Innovative methods for edge computing deployment in healthcare

Abstract

This interdisciplinary research explores the integration of edge computing technology in the healthcare sector, presenting innovative methodologies across three key contributions. In Chapter 3, the first contribution introduces the Healthcare Metropolitan Area Network (HMAN), a novel cooperative hierarchical Edge/Fog computing-based architecture for urban healthcare systems. HMAN offers offloading scenarios and the HOSSC algorithm, tailored for versatile data processing. Simulation results demonstrate its potential as a scalable and robust healthcare system, with efficient computing capacity and service availability. HMAN also ensures patient privacy through local data storage and processing, making it a practical solution for serving a large number of patients. The second part of this research, expounded upon in Chapter 4, comprises dual facets: an AI-based priority mechanism to identify urgent cases, aimed at improving Quality of Service (QoS) and Quality of Experience (QoE) is proposed. Then, an optimal edge-servers placement (OESP) algorithm to obtain a cost-efficient architecture with lower delay and complete coverage is presented. Results show reduced patient latency based on urgency, prioritising critical cases. The OESP algorithm selects optimal deployment sites, achieving over 80% cost-efficiency improvement. In summary, the study enhances healthcare system performance, cost-effectiveness, and reduces latency. The third part of this research, encapsulated in Chapter 5, introduces an adaptive load balancing method that combines the strengths of static and Software-Defined Networking (SDN)-based load balancing algorithms for Edge/Fog-based healthcare systems. A new algorithm called Load Balancing of Optimal Edge-server Placement (LB-OESP) is proposed to balance the workload statically in the systems, followed by the presentation of an SDN-based greedy heuristic (SDN-GH) algorithm to manage the data flow dynamically within the network. LB-OESP efficiently balances workloads while minimising edge server requirements, improving system performance, and reducing costs. The SDN-GH algorithm leverages the benefits of SDN to dynamically balance the load and provide a more efficient system. Simulation results demonstrate that this approach provides adaptive load balancing, considering changing network conditions, resulting in improved system performance and reliability. Furthermore, it achieves a 12% reduction in system latency and up to 28% lower deployment costs compared to previous methods, offering a promising, efficient, and cost-effective solution for Edge/Fog-based healthcare systems.