The recent proliferation of Fifth-Generation(5G)networks and Sixth-Generation(6G)networks has given rise to Vehicular Crowd Sensing(VCS)systems which solve parking collisions by effectively incentivizing vehicle parti...The recent proliferation of Fifth-Generation(5G)networks and Sixth-Generation(6G)networks has given rise to Vehicular Crowd Sensing(VCS)systems which solve parking collisions by effectively incentivizing vehicle participation.However,instead of being an isolated module,the incentive mechanism usually interacts with other modules.Based on this,we capture this synergy and propose a Collision-free Parking Recommendation(CPR),a novel VCS system framework that integrates an incentive mechanism,a non-cooperative VCS game,and a multi-agent reinforcement learning algorithm,to derive an optimal parking strategy in real time.Specifically,we utilize an LSTM method to predict parking areas roughly for recommendations accurately.Its incentive mechanism is designed to motivate vehicle participation by considering dynamically priced parking tasks and social network effects.In order to cope with stochastic parking collisions,its non-cooperative VCS game further analyzes the uncertain interactions between vehicles in parking decision-making.Then its multi-agent reinforcement learning algorithm models the VCS campaign as a multi-agent Markov decision process that not only derives the optimal collision-free parking strategy for each vehicle independently,but also proves that the optimal parking strategy for each vehicle is Pareto-optimal.Finally,numerical results demonstrate that CPR can accomplish parking tasks at a 99.7%accuracy compared with other baselines,efficiently recommending parking spaces.展开更多
Intelligent transportation system （ITS） is proposed as the most effective way to improve road safety and traffic efficiency. However, the future of ITS for large scale transportation infrastructures deployment highl...Intelligent transportation system （ITS） is proposed as the most effective way to improve road safety and traffic efficiency. However, the future of ITS for large scale transportation infrastructures deployment highly depends on the security level of vehicular communication systems （VCS）. Security applications in VCS are fulfilled through secured group broadcast. Therefore, secure key management schemes are considered as a critical research topic for network security. In this paper, we propose a framework for providing secure key management within heterogeneous network. The seeurity managers （SMs） play a key role in the framework by retrieving the vehicle departnre infi^rmation, encapsulating block to transport keys and then executing rekeying to vehicles within the same security domain. The first part of this framework is a novel Group Key Management （GKM） scheme basing on leaving probability （LP） of vehicles to depart current VCS region. Vehicle＇s LP factor is introduced into GKM scheme to achieve a more effieient rekeying scheme and less rekeying costs. The second component of the framework using the blockchain concept to simplify the distributed key management in heterogeneous VCS domains. Extensive simulations and analysis are provided to show the effectiveness and effieiency of the proposed framework： Our GKM results demonstrate that probability-based BR reduees rekeying eost compared to the benchmark scheme, while the blockchain deereases the time eost of key transmission over heterogeneous net-works.展开更多
Despite the expanded efforts,the vehicular ad-hoc networks(VANETs)are still facing many challenges such as network performances,network scalability and context-awareness.Many solutions have been proposed to overcome t...Despite the expanded efforts,the vehicular ad-hoc networks(VANETs)are still facing many challenges such as network performances,network scalability and context-awareness.Many solutions have been proposed to overcome these obstacles,and the edge computing,an extension of the cloud computing,is one of them.With edge computing,communication,storage and computational capabilities are brought closer to end users.This could offer many benefits to the global vehicular network including,for example,lower latency,network off-loading and context-awareness(location,environment factors,etc.).Different approaches of edge computing have been developed:mobile edge computing(MEC),fog computing(FC)and cloudlet are the main ones.After introducing the vehicular environment background,this paper aims to study and compare these different technologies.For that purpose their main features are compared and the state-of-the-art applications in VANETs are analyzed.In addition,MEC,FC,and cloudlet are classified and their suitability level is debated for different types of vehicular applications.Finally,some challenges and future research directions in the fields of edge computing and VANETs are discussed.展开更多
基金supported in part by the Natural Science Foundation of Shandong Province of China(ZR202103040180)the Major Scientific and Technological Projects of CNPC under Grant ZD2019-183-004the Fundamental Research Funds for the Central Universities under Grant 20CX05019A.
文摘The recent proliferation of Fifth-Generation(5G)networks and Sixth-Generation(6G)networks has given rise to Vehicular Crowd Sensing(VCS)systems which solve parking collisions by effectively incentivizing vehicle participation.However,instead of being an isolated module,the incentive mechanism usually interacts with other modules.Based on this,we capture this synergy and propose a Collision-free Parking Recommendation(CPR),a novel VCS system framework that integrates an incentive mechanism,a non-cooperative VCS game,and a multi-agent reinforcement learning algorithm,to derive an optimal parking strategy in real time.Specifically,we utilize an LSTM method to predict parking areas roughly for recommendations accurately.Its incentive mechanism is designed to motivate vehicle participation by considering dynamically priced parking tasks and social network effects.In order to cope with stochastic parking collisions,its non-cooperative VCS game further analyzes the uncertain interactions between vehicles in parking decision-making.Then its multi-agent reinforcement learning algorithm models the VCS campaign as a multi-agent Markov decision process that not only derives the optimal collision-free parking strategy for each vehicle independently,but also proves that the optimal parking strategy for each vehicle is Pareto-optimal.Finally,numerical results demonstrate that CPR can accomplish parking tasks at a 99.7%accuracy compared with other baselines,efficiently recommending parking spaces.
文摘Intelligent transportation system （ITS） is proposed as the most effective way to improve road safety and traffic efficiency. However, the future of ITS for large scale transportation infrastructures deployment highly depends on the security level of vehicular communication systems （VCS）. Security applications in VCS are fulfilled through secured group broadcast. Therefore, secure key management schemes are considered as a critical research topic for network security. In this paper, we propose a framework for providing secure key management within heterogeneous network. The seeurity managers （SMs） play a key role in the framework by retrieving the vehicle departnre infi^rmation, encapsulating block to transport keys and then executing rekeying to vehicles within the same security domain. The first part of this framework is a novel Group Key Management （GKM） scheme basing on leaving probability （LP） of vehicles to depart current VCS region. Vehicle＇s LP factor is introduced into GKM scheme to achieve a more effieient rekeying scheme and less rekeying costs. The second component of the framework using the blockchain concept to simplify the distributed key management in heterogeneous VCS domains. Extensive simulations and analysis are provided to show the effectiveness and effieiency of the proposed framework： Our GKM results demonstrate that probability-based BR reduees rekeying eost compared to the benchmark scheme, while the blockchain deereases the time eost of key transmission over heterogeneous net-works.
文摘Despite the expanded efforts,the vehicular ad-hoc networks(VANETs)are still facing many challenges such as network performances,network scalability and context-awareness.Many solutions have been proposed to overcome these obstacles,and the edge computing,an extension of the cloud computing,is one of them.With edge computing,communication,storage and computational capabilities are brought closer to end users.This could offer many benefits to the global vehicular network including,for example,lower latency,network off-loading and context-awareness(location,environment factors,etc.).Different approaches of edge computing have been developed:mobile edge computing(MEC),fog computing(FC)and cloudlet are the main ones.After introducing the vehicular environment background,this paper aims to study and compare these different technologies.For that purpose their main features are compared and the state-of-the-art applications in VANETs are analyzed.In addition,MEC,FC,and cloudlet are classified and their suitability level is debated for different types of vehicular applications.Finally,some challenges and future research directions in the fields of edge computing and VANETs are discussed.
