Decoding the Interplay Between Latency, Reliability, Cost, and Energy While Provisioning Resources in Fog Computing Enabled IoT Networks

Desikan, K E Srinivasa and Kotagi, Vijeth J and Murthy, C Siva Ram (2022) Decoding the Interplay Between Latency, Reliability, Cost, and Energy While Provisioning Resources in Fog Computing Enabled IoT Networks. IEEE Internet of Things Journal. pp. 1-13. ISSN 2372-2541

Text
Internet_of_Things.pdf - Published Version
Restricted to Registered users only
Download (5MB) | Request a copy

Abstract

By bringing the processing and storage capabilities of the cloud closer to the end devices, Fog Computing (FC) enhances the Quality of Service (QoS) for latency-critical IoT applications such as autonomous driving, haptics, and Augmented Reality (AR). To facilitate the processing and storage of data packets, the fog nodes in the underlying FC-enabled IoT network (FC-IoTN) are to be provisioned with storage and processing resources. Existing resource provisioning solutions focus mainly on latency-sensitivity and cost-efficiency. They also operate under the assumption that these fog nodes are completely reliable and energy-efficient. In reality, this is not true. The fog nodes are not 100% reliable. Neither are they energy-efficient. In this study, we propose a novel resource provisioning framework for the fog nodes that considers reliability and energy efficiency, in addition to latencysensitivity and cost-efficiency. We first give an analytical framework to model the failures and recoveries in a fog node and use this modeling to provision resources in the fog nodes such that the resultant resource provisioning is optimal in terms of cost and energy consumption. Further, to understand the effect of latency, reliability, cost, and energy on resource provisioning, we analyze and decode the interplay between these factors during resource provisioning in fog nodes. We finally show the efficacy of our approach over the scenario that does not consider reliability and energy efficiency while provisioning resources. Without affecting the latency-sensitivity and reliability of the system, our framework achieves an enhancement of 35%, and 37% in terms of cost, and energy consumption, respectively, over a non-optimized framework. IEEE

[error in script]

IITH Creators:

IITH Creators	ORCiD

Item Type:

Article

Uncontrolled Keywords:

analytical modeling; Analytical models; Cloud computing; cost; Costs; energy; Energy efficiency; Fog computing; frequency scaling; Internet of Things; internet of things; latency; Quality of service; reliability; Reliability; resource provisioning

Subjects:

Computer science

Divisions:

Department of Computer Science & Engineering

Depositing User:

. LibTrainee 2021

Date Deposited:

25 Oct 2022 10:09

Last Modified:

25 Oct 2022 10:09

URI:

http://raiithold.iith.ac.in/id/eprint/11040