The symbiosis of network virtualization and software-defined networking (SDN) enables an infrastructure provider (InP) to build various virtual software defined networks (vSDNs) over a shared substrate network (SNT). To handle a dynamic network environment, the InP may need to reconfigure the mapping schemes of vSDNs for a variety of reasons. Although previous studies have addressed how to calculate the new virtual network embedding (VNE) schemes for vSDN reconfiguration under different objectives, the transition to migrate vSDNs from their original VNE schemes to new ones is still under-explored. Hence, this article studies how to realize parallel and hitless vSDN reconfiguration, by leveraging the “make-before-break” scenario. We come up with a generic solution to optimize the transition to remap vSDNs to new VNE schemes, such that the remappings can be done in the parallel, hitless and resource-efficient manner, as long as the new VNE schemes are feasible. More specifically, our proposal is the multi-stage parallel vSDN reconfiguration based on maximal connected reconfigurable subgraph (MCRSG). To ensure the efficiency of our proposal, we formulate the optimization for selecting MCRSGs to reconfigure in each stage, and prove the $\mathcal {NP}$ -hardness of the problem. Then, we design an approximation algorithm based on Lagrangian relaxation to solve it time-efficiently. Extensive simulations verify that the proposed algorithm can obtain near-optimal solutions quickly. In addition to the algorithmic study, we also realize our multi-stage parallel vSDN reconfiguration in a practical NVH system, and demonstrate its performance in a real network testbed. Our experimental study identifies in what condition losing of packets during remapping would be inevitable, studies the tradeoff between reconfiguration latency and packet loss rate, and reveal an empirical method to adjust key parameters of our NVH system, for adapting to various network environments.

中文翻译：

---

在并行且无中断的vSDN重新配置上

网络虚拟化和软件定义网络（SDN）的共生使基础架构提供商（InP）可以在共享基础网络（SNT）上构建各种虚拟软件定义网络（vSDN）。为了处理动态网络环境，InP可能出于多种原因需要重新配置vSDN的映射方案。尽管先前的研究已经解决了如何在不同目标下为vSDN重新配置计算新的虚拟网络嵌入（VNE）方案，但是将vSDN从其原始VNE方案迁移到新方案的过渡仍处于探索阶段。因此，本文研究如何利用“先断后合”方案来实现并行且无中断的vSDN重新配置。我们提出了一个通用解决方案，以优化将vSDN重新映射到新的VNE方案的过渡，这样，只要新的VNE方案可行，重新映射就可以并行，无中断且节省资源的方式完成。更具体地说，我们的建议是基于最大连接可重配置子图（MCRSG）的多阶段并行vSDN重配置。为了确保我们提案的效率，我们制定了用于选择要在每个阶段进行重新配置的MCRSG的优化，并证明了 $ \ mathcal {NP} $ -问题的难度。然后，我们设计了一个基于拉格朗日松弛的近似算法，以高效地解决它。大量的仿真验证了所提算法能够快速获得近似最优解。除了进行算法研究之外，我们还可以在实际的NVH系统中实现多阶段并行vSDN重新配置，并在真实的网络测试平台中演示其性能。我们的实验研究确定了在重新映射期间丢失数据包的情况是不可避免的，研究了重新配置延迟和丢包率之间的折衷，并揭示了一种经验方法来调整我们的NVH系统的关键参数，以适应各种网络环境。