Design of Computing-Aware Traffic Steering Architecture for 5G Mobile User Plane

Abstract

One of the critical targets of the fifth generation (5G) mobile network is supporting low latency and high reliable services at the network edge servers. Multiple service instances of the same service can be deployed on different geographically distributed edge sites for high availability purposes. However, the dynamic changes over time in edge servers' computing capabilities and underlay infrastructure network quality might affect service performance. To avoid service performance degradation, an efficient computing-aware traffic steering (CATS) solution between different service instance locations is required. Multiple advanced traffic steering algorithms have been proposed in different existing 5G traffic steering works. However, no available works addressed the possible 5G architecture and procedure changes to convert these CATS algorithms' decisions into 5G mobile user plane routing paths. This work aims to cover this research gap. We propose enhancing the current 5G architecture by applying the Mobile User Plane Controller (MUP-C) concept and using anycast address for multi-instance services. We discuss three implementation options to apply these enhancement features to 5G architecture: CATS Application Function (AF) traffic influence method, CATS MUP-C dummy User Plane Function (UPF) method, and CATS MUP-C non-UPF method. We implemented and evaluated the performance of our solutions against a 3GPP standard dynamic edge discovery method, which can also be used to support CATS. The results showed that our solutions had better Protocol Data Unit (PDU) session setup procedure efficiency for CATS than the standard method by reducing the setup latency from 30% to 50%.