Machine learning-driven service function chain placement and scaling in MEC-enabled 5G networks

5G mobile network technology promises to deliver unprecedented ultra-low latency and high data rates, paving the way for many novel applications and services. Network Function Virtualization (NFV) and Multi-access Edge Computing (MEC) are two of the technologies that are expected to play a pivotal role in 5G to achieve ambitious Quality of Service requirements of such applications. While NFV provides flexibility by enabling network functions to be dynamically deployed and inter-connected to realize Service Function Chains (SFC), MEC brings the computing capability to the edges of the mobile network thus reducing latency and alleviating the transport network load. However, adequate mechanisms are needed to meet the dynamically changing network service demands, to optimally utilize the network resources while, at the same time, making sure that the end-to-end latency requirement of services is always satisfied. In this work, we first propose machine learning models, in particular neural-networks, that can perform auto-scaling by predicting the required number of virtual network function instances based on the traffic demand, using the traffic traces collected over a real-operator commercial network. We then employ Integer Linear Programming (ILP) techniques to formulate and solve a joint user association and SFC placement problem, where each SFC represents a service requested by a user with end-to-end latency and data rate requirements. Finally, we propose a heuristic to address the scalability concern of the ILP model.