Treffer: Enhancing an Intelligent Model for Enhancing Software-Defined Networking (SDN) Achievement Using Fog Computing and Reinforcement Learning for Operational Performance and Dynamic Resource Management.

Software-defined networking (SDN) has fundamentally transformed network management through centralization and programmability. But, high latency, resource waste, and limited adaptability prevent it from performing well, especially in dynamic applications, such as IoT,5G/6G networks, and smart cities. In order to overcome these limitations, this research presents an intelligent framework which is a combination of SDN, Fog Computing and Reinforcement Learning (RL). Fog Computing to process data from source thus removing latency and bandwidth utilization and RL algorithms can provide an efficient framework for dynamic resource allocation and intelligent decision making. The proposed work targets at establishing a conceptual model that leverage the best of both SDN as well as Fog Computing, RL-based algorithms for adapting traffic routing and efficient resource management, and the design specification of the conceptual framework performance evaluation in terms of latency, energy and resources consumption. The research applied artificial data that produced simulated environments of IoT networks and 5G/6G environments and smart city applications. Mininet software handled SDN simulation while IFogSim operated to model fog computing through custom Python scripts that generated the traffic patterns. The realness of synthetic data was verified using publicly accessible datasets which included CAIDA and IoT Network Intrusion Dataset. The research tested various network topologies from 50 nodes to 200 nodes to verify scalability as well as robustness through different operational situations. Experimental results show that the proposed framework saturates all resources with an 85% resource utilization and outperforms traditional SDN architectures in terms of latency (by 40%) and energy efficiency (by 25%). The framework was found to improve overall network performance while supporting next generation Techs, enabling scalable, flexible, and high performing medium to larger-scale networks. [ABSTRACT FROM AUTHOR]

Copyright of International Journal of Intelligent Engineering & Systems is the property of Intelligent Networks & Systems Society and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)