A Layered Architecture For Decentralized Computing in the Edge-Cloud Continuum
Guardado en:
| Udgivet i: | PQDT - Global (2025) |
|---|---|
| Hovedforfatter: | |
| Udgivet: |
ProQuest Dissertations & Theses
|
| Fag: | |
| Online adgang: | Citation/Abstract Full Text - PDF Full text outside of ProQuest |
| Tags: |
Ingen Tags, Vær først til at tagge denne postø!
|
| Resumen: | The growing demand for computational, storage and networking capabilities at the network’s edge has driven the development of novel infrastructure concepts like edge and fog computing. These environments involve highly distributed resources and enable computing in close proximity to users and data origins. Edge and fog computing technologies are applied in a variety of use cases, including smart cities, autonomous vehicles, environmental monitoring, or manufacturing.However, the control and management of these infrastructures remains mostly centralized, leading to signifcant challenges in terms of scalability, increased latency due to reliance on distant servers, and the potential for single points of failure. Additionally, the dynamic nature of edge and fog environments poses further challenges in adapting to changes in the network topology.This thesis addresses the inherent challenges of distributed computing within the edgecloud continuum, focusing on decentralized methods to foster a cooperative environment. We present a layered architecture designed to overcome the limitations of centralized control and to promote the collaboration of devices in highly distributed environments. The proposed layers are tailored to accommodate the increasing scale of environments in the edge-cloud continuum. We provide methods to optimize the efciency of the service delivery process and to enable self-adaptive and collaborative resource management and scheduling. These methods facilitate the ad-hoc integration of new devices and dynamically handle network changes due to node churns, further enhancing the robustness of the system. Additionally, we adopt decentralized approaches to optimize the allocation and placement of workloads in edge environments, thereby eliminating the need for centralized management.Our work contributes to the feld of distributed computing by introducing a collaborative architecture for the edge-cloud continuum, highlighting the potential of decentralized strategies in managing unreliable networks and accommodating ad-hoc scenarios. |
|---|---|
| ISBN: | 9798290612645 |
| Fuente: | ProQuest Dissertations & Theses Global |