Intelligent Traffic Engineering in Software-Defined Vehicular Networking Based on Multi-Path Routing

Abstract

This paper addresses traffic engineering (TE) issues in software-defined vehicular networking (SDVN). A brief analysis of the features of SDVN, which improves the efficiency of TE in SDVN, is presented. The feasibility of using multi-path routing with TE is substantiated. A procedure and an example of the formation of multiple routes based on a modified wave routing algorithm are given. Considering the features of the SDVN technology, a modified TE method is proposed, which reduces both the time complexity of forming multiple paths and the path reconfiguration time. The dynamic path reconfiguration algorithm is presented. INDEX TERMS Intelligent transportation system (ITS), multi-path routing, software-defined network, traffic engineering (TE). I. INTRODUCTION The ever-growing number of vehicles on the roads makes the vehicular ad-hoc network (VANET) an important research topic in the field of automotive and wireless technologies. VANETs are considered as a subclass of classic mobile ad hoc networks (MANETs) [1]-[3]. Where vehicles play the role of mobile nodes of the VANETs. That have embedded advanced equipment on-board, traveling on restricted routes (i.e., roads, streets and lanes), and communicating with each other for information exchange using vehicle-to-vehicle (V2V) communication protocols, and also between vehicles and roadside units (RSU) installed on the side of the roads (i.e., wireless and cellular network infrastructure), to form a link between a Vehicle-to-Infrastructure (V2I). Compared to static or low-speed moving nodes in a traditional wireless network, vehicles move faster and more unpredictably, resulting in frequent changes to VANET network settings [4]-[7]. This places higher demands on routing protocols in VANET networks. Most well-known routing methods are not effective for VANET networks [8]-[11]. In this regard, the urgent The associate editor coordinating the review of this manuscript and approving it for publication was Chao Chen.

Systematic Literature Review of AI/ML Techniques Applied to VANET Routing

“…One candidate ( [10]) was excluded based on being a secondary study. Four more candidates ( [23], [24], [25] and [26]) were excluded, with two focusing on security challenges, one concerns vehicle routing instead of packet routing, and a fourth does not employing any AI/ML technique. The papers [27], [28], [29], [30] and [31] were included as the start set for the snowballing.…”

QIBMRMN: Design of a Q-Learning based Iterative sleep-scheduling & hybrid Bioinspired Multipath Routing model for Multimedia Networks

“…This is due to the fact that in a highly dynamic environment where variables like wireless channel conditions, traffic, and energy restrictions are always changing, effective decision-making is crucial. With WMSNs, the Software Defined Networks (SDN) [35,36,37,38] is a dynamic optimization approach that is effective. Node radio transmission often uses the bulk of the network's power in a WMSN [39].…”