Software-Defined Networking has become an integral technology for large scale networks that require dynamic flow management. It separates the control function from data plane devices and centralizes it in a domain controller. However, only a limited number of switches can be managed by a single and centralized controller which introduces challenges such as scalability, reliability, and availability. Distributed controller architecture resolves these issues but also introduces new challenges of uneven load and traffic management across domains. As real-world networks have redundant links, hence a significant challenge is to distribute traffic flows on multiple paths, within a domain, and across multiple independent domains. The selection of ingress and egress switches becomes even more problematic if the intermediate domain is non-cooperative. In this work, we propose a Dynamically Optimized and Load-balanced Path for Inter-domain (DOLPHIN) communication system, a customized solution for different SDN controllers. It provides control beyond the virtual switch elements in intra and inter-domain communication and extends the range of programmability to wireless devices, such as the Internet of Things or vehicular networks. Extensive simulation results show that the traffic load is distributed evenly on multiple links connecting different domains. We model data center communication and 5G vehicular network communication to show that, by load balancing the flow completion times of the different types of network traffic can be significantly improved.

中文翻译：

---

DOLPHIN：用于域间 SDN 通信的动态优化和负载平衡路径


软件定义网络已成为需要动态流量管理的大规模网络的集成技术。它将控制功能与数据平面设备分离，并将其集中在域控制器中。然而，单个集中控制器只能管理有限数量的交换机，这带来了可扩展性、可靠性和可用性等挑战。分布式控制器架构解决了这些问题，但也带来了跨域负载和流量管理不均匀的新挑战。由于现实世界的网络具有冗余链路，因此一个重大挑战是在一个域内以及跨多个独立域的多个路径上分配流量。如果中间域不合作，入口和出口交换机的选择会变得更加成问题。在这项工作中，我们提出了一种动态优化和负载均衡的域间通信系统路径（DOLPHIN），这是针对不同 SDN 控制器的定制解决方案。它提供域内和域间通信中虚拟交换机元件之外的控制，并将可编程性范围扩展到无线设备，例如物联网或车辆网络。大量的仿真结果表明，流量负载均匀分布在连接不同域的多条链路上。我们对数据中心通信和 5G 车载网络通信进行建模，结果表明，通过负载均衡，可以显着改善不同类型网络流量的流量完成时间。