The wide variety of smart embedded computing devices and their increasing number of applications in our daily life have created new opportunities to acquire knowledge from the physical world anytime and anywhere,which is envisioned as the “Internet of Things” (IoT).Since a huge number of heterogeneous resources are brought into IoT,one of the main challenges is how to efficiently manage the increasing complexity of IoT in a scalable,flexible,and autonomic way.Furthermore,the emerging IoT applications will require collaborations among loosely coupled devices,which may reside in various locations of the Internet.In this paper,we propose a new IoT network management architecture based on cognitive network management technology and Service-Oriented Architecture to provide effective and efficient network management of IoT. The wide variety of smart embedded computing devices and their increasing number of applications in our daily life have created new opportunities to acquire knowledge from the physical world anytime and anywhere, which is envisioned as the “Internet of Things” (IoT) .Since a huge number of heterogeneous resources are brought into IoT, one of the main challenges is how to efficiently manage the increasing complexity of IoT in a scalable, flexible, and autonomic way. Future and the emerging IoT applications will require collaborations among loosely coupled devices, which may reside in various locations of the Internet. This paper, we propose a new IoT network management architecture based on cognitive network management technology and Service-Oriented Architecture to provide effective and efficient network management of IoT.