Problem In Vehicular Networks Research Articles

Channel reconfiguration for intelligent reflecting surface‐aided vehicular networks

AbstractIntelligent reflecting surface (IRS) has been recognized as one of the core technologies in the sixth generation (6G). Nevertheless, the character of channel state rapid change is a major problem in vehicular networks due to the dynamic vehicle movement and electromagnetic wave random scattering. In order to address the above problem, a strategy that joint phase shifts and channel alignment (PS‐CA) is proposed to reduce Doppler shift impact and improve communication performance in IRS‐aided vehicular networks. In this article, the channels can be divided into two types: the one type is the cascaded channel from the base station (BS) to the IRS and then to the vehicle; the other one is the direct channel from the BS to the vehicle. Thus, the proposed PS‐CA strategy can be divided into two stages. In the first stage, the cascaded channel fast fading state is reduced by designing IRS reflection phase shifts. In the second stage, considering the phase difference between the direct channel and the cascaded channel, we designed a correction function to align the direct channel with the cascaded channel. Then, we combined the designed correction function with IRS reflection phase shifts to reduce the impact of the direct channel fast fading state on overall performance. Simulation results demonstrate that compared to the RPS strategy, the PS‐CA strategy achieves higher spectral efficiency by 31.5.

Mean-Field-Aided Multiagent Reinforcement Learning for Resource Allocation in Vehicular Networks

As one technique for autonomous driving, vehicular networks can achieve high efficiency with vehicle-and-infrastructure cooperation, bringing high safety and many value-added services. To achieve higher communication efficiency, much effort has been done to cope with the resource allocation issues for vehicular networks. Nevertheless, due to the strong nonconvexity and nonlinearity, the classical joint resource allocation problem in vehicular networks is typically NP-hard. The multiagent reinforcement learning (MARL) has emerged as a promising solution to tackle this challenge but its stability and scalability are not satisfactory when the amount of vehicles gets increased. In this article, we mainly investigate the issue of joint spectrum and power allocation in vehicular communication networks, and carefully consider the interactions between the vehicles and environment by incorporating the cooperative stochastic game theory with MARL, named complete-game MARL (CG-MARL), to achieve a better convergence and stability with the theoretical computational complexity <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathcal {O}(n^{N})$ </tex-math></inline-formula> with <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$n$ </tex-math></inline-formula> denoting the dimension of action space and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$N$ </tex-math></inline-formula> denoting the number of V2X Vehicular. Furthermore, the mean-field game (MFG) theory is employed to further enhance the MARL for decreasing the horrible computing resource consumption caused by the CG-MARL to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathcal {O}(n^{2})$ </tex-math></inline-formula> while maintaining an approximate performance. The simulation results demonstrate that the proposed mean-field-aided MARL (MF-MARL) for vehicular network resource allocation can achieve 95% near-optimal performance with much lower complexity, which indicates its significant potentials in the scenarios with massive and dense vehicles.

A Hybrid Proactive Caching System in Vehicular Networks Based on Contextual Multi-Armed Bandit Learning

Proactive edge caching has been regarded as an effective approach to satisfy user experience in mobile networks by providing seamless content transmission and reducing network delay. This is particularly useful in rapidly changing vehicular networks. This paper addresses the proactive edge caching (at the roadside unit (RSU)) problem in vehicular networks by mobility prediction, i.e., the next RSU prediction. Specifically, the paper proposes a distributed <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Hybrid cMAB Proactive Caching System</i> where RSUs act as independent learners that implement two parallel online reinforcement learning-based mobility prediction algorithms between which they can adaptively finalize their predictions for the next RSU. The two parallel prediction algorithms are based on <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Contextual Multi-armed bandit</i> (cMAB) learning, called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Dual-context cMAB</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Single-context cMAB</i> . The hybrid system is further developed into two variants: <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Vehicle-Centric</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">RSU-Centric</i> . In addition, the paper also conducts comprehensive simulation experiments to evaluate the prediction performance of the proposed hybrid system. They include three traffic scenarios: <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Commuting traffic, Random traffic</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Mixed traffic</i> in Las Vegas, USA and Manchester, UK. With the different road layouts in the two urban areas, the paper aims to generalize the application of the system. Simulation results show that the hybrid Vehicle-Centric system can reach nearly 95% cumulative prediction accuracy in the Commuting traffic scenario and outperform the other methods used for comparison by reaching nearly 80% accuracy in Mixed traffic scenario. Even in the completely Random traffic scenario, it also guarantees a minimum accuracy of nearly 60%.

Generation rate control with AoI under traffic hole problem in vehicular networks

In 6G mobile networks, vehicular networks will significantly benefit from extremely high network throughput and capacity. For Internet of Things (IoT) within a vehicular network, the sensor data as an update is delivered from each sensor source to a nearby gateway, by Vehicle-to-Vehicle (V2V) and Vehicle to Roadside unit (V2R) communications. The mobility of the vehicles is not only affected by the vehicle itself, but also by external means, such as the signal operations of traffic lights. The red light stops the vehicles at the intersection, which will increase the time it takes for updates carried by the vehicle to be delivered. On the other hand, the red light can also increase the opportunities of vehicles moving behind to catch up with the waiting vehicles in forwarding updates. This is termed as the traffic hole problem by the traffic lights in vehicular networks. In this paper, we investigate the influence of traffic lights in vehicular networks using the metric of Age of Information (AoI). We discuss the optimal generation rate at the source by considering the trade-off between AoI and transmission cost. We propose a Total Average Cost aware generation rate Algorithm (TACA) for the generation interval time at the sensor source. Our intensive simulations verify the proposed algorithm and evaluate the influence of the traffic lights on AoI.

Spectrum Access Allocation in Vehicular Networks With Intermittently Interrupted Channels

In this letter, we study the spectrum access problem in vehicular networks, where a base station (BS) assigns its spectrum to vehicles to fulfill data demands of these vehicles. In our model, connection links between the BS and vehicles are assumed to be intermittently interrupted by local jammers that have attacking strategies following a Markov chain. Furthermore, the channel availability of vehicles is correlated due to the correlated jamming pattern created by different groups of jammers. Consequently, uncertainties in the system dynamics make the spectrum allocation problem in vehicular networks partially observable. Besides, the constraints on data demands, along with the high mobility of the vehicular environment further complicate the design of the access policy. To address the aforementioned issues, the deep Q-learning method is proposed to provide an efficient and structured solution to such spectrum access problem. Besides, the double Q learning method is also integrated into the deep Q-network to improve the training speed of the proposed method. Numerical results are presented to demonstrate the advantages of the proposed policy compared to other benchmark strategies.

Network slicing for vehicular communications: a multi-agent deep reinforcement learning approach

This paper studies the multi-agent resource allocation problem in vehicular networks using non-orthogonal multiple access (NOMA) and network slicing. Vehicles want to broadcast multiple packets with heterogeneous quality-of-service (QoS) requirements, such as safety-related packets (e.g., accident reports) that require very low latency communication, while raw sensor data sharing (e.g., high-definition map sharing) requires high-speed communication. To ensure heterogeneous service requirements for different packets, we propose a network slicing architecture. We focus on a non-cellular network scenario where vehicles communicate by the broadcast approach via the direct device-to-device interface (i.e., sidelink communication). In such a vehicular network, resource allocation among vehicles is very difficult, mainly due to (i) the rapid variation of wireless channels among highly mobile vehicles and (ii) the lack of a central coordination point. Thus, the possibility of acquiring instantaneous channel state information to perform centralized resource allocation is precluded. The resource allocation problem considered is therefore very complex. It includes not only the usual spectrum and power allocation, but also coverage selection (which target vehicles to broadcast to) and packet selection (which network slice to use). This problem must be solved jointly since selected packets can be overlaid using NOMA and therefore spectrum and power must be carefully allocated for better vehicle coverage. To do so, we first provide a mathematical programming formulation and a thorough NP-hardness analysis of the problem. Then, we model it as a multi-agent Markov decision process. Finally, to solve it efficiently, we use a deep reinforcement learning (DRL) approach and specifically propose a deep Q learning (DQL) algorithm. The proposed DQL algorithm is practical because it can be implemented in an online and distributed manner. It is based on a cooperative learning strategy in which all agents perceive a common reward and thus learn cooperatively and distributively to improve the resource allocation solution through offline training. We show that our approach is robust and efficient when faced with different variations of the network parameters and compared to centralized benchmarks.

Blockchain Empowered Cooperative Authentication With Data Traceability in Vehicular Edge Computing

The dynamic environment due to traffic mobility and wireless communication from/to vehicles make identity authentication and trust management for privacy preservation based on vehicular edge computing (VEC) an increasingly important problem in vehicular networks. However, existing authentication schemes mainly focus on communication between a single trusted edge computing node and multiple vehicles. This framework may suffer the bottleneck problem due to the single edge computing node, and the performance depends heavily on its resources. In this paper, a blockchain empowered group-authentication scheme is proposed for vehicles with decentralized identification based on secret sharing and dynamic proxy mechanism. Sub-authentication results are aggregated for trust management based blockchain to implement collaborative authentication. The edge computing node with a higher-reputation stored in the tamper-proof blockchain can upload the final aggregated authentication result to the central server to achieve the decentralized authentication. This work analyzes typical attacks for this scheme and shows that the proposed scheme achieves cooperative privacy preservation for vehicles while also reducing communication overhead and computation cost.

Spectrum Sharing in Vehicular Networks Based on Multi-Agent Reinforcement Learning

This paper investigates the spectrum sharing problem in vehicular networks based on multi-agent reinforcement learning, where multiple vehicle-to-vehicle (V2V) links reuse the frequency spectrum preoccupied by vehicle-to-infrastructure (V2I) links. Fast channel variations in high mobility vehicular environments preclude the possibility of collecting accurate instantaneous channel state information at the base station for centralized resource management. In response, we model the resource sharing as a multi-agent reinforcement learning problem, which is then solved using a fingerprint-based deep Q-network method that is amenable to a distributed implementation. The V2V links, each acting as an agent, collectively interact with the communication environment, receive distinctive observations yet a common reward, and learn to improve spectrum and power allocation through updating Q-networks using the gained experiences. We demonstrate that with a proper reward design and training mechanism, the multiple V2V agents successfully learn to cooperate in a distributed way to simultaneously improve the sum capacity of V2I links and payload delivery rate of V2V links.

Resource Allocation for V2X Communications: A Large Deviation Theory Perspective

In vehicular communications, one of the key requirements of the vehicle-to-vehicle (V2V) links is to transmit a given amount of data successfully during a given time period. To this end, this letter investigates a spectrum and power allocation problem in vehicular networks to maximize the sum ergodic capacity of the vehicle-to-network (V2N) links subject to the V2V links’ data amount violation probability. By using the large deviation theory, we express the data amount outage probability in a tractable form and derive the optimal power allocation for each possible spectrum reusing pair consisting of one V2N link and one V2V link. Then, the optimal spectrum reusing pattern is obtained by addressing a bipartite matching issue. Finally, the effectiveness of our proposal is validated by simulation results.

Modeling and improving the throughput of vehicular networks using cache enabled RSUs

Newly emerged applications in vehicular networks demand high throughput to transfer large amount of data through both Vehicle-to-Vehicle and Vehicle-to-Infrastructure links. One solution which recently draws researchers attention to itself for improving the throughput in this type of network is to deploy some Road-Side-Units (RSUs) in the streets with storage capability and store the data closer to the end users. Consequently, vehicles are able to download their inquired contents from these local RSUs instead of the base station. This will decrease the network traffic of the base station and also the average delay each vehicle has to wait to receive his requested files. The main issue to implement this distributed approach in this type of environment compared to other types of networks is that the fast moving vehicles make the topology of the network highly dynamic. Also due to limited storage capacity of the caches in the RSUs, we should decide on how to distribute the contents in the RSUs to maximize the number of locally satisfied vehicles. In this paper, we address the cache content placement problem in vehicular networks and model it using a game theoretic approach. We show that the proposed game model is a special case of generalized covering games. Considering the hit ratio of the caches as the performance metric in our model, we propose a method to distributively optimize this metric using the RSU’s local information. In addition, we propose a combinatorial approach to find efficient file placements in the RSUs using Markov approximation. Empirical evaluations on realistic trace-based simulations show an improvement of 7.5% in the average hit ratio of the proposed method compared to other well-known cache content placement approaches. Newly emerged applications in vehicular networks demand high throughput to transfer large amount of data through both Vehicle-to-Vehicle and Vehicle-to-Infrastructure links. To improve the network throughput, we deploy some Road-Side-Units (RSUs) in the streets with storage capability and store the data closer to the end users. Consequently, vehicles are able to download their inquired contents from these local RSUs instead of the base station. The main issue to implement this distributed approach is that the fast moving vehicles make the topology of the network highly dynamic. Also due to limited storage capacity of the caches in the RSUs, we should decide on how to distribute the contents in the RSUs to maximize the number of locally satisfied vehicles. In this paper, we address the cache content placement problem in vehicular networks and model it using game theoretic approach and Combinatorial approach. We show that the proposed game model is a special case of generalized covering games. Considering the hit ratio of the caches as the performance metric in our model, we propose a method to distributively optimize this metric using the RSU’s local information. In addition, we propose a Combinatorial approach to find efficient file placements in the RSUs using Markov approximation. Empirical evaluations on realistic trace-based simulations show an improvement of 7.5% in the average hit ratio of the proposed method compared to other well-known cache content placement approaches.

Directed broadcasting with mobility prediction for vehicular sensor networks

This article suggests a new directed broadcasting method with mobility prediction of moving vehicles in vehicular sensor networks (VSNs). VSNs can play a critical role to ensure prompt delivery of real-time sensing data and be able to prevent various road dangers. The suggested method is particularly for vehicle safety communication (VSC) on highway roads by using directed broadcasting between vehicles. In VSNs, broadcasting is the most suitable communication mechanism for VSC. The simplest broadcasting mechanism is flooding, which introduces the redundant message retransmission and the broadcast storm problem. It is because all vehicles rebroadcast the messages in flooding. The broadcast storm problem can be addressed with selective flooding schemes which select rebroadcast vehicles to perform rebroadcasting. However, selective flooding schemes cannot promise enough reliability for VSC because of the highly dynamic topology and frequent disconnections of vehicular networks. Fast movement and frequent topology changes cause repeated link breakages and it increases the packet loss rate of vehicular networks. In this article, we propose a mobility prediction-based directed broadcasting (MPDB) protocol to achieve a reliable broadcasting in VSNs. MPDB protocol broadcasts emergent messages only to the rear vehicles on the same road. MPDB protocol consists of two phases: (i) mobility prediction phase and (ii) broadcasting phase. The mobility prediction can be acquired through periodical beaconing. In mobility prediction phase, each vehicle gets its rear vehicle set on the same road through neighbour’s position, inter-vehicle distance, relative speed and moving direction. In broadcast phase, MPDB protocol selects a vehicle having the largest link available time (LAT) values acquired by the mobility prediction as a rebroadcast vehicle among the rear vehicle set acquired in previous phase. By using LAT for broadcasting propagation, MPDB protocol can intensify the reliability of the message dissemination and also prevent the broadcast storm problem in vehicular networks. The simulation results show that MPDB protocol has better performance improvement in terms of average packet rate and packet delay.

Interference Graph-Based Resource-Sharing Schemes for Vehicular Networks

This paper investigates the resource-sharing problem in vehicular networks, including both vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication links. A novel underlaying resource-sharing communication mode for vehicular networks is proposed, in which different V2V and V2I communication links are permitted to access the same resources for their individual data transmission. To solve the resource-sharing problem in vehicular networks, we, for the first time, apply graph theory and propose the following two interference graph-based resource-sharing schemes: 1) the interference-aware graph-based resource-sharing scheme and 2) the interference-classified graph-based resource-sharing scheme. Compared with the traditional orthogonal communication mode in vehicular networks, the proposed two resource-sharing schemes express better network sum rate. The utility of the proposed V2V and V2I underlaying communication mode and the two proposed interference graph-based resource-sharing schemes are verified by simulations.

A Cost-Effective Strategy for Road-Side Unit Placement in Vehicular Networks

In this paper, we study the Roadside Unit (RSU) placement problem in vehicular networks. We focus on the highway-like scenario in which there may be multiple lanes with exits or intersections along the road. In our model, each vehicle can access RSUs in two ways: 1) direct delivery, which occurs when the vehicle is in the transmission range of the RSUs, and 2) multi-hop relaying, which takes place when the vehicle is out of RSU transmission range. We account for both access patterns in our placement strategy and formulate this placement problem via an integer linear programming model such that the aggregate throughput in the network can be maximized. We also take into account the impact of wireless interference, vehicle population distribution, and vehicle speeds in the formulation. The performance of the proposed placement strategy is evaluated via ns-2 simulations together with VanetMobisim to generate vehicle mobility patterns. The results show that our strategy leads to the best performance as compared with the uniformly distributed placement and the hot spot placement. More importantly, our solution needs the least number of RSUs to achieve the maximal aggregate throughput in the network, indicating that our scheme is indeed a cost effective yet highly efficient placement strategy for vehicular networks.