[Paper Review] Application Management in Fog Computing Environments: A Taxonomy, Review and Future Directions

Redowan Mahmud, Kotagiri Ramamohanarao+1 more|arXiv (Cornell University)|May 21, 2020

IoT and Edge/Fog ComputingComputer Science141 references165 citations

TL;DR

This paper proposes a comprehensive taxonomy, review, and future research framework for application management in fog computing environments. It addresses challenges in application architecture, placement, and maintenance across distributed, heterogeneous, and resource-constrained fog nodes, offering a multi-level orchestration model and identifying key research gaps and directions such as AI-driven management, energy-accuracy trade-offs, and trusted service orchestration.

ABSTRACT

The Internet of Things (IoT) paradigm is being rapidly adopted for the creation of smart environments in various domains. The IoT-enabled Cyber-Physical Systems (CPSs) associated with smart city, healthcare, Industry 4.0 and Agtech handle a huge volume of data and require data processing services from different types of applications in real-time. The Cloud-centric execution of IoT applications barely meets such requirements as the Cloud datacentres reside at a multi-hop distance from the IoT devices. extit{Fog computing}, an extension of Cloud at the edge network, can execute these applications closer to data sources. Thus, Fog computing can improve application service delivery time and resist network congestion. However, the Fog nodes are highly distributed, heterogeneous and most of them are constrained in resources and spatial sharing. Therefore, efficient management of applications is necessary to fully exploit the capabilities of Fog nodes. In this work, we investigate the existing application management strategies in Fog computing and review them in terms of architecture, placement and maintenance. Additionally, we propose a comprehensive taxonomy and highlight the research gaps in Fog-based application management. We also discuss a perspective model and provide future research directions for further improvement of application management in Fog computing.

Motivation & Objective

• To analyze and categorize existing application management strategies in fog computing environments.
• To identify research gaps in application architecture, placement, and maintenance within fog computing.
• To propose a multi-level perspective model for orchestrating application management across fog and cloud infrastructures.
• To outline future research directions for improving efficiency, reliability, and scalability in fog-based IoT systems.

Proposed method

• Proposes a three-tier taxonomy for application management: architecture, placement, and maintenance.
• Introduces a perspective model integrating CPS managers, application placement engines (APE), and resource managers (FRM/CRM) across fog and cloud layers.
• Utilizes a layered architecture where the CPS manager coordinates application deployment based on resource state and QoS requirements.
• Employs dynamic workload scheduling to adapt to environmental changes and optimize task dispatching.
• Leverages feedback from FRM and CRM to adjust application specifications and placement policies in real time.
• Supports runtime orchestration, migration, and multi-level resource provisioning through coordinated management components.

Experimental results

Research questions

• RQ1 How can application architectures be effectively designed and categorized for fog computing environments?
• RQ2 What are the key challenges and limitations in current fog-based application placement strategies?
• RQ3 How can application maintenance be optimized in distributed, heterogeneous, and constrained fog infrastructures?
• RQ4 What are the critical research gaps in application management that hinder the full exploitation of fog computing capabilities?
• RQ5 What future research directions are essential for advancing scalable, efficient, and trustworthy fog application management?

Key findings

• The paper identifies significant research gaps in application architecture, placement, and maintenance, particularly in handling heterogeneity, resource constraints, and dynamic workloads.
• A multi-level management framework is proposed that integrates fog and cloud resource managers with application placement and workload scheduling components.
• The study highlights that AI-based management can improve prediction of resource needs, context changes, and node failures.
• Energy-accuracy trade-offs are critical, especially when using renewable energy sources, and require dynamic tuning of sensing frequency and accuracy.
• Trusted service orchestration is essential for secure collaboration between public and private fog infrastructures.
• Dynamic consolidation and scaling of fog nodes can reduce costs and energy consumption while maintaining performance.