Efficient AI and Prediction Techniques for Smart 5G-enabled Vehicular Networks

FieldValue
dc.contributor.authorAljeri, Noura
dc.date.accessioned2020-11-24T16:26:15Z
dc.date.available2020-11-24T16:26:15Z
dc.date.issued2020-11-24
dc.identifier.urihttp://hdl.handle.net/10393/41497
dc.identifier.urihttp://dx.doi.org/10.20381/ruor-25721
dc.description.abstractWith the recent growth and wide availability of heterogeneous wireless access technologies, inter-vehicle communication systems are expected to culminate in integrating various wireless standards for the next generation of connected and autonomous vehicles. The role of 5G-enabled vehicular networks has become increasingly important, as current Internet clients and providers have urged robustness and effectiveness in digital services over wireless networks to cope with the latest advances in wireless mobile communication. However, to enable 5G wireless technologies' dense diversity, seamless and reliable wireless communication protocols need to be thoroughly investigated in vehicular networks. 5G-enabled vehicular networks applications and services such as routing, mobility management, and service discovery protocols can integrate mobility-based prediction techniques to elevate those applications' performance with various vehicles, applications, and network measurements. In this thesis, we propose a novel suite of 5G-enabled smart mobility prediction and management schemes and design a roadmap guide to mobility-based predictions for intelligent vehicular network applications and protocols. We present a thorough review and classification of vehicular network architectures and components, in addition to mobility management schemes, benchmarks advantages, and drawbacks. Moreover, multiple mobility-based schemes are proposed, in which vehicles' mobility is managed through the utilization of machine learning prediction and probability analysis techniques. We propose a novel predictive mobility management protocol that incorporates a new networks' infrastructure discovery and selection scheme. Next, we design an efficient handover trigger scheme based on time-series prediction and a novel online neural network-based next roadside unit prediction protocol for smart vehicular networks. Then, we propose an original adaptive predictive location management technique that utilizes vehicle movement projections to estimate the link lifetime between vehicles and infrastructure units, followed by an efficient movement-based collision detection scheme and infrastructure units localization strategy. Last but not least, the proposed techniques have been extensively evaluated and compared to several benchmark schemes with various networks' parameters and environments. Results showed the high potentials of empowering vehicular networks' mobility-based protocols with the vehicles' future projections and the prediction of the network's status.
dc.language.isoen
dc.publisherUniversité d'Ottawa / University of Ottawa
dc.subjectPrediction models
dc.subjectVehicular Networks
dc.subject5G
dc.subjectMobility Management
dc.subjectMobility Prediction
dc.subjectMachine Learning
dc.subjectArtificial intelligence
dc.titleEfficient AI and Prediction Techniques for Smart 5G-enabled Vehicular Networks
dc.typeThesis
dc.contributor.supervisorBoukerche, Azzedine
thesis.degree.namePhD
thesis.degree.levelDoctoral
thesis.degree.disciplineGénie / Engineering
uottawa.departmentScience informatique et génie électrique / Electrical Engineering and Computer Science
CollectionThèses, 2011 - // Theses, 2011 -

Files