A distributed framework is proposed for addressing resource sharing problems in communications, micro-economics, and various other network systems. The approach uses a hierarchical multi-layer decomposition for network utility maximization. This methodology uses central management and distributed computations to allocate resources, and in dynamic environments, it aims to efficiently respond to network changes. The main contributions include a comprehensive description of an exemplary unifying optimization framework to share resources across different operators and platforms, and a detailed analysis of the generalized methods under the assumption that the network changes are on the same time-scale as the convergence time of the algorithms employed for local computations.Assuming strong concavity and smoothness of the objective functions, and under some stability conditions for each layer, convergence rates and optimality bounds are presented. The effectiveness of the framework is demonstrated through numerical examples. Furthermore, a novel Federated Edge Network Utility Maximization (FEdg-NUM) architecture is proposed for solving large-scale distributed network utility maximization problems in a fully decentralized way. In FEdg-NUM, clients with private utilities communicate with a peer-to-peer network of edge servers. Convergence properties are examined both through analysis and numerical simulations, and potential applications are highlighted. Finally, problems in a complex stochastic dynamic environment, specifically motivated by resource sharing during disasters occurring in multiple areas, are studied. In a hierarchical management scenario, a method of applying a primal-dual algorithm in higher-layer along with deep reinforcement learning algorithms in localities is presented. Analytical details as well as case studies such as pandemic and wildfire response are provided.

The Internet-of-Things (IoT) paradigm is reshaping the ways to interact with the physical space. Many emerging IoT applications need to acquire, process, gain insights from, and act upon the massive amount of data continuously produced by ubiquitous IoT sensors. It is nevertheless technically challenging and economically prohibitive for each IoT application to deploy and maintain a dedicated large-scale sensor network over distributed wide geographic areas. Built upon the Sensing-as-a-Service paradigm, cloud-sensing service providers are emerging to provide heterogeneous sensing data to various IoT applications with a shared sensing substrate. Cyber threats are among the biggest obstacles against the faster development of cloud-sensing services. This dissertation presents novel solutions to achieve trustworthy IoT sensing-as-a-service. Chapter 1 introduces the cloud-sensing system architecture and the outline of this dissertation. Chapter 2 presents MagAuth, a secure and usable two-factor authentication scheme that explores commercial off-the-shelf wrist wearables with magnetic strap bands to enhance the security and usability of password-based authentication for touchscreen IoT devices. Chapter 3 presents SmartMagnet, a novel scheme that combines smartphones and cheap magnets to achieve proximity-based access control for IoT devices. Chapter 4 proposes SpecKriging, a new spatial-interpolation technique based on graphic neural networks for secure cooperative spectrum sensing which is an important application of cloud-sensing systems. Chapter 5 proposes a trustworthy multi-transmitter localization scheme based on SpecKriging. Chapter 6 discusses the future work.

Individuals and organizations have greater access to the world's population than ever before. The effects of Social Media Influence have already impacted the behaviour and actions of the world's population. This research employed mixed methods to investigate the mechanisms to further the understand of how Social Media Influence Campaigns (SMIC) impact the global community as well as develop tools and frameworks to conduct analysis. The research has qualitatively examined the perceptions of Social Media, specifically how leadership believe it will change and it's role within future conflict. This research has developed and tested semantic ontological modelling to provide insights into the nature of network related behaviour of SMICs. This research also developed exemplar data sets of SMICs. The insights gained from initial research were used to train Machine Learning classifiers to identify thematically related campaigns. This work has been conducted in close collaboration with Alliance Plus Network partner, University of New South Wales and the Australian Defence Force.

Software Defined Networking has been the primary component for Quality of Service provisioning in the last decade. The key idea in such networks is producing independence between the control and the data-plane. The control plane essentially provides decision making logic to the data-plane, which in-turn is only responsible for moving the packets from source to destination based on the flow-table entries and actions. In this thesis an in-depth design and analysis of Software Defined Networking control plane architecture for Next Generation Networks is provided. Typically, Next Generation Networks are those that need to satisfy Quality of Service restrictions (like time bounds, priority, hops, to name a few) before the packets are in transit. For instance, applications that are dependent on prediction popularly known as ML/AI applications have heavy resource requirements and require completion of tasks within the time bounds otherwise the scheduling is rendered useless. The bottleneck could be essentially on any layer of the network stack, however in this thesis the focus is on layer-2 and layer-3 scheduling. To that end, the design of an intelligent control plane is proposed by paying attention to the scheduling, routing and admission strategies which are necessary to facilitate the aforementioned applications requirement. Simulation evaluation and comparisons with state of the art approaches is provided withreasons corroborating the design choices. Finally, quantitative metrics are defined and measured to justify the benefits of the designs.

Ethernet based technologies are emerging as the ubiquitous de facto form of communication due to their interoperability, capacity, cost, and reliability. Traditional Ethernet is designed with the goal of delivering best effort services. However, several real time and control applications require more precise deterministic requirements and Ultra Low Latency (ULL), that Ethernet cannot be used for. Current Industrial Automation and Control Systems (IACS) applications use semi-proprietary technologies that provide deterministic communication behavior for sporadic and periodic traffic, but can lead to closed systems that do not interoperate effectively. The convergence between the informational and operational technologies in modern industrial control networks cannot be achieved using traditional Ethernet. Time Sensitive Networking (TSN) is a suite of IEEE standards designed by augmenting traditional Ethernet with real time deterministic properties ideal for Digital Signal Processing (DSP) applications. Similarly, Deterministic Networking (DetNet) is a Internet Engineering Task Force (IETF) standardization that enhances the network layer with the required deterministic properties needed for IACS applications. This dissertation provides an in-depth survey and literature review on both standards/research and 5G related material on ULL. Recognizing the limitations of several features of the standards, this dissertation provides an empirical evaluation of these approaches and presents novel enhancements to the shapers and schedulers involved in TSN. More specifically, this dissertation investigates Time Aware Shaper (TAS), Asynchronous Traffic Shaper (ATS), and Cyclic Queuing and Forwarding (CQF) schedulers. Moreover, the IEEE 802.1Qcc, centralized management and control, and the IEEE 802.1Qbv can be used to manage and control scheduled traffic streams with periodic properties along with best-effort traffic on the same network infrastructure. Both the centralized network/distributed user model (hybrid model) and the fully-distributed (decentralized) IEEE 802.1Qcc model are examined on a typical industrial control network with the goal of maximizing scheduled traffic streams. Finally, since industrial applications and cyber-physical systems require timely delivery, any channel or node faults can cause severe disruption to the operational continuity of the application. Therefore, the IEEE 802.1CB, Frame Replication and Elimination for Reliability (FRER), is examined and tested using machine learning models to predict faulty scenarios and issue remedies seamlessly.

Nowadays, demand from the Internet of Things (IoT), automotive networking, and video applications is driving the transformation of Ethernet. It is a shift towards time-sensitive Ethernet. As a large amount of data is transmitted, many errors occur in the network. For this increased traffic, a Time Sensitive Network (TSN) is important. Time-Sensitive Network (TSN) is a technology that provides a definitive service for time sensitive traffic in an Ethernet environment that provides time-synchronization. In order to efficiently manage these errors, countermeasures against errors are required. A system that maintains its function even in the event of an internal fault or failure is called a Fault-Tolerant system. For this, after configuring the network environment using the OMNET++ program, machine learning was used to estimate the optimal alternative routing path in case an error occurred in transmission. By setting an alternate path before an error occurs, I propose a method to minimize delay and minimize data loss when an error occurs. Various methods were compared. First, when no replication environment and secondly when ideal replication, thirdly random replication, and lastly replication using ML were tested. In these experiments, replication in an ideal environment showed the best results, which is because everything is optimal. However, except for such an ideal environment, replication prediction using the suggested ML showed the best results. These results suggest that the proposed method is effective, but there may be problems with efficiency and error control, so an additional overview is provided for further improvement.

Existing radio access networks (RANs) allow only for very limited sharing of thecommunication and computation resources among wireless operators and heterogeneous wireless technologies. The introduced LayBack architecture facilitates communication and computation resource sharing among different wireless operators and technologies. LayBack organizes the RAN communication and multiaccess edge computing (MEC) resources into layers, including a devices layer, a radio node (enhanced Node B and access point) layer, and a gateway layer. The layback optimization study addresses the problem of how a central SDN orchestrator can flexibly share the total backhaul capacity of the various wireless operators among their gateways and radio nodes (e.g., LTE enhanced Node Bs or Wi-Fi access points). In order to facilitate flexible network service virtualization and migration, network functions (NFs) are increasingly executed by software modules as so-called "softwarized NFs" on General-Purpose Computing (GPC) platforms and infrastructures. GPC platforms are not specifically designed to efficiently execute NFs with their typically intense Input/Output (I/O) demands. Recently, numerous hardware-based accelerations have been developed to augment GPC platforms and infrastructures, e.g., the central processing unit (CPU) and memory, to efficiently execute NFs. The computing capabilities of client devices are continuously increasing; at the same time, demands for ultra-low latency (ULL) services are increasing. These ULL services can be provided by migrating some micro-service container computations from the cloud and multi-access edge computing (MEC) to the client devices.

The mobile crowdsensing (MCS) applications leverage the user data to derive useful information by data-driven evaluation of innovative user contexts and gathering of information at a high data rate. Such access to context-rich data can potentially enable computationally intensive crowd-sourcing applications such as tracking a missing person or capturing a highlight video of an event. Using snippets and pictures captured from multiple mobile phone cameras with specific contexts can improve the data acquired in such applications. These MCS applications require efficient processing and analysis to generate results in real time. A human user, mobile device and their interactions cause a change in context on the mobile device affecting the quality contextual data that is gathered. Usage of MCS data in real-time mobile applications is challenging due to the complex inter-relationship between: a) availability of context, context is available with the mobile phones and not with the cloud, b) cost of data transfer to remote cloud servers, both in terms of communication time and energy, and c) availability of local computational resources on the mobile phone, computation may lead to rapid battery drain or increased response time. The resource-constrained mobile devices need to offload some of their computation.



This thesis proposes ContextAiDe an end-end architecture for data-driven distributed applications aware of human mobile interactions using Edge computing. Edge processing supports real-time applications by reducing communication costs. The goal is to optimize the quality and the cost of acquiring the data using a) modeling and prediction of mobile user contexts, b) efficient strategies of scheduling application tasks on heterogeneous devices including multi-core devices such as GPU c) power-aware scheduling of virtual machine (VM) applications in cloud infrastructure e.g. elastic VMs. ContextAiDe middleware is integrated into the mobile application via Android API. The evaluation consists of overheads and costs analysis in the scenario of ``perpetrator tracking" application on the cloud, fog servers, and mobile devices. LifeMap data sets containing actual sensor data traces from mobile devices are used to simulate the application run for large scale evaluation.

The commercial semiconductor industry is gearing up for 5G communications in the 28GHz and higher band. In order to maintain the same relative receiver sensitivity, a larger number of antenna elements are required; the larger number of antenna elements is, in turn, driving semiconductor development. The purpose of this paper is to introduce a new method of dividing wireless communication protocols (such as the 802.11a/b/g
and cellular UMTS MAC protocols) across multiple unreliable communication links using a new link layer communication model in concert with a smart antenna aperture design referred to as Vector Antenna. A vector antenna is a ‘smart’ antenna system and as any smart antenna aperture, the design inherently requires unique microwave component performance as well as Digital Signal Processing (DSP) capabilities. This performance and these capabilities are further enhanced with a patented wireless protocol stack capability.

Emerging modular cable network architectures distribute some cable headend functions to remote nodes that are located close to the broadcast cable links reaching the cable modems (CMs) in the subscriber homes and businesses. In the Remote- PHY (R-PHY) architecture, a Remote PHY Device (RPD) conducts the physical layer processing for the analog cable transmissions, while the headend runs the DOCSIS medium access control (MAC) for the upstream transmissions of the distributed CMs over the shared cable link. In contrast, in the Remote MACPHY (R-MACPHY) ar- chitecture, a Remote MACPHY Device (RMD) conducts both the physical and MAC layer processing. The dissertation objective is to conduct a comprehensive perfor- mance comparison of the R-PHY and R-MACPHY architectures. Also, development of analytical delay models for the polling-based MAC with Gated bandwidth alloca- tion of Poisson traffic in the R-PHY and R-MACPHY architectures and conducting extensive simulations to assess the accuracy of the analytical model and to evaluate the delay-throughput performance of the R-PHY and R-MACPHY architectures for a wide range of deployment and operating scenarios. Performance evaluations ex- tend to the use of Ethernet Passive Optical Network (EPON) as transport network between remote nodes and headend. The results show that for long CIN distances above 100 miles, the R-MACPHY architecture achieves significantly shorter mean up- stream packet delays than the R-PHY architecture, especially for bursty traffic. The extensive comparative R-PHY and R-MACPHY comparative evaluation can serve as a basis for the planning of modular broadcast cable based access networks.