Software-Defined Vehicular Networks (SDVNs) revolutionize modern transportation by enabling dynamic and adaptable communication infrastructures. However, accurately capturing the dynamic communication patterns in vehicular networks, characterized by intricate spatio-temporal dynamics, remains a challenge with traditional graph-based models. Hypergraphs, due to their ability to represent multi-way relationships, provide a more nuanced representation of these dynamics. Building on this hypergraph foundation, we introduce a novel hypergraph-based routing algorithm. We jointly train a model that incorporates Convolutional Neural Networks (CNN) and Gated Recurrent Units (GRU) using a Deep Deterministic Policy Gradient (DDPG) approach. This model carefully extracts spatial and temporal traffic matrices, capturing elements such as location, time, velocity, inter-dependencies, and distance. An integrated attention mechanism refines these matrices, ensuring precision in capturing vehicular dynamics. The culmination of these components results in routing decisions that are both responsive and anticipatory. Through detailed empirical experiments using a testbed, simulations with OMNeT++, and theoretical assessments grounded in real-world datasets, we demonstrate the distinct advantages of our methodology. Furthermore, when benchmarked against existing solutions, our technique performs better in model interpretability, delay minimization, rapid convergence, reducing complexity, and minimizing memory footprint.

Deep learning (DL) based cognitive radio networks (CRN) serve as a potential solution to the dilemma posed by spectrum limits and the rising demand for vehicular ad hoc networks (VANETs) routing services. However, the unpre-dictability of VANET restricts the generalization potential of DL-based techniques. Variations in traffic volume, road topologies, and radio propagation characteristics affect the training data significantly. Therefore, in this paper, we propose RF -CVN, a recurrent reinforcement learning (RRL) technique to sense the spectrum and discover a trustworthy path between the source and the destination using belief transmission (i.e., channel conditions, interference levels, and vehicle locations). We first devise a deep recurrent Q network for a multi-channel access scheme for unlicensed users to use available channels. The RRL allows the Q function to learn hidden states in partial observation or highly time-correlated network sensing cases. Later, the trust values are used to gain a more nuanced understanding of the network state, thereby enhancing the efficiency and reliability of the routing process. In this work, we argue that trust should be an integral part of the routing process and, therefore, design a trust mechanism to select a path. The trust mechanism aims to detect those spectrums that over-utilize or under-utilize their channel capacity during the local training. The outcomes of our simulations indicate that our RF -CVN routing method outperforms traditional routing systems based on cognitive radio-based vehicular ad hoc networks in terms of network performance and spectrum sensing efficiency.

The integration of software-defined networking (SDN) and cloud radio access networks (CRANs) into vehicular ad hoc networks (VANETs) presents intricate challenges to achieving stringent service level objectives (SLOs). These objectives include optimizing data flow and resource management, achieving low latency and rapid response times, and ensuring network resilience under fluctuating conditions. Traditional load balancing and clustering approaches, designed for more static environments, fall short in the dynamic and variable context of VANETs. This necessitates a paradigm shift towards more adaptive and robust strategies to meet these advanced SLOs reliably. This paper proposes a software-defined vehicular fog computing (SDFC) framework that refines resource allocation in VANETs. Our SDFC framework utilizes an intelligent controller placement that strategically positions decision-making entities within the network to optimize data flow and resource distribution. This placement is governed by a dynamic clustering algorithm that responds to variable network conditions, an advancement over the static mappings used by traditional methods. By incorporating parallel processing principles, the framework ensures that computational tasks are distributed effectively across network nodes, reducing bottlenecks and enhancing overall network agility. Empirical evaluations (testbed) and simulation results of our framework indicate a substantial increase in network efficiency: a 28% improvement in average response time, a 23% decrease in network latency, and a 25% faster convergence to optimal resource distribution compared to state-of-the-art methods. These improvements testify to the framework's ability to underscore its potential to refine operational efficacy within VANETs.

This paper investigates the feasibility of cache content prediction and coherence in the context of secure communication and search. We introduce a distributed multi-tier mobility-assisted edge intelligence based caching framework for the Internet of Vehicles (IoVs), called CacheIn. The proposed framework leverages user preferences, data correlations, and mobility information to prefetch content to the IoV edge. To enable content management based on mobility, we propose a novel Normalized Hidden Markov Model (NM-HMM) that anticipates a vehicle's future position. The framework also utilizes a mobility-aware collaborative filtering-based federated learning (FL) technique to enhance cache hit, reduce latency, and protect user privacy. To ensure secure cross-domain data sharing and mitigate the risk of data breaches, we also propose an extended ciphertext policy attribute-based encryption (ECP-ABE) mechanism. Compared to content popularity-based caching schemes, CacheIn achieves up to 80%, 38%, and 55% improvement in cache hit ratio for different cache sizes, vehicle densities, and cache lookup scenarios. Moreover, our approach reduces key generation, encryption, and decryption times by 35 %.

The performance of vehicular edge computing (VEC) depends on the effective optimization of task offloading. However, uneven distribution of vehicular traffic, rapidly changing network conditions, and stochastic nature of vehicular networks motivate us to innovate approaches to efficient resource management while maintaining system's stability. To address these challenges, we propose a novel queue length-based stochastic task migration strategy that leverages model predictive control (MPC) and Lyapunov optimization techniques. Our approach employs the queue length at the edge node as the criterion for offloading decisions. The MPC controller dynamically allocates the processing power and bandwidth resources to vehicles based on their current requirements, facilitating prompt offloading decisions. The Lyapunov optimization ensures long-term system stability. Our method also incorporates dynamic request selection from multi-dimensional queuing load optimization and ensures fair and efficient load distribution, thereby enhancing edge server utilization. We evaluate the performance of our proposed approach via simulation experiments and demonstrate its superiority by reducing the queue length at the edge node and adhering to delay constraints of vehicular networks.

Over the period, the universal internet of vehicles (UIo V) has acquired considerable attention in enhancing drive safety, traffic management, infotainment. Due to the heteroge-neous communication, it is highly vulnerable to various types of security and privacy attacks. Security and privacy concerns in the UIo V are commonly addressed with central authentication, in which only the registration authority has the power to authenticate vehicles and other UIo V components. Some of the researchers proposed anonymous authentication techniques to re-move this dependency. However, the existing methods for anony-mous authentication endure a very high computation overhead for the certificate and signature validation process, due to which a high rate of message loss happens. In this paper, we propose a lightweight anonymous authentication scheme called LAAS for UIo V using a bilinear map and lightweight cryptographic operation (i.e., one-way hash function, XOR, concatenation) to achieve a high level of security and privacy. Additionally, we propose an idea of batch message verification. The performance analysis of LAAS demonstrates that it is lightweight and produces an efficient result in terms of computational cost and latency when compared to other existing state-of-the-art schemes for verifying signatures and certificates by holding conditional privacy in UIo V, as demonstrated in this paper.

This paper presents an adaptive self-learning classifier-based clustering algorithm called AlcFier, to support scalability, enhance the stability of the network topology, and provide efficient routing. We incorporate mobility and channel characteristics (i.e., orientation, adjacency, link availability, queue occupancy, and signal-to-noise ratio) into the clustering approach as a channel-aware metric to provide a new direction to the taxonomy of the approaches employed to handle cluster head election, cluster affiliation, and cluster administration challenges. Experimental results show that AlcFier performs efficiently, improves cluster stability, reduces transmission delays, and improves throughput compared with the state-of-the-art routing protocols.

Clustering plays a vital role in establishing a more stable global network topology in Vehicular Ad Hoc NETworks (VANETs) and supports Intelligent Transportation Systems (ITS) applications and message routing. However, due to the unstable infrastructure of VANETs, cluster size and geographical span have a significant impact on maintaining cluster stability and network efficiency. Thus, this paper presents a hybrid machine learning (ML) and meta-heuristics (MH) based routing scheme called MetoidS to support scalability, enhance the stability of the network topology, and provide efficient routing. We incorporate vehicle orientation-based unsupervised clustering and population based MH to provide a new direction to the taxonomy of the approaches to handling efficient route discovery and cluster maintenance challenges. To represent a real-world simulation of our approach, we have conducted the experiments using a combination of four frameworks (i.e., OMNeT++, SUMO, VEINS, and INET) that demonstrate better performance in terms of high cluster stability, enhanced throughput, high packet delivery ratio, and minimizes average transmission delay compared to the existing routing protocols used in this research.

The integration of learning architecture with SDN-based VANETs (SDVN) is beneficial for utilizing computing power by decoupling network management services from data transfer services. However, fast safety messages dissemination in a highly dynamic vehicular environment is a challenging and complex dilemma due to bi-directional traffic and the directional movement of vehicles. It is also challenging to get an effective solution against bottleneck situations and a reliable and fault-tolerant SDN network using clustering. So considering the features of adaptive learning, in this paper, we propose adaptive self-learning clustering algorithm with reinforcement routing in SDVN known as RL-SDVN. An Expectation-Maximization model is used to predict a vehicle's movement and further Q-learning model is used to route data packets, so that vehicles in the same cluster coordinate with each other to find optimum routes. We evaluate our experimental results by comparing our approach with the clustering and self-learning based schemes proposed in the past. The outcomes exhibit that the proposed scheme improved cluster stability and life-time of a cluster member vehicle with better performance in terms of low average transmission delay, and high throughput compared to the existing routing protocols used in this research.

The source-based routing using quality of service (QoS) metrics results in alternate path discovery considering link-availability time, link costs, and path delays to overcome the barrier of information blocking on a selected path by choosing alternative routes. However, multipath selection, as well as the cost of selecting a path, make the route selection a challenging task. This paper proposes a vehicle orientation based QoS routing in vehicular ad-hoc networks (VANETs), called OBQR that exploits vehicle orientational information instead of magnitude information. The cosine similarity concept with a preliminary scalarization model converts the multi-constraint objectives into a single constraint objective to find a set of possible paths to the destination. We evaluate the performance of our approach and compare it with existing state-of-the-art schemes based on QoS routing and clustering. Experimental results demonstrate that the proposed scheme significantly improves path selection and load balancing with better QoS routing performance.

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.

With the rapid technological advancement of the universal internet of vehicles (UIoV), it becomes crucial to ensure safe and secure communication over the network, in an effort to achieve the implementation objective of UIoV effectively. A UIoV is characterized by highly dynamic topology, scalability, and thus vulnerable to various types of security and privacy attacks (i.e., replay attack, impersonation attack, man-in-middle attack, non-repudiation, and modification). Since the components of UIoV are constrained by numerous factors (e.g., low memory devices, low power), which makes UIoV highly susceptible. Therefore, existing schemes to address the privacy and security facets of UIoV exhibit an enormous scope of improvement in terms of time complexity and efficiency. This paper presents a lightweight authentication and batch verification scheme (LABVS) for UIoV using a bilinear map and cryptographic operations (i.e., one-way hash function, concatenation, XOR) to minimize the rate of message loss occurred due to delay in response time as in single message verification scheme. Subsequently, the scheme results in a high level of security and privacy. Moreover, the performance analysis substantiates that LABVS minimizes the computational delay and has better performance in the delay-sensitive network in terms of security and privacy as compared to the existing schemes.