Software-Defined Networking (SDN) provides programmable, flexible and fine-grained traffic control capability, which paves the way for realizing dynamic and high-performance traffic measurement and traffic engineering. In the SDN paradigm, the traffic forwarding and measurement strategies are realized through flow tables stored in the Tenantry Content Addressable Memories (TCAM) of SDN switches. However, the number of TCAM entries in SDN switches is limited. In this paper, we aim to jointly optimize the Traffic Matrix Measurement (TMM) and Traffic Engineering (TE) process under the TCAM capacity and flow aggregation constraints in software-defined networks. We first formulate the joint optimization problem as a Mixed Integer Linear Programming (MILP) model. Then to get an initial traffic matrix for the joint optimization problem, we propose a simple flow rule generation strategy named Maximum Load Rule First (MLRF) to efficiently generate feasible flow rules, which are used to provide direct measurements for the traffic matrix measurement problem. At last, to solve the joint optimization efficiently, we propose two efficient heuristic algorithms named Traffic Matrix Measurement First (TMMF) and Traffic Engineering First (TEF), respectively. TMMF and TEF can generate feasible flow rules for realizing TMM and TE strategies. Our evaluations on real network topologies and traffic traces verify that by jointly optimizing the TMM and TE strategies, both TMMF and TEF can significantly improve TMM accuracy and TE objective (i.e., load balancing) with limited TCAM resource.

中文翻译：

---

软件定义网络在线流量矩阵测量与流量工程的联合优化

软件定义网络（SDN）提供可编程，灵活和细粒度的流量控制功能，为实现动态和高性能流量测量和流量工程铺平了道路。在SDN范例中，流量转发和测量策略是通过存储在SDN交换机的Tenantry Content Addressable Memories（TCAM）中的流表实现的。但是，SDN交换机中TCAM条目的数量是有限的。在本文中，我们旨在在软件定义的网络中，在TCAM容量和流聚合约束下，共同优化流量矩阵测量（TMM）和流量工程（TE）流程。我们首先将联合优化问题表述为混合整数线性规划（MILP）模型。然后获得联合优化问题的初始流量矩阵，我们提出了一种名为最大负载规则优先（MLRF）的简单流规则生成策略，以有效地生成可行的流规则，该规则用于为流量矩阵测量问题提供直接测量。最后，为了有效地解决联合优化问题，我们提出了两种有效的启发式算法，分别称为流量矩阵度量优先（TMMF）和流量工程优先（TEF）。TMMF和TEF可以生成可行的流规则，以实现TMM和TE策略。我们对真实网络拓扑和流量跟踪的评估证明，通过共同优化TMM和TE策略，TMMF和TEF都可以在TCAM资源有限的情况下显着提高TMM准确性和TE目标（即负载平衡）。