Network function Virtualization (NFV) and Mobile Edge Computing (MEC) are promising 5G technologies to support resource-demanding mobile applications. In NFV, one must process the service function chain (SFC) in which a set of network functions must be executed in a specific order. Moreover, the MEC technology enables computation offloading of service requests from mobile users to remote servers to potentially reduce energy consumption and processing delay for the mobile application. This paper considers the optimization of the computation offloading, resource allocation, and SFC placement in the multi-site MEC system. Our design objective is to minimize the weighted normalized energy consumption and computing cost subject to the maximum tolerable delay constraint. To solve the underlying mixed integer and non-linear optimization problem, we employ the decomposition approach where we iteratively optimize the computation offloading, SFC placement and computing resource allocation to obtain an efficient solution. Numerical results show the impacts of different parameters on the system performance and the superior performance of the proposed algorithm compared to benchmarking algorithms.

中文翻译：

---

多站点 MEC 系统的联合计算卸载、SFC 放置和资源分配

网络功能虚拟化 (NFV) 和移动边缘计算 (MEC) 是有前途的 5G 技术，可支持对资源要求高的移动应用程序。在 NFV 中，必须处理服务功能链 (SFC)，其中必须以特定顺序执行一组网络功能。此外，MEC 技术可以将移动用户的服务请求计算卸载到远程服务器，以潜在地减少移动应用程序的能耗和处理延迟。本文考虑了多站点 MEC 系统中计算卸载、资源分配和 SFC 放置的优化。我们的设计目标是在最大可容忍延迟约束下最小化加权归一化能耗和计算成本。为了解决底层混合整数和非线性优化问题，我们采用分解方法，迭代优化计算卸载、SFC 放置和计算资源分配，以获得有效的解决方案。数值结果显示了不同参数对系统性能的影响以及与基准算法相比所提出算法的优越性能。