Network Function Virtualization (NFV) is changing the way we implement the network functions from expensive hardware to software middleboxes, called Virtual Network Functions (VNFs). Flows always request to be processed by several middleboxes in a specific order, which is known as a service chain. Most researches study the middlebox placement problemand few of them pay attention to the flow scheduling of a deployed service chain, resulting in poor control of flow completion times. However, the flow completion time is an extreme metric to evaluate the performance of a network. Therefore, we focus on the service chain scheduling problem. We aim to minimize the flow completion time in two aspects:the longest completion time (makespan) and the average completion time. First, a transmission and processing delay model is proposed to formulate the communication latency behaviour of flows being processed by middleboxes. When there are only two middleboxes in theservice chain, we propose one optimal solution for each aspect, respectively. For a service chain with an arbitrary length, we prove the NP-hardness of our problem in both aspects and two corresponding heuristic algorithms are designed, which are extended from ourproposed optimal solutions for a service chain with a length of two. Real testbed experiments and extensive simulations are conducted to evaluate the performance of our proposed algorithms in various scenarios.

中文翻译：

---

基于 NFV 的网络中服务链处理的流程调度


网络功能虚拟化 (NFV) 正在改变我们实现网络功能的方式，从昂贵的硬件到软件中间盒，称为虚拟网络功能 (VNF)。流总是请求按特定顺序由多个中间件处理，这称为服务链。大多数研究研究中间盒放置问题，但很少关注已部署服务链的流量调度，导致流量完成时间控制不佳。然而，流程完成时间是评估网络性能的极端指标。因此，我们重点关注服务链调度问题。我们的目标是在两个方面最小化流程完成时间：最长完成时间（makespan）和平均完成时间。首先，提出了传输和处理延迟模型来制定中间盒处理的流的通信延迟行为。当服务链中只有两个中间盒时，我们分别针对每个方面提出一个最优解决方案。对于任意长度的服务链，我们在两个方面证明了问题的 NP 难度，并设计了两种相应的启发式算法，它们是从我们提出的长度为 2 的服务链的最优解决方案扩展而来的。进行真实的测试台实验和广泛的模拟来评估我们提出的算法在各种场景下的性能。