is low.In order to solve these problems,a fusion model combining Long-Short Term Memory(LSTM)network,convolutional residual network and attention mechanism was proposed.Firstly,an encoder-decoder-based architecture was used to mine the temporal domain features of different scales by adding LSTM network into the encoder-decoder.Secondly,a convolutional residual network based on the Squeeze-and-Excitation(SE)block of attention mechanism was constructed and embedded into the LSTM network structure to mine the spatial domain features of traffic flow data.Finally,the implicit state information obtained from the encoder was input into the decoder to realize the prediction of high-precision multi-step traffic flow.The real traffic data was used for the experimental testing and analysis.The results show that,compared with the original graph convolution-based model,the proposed model achieves the decrease of 1.622 and 0.08 on the Root Mean Square Error(RMSE)for Beijing and New York traffic flow public datasets,respectively.The proposed model can predict the traffic flow efficiently and accurately.

关 键 词：时空数据挖掘 编解码器 长短期记忆 挤压-激励模块 空间注意力 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]