Mobile-aware service function chain migration in cloud-fog computing
Mobile-aware service function chain migration in cloud-fog computing
复制标题
DOI：
10.1016/j.future.2019.02.031
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
Dongcheng Zhao;Gang Sun;D. Liao;Shizhong Xu;Victor Chang
中科院分区：
文献类型：
--
作者：
Dongcheng Zhao;Gang Sun;D. Liao;Shizhong Xu;Victor Chang
网络功能虚拟化（NFV）为共享物理网络资源提供了良好的范例。由特定顺序的虚拟网络功能（VNF）组成的服务功能链（SFC）的部署问题已成为研究的焦点。此外，为了解决集中式云计算面临的挑战，研究人员提出了分布式雾计算。当移动用户在不同的基于雾的无线接入网络之间移动时，必须迁移SFC。因此，在本文中，我们研究了云雾计算环境中用户移动引起的SFC迁移/重新映射问题。我们首先将 SFC 的迁移问题建模为整数线性程序；然后提出两种SFC迁移策略：最小VNF数量迁移策略和两步迁移策略，以减少SFC的重新配置成本、迁移时间和停机时间，提高SFC的重映射成功率。我们设计了一个两步迁移算法来迁移SFC。我们使用云雾计算环境来评估我们提出的算法。我们提出的算法的重新配置成本、重新映射成功率、迁移时间和停机时间都比基准算法更优异。
Network Function Virtualization (NFV) provides a good paradigm for sharing the resources of the physical network. The deployment problem of Service Function Chains (SFCs) composed of a specific order of Virtual Network Functions (VNFs) has become the focus of research. Moreover, to solve the facing challenges of the centralized cloud computing, the researchers have proposed the distributed fog computing. When the mobile user moves among different fog-based radio access networks, the SFC must be migrated. Therefore, in the paper, we research the problem of SFCs migration/remapping caused by the user movement in cloud–fog computing environments. We firstly model the migration problem of SFCs as an integer linear program; then we propose two SFC migration strategies: the minimum number of VNFs migration strategy and the two-step migration strategy, to reduce the reconfiguration cost, the migration time and downtime of SFCs and improve the remapping success ratio of SFCs; and we have designed a two-step migration algorithm to migrate SFCs. We use the cloud–fog computing environment to evaluate our proposed algorithms. The reconfiguration cost, the remapping success ratio, the migration time and the downtime of our proposed algorithms are more excellent than that of benchmark algorithm.