Improving Software Defined Cognitive and Secure Networking

Abstract

Traditional communication networks consist of large sets of vendor-specific manually configurable devices which are hardwired with specific control logic or algorithms. The resulting networks comprise distributed control plane architectures that are complex in nature, difficult to integrate and operate, and are least efficient in terms of resource usage. However, the rapid increase in data traffic requires an integrated use of diverse access technologies and autonomic network operations with increased efficiency. Therefore, the concepts of Software Defined Networking (SDN) are proposed that decouple the network control plane from the data-forwarding plane. The SDN control plane can integrate a diverse set of devices, and tune them at run-time through vendor-agnostic programmable Application Programming Interfaces (APIs). This thesis proposes software defined cognitive networking to enable intelligent use of network resources. Different radio access technologies, including cognitive radios, are integrated through a common control platform to increase the overall network performance. The architectural framework of software defined cognitive networking is presented alongside the experimental performance evaluation. Since SDN enables applications to change the network behavior and centralizes the network control plane to oversee the whole network, it is highly important to investigate security of SDNs. Therefore, this thesis finds potential security vulnerabilities in SDN, studies proposed security platforms and architectures for those vulnerabilities, and presents future directions for unresolved security vulnerabilities. Furthermore, this thesis also investigates the potential security challenges and their solutions for the enabling technologies of 5G, such as SDN, cloud technologies, and virtual network functions, and provides key insights into increasing the security of 5G networks.