D2A: Operating a Service Function Chain Platform With Data-Driven Scheduling Policies

Realizing Service Function Chaining with a micro-service-based architecture results in an increased number of computationally cheap Virtual Network Functions (VNFs). Pinning cheap VNFs to dedicated CPU cores can waste resources since not every VNF fully utilizes its core. Thus, cheap VNFs should share CPU cores to improve resource utilization. However, sharing cores can result in degraded performance due to interference between VNFs, even in mildly loaded scenarios. We propose
D₂A
, a system that combines Neural Combinatorial Optimization, Machine Learning (ML)-based Digital Twins (DTs), and Game Theory to optimize VNF assignments. Measurements in a testbed show that
D₂A
increases throughput by up to 46% and reduces latency by up to 93%, compared to three baseline algorithms. Using an ML-based DT to model VNF interference increases throughput by up to 11%, and reduces latency by up to 90% compared to an analytical model of the system.