摘要：Software Defined Network (SDN) realizes the separation of control functions from data planes and network programming. It lays the foundation for centralized and refined control and has greater advantages over traditional networks. At present, the research on SDN mainly focuses on wired network and data center, while software definition is proposed in some studies, but only in the stages of models and concepts. According to the characteristics of wireless sensor networks, this paper takes anomaly intrusion detection as the main research content. The sensor network is defined based on OpenFlow software combined with SDN, and intrusion detection technology is studies on the basis of this. It is easier for the system to control the network and its resources in SDN architecture. The Network traffic shows self-similarity in large time scale. In this paper, it can distinguish between the normal situation and the attack by observing the change of the self-similarity coefficient of the network, so as to realize the intrusion detection.
