A systematic review on resource provisioning in fog computing

Abstract

Resource provisioning is allocating resources to clients over the Internet and plays a prominent role in cloud computing infrastructure-as-a-service (IaaS).The main issues of resource provisioning are meeting user demands like bandwidth, response time, throughput, availability, and so on. The cloud computing framework uses virtualization technology to provide on-demand access to computer system resources, specifically computation and storage. In cloud computing, computing resources are shared across another communication network using virtualization. However, the cloud computing mechanism cannot meet the needs of a large number of Internet of Things (IoT) services. To consider this, fog computing was introduced as a modified mechanism of the cloud paradigm by providing cloud services for the end devices. Fog computing is a decentralized computing model placed between devices, edges, data centers or the cloud. In this way, it helps to meet the demands initiated by IoT services, such as reduced latency, wide mobility coverage, and so on. Several solutions regarding resource allocation in fog computing are available in the research field, but such solutions have not achieved satisfactory results. Therefore, finding a solution by analyzing recent problems is open research. Therefore, this paper reviews different methods established for resource provisioning in fog computing using different parameters from 2015 to 2021 and introduces the limitations, advantages and future directions related to different resource provisioning techniques.

Resource provisioning model for executing realistic workload in heterogenous internet of things environment

“…Resource provisioning considering realistic workload in a heterogeneous IoT environment poses significant challenges in terms of execution time and energy consumption [11]. Addressing these challenges is crucial to ensure efficient and sustainable operation of IoT applications.…”

PMRNA: Parameter matching of realtime and non‐realtime applications for resource provisioning in fog‐integrated cloud

“…4 Cloud and Fog employ distributed computing; however, comparatively, Cloud is more centralized than Fog. 5 The Cloud datacenter houses powerful servers, managed and operated by the datacenter owners. However, in Fog computing, any device with computational or storage capacity (such as a router, switch, or other network devices) can act as a Fog device/node.…”

“…In a three‐tier architecture, Fog computing lies between Cloud and IoT/edge devices 4 . Cloud and Fog employ distributed computing; however, comparatively, Cloud is more centralized than Fog 5 …”