Delay reduction in MTC using SDN based offloading in Fog computing

Area of Science:

• Computer Science
• Networking
• Distributed Systems

Background:

• Fog computing (FC) extends cloud capabilities closer to users, improving service quality and reducing latency.
• Traditional cloud computing faces challenges with high latency and resource limitations for real-time applications.
• Software-Defined Networking (SDN) offers a flexible and programmable approach to network management.

Purpose of the Study:

• To propose a framework integrating Fog computing (FC) and Software-Defined Networking (SDN) for efficient resource management.
• To address heterogeneous requests in Machine-Type Communications (MTC) by prioritizing delay-sensitive flows.
• To investigate flow offloading mechanisms between fog nodes to overcome resource limitations.

Main Methods:

• Implemented a framework combining FC and SDN for resource management.
• Applied priority and differential flow space allocation for heterogeneous MTC requests.
• Modeled fog nodes using queueing theory and polling priority algorithms to manage multi-queueing systems.
• Utilized an SDN controller for intelligent flow offloading decisions.

Main Results:

• Achieved approximately 80% improvement in processing delay-sensitive flows.
• Reduced network consumption by about 65%.
• Decreased average service time by approximately 60% compared to traditional cloud computing.
• Demonstrated significant delay reductions based on flow types and task offloading.

Conclusions:

• The proposed FC and SDN convergence effectively manages resources for MTC.
• Priority queueing and flow offloading are crucial for minimizing delay in fog environments.
• The framework offers substantial performance gains over traditional cloud computing for delay-sensitive applications.