Applying Smart Security Model to Protect the Client Services from the Threats of the Optical Network

Abstract

The paper discusses the role of the artificial intelligence and the centralized controller in the protection of the client signals from any wiretapping or loosing over the optical network. The physical layer of the Optical Transport Network (OTN) is the weakest layer in the network as anyone can access the optical cables from any location and states his attack. To overcome this thread a security layer is proposed to be added during the mapping processes of OTN frames. The automatic detection of any intrusion is done by monitoring the variations of the optical signal to noise ratio (OSNR) by using intelligent software-defined networks (SDN). For the first time the paper shows the role of the machine learning (ML) techniques in the multi-failure restorations of the optical transport network, and a new model is introduced by slicing the multi-domains to 3 layers to fit the needs of 5G at the same time all these domains are managed by only one centralized intelligent controller. The results show that using intelligent techniques such as artificial intelligence in the provisioning of optical transport network could improve the multi-failure restoration from 25% to 100%, the revenue from some OTN domains could be increased by 50%, the switching time could be enhanced by 50%, the latency could be reduced from 27 msec to 742 musec, and it will take many years to figure out the right keys to perform the decryption process from any intruder.