Abstract
Software-defined networking (SDN) has become one of the most promising paradigms to manage large scale networks. Distributing the SDN control proved its performance in terms of resiliency and scalability. However, the choice of the number of controllers to use remains problematic. A large number of controllers may be oversized inducing an overhead in the investment cost and the synchronization cost in terms of delay and traffic load. However, a small number of controllers may be insufficient to achieve the objective of the distributed approach. So, the number of used controllers should be tuned in function of the traffic charge and application requirements. In this paper, we present an intelligent and resizable control plane for software defined vehicular network architecture, where SDN capabilities coupled with deep reinforcement learning (DRL) allow achieving better QoS for vehicular applications. Interacting with SDVN, DRL agent decides the optimal number of distributed controllers to deploy according to the network environment (number of vehicles, load, speed etc.). To the best of our knowledge, this is the first work that adjusts the number of controllers by learning from the vehicular environment dynamicity. Experimental results proved that our proposed system outperforms static distributed SDVN architecture in terms of end-to-end delay and packet loss.
Highlights
Network softwarization is a key trend of current network evolution
We propose a Deep Reinforcement Learning (DRL) approach that learns from the vehicular network environment and decides the optimal number of controllers
The sudden fall in delay is the result of IRCP agent intervention when it decides to add a second controller around the sixth minute as described in figure10
Summary
Network softwarization is a key trend of current network evolution. The aim of network programmability and virtualization technologies, known as Software Defined Networks (SDN), is to offer more flexibility, scalability, and reliability making in turn the network services deployment faster and cheaper. Even if the control plane is physically distributed, its operation remains logically centralized since the controllers exchange reports on their corresponding domains to have a global state of the whole network and act as a single controller This issue can have a negative impact on delay-sensitive vehicular applications especially road-safety services. We propose an Intelligent and Resizable Control Plane for Software Defined Vehicular Network (IRCP-SDVN) which consists in adjusting the number of the distributed controllers according to the real traffic load of the vehicular network. The proposed DRL agent learns vehicles density and speed from the vehicular network and predicts the efficient number of controllers based on a reward function which is a compromise between responsiveness (end-to-end delay) and reliability (packet loss) and taking into account the vehicular applications stringency in terms of QoS.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
