• Vinod Kumar Shamrao Jadhav
• Dr, Vijay Prakash Singh

In this article, the ML algorithm, an adaptive bandwidth mechanism, and a dynamic threshold approach are proposed as part of a security strategy. Thus, the primary emphasis is placed on the DDoS attack mitigation technique taken into account by the SDN controller's ML-trained model. The best ML is used in the suggested technique to identify security solutions that improve both the safety of the SDN controller and the efficiency of the network. The Extreme Gradient Boosting (XGBoost) and other ML algorithms utilized in this approach not only improved the precision of the security solutions, but also the efficiency of the whole network. A radical shift in the abstraction, separation, and mapping of forwarding, control, and management components of services has been spurred by the rising consumption of multimedia services and the need for high-quality services from clients. With the EstiNet simulator, we test our proposed architecture in terms of latency, reliability, and user satisfaction. To evaluate how well the suggested design performs, it is simulated and then compared to the performance of other architectures, including the software-defined unified virtual monitoring function and the Advanced Static Analysis and Transformation Protocol. Analysis shows that our suggested architecture outperforms the alternatives in terms of overall time delay (1800 s for 200 IoT devices), reliability (90%), and satisfaction (90%).

Machine learning; Distributed Denial-of-Service; SDN based 5G networks; Security solution; Extreme Gradient Boosting Algorithm (XGBoost)

"ROLE OF ML ALGORITHM IN SDN IN 5G NETWORK", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.401-408, April-2019, Available :http://www.jetir.org/papers/JETIRFU06050.pdf

"ROLE OF ML ALGORITHM IN SDN IN 5G NETWORK", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp401-408, April-2019, Available at : http://www.jetir.org/papers/JETIRFU06050.pdf