Algorithms Optimization for Intelligent IoV Applications

Introduction

Recently, Internet of vehicles (IoV) has become an emerging promising field of research due to the increasing number of vehicles each day. It is a branch of the internet of things (IoT) which deal with communication among vehicles (Mahmoud et al, 2012). IoV enables vehicles to send information among vehicles, road infrastructures, passengers, drivers, sensors and electric actuators through different communication media including IEEE 802.11p, vehicular cooperative media access control (VC-MAC), dynamic source routing (DSR), Ad hoc on demand distance vector (AODV), directional medium access control (DMAC) and general packet radio services (GPRS) (Amal et al, 2016). As know, that vehicular nodes are always in motion that causes the frequent changes in the network topology (Mahmoud et al,2014). These changes cause issues in IoV as scalability, dynamic topology changes and shortest path for routing.

The design of an effective application is a major challenge that should not be neglected in IoV, considering their special features and characteristics, such as high vehicle mobility and quick topology changes, which make the design and implementation of effective solutions for such networks a difficult task (Mayada et al,2018) (Nahla et al,2021). First, high mobility is the main factor distinguishing IoV from other networks. Vehicle speed varies according to road conditions and may be low or medium in urban areas and large on highways (Amal et al,2018). This speed variation has a direct impact on network stability and results in a dynamic network topology. Secondly, node density is not uniform but exhibits spatiotemporal variation. Typically, the density in urban areas is higher than in rural areas and depends on the time of day. Finally, network fragmentation generally occurs when vehicle density is low and irregular. Then, the vehicles move in disconnected isolated clusters, and therefore, end-to-end communication becomes difficult.

Generally, the focus on optimization in IoV applications is related to the importance of traffic accuracy and protection of information and entertainment network, as well as ensuring road safety when deploying the IoVs applications. According to what has been mentioned, IoV applications face a number of problems related to the reliability and consistency in the exchange of information between the vehicles and the appropriate decision-making to improve safety on the road (Mayada et al,2017). Artificial intelligence (AI) techniques provide appropriate and effective solutions to a number of the aforementioned problems, especially those related to decision-making in IoV systems. Recently, many studies have been presented that rely on the capabilities of AI and the use of its algorithms in various processes related to improving quality in IoV applications and services. Table 1 shows the summary of different optimization studies in IoV applications.

(Farhan et al, 2018), presented a method for using the metaheuristic dragonfly-based clustering algorithm (CAVDO) to optimize cluster-based packet route to create a stable IoV topology in a dynamic environment. The study is presented on the basis that the mobility aware dynamic transmission range algorithm (MA-DTR) algorithm is used with CAVDO to adapt the transmission range based on traffic density. A comparison of the proposed algorithm was also made with other algorithm such as the Ant Colony Improvement (ACO) and learning particle swarm optimization (LPSO). Through the analysis, it was found that the proposed algorithm has much better performance than ACO and LPSO as it provides the minimum number of clusters according to the current channel conditions, as it improves network availability and integrates the functions of the network infrastructure.

The study presented by (Ali et al, 2019), reviews two algorithms known as Energy Perceived QoE Optimization (PQO) and Store Perceived QoE Improvement (BQO) as their performance was compared, in addition to proposing a multimedia communication mechanism based on the two algorithms. Also, the researchers demonstrated a framework that improves QoE during IoV multimedia communication through mobile devices. Through the analysis, it was found that the proposed algorithms give a significant improvement in QoE, as they greatly assist in enabling applications during multimedia communication.