基于循环神经网络的空载电动出租车的充电桩推荐方法

doi:10.11959/j.issn.2096-109x.2020085

摘要/Abstract

摘要：

提出了一种基于循环神经网络的空载电动出租车的充电桩推荐方法（CPRM-IET，charging pile recommendation method for idle electric taxis），来为空载状态下的电动出租车推荐最佳充电桩。空载状态下的电动出租车移动一般依赖于驾驶人的潜意识移动倾向和驾驶习惯，因此需要根据其历史移动轨迹来预测其未来移动，从而找到充电额外移动最小的若干充电桩。在CPRM-IET中，使用了一种基于双阶段注意力机制的循环神经网络（DA-RNN，dual-stage attention-based recurrent neural network）模型来预测电动出租车的未来轨迹，DA-RNN模型包括输入注意力机制和时间注意力机制。输入注意力机制在每个时刻为输入的行驶记录分配权重，而时间注意机制为编码器的隐藏状态分配权重。根据预测轨迹，再选择额外移动最小的若干充电桩，并推荐给电动出租车驾驶人。仿真结果表明，CPRM-IET可以在额外移动和均方根误差方面取得较好的结果，反映了CPRM-IET可以准确地预测空载电动出租车的未来轨迹，并向这些电动出租车推荐合适的充电桩。

Abstract:

A charging pile recommendation method for idle electric taxis (CPRM-IET) based on recursive neural network was proposed to recommend the optimal charging piles for idle electric taxis.Usually,the movement of each idle electric taxi depends on the subconscious movement tendency and driving habits of the driver.Therefore,it is necessary to predict the future movement based on its historical movement trajectories,so as to find the charging piles with the least extra movements.In CPRM-IET,a dual-stage attention-based recurrent neural network (DA-RNN) model was provided to predict the future trajectories of electric taxis.DA-RNN model includes two types of attention mechanisms which are input attention mechanism and temporal attention mechanism.The input attention mechanism assigns different weights to the input driving sequence at each time slot,and the temporal attention mechanism assigns weights to the hidden state of the encoder.Based on the predicted future trajectories,several charging piles with the least extra movements were selected and recommended for the idle electric taxis.The simulation results show that CPRM-IET can achieve preferable results in terms of charging extra movement and root mean square error,which reflects that CPRM-IET can accurately predict the future trajectories of idle electric taxis and recommend optimal charging piles for these electric taxis.

Key words: charging pile recommendation, recurrent neural network, input attention mechanism, time attention mechanism, trajectory prediction

中图分类号:

TP393

贾鉴,刘林峰,吴家皋. 基于循环神经网络的空载电动出租车的充电桩推荐方法[J]. 网络与信息安全学报, 2020, 6(6): 152-163.

Jian JIA,Linfeng LIU,Jiagao WU. Charging pile recommendation method for idle electric taxis based on recurrent neural network[J]. Chinese Journal of Network and Information Security, 2020, 6(6): 152-163.

图/表 20

图1

表1

参数说明　Table 1 Parameter description"

参数	描述
$x_{t}$	行驶记录向量（时刻t）
${\tilde{x}}_{t}$	加权的行驶记录向量（时刻t）
$C_{t}$	在t时刻的上下文向量
$h_{t}$	编码器的隐藏状态
$[y_{t - 1}; C_{t - 1}]$	目标轨迹记录上一时刻的位置y_t-1和上下文向量 $C_{t - 1}$ 的串联
$[{\hat{y}}_{t - 1}; C_{t - 1}]$	预测轨迹记录上一时刻的预测位置 ${\hat{y}}_{t - 1}$ 和上下文向量 $C_{t - 1}$ 的串联
$V_{y}, b_{y}$	函数F的权重和偏差
$[d_{t}; C_{t}]$	解码器隐藏状态 $d_{t}$ 和上下文向量 $C_{t}$ 的串联

表1

图2

图3

图4

图5

图6

图7

图8

表2

图9

图10

图11

图12

图13

图14

图15

图16

图17

图18

参考文献 31

[1]	LU J , CHEN Z H , MA Z F ,et al. The role of nanotechnology in the development of battery materials for electric vehicles[J]. Nature Nanotechnology, 2016,12: 1031-1038.
[2]	ALTANO D , WU G , BARTH M J . GlidePath:eco-friendly automated approach and departure at signalized intersections[J]. IEEE Transactions on Intelligent Vehicles, 2017,2(4): 266-277.
[3]	WALLACE B , GOUBRAN R , KNOEFEL F ,et al. Measuring variation in driving habits between drivers[C]// IEEE International Symposium on Medical Measurements and Applications (MeMeA). 2014.
[4]	QIN Y , SONGD J , CHENG H F ,et al. A dual-stage attention-based recurrent neural network for time series prediction[J]. arXiv:1704.02971, 2017
[5]	GRECHE L , JAZOULI M , ES-SBAI N ,et al. Comparison between Euclidean and Manhattan distance measure for facial expressions classification[C]// International Conference on Wireless Technologies. 2017.
[6]	LIU W , SHOJI Y . DeepVM:RNN-based vehicle mobility prediction to support intelligent vehicle applications[C]// IEEE Transactions on Industrial Informatics. 2019.
[7]	MADAN R , MANGIPUDI P S . Predicting computer network traffic:a time series forecasting approach using DWT,ARIMA,and RNN[C]// InternationalConference Contemporary Computing(IC3). 2018.
[8]	XIAO S , YAN J , FARAJTABAR M ,et al. Learning time series associated event sequences with recurrent point process networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019,30(10):3124 - 3136.
[9]	LIU W , SHOJI Y . Applying deep recurrent neural network to predict vehicle mobility[C]// IEEE Vehicular Networking Conference (VNC). 2018.
[10]	WU J , WOOH , TAMURA Y ,et al. Pedestrian trajectory prediction using BiRNN encoder–decoder framework[J]. Advanced Robotics, 2019,33(18): 956-969.
[11]	KORDMAHALLEH M M , SEFIDMAZGI M G , HOMAIFAR A ,et al. Hurricane trajectory prediction via a sparse recurrent neural network[C]// International Workshop on Climate Informatics. 2015.
[12]	ZHAO Z , CHEN W H , WU X M ,et al. LSTM network:a deep learning approach for short-term traffic forecast[J]. Iet Intelligent Transport Systems, 2017,11(2): 68-75.
[13]	XIN L , WANG P , CHAN C Y ,et al. Intention-aware long horizon trajectory prediction of surrounding vehicles using dual LSTM networks[C]// 2018 IEEE International Conference on Intelligent Transportation Systems (ITSC). 2018.
[14]	ALTCHé F , FORTELLEA D L , . An LSTM network for highway trajectory prediction[C]// International Conference on Intelligent Transportation Systems (ITSC). 2017.
[15]	PARK S H , KIM B D . Sequence-to-sequence prediction of vehicle trajectory via LSTM encoder-decoderarchitecture[C]// IEEE Intelligent Vehicles Symposium(IV). 2018.
[16]	ZHANG P , OUYANG W . SR-LSTM:state refinement for LSTM towards pedestrian trajectory prediction[C]// IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016: 12085-12094.
[17]	KIM B D , KANGC M . Probabilistic vehicle trajectory prediction over occupancy grid map via recurrent neural network[C]// IEEE International Conference on Intelligent Transportation Systems (ITSC). 2017.
[18]	JI Z , XIONG K , PANG Y ,et al. Video summarization with attention-based encoder-decoder networks[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2019
[19]	TJANDRA A , SAKTI S . Attention-based Wav2Text with feature transfer learning[C]// IEEE Automatic Speech Recognition and Understanding Workshop(ASRU). 2017.
[20]	YAN C,TUY ， TUY . STAT:spatial-temporal attention mechanism for video captioning[J]. IEEE Transactions on Multimedia, 2019,22(2): 229-241.
[21]	CHIOU J , YANG Y . Multivariate functional linear regression and prediction[J]. Journal of Multivariate Analysis, 2016,146: 301-312.
[22]	KANKANAMGE K D , WITHARANAGEY R . Taxi trip travel time prediction with isolated XGBoost regression[C]// Moratuwa Engineering Research Conference (MERCon). 2019.
[23]	QIAN C , JIANGR . Vehicle trajectory modelling with consideration of distant neighbouring dependencies for destination prediction[J]. International Journal of Geographical Information Science, 2019,33(10): 2011-2032.
[24]	XIE G , GAO H . Vehicle trajectory prediction by integrating physics and maneuver-based approaches using interactive multiple models[J]. IEEE Transactions on Industrial Electronics, 2017,65(7): 5999-6008.
[25]	TIAN Z , JUNGT . Real-Time charging station recommendation system for electric-vehicle taxis[J]. IEEE Transactions on Intelligent Transportation Systems, 2016,17(11): 3098-3109.
[26]	JUNG J , CHOW J Y , JAYAKRISHNAN R ,et al. Stochastic dynamic itinerary interception refueling location problem with queue delay for electric taxi charging stations[J]. Transportation Research Part C:Emerging Technologies, 2014,40: 123-142.
[27]	ZHANG F , WILKIE D . Sensing the pulse of urban refueling behavior[C]// ACM International Joint Conference on Pervasive and Ubiquitous Computing. 2013: 13-22.
[28]	YANG Z Y , SUN L H , CHEN J M . Profit maximization for plug-in electric taxi with uncertain future electricity prices[J]. IEEE Transactions on Power Systems, 2014,29(6): 3058-3068.
[29]	YOU P , YANG Z . Efficient optimal scheduling of charging station with multiple electric vehicles via V2V[C]// IEEE International Conference on Smart Grid Communications. 2014: 716-721.
[30]	GAOW , KIMS W , BOSSE H ,et al. Measurement technologies for precision positioning[J]. CIRP Annals, 2015,64(2): 773-796.
[31]	YU Z , XING X , MAW Y . Geolife:a collaborative social networking service among user,location and trajectory[J]. IEEE Data Engineering Bulletin, 2010,33(2): 32-40.

参数	描述	值
T	n条行驶记录时长	20 min
n	行驶记录的条数	8
m	编码器隐藏状态的大小	128
p	解码器隐藏状态的大小	128
δ	电量阈值	25%
r	推荐的充电桩数量	2
s	充电桩数量	25