Software Defined Network (SDN) is the next generation network that decouples the control plane from the data plane of forwarding devices by utilizing the OpenFlow protocol as a communication link between the data plane and the control plane. However, there are some security issues might be in actions on SDN that the attackers can take control over the SDN control plane. Thus, traffic measurement is a fundamental technique of protecting SDN against the high-security threats such as DDoS, heavy hitter, superspreader as well as live video calling, QoS control, high bandwidth requirement, resource management are also inevitable in SDN/Software Defined Cellular Network (SDCN). In such a scenario, we survey SDN traffic measurement solutions, in order to assess how these solutions can make a secured, efficient and robust SDN/SDCN architecture. In this paper, various types of SDN traffic measurement solutions have been categorized based on network applications behaviour. Furthermore, we find out the challenges related to SDN/SDCN traffic measurement and future scope of research, which will guide to design and develop more advanced traffic measurement solutions for a scalable, heterogeneous, hierarchical and widely deployed SDN/SDCN in future prospects. More in details, we list out kinds of practical machine learning (ML) approaches to analyze how we can make improvement in the traffic measurement performances. We conclude that using ML in SDN traffic measurement solutions will give benefit to get secured SDN/SDCN network in complementary ways.
翻译:软件定义网络(SDN)是下一代网络,它利用OpenFlow协议作为数据平面与控制平面之间的通信链接,将控制平面与传输设备的数据平面分离出来,利用OpenFlow协议作为数据平面与控制平面之间的通信链接。然而,在SDN的行动中,可能存在一些安全问题,攻击者可以控制SDN控制平面。因此,交通量测量是保护SDN免遭高安全威胁的基本方法,如DDoS、重击器、超级传播器以及现场视频呼叫、QOS控制、高带宽要求,资源管理也是SDN/Software定义的细胞网络(SDCN)中不可避免的。在这种情况下,我们调查SDN交通量度解决方案可能存在一些安全、高效和稳健的SDN/SDCN结构。在本文中,各种SDN的交通量度解决方案已经根据网络应用行为进行了分类。此外,我们发现与SDN/SDCN交通量度测量和未来研究范围有关的挑战,这将指导设计和开发更先进的CN交通量度解决方案,以便在SDMMADM(我们如何在SDMAD/广泛地改进SD/SDM的测量方法中,我们如何在SDM/SDM的改进未来改进了我们如何在SDMBBBBBM的改进的进度中,我们如何改进。