Open AccessA Hierarchical Approach for Accelerating IoT Data Management Process Based on SDN Principles
Author(s) -
Zahra Eghbali,
Mina Zolfy Lighvan
Publication year - 2019
Publication title -
mendel ... (brno. on-line)/mendel ...
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.221
H-Index - 13
eISSN - 1803-3822
pISSN - 1803-3814
DOI - 10.13164/mendel.2019.1.121
Subject(s) - computer science , distributed computing , process (computing) , forwarding plane , software defined networking , load balancing (electrical power) , internet of things , the internet , control (management) , computer network , embedded system , world wide web , operating system , artificial intelligence , mathematics , geometry , network packet , grid
Internet of things is a new technology that connects billions of smart devices through the Internet. This important technology is heavily affecting different aspects of human life and plays an important role in variety of domains. The number of smart devices connecting to IoT and the amount of data gathered or produced by these devices are increasing. This large volume of data requires a lot of effort for processing and analysis. In order to organize, secure and balance the load in IoT, the novel and creative ideas for IoT design and management are required. Software Defined Networking is a new and promising paradigm and its main idea is to decouple the control and management operations from physical devices and setting them inside a logically centralized control layer. Due to its unique capabilities, SDN can be a good choice for managing dynamic and complicated networks such as IoT. In this paper, a distributed approach is proposed for accelerating data management and balancing the load between IoT devices. The proposed framework makes it possible to apply different kinds of management, security and load balancing strategies using a distributed control plane. Experimental results indicate that our scheme exhibits a reduction in the average turnaround time and the average waiting time and it will improve the processing performance. The proposed approach will also distribute tasks between devices, so that there will be no under-loaded device when a part of network is under the processing pressure.