Investigation of Deep Learning and Blockchain Applicability for Software-Defined Internet of Things

Résumé

5G mobile network has seen phenomenal growth in providing IoT services and applications. IoT devices are often battery-powered to perform their operations autonomously and serve a variety of situations, such as smart cities, autonomous cars, smart manufacturing, etc., thereby needing efficient energy consumption to extend their lifespan. IoT networks should provide i) an on-demand resource allocation to support adaptive horizontal and vertical scaling of the network resources; ii) flexible infrastructure virtualization that exploits in-network programmability capabilities to operate inside an SDN-enabled virtualization platform; iii) a device-driven and human-driven intelligence to address the issues of energy efficiency and ultra-low latency requirements for future reliable and real-time IoT applications. Despite the promise, IoT networks face several challenging issues stemming from resource constraints and low-computation performance. Additionally, IoT systems encounter several security and privacy concerns to prevent unauthorized access to smart devices and secure trust-less interactions between devices themselves and service providers on the Internet. To address this plethora of challenges, this thesis presents an energy-efficiency IoT system, less computation-intensive, easy to implement, and amenable to online adaptation to the variations of the network condition. In the first contribution, we introduce a novel IoT network virtualization approach based on SDN/NFV to offer a high degree of automation in service chaining delivery for IoT devices. The second contribution introduces a Deep Reinforcement Learning energy-efficient task assignment and scheduling in SDN-based fog IoT Network. Furthermore, we present a computing model for reducing network latency and traffic overhead by centralizing the network control and orchestration in a single SDN controller layer. The last contribution introduces a deep learning approach that combines SDN and blockchain to achieve task scheduling and offloading, improve the response rate of IoT services to offer high levels of performance, and strive to perform dynamic resource management.

Citer ce document

Accès au document

Ce document est hébergé sur son dépôt institutionnel d'origine.

Auteur(s)

Statistiques

Consultations : 4

Téléchargements : 0