Machine Learning and Deep Learning Based Network Slicing Models for 5G Network

Abstract

5G network can provide high speed data transfer with low latency at present days. Network slicing is the prime capability of 5G, where different slices can be utilized for different purposes. Therefore, the network operators can utilize their resources for the users. Machine Learning (ML) or Deep Learning (DL) approach is recently used to address the network issues. Efficient 5G network slicing using ML or DL can provide an effective network. An endeavour has been made to propose an effective 5G network slicing model by applying different ML and DL algorithms. All the methods are adopted in developing the model by data collection, analysis, processing and finally applying the algorithm on the processed dataset. Later the appropriate classifier is determined for the model subjected to accuracy assessment. The dataset collected for use in the research work focuses on type of uses, equipment, technology, day time, duration, guaranteed bit rate (GBR), rate of packet loss, delay budget of packet and slice. The five DL algorithms used are CNN, RNN, LSTM, Bi-LSTM, CNN-LSTM and the four ML algorithms used are XGBoost, RF, NB, SVM. Indeed, among these algorithms, the RNN algorithm has been able to achieve maximum accuracy. The outcome of the research revealed that the suggested model could have an impact on the allocation of precise 5G network slicing.