پروتکل های مبتنی بر پیش بینی برای شبکه های ادهاک خودرویی: نظرسنجی و طبقه بندی Prediction-based protocols for vehicular Ad Hoc Networks: Survey and taxonomy

1. Introduction Vehicular Ad Hoc Networks (VANETs) is a subclass of Mobile Ad Hoc Networks (MANETs) and the general characteristics of VANETs are typically inherited from MANETs in terms of lack of infrastructure, self-management and shared transmission media [1]. However, VANETs exhibit plenty of unique characteristics and operate in a challenging communications environment, which create diverse considerable challenges to develop efficient vehicular communication protocols [2]. For instance, the high speed of the vehicles and the large scale of the network lead to dynamic topology. Consequently, the rapid and continuous changing topology causes frequent disconnections of the communication links, which results in an increased overhead of the communication protocols [3]. From another perspective, the future movements of the vehicles in VANETs are predictable due to the constraints of urban layout, road geometry, and traffic conditions [4-5]. Hence, accurate prediction of the vehicles future movements could play a crucial role for both building efficient vehicular communication protocols and enhancing the vehicular transportation systems. Predicting the vehicles future movements is defined as ―the estimation of their future locations, trajectories and the time required to reach their destinations‖, which requires precise analysis of their mobility characteristics [6]. In the literature, numerous prediction-based protocols were proposed to improve the efficiency, reliability and robustness of vehicular communication networks. Fig. 1 shows the number of publications between 2006 and 2016 in relevant scientific sources (IEEE, ACM, Springer, and Science Direct). As shown, the noticeable increase of the number of publications in the last decade emphasize the importance of studying the various prediction objectives and applications of those protocols.