Delay Reduction in MTC Using SDN Based Offloading in Fog Computing

Arefian, Zahra; Khayyambashi, Mohammad Reza; Movahhedinia, Naser

doi:10.21203/rs.3.rs-2046505/v1

Cited by 1 publication

(1 citation statement)

References 50 publications

(77 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If all neighboring nodes cannot process the request, it is sent to the Cloud. This paper extends our previous work [56] by introducing a comprehensive analytical model for service delay evaluation. In addition to method presented in [4], the Figure 13 also compares the previously written article with the proposed model.…”

Section: Numerical Resultssupporting

confidence: 54%

Delay reduction in MTC via SDN based offloading in a Fog Computing environment with the assistance of volunteer nodes

Arefian,

Khayyambashi,

Movahhedinia

2023

Preprint

Self Cite

View full text Add to dashboard Cite

This article discusses the integration of Distributed Fog Computing (FC) and Software-Defined Networking (SDN) for efficient resource management in Machine Type Communications (MTC). FC brings Cloud resources closer to the user, enhancing service quality and reducing delays. Some MTC devices have powerful processors that can be used as volunteer nodes to process lightweight requests, thereby increasing the network's distributed processing capabilities. The paper proposes a framework that uses priority and differential flow space allocation to handle heterogeneous requests in MTC and assign delay-sensitive flows to priority queues on each Fog node. To address the limited resources available on individual Fog nodes, the article recommends offloading flows to other Fog nodes and volunteer nodes through a decision-based SDN controller. The article models flow-based Fog nodes using queueing theory, employing priority polling algorithms to service the flows and alleviate the issue of resource starvation in a multi-queueing environment. It is observed that the percentage of delay-sensitive processed flows, the network consumption, and the average service time in the proposed mechanism are improved by about85%, 68%, and 62%, respectively, compared to traditional Cloud computing. Therefore, the delay reductions based on the types of flows and task offloading is proposed.

show abstract

Section: Numerical Resultssupporting

confidence: 54%