학술논문

Resource Utilization based Load Balancing for a Virtualized Security Functions Platform
Document Type
Conference
Source
2021 IEEE 12th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), 2021 IEEE 12th Annual. :0065-0068 Dec, 2021
Subject
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Fields, Waves and Electromagnetics
General Topics for Engineers
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Cloud computing
Heuristic algorithms
Telecommunication traffic
Load management
Dynamic scheduling
Resource management
Time factors
Cloud Service Provider (CSP)
Software Defined Networks (SDN)
Security Functions Virtualization (SFV)
Language
Abstract
Cloud Service Providers (CSPs) are moving to a Software Defined Networks (SDN) based approach to managing their network infrastructure. The introduction of Virtualized Security Functions (VSFs) and offering them as a service has to make SDN more popular among CSPs because SDN brings advantages such as flexibility, elasticity, and easy management. When offering VSFs, resource management is one of the important aspects, especially considering the dynamic nature of the traffic, where traffic increases and decreases dynamically over time. In parallel to the traffic changes, resources also have to increase/ decrease and traffic load must be balanced over the resources. This research focuses on exploring a resource utilization-based load balancing algorithm, that considers memory and CPU utilization of the VSFs. We have used Mininet simulation to build an SDN-based cloud architecture with VSFs, and POX controller to explore the performances of the proposed algorithm, in terms of average workload and average response time. Our results show that the resource utilization-based load balancing algorithm balances the workload and traffic adequately, within an acceptable time.