A Multi-Protocol Controller Deployment in SDN-based IoMT Architecture

CİCİOĞLU M., Calhan A.

IEEE Internet of Things Journal, vol.9, no.21, pp.20833-20840, 2022 (SCI-Expanded, Scopus) identifier identifier

  • Publication Type: Article / Article
  • Volume: 9 Issue: 21
  • Publication Date: 2022
  • Doi Number: 10.1109/jiot.2022.3175669
  • Journal Name: IEEE Internet of Things Journal
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, ABI/INFORM, Compendex, INSPEC
  • Page Numbers: pp.20833-20840
  • Keywords: Protocols, Wireless communication, Computer architecture, IEEE 802, 15 Standard, Time division multiple access, Standards, Internet of Things, Machine learning (ML), software-defined networking (SDN), wireless sensor networks, INTERNET, FRAMEWORK, THREATS
  • Bursa Uludag University Affiliated: Yes

Abstract

IEEEInternet of Medical Things (IoMT) as a next-generation network requires heterogeneous services, technologies, and equipment infrastructure management resulting in more complex systems. The Software-Defined Networking (SDN) approach has emerged as a promising solution to reduce this complexity by proposing a vendor-independent structure that disaggregates the control and data planes. In this study, an architecture based on the SDN is proposed for such heterogeneous and complex IoMT networks. A new controller that supports different wireless communication protocols has been developed for the control plane. We propose machine learning-based load balancing and time-sensitive prioritization (MLA) algorithms for dense and dynamic networks. SDN-based IoMT network that consists of IEEE 802.15.6, TDMA, and IEEE 802.11 protocols are analyzed in a simulation program simultaneously using various scenarios in terms of throughput, delay, packet loss ratio, bit error rate and user density parameters. In addition, in this study, a new dataset is created for load balancing. The performances of Support Vector Machine SVM), Ensemble of Decision Trees, k-NN, and Naive Bayes machine learning algorithms are compared, and SVM gives the best result with 95.1% accuracy.