Energy efficient and delay aware deployment of parallelized service function chains in NFV-based networks

Abstract

Network Functions Virtualization (NFV) replaces traditional hardware-based network equipment and middleboxes with flexible Virtualized Network Functions (VNFs) in order to reduce costs and improve agility and scalability. The VNFs are logically arranged in a specific sequence to form a Service Function Chain (SFC) which ensures that the traffic is processed according to the desired service requirements. However, the inherent length of SFCs leads to an undesirable increase in end-to-end delay experienced by the packets. Parallelized SFC (PSFC) addresses this problem by trying to allow multiple VNFs of the SFC to process packets in parallel by co-locating parallelizable VNFs on the same server. The energy-efficient deployment of PSFCs while considering the impact of contention for the shared resources on the server is unexplored in the literature. Hence, in this work, we formulate the PSFC deployment problem as an Integer Linear Program (ILP) that minimizes energy consumption while considering the impact of shared resource contentions without violating end-to-delay constraints. Since the ILP is NP-hard, we also propose a heuristic scheme named EPSFC, which provides flexible resource allocation-based deployment that minimizes the total energy consumption and ensures end-to-end delay requirements while considering the effects of shared resource contentions on the end-to-end delay. The effectiveness of EPSFC is evaluated through extensive simulations, and the results show a significant reduction in energy consumption while improving the PSFC acceptance ratio as compared to state-of-the-art schemes. © 2024 Elsevier B.V.