Software defined optical networks to exploring machine- learning-based control plane intrusion detection techniques

In this paper software defined optical networks (SDON), the centralized control plane may encounter numerous intrusion threatens which compromise the security level of provisioned services. In this current research paper, the issue of control plane security is studied and two machine-learning-based control plane intrusion detection techniques are proposed for SDON with properly selected features such as bandwidth, route length, In this paper, with the coordination of SDON and cloud platform, a multi-domain SDON architecture based on cloud control plane has been proposed, which is composed of data centers with database (DB), path computation element (PCE), SDON controller and orchestrator. In addition, the structure of the multidomain SDON orchestrator and Open Flow-enabled optical node are proposed to realize the combination of centralized and distributed effective management and control platform. As the focus of network security, Intrusion Detection Systems (IDS) are usually deployed separately without collaboration. They are also unable to detect novel attacks with limited intelligent abilities, which are hard to meet the needs of software defined 5G.