Artificial Intelligence Based Smart Routing in Software Defined Networks

In a non-static information exchange network,routing is an overly com-plex task to perform,which has to satisfy all the needs of the network.Software Defined Network(SDN)is the latest and widely used technology in the future communication networks,which would provide smart routing that is visible uni-versally.The various features of routing are supported by the information centric network,which minimizes the congestion in the dataflow in a network and pro-vides the content awareness through its mined mastery.Due to the advantages of the information centric network,the concepts of the information-centric net-work has been used in the paper to enable an optimal routing in the software-defined networks.Although there are many advantages in the information-centric network,there are some disadvantages due to the non-static communication prop-erties,which affects the routing in SDN.In this regard,artificial intelligence meth-odology has been used in the proposed approach to solve these difficulties.A detailed analysis has been conducted to map the content awareness with deep learning and deep reinforcement learning with routing.The novel aligned internet investigation technique has been proposed to process the deep reinforcement learning.The performance evaluation of the proposed systems has been con-ducted among various existing approaches and results in optimal load balancing,usage of the bandwidth,and maximization in the throughput of the network.

A Receiver-Forwarding Decision Scheme Based on Bayesian for NDN-VANET

Named Data Network(NDN) has caused wide concerns in VANET community because NDN uses a content-centric mechanism that naming content rather than the host. However, integrating NDN into VANET(NDN-VANET) also faces several challenges including consumer/provider mobile, broadcast storm problem and so on. In this paper, we propose a Bayesian-based Receiver Forwarding Decision(BRFD) scheme to mitigate the broadcast storm problem incurred by interest packets in NDN-VANET. In the BRFD, vehicles received an interest packet are required to make forwarding decisions based on Bayesian decision theory according to current network conditions obtained by neighbor interaction. However, the receiver-forwarding decision in BRFD can also cause a conflict issue because multiple vehicles forward copies of the same packet at the same time. So a back-off mechanism is introduced in BRFD. Experimental results show that the BRFD algorithm has better performance in several aspects in contrast to probability-based forwarding scheme and "bread crumb" routing.

SDICN: A Software Defined Deployable Framework of Information Centric Networking

the Information-Centric Networking(ICN) paradigm is proved to have the advantages of decreasing data delivery latency, enhancing user mobility, etc. However, current implementations of ICN require changing the infrastructure of Internet, which hinders its deployment and development. Meanwhile, Software Defined Networking(SDN) emerges as a viable solution to facilitate the deployment of new network paradigm without disrupting production traffic by decoupling the control plane from data forwarding plane. In this paper, the essential properties which reflect ICN working principles are summarized, and a framework called SDICN is designed in accordance to the SDN philosophy. The algorithmic frameworks of SDICN which can satisfy the essential properties are designed based on the programmability and virtualization functions of SDN. Based on Open Flow and data center technology, a prototype of SDICN is implemented. By comparing the performance with the CCNx, the SDICN is proved to be feasibility and availability.