Abstract
Edge computing is proved to be an effective solution for the Internet of Things (IoT)-based systems. Bringing the resources closer to the end devices has improved the performance of the networks and reduced the load on the cloud. On the other hand, edge computing has some constraints related to the amount of the resources available on the edge servers, which is considered to be limited as compared with the cloud. In this paper, we propose Software-Defined Networking (SDN)-based resources allocation and service placement system in the multi-edge networks that serve multiple IoT applications. In this system, the resources of the edge servers are monitored using the proposed Edge Server Application (ESA) to determine the state of the edge server and, therefore, the acceptable services by each server. Benefiting from the information gathered by ESA, the service offloading decision would be taken by the proposed SDN Non-core Application (SNA) in a way that ensures an efficient load distribution and better resources utilization for the edge servers. A Weighted Aggregated Sum Product Assessment Method (WASPAS) was used to determine the best edge server. The proposed system was compared with a non-SDN system and showed improvement in the performance and the utilization of resources of the edge servers. Furthermore, the request handling time was considerably reduced and settled in constant rates for a different number of devices.
Highlights
The recent years have witnessed vast growth in the information and communication technologies.The Internet of Things (IoT) technology is considered as the base stone for the development of smart cities, smart grid, smart factory, smart health care, etc
The second physical machine is used to run two virtual machines (VMs), one is for the Cloud and the other is for IoT devices
The proposed SDN Assisted Service Placement in Multi-Edge Environment (SASPME) system aims to improve the performance of the IoT-based applications by allocating computational resources for the delay-sensitive services in the edge servers
Summary
The recent years have witnessed vast growth in the information and communication technologies. Instead of sending all the IoT devices’ data to far located cloud DCs, some of the data can be processed in local distributed edge servers, fog, or cloudlets This can reduce the load on the cloud DCs and ensures better latency, link utilization, and more efficient energy consumption [7]. This paper presents an SDN-based resource allocation and service placement mechanism in an Edge-Cloud environment. The SDN controller is responsible for offloading services to an edge server or the cloud. The main contributions of this work are: Reducing the total time for handling IoT service’s requests by presenting an efficient SDN assisted offloading mechanism to determine the convenient edge server for each service/microservice using multiple-criteria decision-making (MCDM) algorithms. The results were measured depending on delay, complexity, and number of handovers
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
