Fog Computing: Survey of Trends, Architectures, Requirements, and Research Directions

Ranesh Kumar Naha, Saurabh Kumar Garg, Dimitrios Georgakopoulos, Prem Prakash Jayaraman, Longxiang Gao, Yong Xiang, Rajiv Ranjan

TL;DR

This paper provides a comprehensive survey of Fog Computing, a distributed computing paradigm that brings computation closer to the edge of the network. It addresses the growing need for low-latency processing of IoT data by analyzing existing trends, architectures, requirements, and research directions, offering a taxonomy to guide future development.

What Problem Does This Paper Address?

The explosion of data generated by the Internet of Things (IoT) presents a significant challenge for traditional cloud computing. While cloud infrastructure offers scalability and on-demand services, its inherent latency makes it unsuitable for time-sensitive IoT applications. Fog Computing emerges as a solution by placing computation and storage closer to IoT devices, bridging the gap between the edge and the cloud. However, the field is still nascent, lacking a standardized architecture and a clear understanding of its requirements, leading to fragmented research. This paper aims to synthesize the current landscape, identify research gaps, and provide a roadmap for future Fog Computing development.

Methods

The authors conducted a thorough literature review to achieve their objectives. They analyzed research trends by examining publication numbers and search occurrences in academic databases. They investigated various proposed Fog Computing architectures, detailing their components. A key contribution is the development of a taxonomy for Fog Computing based on infrastructure, platform, and application requirements. Furthermore, they reviewed existing research in areas like resource allocation, scheduling, fault tolerance, simulation tools, and microservices, highlighting limitations and open issues.

Datasets

Not discussed in the paper.

Key Insights and Ideas

  • Fog Computing as a Necessity, Not a Replacement: The paper emphasizes that Fog Computing is not intended to replace the cloud but rather to complement it, handling latency-sensitive tasks at the edge while leveraging the cloud for complex processing and long-term storage.
  • Heterogeneity is a Defining Challenge: The diverse nature of devices and resources in Fog environments (smartphones, routers, base stations, etc.) presents significant challenges for resource management, scheduling, and fault tolerance.
  • A Taxonomy for Clarity: The proposed taxonomy, based on infrastructure, platform, and application requirements, provides a much-needed structured framework for understanding and comparing Fog Computing research.
  • Research Gaps are Abundant: Despite growing interest, significant research gaps exist in areas like fault tolerance, comprehensive simulation tools, and the practical implementation of microservices in Fog environments.
  • Mobility is Key: The dynamic nature of mobile devices and their changing locations is a critical factor that needs to be addressed for effective Fog Computing deployment.

Key Results

The paper provides a comprehensive overview of the Fog Computing landscape, including:

  • Research Trends: Analysis shows a significant increase in Fog Computing research publications, indicating its growing importance.
  • Architectural Diversity: Various layered architectures for Fog Computing have been proposed, with differing numbers of layers and component focuses.
  • Taxonomy Development: A detailed taxonomy is presented, categorizing requirements into infrastructure, platform, and application levels.
  • Identification of Research Gaps: The authors highlight critical areas requiring further investigation, including resource allocation and scheduling, fault tolerance, simulation tools, and Fog-based microservices.
  • Comparison with Similar Paradigms: The paper clearly distinguishes Fog Computing from related concepts like Mobile Cloud Computing (MCC), Mobile Edge Computing (MEC), and Edge Computing.

Limitations and Future Work

The authors acknowledge that Fog Computing is still in its infancy, and much research is needed. Key limitations and future work directions identified include:

  • Lack of Standardized Architecture: While initiatives like the OpenFog Consortium are working towards this, a universally accepted standard architecture is still missing.
  • Resource Management Complexity: The dynamic and heterogeneous nature of Fog resources makes efficient resource allocation and scheduling a significant challenge.
  • Fault Tolerance in a Distributed Environment: The high probability of device failure in a distributed Fog environment necessitates robust fault tolerance mechanisms, which are still under-explored.
  • Simulation Tools: Current simulation tools are often based on cloud environments and may not accurately reflect the complexities of Fog Computing. Development of more realistic simulators is crucial.
  • Security and Privacy: Ensuring security and privacy across a distributed and multi-tenant Fog environment is a complex issue that requires further investigation.
  • Application Modeling: Developing generic applications that can seamlessly run across diverse IoT devices and Fog nodes remains a challenge.
  • User Participation: Mechanisms to encourage and manage user participation in Fog computation are needed for its widespread adoption.

Summary updated

Abstract

Emerging technologies like the Internet of Things (IoT) require latency-aware computation for real-time application processing. In IoT environments, connected things generate a huge amount of data, which are generally referred to as big data. Data generated from IoT devices are generally processed in a cloud infrastructure because of the on-demand services and scalability features of the cloud computing paradigm. However, processing IoT application requests on the cloud exclusively is not an efficient solution for some IoT applications, especially time-sensitive ones. To address this issue, Fog computing, which resides in between cloud and IoT devices, was proposed. In general, in the Fog computing environment, IoT devices are connected to Fog devices. These Fog devices are located in close proximity to users and are responsible for intermediate computation and storage. Fog computing research is still in its infancy, and taxonomy-based investigation into the requirements of Fog infrastructure, platform, and applications mapped to current research is still required. This paper starts with an overview of Fog computing in which the definition of Fog computing, research trends, and the technical differences between Fog and cloud are reviewed. Then, we investigate numerous proposed Fog computing architecture and describe the components of these architectures in detail. From this, the role of each component will be defined, which will help in the deployment of Fog computing. Next, a taxonomy of Fog computing is proposed by considering the requirements of the Fog computing paradigm. We also discuss existing research works and gaps in resource allocation and scheduling, fault tolerance, simulation tools, and Fog-based microservices. Finally, by addressing the limitations of current research works, we present some open issues, which will determine the future research direction.
BibTeX
@article{naha2018fog,
  author = {Ranesh Kumar Naha and Saurabh Kumar Garg and Dimitrios Georgakopoulos and Prem Prakash Jayaraman and Longxiang Gao and Yong Xiang and Rajiv Ranjan},
  title = {{Fog Computing: Survey of Trends, Architectures, Requirements, and Research Directions}},
  journal = {IEEE Access},
  year = {2018},
  doi = {10.1109/access.2018.2866491},
}
Figure