Comparative Analysis: Software Defined Network Frameworks for IOT Devices Using Machine Learning
The Internet of Things (IoT) has become a vital part of our daily lives. As the number of IoT devices continues to grow, SDN with Distributed Resource Management (DRM) can efficiently manage the dynamic and diverse resource needs of the devices. This paper presents a novel solution which is referred to as the Enhanced Machine Learning (ML) based SDN framework. The proposed paper addresses the multifaceted challenges of optimizing IoM network resources through a comprehensive approach encompassing dynamic resource allocation, traffic flow optimization, QoS policy implementation, centralized network management, energy-efficient communication, and enhanced data processing DN's ability to intelligently assign channels using deep learning models prevents network congestion and improves performance, making it an ideal solution for managing the dynamic and large-scale traffic flows in IoT environments [10]. Overall, SDN's centralized control, flexibility, and advanced security mechanisms make it a pivotal technology for enhancing IoT networks.
Authors
- Madhavi Dhingra (ORCID: https://orcid.org/0000-0002-9883-7620)
- Nisha Chaurasia (ORCID: https://orcid.org/0000-0002-0007-2712)
- Nidhi Bajpai
Institutions
- Amity University (AE)
- Dr. B. R. Ambedkar National Institute of Technology Jalandhar (IN)
Publication Details
- Published
- 2024-11-29
- DOI
- https://doi.org/10.1109/icdcc62744.2024.10961753
- Primary Topic
- IoT and Edge/Fog Computing
- Type
- article
- Field-Weighted Citation Impact
- 0.00