Header menu link for other important links
SeScR: SDN-Enabled Spectral Clustering-Based Optimized Routing Using Deep Learning in VANET Environment
A. Nahar,
Published in Institute of Electrical and Electronics Engineers Inc.
In recent years, integration of clustering architecture with software-defined networking (SDN) has emerged as is the crucial enabler for next-generation intelligent transportation services (ITS). This paper proposes a spectral clustering technique along with the deep deterministic policy gradient (DDPG) algorithm using hybrid SDN architecture, called SeScR to enhance cluster stability and route selection method. The spectral clustering is used to overcome the arbitrary node distribution of vehicular ad-hoc networks (VANETs) and provide a flexible clustering using eigenvalues of graph laplacian. Moreover, the DDPG algorithm addresses the continuous address space of VANETs and provides an actor-critic architecture for optimal routing decisions. The experimental results demonstrate that the proposed scheme improves path selection and load balancing with better performance in terms of low average transmission delay up to 15%, throughput up to 18-22%, and low computation overhead 10% compared to the existing state-of-the-art protocols used in this research. © 2020 IEEE.
About the journal
JournalData powered by Typeset2020 IEEE 19th International Symposium on Network Computing and Applications, NCA 2020
PublisherData powered by TypesetInstitute of Electrical and Electronics Engineers Inc.
Open AccessNo