基于GA-BP神经网络的交叉口短时交通流预测

PDF(1724 KB)

交通运输研究 ›› 2019, Vol. 5 ›› Issue (2) : 45-51.

专题

基于GA-BP神经网络的交叉口短时交通流预测

朱云霞,郭唐仪

作者信息 +

Intersection Short-Term Traffic Flow Forecast Based on GA-BP Neural Network

ZHU Yun-xia and GUO Tang-yi

Author information +

文章历史 +

摘要

交叉口车辆运行效率不高主要由两个原因造成：一是目前很多交叉口交通信号的配时与实际交通流不匹配；二是当前短时交通流预测的时长集中在5~15min，过长的时间间隔无法给信号控制提供准确的数据支撑。为了改善这种状况，提出了一种基于优化的BP（Back Propagation）神经网络的交叉口短时交通流预测方法。首先针对流量预测提出了准实时的概念，其次引入BP神经网络，再利用遗传算法对BP神经网络进行优化，最后在优化的BP神经网络的基础上建立交叉口短时交通流预测模型，且将传统的预测时长从5min 缩短到5s。利用南京市某一道路交叉口采集的数据对提出的预测方法进行验证，结果表明：与传统的BP神经网络以5min为预测时长相比，该预测方法以5s 为预测时长能够将预测精度提高77%。

Abstract

The inefficiency of vehicle operation at intersections was caused by the following two reasons. One was that the signal timing of the traffic signal of many intersections didn′t match the actual traffic flow. The other was that the short-term traffic flow prediction time was focused on 5 to 15 minutes which was too long to provide effective data support for signal control. To improve this situation, a short-term traffic flow prediction method based on optimized BP (Back Propagation) neural network was proposed for intersections. Firstly, the quasi- time real concept was defined for traffic prediction. Secondly, the BP neural network model was introduced. Then the BP neural network was optimized by genetic algorithm. Finally, the intersection short-term traffic flow prediction model was established based on the optimized BP neural network. Also, the forecast duration was shortened from 5 minutes to 5 seconds. Using the data collected at a certain intersection in Nanjing, the prediction method was verified and compared with traditional BP Neural Network prediction method with 5 minutes duration. The result shows that the prediction method used in the research can increase the prediction accuracy by 77%.

导出引用

朱云霞,郭唐仪. 基于GA-BP神经网络的交叉口短时交通流预测[J]. 交通运输研究. 2019, 5(2): 45-51

ZHU Yun-xia and GUO Tang-yi. Intersection Short-Term Traffic Flow Forecast Based on GA-BP Neural Network[J]. Transport Research. 2019, 5(2): 45-51

参考文献

[1] CHIOU S W. An Efficient Algorithm for Computing Traffic Equilibria Using TRANSYT Model[J]. Applied Mathematical Modelling, 2010, 34(11): 3390-3399.
[2] FERNANDEZ R, VALENZUELA E, CASANELLO F, et al. Evolution of the TRANSYT Model in a Developing Country[J]. Transportation Research Part A: Policy and Practice, 2006, 40(5): 386-398.
[3] BRETHERTON D, BODGER M, BABER N. SCOOT The Future Urban Traffic Control[C]// IEE International Conference on Road Transport Information and Control. London: IET, 2004: 301-306.
[4] ROBERTSON D I, BRETHERTON R D. Optimizing Net- works of Traffic Signals in Real Time-the SCOOT Method[J]. IEEE Transactions on Vehicular Technology, 1991, 40(1): 11-15.
[5] MIRCHANDANI P, HEAD L. A Real-Time Traffic Signal Control System: Architecture Algorithms and Analysis[J]. Transportation Research Part C: Emerging Technologies, 2001, 9(6): 415-432.
[6] DOCHY T, DANECHPAJOUH M, LECHEVALLIER Y. Short-Term Road Traffic Forecasting Using Neuronal Network[J]. IFAC Proceedings Volumes, 1994, 27(12): 633-638.
[7] 金玉婷，余立建. 基于小波神经网络的短时交通流预测[J]. 交通科技与经济，2014，16（1）：82-86.
[8] 高慧，赵建玉，贾磊. 短时交通流预测方法综述[J]. 济南大学学报（自然科学版）， 2008， 22（1）： 88-94.
[9] 程山英. 基于K近邻非参数回归的短时交通流预测模型研究[J]. 数字技术与应用，2017（4）：130-132.
[10] ANTONIOU C, KOUTSOPOULOS H N, YANNIS G. An Efficient Non- Linear Kalman Filtering Algorithm Using Simultaneous Perturbation and Applications in Traffic Estimation and Prediction[C]// Intelligent Transportation Systems Conference. Seattle, USA: IEEE, 2007: 217-222.
[11] MIR Z H, FILALI F. An Adaptive Kalman Filter Based Traffic Prediction Algorithm for Urban Road Network[C]// International Conference on Innovations in Information Technology. Al- Ain, United Arab Emirates: IEEE, 2017: 1-6.
[12] SUVITHA D, MUTHUSWAMY V, SATHYABAMA P. Prediction on Road Traffic Data Using Regression Analysis in FIMT-DD Technique[C]// International Conference on Recent Trends & Challenges in Computational Models. Tindivanam, India: IEEE, 2017: 176-181.
[13] KHOTANZAD A, SADEK N. Multi- Scale High- Speed Network Traffic Prediction Using Combination of Neural Networks[C]// International Joint Conference on Neural Networks. Portland, USA: IEEE, 2003: 1071-1075.
[14] YI H, JUNG H J, BAE S. Deep Neural Networks for Traffic Flow Prediction[C]// IEEE International Conference on Big Data and Smart Computing. Jeju, South Korea: IEEE, 2017: 328-331.
[15] HE G, MA S. A Study on The Short-Term Prediction of Traffic Volume Based on Wavelet Analysis[C]// Proceedings of International Conference on Intelligent Transportation Systems. Singapore: IEEE, 2002: 731-735.
[16] RIGLER A K, IRVINE J M, VOGL T P. Rescaling of Variables in Back Propagation Learning[J]. Neural Networks, 1990, 3(5): 561-573.
[17] LEUNG M T, ENGELER W E, FRANK P. Fingerprint Processing Using Back Propagation Neural Networks[C]// IJCNN International Joint Conference on Neural Networks. San Diego, USA: IEEE, 1990: 15-20.
[18] 慕飞飞，张惠珍. 基于遗传算法的单点交叉口信号配时优化[J]. 上海理工大学学报， 2015，37（6）：600-604.