5G Network Slicing Algorithm Development using Bagging based-Gaussian Naive Bayes

Existing cellular communications and future communication networks requires very low latency, high reliability standards, increased capacity, enhanced security, and efficient user communication. The ability to accommodate several independent devices is a feature that mobile operators are seeking for a programmable solution, comparable functional networks technical foundation. Through the use of the Network Slicing concept, 5G networks enable end-to-end deployment of network resources (NS). Due to the surge in traffic and the acceleration of 5G network performance, emerging communication networks will demand data-driven strategic planning. This paper has to implement machine learning based network slicing algorithm to divide 5G network IoT devices into effective network slices such as eMBB, mMTC, URLLC for the traffic. The GNB and B-GNB algorithms are used to classify the usecase devices under the three network slices. This work developed bagging integrated with GNB algorithm and its performance metrics have been analysed. The B-GNB algorithm works well for prediction of best slice and strategic recommendations even there is network interruption, be able to predict the best network slice and implement strategic recommendations. The performance metrics such as sensitivity, F-score, precision and accuracy have also been analyzed. The comparative analysis shows B-GNB classify the slices with 86% of accuracy.