Manage and Evaluate the Performance of the End-to-End 5G Inter/Intra Slicing using Machine Learning in a Sustainable Environment

The 3G Partnership Project (3GPP) defined network slicing as a set of resources that could be scaled up and down to cover users' requirements. Machine learning and network slicing will be used together to manage and optimize the resources efficiently. In this research, a set of slices is implemented over the 5G networks to provide an efficient service to the end-user using softwarization and virtualization technologies. In the proposed prototype, the end-user connected to more than eight inter and intra-slices according to the demands. Traffic is generated over multiple scenarios then End-to-End slicing was analyzed after generating real-time traffic over the 5G networks and the features extracted from the traffic based on the flow behaviors. A set of elements selected from the datasets according to machine learning behaviours. From the first and second datasets, only five out of seven features will be selected. Then, seven out of nine features will be selected from the third dataset. Machine learning is applied to our datasets using MATLAB. After that, the best model is chosen to train and predict the slices in less CPU usage and less training time to reduce the computational power in future networks to build a sustainable environment. Furthermore, regression application is used to predict the slice type on the third dataset with the minimum squared error.