Resource Scheduling Strategies to Optimise QoS in Integrated IoT and Fog Computing Environments

Abstract

In recent years, there has been a tremendous increase in the internet and its applications, which has attracted the attention of scholars and industries to investigate how to improve the quality of services (QoS). Improving QoS is considered a major challenge for users of IoT devices. To address this challenge, several technologies have emerged to extend cloud computing, including fog computing, which provides computational resources at the network’s edge. Nevertheless, fog computing faces limitations due to the constrained resources, limited computational processes and storage in fog devices compared to cloud infrastructure. This thesis investigates resource scheduling strategies to optimise QoS in fog computing, focusing on task scheduling and resource allocation approaches. The thesis begins with a qualitative comparative analysis of existing resource management approaches to optimise QOS. It classifies resource management approaches into several categories: application placement, task scheduling, resource allocation, task offloading, load balancing, and resource provisioning. These categories are either task-oriented, such as application placement, task scheduling, and task offloading, or resource-oriented, including resource allocation, load balancing, and resource provisioning. It also introduces a novel intelligent resource scheduling model using gated graph convolution neural networks (GGCNs) to trade off between delay and network usage with a limited number of fog nodes. The GGCN model outperforms various other existing approaches like PSO, FCFS, and JSF by 86.09%, 98.53%, and 98.02% respectively, in terms of total network usage. Additionally, in terms of loop delay, it achieves improvements of 68.64% over PSO, 92.07% over FCFS, and 76.26% over SJF. Furthermore, it presents a novel multi-objective scheduling framework utilising an enhanced multi-layer perceptron (eMLP). This new mechanism optimises several parameters, including delay, power consumption, and cost, while simultaneously optimising bandwidth. Experimental results show that eMLP reduces delay, network usage and cost by 75%, 65%, and %70 respectively, compared to other benchmark schemes such as GNN, SMA, FCFS, and SJF. Finally, the thesis discusses the current gaps and future directions for enhancing and further investigating QoS through fog computing.