Machine learning based optimization for vehicle-to-infrastructure communications

In this paper, we study wireless communications in vehicle-to-infrastructure communications. In certain situations, multiple vehicles within a local range need to exchange information via common roadside infrastructure. Example scenarios include busy intersections, and a driver with the knowledge of information from other vehicles can make safer decisions. Fast and reliable communications are essential in such use cases. We consider two different system models in this paper. In the first model, we consider the case where both the base station and vehicles are equipped with a single antenna. In the second model, we discuss the case where multiple antennas are installed on both the base station and vehicles. We show how the system can be optimized in both cases. We then discuss how machine learning can be adopted in both models to realize the optimized system performance. (C) 2018 Elsevier B.V. All rights reserved.

[1]  Soung Chang Liew,et al.  Channel coding and decoding in a relay system operated with physical-layer network coding , 2008, IEEE Journal on Selected Areas in Communications.

[2]  Min Chen,et al.  Cognitive Internet of Vehicles , 2018, Comput. Commun..

[3]  Neha Sharma,et al.  An Analysis Of Convolutional Neural Networks For Image Classification , 2018 .

[4]  Tao Huang,et al.  On Lattice-Partition-Based Physical-Layer Network Coding over GF(4) , 2013, IEEE Communications Letters.

[5]  Christian Wietfeld,et al.  Client-Based Control of the Interdependence Between LTE MTC and Human Data Traffic in Vehicular Environments , 2015, IEEE Transactions on Vehicular Technology.

[6]  Tao Chen,et al.  Resource Allocation and Interference Management for Opportunistic Relaying in Integrated mmWave/sub-6 GHz 5G Networks , 2017, IEEE Communications Magazine.

[7]  N. J. A. Sloane,et al.  Sphere Packings, Lattices and Groups , 1987, Grundlehren der mathematischen Wissenschaften.

[8]  Tao Yang,et al.  Distance Spectrum and Performance of Channel-Coded Physical-Layer Network Coding for Binary-Input Gaussian Two-Way Relay Channels , 2012 .

[9]  Victor C. M. Leung,et al.  From cloud-based communications to cognition-based communications: A computing perspective , 2018, Comput. Commun..

[10]  Michael Gastpar,et al.  Compute-and-Forward: Harnessing Interference Through Structured Codes , 2009, IEEE Transactions on Information Theory.

[11]  Shangguang Wang,et al.  An overview of Internet of Vehicles , 2014 .

[12]  Nicola Bui,et al.  A Survey of Anticipatory Mobile Networking: Context-Based Classification, Prediction Methodologies, and Optimization Techniques , 2016, IEEE Communications Surveys & Tutorials.

[13]  Kenneth W. Shum,et al.  Lattice Network Codes Based on Eisenstein Integers , 2013, IEEE Trans. Commun..

[14]  Victor C. M. Leung,et al.  SOVCAN: Safety-Oriented Vehicular Controller Area Network , 2017, IEEE Communications Magazine.

[15]  Frank R. Kschischang,et al.  An Algebraic Approach to Physical-Layer Network Coding , 2010, IEEE Transactions on Information Theory.

[16]  Tao Yang,et al.  Design of Irregular Repeat-Accumulate Coded Physical-Layer Network Coding for Gaussian Two-Way Relay Channels , 2013, IEEE Transactions on Communications.