Fog Computing: A Comprehensive Architectural Survey

Pooyan Habibi, Mohammad Farhoudi, Sepehr Kazemian, Siavash Khorsandi, Alberto Leon‐Garcia

IEEE Access · 2020 · 226 citations · 158 references

DOIFull text

Open access

Concepts

TL;DR

Fog computing is an emerging paradigm that extends cloud capabilities to the edge, deploying virtualized computing, networking, storage, and acceleration functions on distributed devices to alleviate bottlenecks in large‑scale IoT deployments. The paper aims to provide an inclusive taxonomy of fog computing’s architectural, algorithmic, and technological aspects to contextualize current research. The authors review fog computing paradigms, architectural distinctions, and practical deployment aspects—including system design, application design, software implementation, security, resource management, and networking—while surveying reference and application‑specific architectures. They present base architectures for application, software, security, resource management, and networking, evaluating them with a proposed maturity model.

Abstract

Fog computing is an emerging technology to address computing and networking bottlenecks in large scale deployment of IoT applications. It is a promising complementary computing paradigm to cloud computing where computational, networking, storage and acceleration elements are deployed at the edge and network layers in a multi-tier, distributed and possibly cooperative manner. These elements may be virtualized computing functions placed at edge devices or network elements on demand, realizing the "computing everywhere" concept. To put the current research in perspective, this paper provides an inclusive taxonomy for architectural, algorithmic and technologic aspects of fog computing. The computing paradigms and their architectural distinctions, including cloud, edge, mobile edge and fog computing are subsequently reviewed. Practical deployment of fog computing includes a number of different aspects such as system design, application design, software implementation, security, computing resource management and networking. A comprehensive survey of all these aspects from the architectural point of view is covered. Current reference architectures and major application-specific architectures describing their salient features and distinctions in the context of fog computing are explored. Base architectures for application, software, security, computing resource management and networking are presented and are evaluated using a proposed maturity model.

References

158