Towards Optimal Parallelism-Aware Service Chaining and Embedding

Emerging 5G technologies can significantly reduce end-to-end service latency for applications requiring strict quality of (QoS). With network function virtualization (NFV), to complete a client’s request from those applications, the data sequentially go through multiple functions (SFs) processing/analysis but introduce additional processing delay. To delay serially-running SFs, parallelism (NFP) that allows SFs run in parallel is introduced. In this work, we study how apply NFP into SF chaining and embedding process such latency, including propagation delays, be jointly minimized. We novel augmented graph address relationship constraint among required SFs. Considering constraints, propose problem called parallelism-aware (PSFCE). For problem, near-optimal maximum block gain (MPBG) first optimization algorithm when computing resources at each physical node are enough host When limited, logarithm-approximate algorithm, deployment (PSFD), optimize delays. conduct extensive simulations on scenarios evaluate performances our schemes. Accordingly, find (i) MPBG near-optimal, (ii) largely depends small networks impacted more by large networks, (iii) PSFD outperforms schemes directly extended existing works regarding latency.