Towards a cognitive routing engine for software defined networks

Abstract

In Software Defined Networks (SDN), intensive traffic monitoring is used to optimize the Quality-of-Service (QoS) of the network paths which are selected. Thus, we introduce the use of the Cognitive Packet Network (CPN) algorithm to SDN in order to optimize the search for new high-QoS paths. We install the CPN algorithm in the Cognitive Routing Engine (CRE), a new application software for SDN, and show that with limited monitoring overhead we are able to determine the near-optimal paths for given QoS metrics that may be proposed by the end users. Measurements that we have conducted on an experimental replica of the GEANT network that our approach uses close to 10 times less monitoring data than conventional SDN, but that we are able to approach the optimal paths within 2%

A Manifesto for Future Generation Cloud Computing

“…Proposals have been made and tested regarding the design of smart energy-aware routing algorithms [93], but this area in general has received less attention compared to energy consumption and power efficiency of computing elements. With the advent of SDN, the global network awareness and centralised decision-making offered by SDN may provide a better opportunity for creating sustainable networks for Clouds [79]. This is perhaps one of the areas that will draw substantially more research efforts and innovation in the next decade.…”

Research and Innovation Action for the Security of the Internet of Things: The SerIoT Project

“…that will be both integrally connected with the core network components and centrally controlled, as well as that will have a transparent function within the network's total behaviour either it is active or passive. -To deliver the design and implement the corresponding prototype of smart SDN routers [13] for the dynamic (i) detection of suspicious/high risk paths, (ii) re-planning and (iii) re-scheduling of the routing paths of the transmitted information in IoT networks over secure and (per user-or per case-) preferable connections, supporting among others the interference of the human (i.e. semisupervised approach), when needed.…”

“…Smart network management of SDN [12,13] will be considered for anomaly detection and mitigation [32,39,40]. The smart flow controller will be based on the Cognitive Packet Network (CPN) [18] and its Random Neural Network [14,23] based learning algorithm.…”

Next Generation Internet of Things

“…Anomaly detection techniques based on local traffic characteristics (as dynamic changes in queue lengths) will be regularly probed by smart "cognitive packets" sent by the SDN controller and feeding the controller routing decisions. The controller will have the ability to detect suspicious and risky paths, and re-schedule the routing paths over secure, preferable connections according to secure aware routing, but also energy and Qality of Service (QoS) aware routing [71][72][73].…”

“…The concept is a combination of neuralnetworks-based routing and source routing. It was successfully applied in SDN network [71], and in the SerIoT project will be extended both in terms of data used as input for routing engine and of scale of the networks. Security data will be used as input for learning of RNN, along with QoS and energy usage data, to allow finding secure and efficient routes for every SDN flow.…”