The digitalisation of industries and the increased need for better internet and mobile networks have given rise to several innovations. One of these is network slicing. It has garnered attention as an enabling technology for 5G networks, allowing for multiple logical network instances on the same physical network, which can be formed or combined depending on the users’ needs. However, there is not enough research on the technologies needed for characterising and predicting traffic patterns in real-time so implementation of network slicing lacks feasibility. What is needed is information on service-level mobile traffic, traffic characteristics in 5G services, traffic correlation, and inter-service correlations. The EU-funded CORRELATION project will fill this knowledge gap and enable the optimal use of proactive network slicing.
Network slicing is a key enabling technology for the 5th generation (5G) and beyond mobile networks. Network slicing allows the creation of multiple logical network instances on the same underlying physical network. Slices can then be formed or combined on-demand, with parameters optimized according to various service requirements so as to meet the users’ instant requests for specific mobile services. Hence, the performance of network slicing heavily depends on characterizing and predicting the spatial-temporal traffic patterns for individual services in near real-time.
Research on characterization and prediction for service-level mobile traffic is still in nascence. Firstly, the traffic characteristics and predicting methods of individual services, especially the 5G services, have not been studied adequately. Secondly, traffic correlation among different services and the reasons behind it have not been well studied. Thirdly, inter-service correlations have not been well exploited in service-level mobile traffic prediction.
In this project, we will address these gaps. Firstly, we will study the spatial-temporal characteristics of service-level traffic patterns at multi-scales, based on which, we will investigate the traffic predicting frameworks for individual services. Secondly, for the first time, we will investigate the traffic correlation among different services and try to discover the underlying reasons by analyzing the service usage profiles of different user groups. Finally, based on inter-service correlations, we will investigate whether we can improve service-level traffic prediction accuracy and whether we could execute prediction for diverse services according to the historical records of only a few key services.
The success of the CORRELATION project will make proactive network slicing possible, which will then drive proactive network optimisation for 5G and beyond mobile networks.