Adaptive Resilience of Intelligent Distributed Applications in the Edge-Cloud Environment
No Thumbnail Available
Date
2024-04
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Cardiff University
Abstract
This thesis navigates the complexities of Internet of Things (IoT) application placement in hybrid fog-cloud environments to improve Quality of Service (QoS) in IoT applications. It investigates the optimal distribution of a Service Function Chain (SFC), the building blocks of an IoT application, across the fog-cloud infrastructure, taking into account the intricate nature of IoT and fog-cloud environments.
The primary objectives are to define a platform architecture capable of operating IoT applications efficiently and to model the placement problem comprehensively. These objectives involve detailing the infrastructure's current state, execution requirements, and deployment goals to enable adaptive system management.
The research proposes optimal placement methods for IoT applications, aiming to reduce execution time, enhance dependability, and minimise operation costs. It introduces an approach to effectively manage trade-offs through the measurement and analysis of QoS metrics and requires the implementation of specialised scheduling and placement strategies. These strategies employ concurrency to
accelerate the planning process and reduce latency, underscoring the need for an algorithm that best corresponds to the specific requirements of the IoT application domain.
The study's methodology begins with a comprehensive literature review in the area of IoT application deployment in hybrid fog-cloud environments. The insights gained inform the development of novel solutions that address the identified limitations, ensuring the proposal of robust and efficient solutions.
Description
Description:
This thesis addresses the complex challenge of optimizing intelligent Internet of Things (IoT) application placement in hybrid fog-cloud environments. The research is structured to systematically tackle various aspects of this problem:
1. Literature Review and Problem Definition:
- Begins with a comprehensive survey of existing approaches in intelligent IoT application deployment.
- Identifies gaps and limitations in current solutions, setting the stage for novel contributions.
2. System Modeling:
- Develops a detailed model for the application placement problem in fog-cloud infrastructures.
- Considers the intricacies of Service Function Chains (SFCs) and their distribution across heterogeneous resources.
3. Platform Architecture:
- Proposes a platform design capable of efficiently managing intelligent IoT applications.
- Incorporates adaptive management features to handle dynamic fog-cloud environments.
4. Algorithm Development:
- Addressing multiple optimization objectives:
-- Minimizing execution time
-- Enhancing system dependability
-- Reducing operational costs
- Introduces the Greedy Nominator Heuristic (GNH) algorithm for function placement.
- Enhances the algorithm with meta-heuristics and machine learning to create the Enhanced Optimised Greedy Nominator Heuristic (EO-GNH).
5. Performance Evaluation:
- Conducts extensive simulations to assess the effectiveness of the proposed solutions.
- Evaluates adaptability in various real-world intelligent IoT application scenarios, including flood preparedness, federated learning for weed detection, and intelligent cooling systems.
6. Implementation Considerations:
- Explores the use of MapReduce and machine learning for efficient function placement.
- Addresses practical aspects such as concurrency, latency reduction, and resource awareness.
The thesis progresses from theoretical foundations to practical implementations, providing a comprehensive exploration of intelligent IoT application management in fog-cloud environments. It concludes with insights into future research directions, including financial strategies, machine learning integration, and security considerations in system scalability.
Keywords
Adaptive system management, Application placement, Artificial Intelligence, Cloud computing, Edge computing, Fog computing, Internet of Things, Quality of Service, Resource optimization, Service Function Chain, System resiliency
Citation
Almurshed, O., 2024. Adaptive resilience of intelligent distributed applications in the edge-cloud environment (Doctoral dissertation, Cardiff University).