Effective Prediction of V2I Link Lifetime and Vehicle's Next Cell for Software Defined Vehicular Networks: A Machine Learning Approach

Predicting, in the one hand, the time duration that a vehicle remains associated to a cell i.e. Network Attachment Point (NAP) and, on the other hand, the next cell can help anticipating network control decisions to provide services with stringent requirements despite vehicle mobility. In this paper, we propose a machine learning based approach for Software Defined Vehicular Networks that allows a cell to estimate the attachment duration of each newly associated vehicle at the association request time, as well as, a prediction of the upcoming cell, performed at the SDN controller that controls the cells. Our proposed models have been evaluated on a large dataset, which we have generated based on a real mobility trace from the city of Luxembourg, and the evaluation shows promising results in terms of prediction accuracy.

[1]  Thomas Engel,et al.  Poster: LuST-LTE: A simulation package for pervasive vehicular connectivity , 2016, 2016 IEEE Vehicular Networking Conference (VNC).

[2]  Hao Wu,et al.  Link Duration for Infrastructure Aided Hybrid Vehicular Ad Hoc Networks in Highway Scenarios , 2014, 2014 IEEE Military Communications Conference.

[3]  András Varga,et al.  An overview of the OMNeT++ simulation environment , 2008, SimuTools.

[4]  Anchare V. Babu,et al.  Analysis of Link Life Time in Vehicular Ad Hoc Networks for Free-Flow Traffic State , 2014, Wirel. Pers. Commun..

[5]  Philippe Owezarski,et al.  An SDN hybrid architecture for vehicular networks: Application to Intelligent Transport System , 2017, ArXiv.

[6]  Mohsen Guizani,et al.  Improving flow delivery with link available time prediction in software-defined high-speed vehicular networks , 2018, Comput. Networks.

[7]  Reinhard German,et al.  Bidirectionally Coupled Network and Road Traffic Simulation for Improved IVC Analysis , 2011, IEEE Transactions on Mobile Computing.

[8]  Philippe Owezarski,et al.  OpenFlow based Topology Discovery Service in Software Defined Vehicular Networks: limitations and future approaches , 2018, 2018 IEEE Vehicular Networking Conference (VNC).

[9]  Sheng-Shih Wang,et al.  PassCAR: A passive clustering aided routing protocol for vehicular ad hoc networks , 2013, Comput. Commun..

[10]  Qing Yang,et al.  Practical Link Duration Prediction Model in Vehicular Ad Hoc Networks , 2015, Int. J. Distributed Sens. Networks.

[11]  Xiaohu Ge,et al.  5G Software Defined Vehicular Networks , 2017, IEEE Communications Magazine.

[12]  Xuemin Shen,et al.  Link duration estimation using neural networks based mobility prediction in vehicular networks , 2016, 2016 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE).

[13]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[14]  Lior Rokach,et al.  Ensemble learning: A survey , 2018, WIREs Data Mining Knowl. Discov..

[15]  Xu Chen,et al.  Predicting a user's next cell with supervised learning based on channel states , 2013, 2013 IEEE 14th Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[16]  Thomas Engel,et al.  Luxembourg SUMO Traffic (LuST) Scenario: 24 hours of mobility for vehicular networking research , 2015, 2015 IEEE Vehicular Networking Conference (VNC).

[17]  Antonio Iera,et al.  5G Network Slicing for Vehicle-to-Everything Services , 2017, IEEE Wireless Communications.

[18]  Daniel Krajzewicz,et al.  Recent Development and Applications of SUMO - Simulation of Urban MObility , 2012 .

[19]  Sylvain Arlot,et al.  A survey of cross-validation procedures for model selection , 2009, 0907.4728.

[20]  Richard Demo Souza,et al.  A Survey of Machine Learning Techniques Applied to Self-Organizing Cellular Networks , 2017, IEEE Communications Surveys & Tutorials.

[21]  Sotiris B. Kotsiantis,et al.  Supervised Machine Learning: A Review of Classification Techniques , 2007, Informatica.

[22]  Qing Yang,et al.  ELDP: Extended Link Duration Prediction Model for Vehicular Networks , 2016, Int. J. Distributed Sens. Networks.

[23]  Mehammed Daoui,et al.  Mobility prediction based on an ant system , 2008, Comput. Commun..

[24]  Giovanni Stea,et al.  Simulating LTE/LTE-Advanced Networks with SimuLTE , 2014, SIMULTECH.

[25]  Wei Zheng,et al.  A History-Based Handover Prediction for LTE Systems , 2009, 2009 International Symposium on Computer Network and Multimedia Technology.

[26]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[27]  Xuemin Shen,et al.  Integrity-oriented content transmission in highway vehicular ad hoc networks , 2013, 2013 Proceedings IEEE INFOCOM.

[28]  Jun Zhang,et al.  Link Duration Prediction in VANETs via AdaBoost , 2017, GLOBECOM 2017 - 2017 IEEE Global Communications Conference.