Lower Earth Orbit(LEO) satellite becomes an important part of complementing terrestrial communication due to its lower orbital altitude and smaller propagation delay than Geostationary satellite. However, the LEO sate...Lower Earth Orbit(LEO) satellite becomes an important part of complementing terrestrial communication due to its lower orbital altitude and smaller propagation delay than Geostationary satellite. However, the LEO satellite communication system cannot meet the requirements of users when the satellite-terrestrial link is blocked by obstacles. To solve this problem, we introduce Intelligent reflect surface(IRS) for improving the achievable rate of terrestrial users in LEO satellite communication. We investigated joint IRS scheduling, user scheduling, power and bandwidth allocation(JIRPB) optimization algorithm for improving LEO satellite system throughput.The optimization problem of joint user scheduling and resource allocation is formulated as a non-convex optimization problem. To cope with this problem, the nonconvex optimization problem is divided into resource allocation optimization sub-problem and scheduling optimization sub-problem firstly. Second, we optimize the resource allocation sub-problem via alternating direction multiplier method(ADMM) and scheduling sub-problem via Lagrangian dual method repeatedly.Third, we prove that the proposed resource allocation algorithm based ADMM approaches sublinear convergence theoretically. Finally, we demonstrate that the proposed JIRPB optimization algorithm improves the LEO satellite communication system throughput.展开更多
Since the evolving standardization of cellular V2X(C-V2X)technologies is continuously developed by 3GPP,research on new radio(NR-V2X)has been on schedule by academic and industries.Though millimeter wave(mm Wave)frequ...Since the evolving standardization of cellular V2X(C-V2X)technologies is continuously developed by 3GPP,research on new radio(NR-V2X)has been on schedule by academic and industries.Though millimeter wave(mm Wave)frequency band is supposed to provide large transmission bandwidth,yet the development of mm Wave band in NR-V2X is still in preliminary stage.In this article,a comprehensive discussion of mm Wave NR-V2X is given covering trends,standardization landscape,and enabling technologies,aiming at tackling the challenge of channel modeling,directional channel access,beamforming and blockage management.The vision of mm Wave NR-V2X is to fully support the development of automated driving,holographic control display and improved in-car infotainment for the future.展开更多
Nowadays urban traffic congestion becomes a major issue due to the increase in vehicles that lead to more commuting time,accidents,traffic violations,and high fuel consumption.Platooning is a good way to solve traffic...Nowadays urban traffic congestion becomes a major issue due to the increase in vehicles that lead to more commuting time,accidents,traffic violations,and high fuel consumption.Platooning is a good way to solve traffic congestion because it drives with a smaller inter-vehicle distance than human-driving.This paper proposes proactive platooning based on C-V2X(cellular vehicle-to-everything)to relieve congestion.Proactive platooning reduces the inter-vehicle distance and increases the throughput of signalized intersections through integrating the networked control platooning and computation-centralized platooning.Model and simulation experiments of proactive platooning were conducted to verify the impact of inter-vehicle distance on platooning latency,platooning safety,and traffic throughput.Simulation results show that the optimal inter-vehicle distance under proactive platooning is less than half of human-driving at a signalized intersection.展开更多
1.Introduction Since the 1980s,when the first generation(1G)of mobile networks came into being,mobile communications have been developing with the trend of a generational upgrade occurring every decade.At present,the ...1.Introduction Since the 1980s,when the first generation(1G)of mobile networks came into being,mobile communications have been developing with the trend of a generational upgrade occurring every decade.At present,the fifth generation(5G)is in the commercial stage and the sixth generation(6G)is in the research stage.It is expected that the standardization for 6G will debut in the year 2025,and the first version for commercialization will be launched in 2030.For the purpose of better understanding 6G.展开更多
With the development of new generation of information and communication technology,the Internet of Vehicles(IoV)/Vehicle-to-Everything(V2X),which realizes the connection between vehicle and X(i.e.,vehicles,pedestrians...With the development of new generation of information and communication technology,the Internet of Vehicles(IoV)/Vehicle-to-Everything(V2X),which realizes the connection between vehicle and X(i.e.,vehicles,pedestrians,infrastructures,clouds,etc.),is playing an increasingly important role in improving traffic operation efficiency and driving safety as well as enhancing the intelligence level of social traffic services.展开更多
Mobile communication standards have been developed into a new era of B5G and 6G.In recent years,low earth orbit(LEO)satellites and space Internet have become hot topics.The integrated satellite and terrestrial systems...Mobile communication standards have been developed into a new era of B5G and 6G.In recent years,low earth orbit(LEO)satellites and space Internet have become hot topics.The integrated satellite and terrestrial systems have been widely discussed by industries and academics,and even are expected to be applied in those huge constellations in construction.This paper points out the trends of two stages towards system integration of the terrestrial mobile communication and the satellite communications:to be compatible with 5G,and to be integrated within 6G.Based on analysis of the challenges of both stages,key technologies are thereafter analyzed in detail,covering both air interface currently discussed in 3GPP for B5G and also novel network architecture and related transmission technologies toward future 6G.展开更多
The airborne base station(ABS) can provide wireless coverage to the ground in unmanned aerial vehicle(UAV) cellular networks.When mobile users move among adjacent ABSs,the measurement information reported by a single ...The airborne base station(ABS) can provide wireless coverage to the ground in unmanned aerial vehicle(UAV) cellular networks.When mobile users move among adjacent ABSs,the measurement information reported by a single mobile user is used to trigger the handover mechanism.This handover mechanism lacks the consideration of movement state of mobile users and the location relationship between mobile users,which may lead to handover misjudgments and even communication interrupts.In this paper,we propose an intelligent handover control method in UAV cellular networks.Firstly,we introduce a deep learning model to predict the user trajectories.This prediction model learns the movement behavior of mobile users from the measurement information and analyzes the positional relations between mobile users such as avoiding collision and accommodating fellow pedestrians.Secondly,we propose a handover decision method,which can calculate the users' corresponding receiving power based on the predicted location and the characteristic of air-to-ground channel,to make handover decisions accurately.Finally,we use realistic data sets with thousands of non-linear trajectories to verify the basic functions and performance of our proposed intelligent handover controlmethod.The simulation results show that the handover success rate of the proposed method is 8% higher than existing methods.展开更多
Vehicular communications and networking(VCN)is considered a billion-dollar industry.Its development not only possesses economic value,but also has enormous social potential.The earliest vehicular network started from ...Vehicular communications and networking(VCN)is considered a billion-dollar industry.Its development not only possesses economic value,but also has enormous social potential.The earliest vehicular network started from the dedicated short range networks,such as the IEEE 802.11p standard established at the beginning of this century.In recent years,the public access network based VCN has been rapidly advanced.For example,LTE-V based on 4G LTE is under standardization。展开更多
Massive Multiple-Input Multiple-Output(MIMO)is considered as a key technology for 4G and 5G wireless communication systems to improve spectrum efficiency by supporting large number of concurrent users.In addition,for ...Massive Multiple-Input Multiple-Output(MIMO)is considered as a key technology for 4G and 5G wireless communication systems to improve spectrum efficiency by supporting large number of concurrent users.In addition,for the target frequency band of 5G system,mmWave band,massive MIMO is pivotal in compensating the high pathloss.In this paper,we investigate the channel state information(CSI)acquisition problem for mmWave massive MIMO.With hybrid analog-digital antenna architecture,how to derive the analog beamforming and digital beamforming is studied.An iterative analog beam acquisition approach is proposed to save system overhead and reduce beam searching complexity.Regarding the digital beamforming,a grouping based codebook is proposed to facilitate CSI feedback.The codebook is then extended to incorporate also analog beam acquisition.Furthermore,channel reciprocity is exploited to save CSI reporting overhead and a two-stage approach is proposed to fully utilize the channel reciprocity at both mobile station and base station side and accelerate the CSI acquisition procedure.展开更多
Cellular vehicle-to-everything(C-V2X)is the most promising V2X communication technology which can greatly improve traffic efficiency and road safety.However,when vehicles are interconnected with the surrounding radio ...Cellular vehicle-to-everything(C-V2X)is the most promising V2X communication technology which can greatly improve traffic efficiency and road safety.However,when vehicles are interconnected with the surrounding radio environment,the CV2X system will face various network security risks and threats,significantly impacting on traffic and life safety.This paper proposes a novel unified identification management framework and security authentication mechanism for the C-V2X equipment based on the security problems analyses of the C-V2X system and the existing security protection schemes.This paper also presents the security analysis and evaluation for the unified identification management and authentication mechanism.A experiment system is implemented to verify feasibility and effectiveness for the proposed mechanism.展开更多
TD-LTE-Advanced was accepted as one of the 4G global standards by ITU in 2012.In 2013,Chinese government issued 4G TD-LTE licenses to all 3 Chinese operators.Now,more than 1/3 of the global 4G equipments and users are...TD-LTE-Advanced was accepted as one of the 4G global standards by ITU in 2012.In 2013,Chinese government issued 4G TD-LTE licenses to all 3 Chinese operators.Now,more than 1/3 of the global 4G equipments and users are using TD-LTE-Advanced technology.Simultaneously,research toward 5G is one of the most attractive topics of mobile communication industry.The 3GPP has launched several workshops to展开更多
Network densification is a promising solution to fulfill network capacity requirement and transmission rate for beyond 5G and 6G wireless communications.Ultra-dense network(UDN)integrates heterogeneous network resourc...Network densification is a promising solution to fulfill network capacity requirement and transmission rate for beyond 5G and 6G wireless communications.Ultra-dense network(UDN)integrates heterogeneous network resources and coordinates technologies on quality of service controlling,to provide users with flexible service.However,dense deployment reduces coverage radius of the cell,resulting in an increase on handover frequency,which makes a serious impact on service continuity.In this paper,we propose a proactive selection method for dynamic access points grouping(DAPGing)in accordance with“user-centric”philosophy,which selects target Access Points(AP)and reduces handover times to ensure communication continuity.This method includes two criteria:1)the user’s sojourn time,which is determined by analyzing the AP coverage area;2)neighbor relationship between APs,which is determined by coverage area and signal strength characteristics between neighboring APs.Therefore,candidate APs become the proactive selected ones to update the AP group.Stochastic geometry is used to build system model and performance metrics are analyzed,including AP group coverage probability and average update frequency.Experimental analysis shows that the proposed proactive selection method brings similar coverage probability to traditional handover method,while average update frequency is reduced more than 20%selection criteria.展开更多
Vehicular networks are expected to empower auto mated driving and intelligent transportation via vehicle-to-everything(V2X)communications and edge/cloud-assisted computation,and in the meantime Cellular V2X(C-V2X)is g...Vehicular networks are expected to empower auto mated driving and intelligent transportation via vehicle-to-everything(V2X)communications and edge/cloud-assisted computation,and in the meantime Cellular V2X(C-V2X)is gaining wide support from the global industrial ecosystem.The 5G NR-V2X technology is the evolution of LTE-V2X,which is expected to provide ultra-Reliable and Low-Latency Communications(uRLLC)with 1ms latency and 99.999%reliability.Nevertheless,vehicular networks still face great challenges in supporting many emerging time-critical applications,which comprise sensing,communication and computation as closed-loops.展开更多
Modelling,predicting and analysing driver behaviours are essential to advanced driver assistance systems(ADAS)and the comprehensive understanding of complex driving scenarios.Recently,with the development of deep lear...Modelling,predicting and analysing driver behaviours are essential to advanced driver assistance systems(ADAS)and the comprehensive understanding of complex driving scenarios.Recently,with the development of deep learning(DL),numerous driver behaviour learning(DBL)methods have been proposed and applied in connected vehicles(CV)and intelligent transportation systems(ITS).This study provides a review of DBL,which mainly focuses on typical applications in CV and ITS.First,a comprehensive review of the state-of-the-art DBL is presented.Next,Given the constantly changing nature of real driving scenarios,most existing learning-based models may suffer from the so-called“catastrophic forgetting,”which refers to their inability to perform well in previously learned scenarios after acquiring new ones.As a solution to the aforementioned issue,this paper presents a framework for continual driver behaviour learning(CDBL)by leveraging continual learning technology.The proposed CDBL framework is demonstrated to outperform existing methods in behaviour prediction through a case study.Finally,future works,potential challenges and emerging trends in this area are highlighted.展开更多
Applications of VANETs(Vehicular Ad hoc Networks)have their own requirements and challenges in wireless communication technology.Although regarded as the rst standard for VANETs,IEEE 802.11p is still in the eld-trial ...Applications of VANETs(Vehicular Ad hoc Networks)have their own requirements and challenges in wireless communication technology.Although regarded as the rst standard for VANETs,IEEE 802.11p is still in the eld-trial stage.Recently,LTE V2X(Long-Term Evolution Vehicular to X)appeared as a systematic V2X solution based on TD-LTE(Time Division Long-Term Evolution)4G.It is regarded as the most powerful competitor to 802.11p.We conduct link level simulations of LTE V2X and DSRC(Dedicated Short-Range Communication)for several di erent types of scenarios.Simulation results show that LTE V2X can achieve the same BLER(Block Error Ratio)with a lower SNR(Signal Noise Ratio)than DSRC.A more reliable link can be guaranteed by LTE V2X,which can achieve the same BLER with lower receiving power than DSRC.The coverage area of LTE V2X is larger than that of DSRC.展开更多
Providing different service priority levels for different kinds of traffic is an important research area in the Internet.As compared with the existing best-effort(BE)service,recent researchers consider devising the be...Providing different service priority levels for different kinds of traffic is an important research area in the Internet.As compared with the existing best-effort(BE)service,recent researchers consider devising the belowbest-effort algorithm to realize a low priority service.The aim of below-best-effort service is to use the available bandwidth as much as possible in the premise of not interfering standard best-effort flows.With the best-effort transmission control protocol(TCP)transporting foreground traffic,below-best-effort service can transport background traffic which users do not urgently need to use.In this paper,we review the evolution of below-besteffort service and classify and compare these below-besteffort schemes.We also present some open problems in the research of below-best-effort service and point out the future work.展开更多
Vehicular network communication technology is currently attracting a considerable amount of attention.We consider a scenario in which vehicular communication nodes share the same spectrum resources and generate interf...Vehicular network communication technology is currently attracting a considerable amount of attention.We consider a scenario in which vehicular communication nodes share the same spectrum resources and generate interference with other nodes.Compared with traditional interference-avoiding vehicular communications,this paper aims to increase the number of accessed communication links under the premise of satisfying the required QoS.In our research,communication nodes have opportunities to select relay nodes to both help improve their data transmissions and reduce their transmit power in order to decrease interference with other links while still satisfying their QoS requirements.Based on these objectives,we propose an innovative interference management method that considers link selection,power adaption,and communication mode selection simultaneously to maximize the number of communication links with the lowest power cost.Compared with traditional link-selection and power-adaption interference management schemes,the proposed scheme improves QoS satisfaction with high energy effciency.Simulation results demonstrate both the effciency and the e ectiveness of the proposed scheme.展开更多
基金supported by the National Key R&D Program of China under Grant 2020YFB1807900the National Natural Science Foundation of China (NSFC) under Grant 61931005Beijing University of Posts and Telecommunications-China Mobile Research Institute Joint Innovation Center。
文摘Lower Earth Orbit(LEO) satellite becomes an important part of complementing terrestrial communication due to its lower orbital altitude and smaller propagation delay than Geostationary satellite. However, the LEO satellite communication system cannot meet the requirements of users when the satellite-terrestrial link is blocked by obstacles. To solve this problem, we introduce Intelligent reflect surface(IRS) for improving the achievable rate of terrestrial users in LEO satellite communication. We investigated joint IRS scheduling, user scheduling, power and bandwidth allocation(JIRPB) optimization algorithm for improving LEO satellite system throughput.The optimization problem of joint user scheduling and resource allocation is formulated as a non-convex optimization problem. To cope with this problem, the nonconvex optimization problem is divided into resource allocation optimization sub-problem and scheduling optimization sub-problem firstly. Second, we optimize the resource allocation sub-problem via alternating direction multiplier method(ADMM) and scheduling sub-problem via Lagrangian dual method repeatedly.Third, we prove that the proposed resource allocation algorithm based ADMM approaches sublinear convergence theoretically. Finally, we demonstrate that the proposed JIRPB optimization algorithm improves the LEO satellite communication system throughput.
基金supported by the National Key Research and Development Program of China(2020YFB1807900)the National Natural Science Foundation of China(61931005,62001051)。
文摘Since the evolving standardization of cellular V2X(C-V2X)technologies is continuously developed by 3GPP,research on new radio(NR-V2X)has been on schedule by academic and industries.Though millimeter wave(mm Wave)frequency band is supposed to provide large transmission bandwidth,yet the development of mm Wave band in NR-V2X is still in preliminary stage.In this article,a comprehensive discussion of mm Wave NR-V2X is given covering trends,standardization landscape,and enabling technologies,aiming at tackling the challenge of channel modeling,directional channel access,beamforming and blockage management.The vision of mm Wave NR-V2X is to fully support the development of automated driving,holographic control display and improved in-car infotainment for the future.
基金supported in part by China Scholarship Council,the National Natural Science Foundation Projects under Grant 61731004 and 61931005Beijing Natural Science foundation under Grant L202018。
文摘Nowadays urban traffic congestion becomes a major issue due to the increase in vehicles that lead to more commuting time,accidents,traffic violations,and high fuel consumption.Platooning is a good way to solve traffic congestion because it drives with a smaller inter-vehicle distance than human-driving.This paper proposes proactive platooning based on C-V2X(cellular vehicle-to-everything)to relieve congestion.Proactive platooning reduces the inter-vehicle distance and increases the throughput of signalized intersections through integrating the networked control platooning and computation-centralized platooning.Model and simulation experiments of proactive platooning were conducted to verify the impact of inter-vehicle distance on platooning latency,platooning safety,and traffic throughput.Simulation results show that the optimal inter-vehicle distance under proactive platooning is less than half of human-driving at a signalized intersection.
基金supported by the National Key Research and Development Program of China(2020YFB1807900)the National Natural Science Foundation of China(61931005)。
文摘1.Introduction Since the 1980s,when the first generation(1G)of mobile networks came into being,mobile communications have been developing with the trend of a generational upgrade occurring every decade.At present,the fifth generation(5G)is in the commercial stage and the sixth generation(6G)is in the research stage.It is expected that the standardization for 6G will debut in the year 2025,and the first version for commercialization will be launched in 2030.For the purpose of better understanding 6G.
文摘With the development of new generation of information and communication technology,the Internet of Vehicles(IoV)/Vehicle-to-Everything(V2X),which realizes the connection between vehicle and X(i.e.,vehicles,pedestrians,infrastructures,clouds,etc.),is playing an increasingly important role in improving traffic operation efficiency and driving safety as well as enhancing the intelligence level of social traffic services.
基金This work was supported in part by the National Science Fund for Distinguished Young Scholars in China under grant 61425012the National Science Foundation Project in China under grant 61931005 and 61731017.
文摘Mobile communication standards have been developed into a new era of B5G and 6G.In recent years,low earth orbit(LEO)satellites and space Internet have become hot topics.The integrated satellite and terrestrial systems have been widely discussed by industries and academics,and even are expected to be applied in those huge constellations in construction.This paper points out the trends of two stages towards system integration of the terrestrial mobile communication and the satellite communications:to be compatible with 5G,and to be integrated within 6G.Based on analysis of the challenges of both stages,key technologies are thereafter analyzed in detail,covering both air interface currently discussed in 3GPP for B5G and also novel network architecture and related transmission technologies toward future 6G.
基金supported in parts by the National Natural Science Foundation of China for Distinguished Young Scholar under Grant 61425012the National Science and Technology Major Projects for the New Generation of Broadband Wireless Communication Network under Grant 2017ZX03001014
文摘The airborne base station(ABS) can provide wireless coverage to the ground in unmanned aerial vehicle(UAV) cellular networks.When mobile users move among adjacent ABSs,the measurement information reported by a single mobile user is used to trigger the handover mechanism.This handover mechanism lacks the consideration of movement state of mobile users and the location relationship between mobile users,which may lead to handover misjudgments and even communication interrupts.In this paper,we propose an intelligent handover control method in UAV cellular networks.Firstly,we introduce a deep learning model to predict the user trajectories.This prediction model learns the movement behavior of mobile users from the measurement information and analyzes the positional relations between mobile users such as avoiding collision and accommodating fellow pedestrians.Secondly,we propose a handover decision method,which can calculate the users' corresponding receiving power based on the predicted location and the characteristic of air-to-ground channel,to make handover decisions accurately.Finally,we use realistic data sets with thousands of non-linear trajectories to verify the basic functions and performance of our proposed intelligent handover controlmethod.The simulation results show that the handover success rate of the proposed method is 8% higher than existing methods.
文摘Vehicular communications and networking(VCN)is considered a billion-dollar industry.Its development not only possesses economic value,but also has enormous social potential.The earliest vehicular network started from the dedicated short range networks,such as the IEEE 802.11p standard established at the beginning of this century.In recent years,the public access network based VCN has been rapidly advanced.For example,LTE-V based on 4G LTE is under standardization。
基金supported in parts by the National Natural Science Foundation of China for Distinguished Young Scholar under Grant 61425012the National Science and Technology Major Projects for the New Generation of Broadband Wireless Communication Network under Grant 2017ZX03001014
文摘Massive Multiple-Input Multiple-Output(MIMO)is considered as a key technology for 4G and 5G wireless communication systems to improve spectrum efficiency by supporting large number of concurrent users.In addition,for the target frequency band of 5G system,mmWave band,massive MIMO is pivotal in compensating the high pathloss.In this paper,we investigate the channel state information(CSI)acquisition problem for mmWave massive MIMO.With hybrid analog-digital antenna architecture,how to derive the analog beamforming and digital beamforming is studied.An iterative analog beam acquisition approach is proposed to save system overhead and reduce beam searching complexity.Regarding the digital beamforming,a grouping based codebook is proposed to facilitate CSI feedback.The codebook is then extended to incorporate also analog beam acquisition.Furthermore,channel reciprocity is exploited to save CSI reporting overhead and a two-stage approach is proposed to fully utilize the channel reciprocity at both mobile station and base station side and accelerate the CSI acquisition procedure.
基金The National Natural Science Foundation of China(No.61931005)。
文摘Cellular vehicle-to-everything(C-V2X)is the most promising V2X communication technology which can greatly improve traffic efficiency and road safety.However,when vehicles are interconnected with the surrounding radio environment,the CV2X system will face various network security risks and threats,significantly impacting on traffic and life safety.This paper proposes a novel unified identification management framework and security authentication mechanism for the C-V2X equipment based on the security problems analyses of the C-V2X system and the existing security protection schemes.This paper also presents the security analysis and evaluation for the unified identification management and authentication mechanism.A experiment system is implemented to verify feasibility and effectiveness for the proposed mechanism.
文摘TD-LTE-Advanced was accepted as one of the 4G global standards by ITU in 2012.In 2013,Chinese government issued 4G TD-LTE licenses to all 3 Chinese operators.Now,more than 1/3 of the global 4G equipments and users are using TD-LTE-Advanced technology.Simultaneously,research toward 5G is one of the most attractive topics of mobile communication industry.The 3GPP has launched several workshops to
基金This work was supported by the National Natural Science Foundation of China(NSFC)under Grant 61931005.
文摘Network densification is a promising solution to fulfill network capacity requirement and transmission rate for beyond 5G and 6G wireless communications.Ultra-dense network(UDN)integrates heterogeneous network resources and coordinates technologies on quality of service controlling,to provide users with flexible service.However,dense deployment reduces coverage radius of the cell,resulting in an increase on handover frequency,which makes a serious impact on service continuity.In this paper,we propose a proactive selection method for dynamic access points grouping(DAPGing)in accordance with“user-centric”philosophy,which selects target Access Points(AP)and reduces handover times to ensure communication continuity.This method includes two criteria:1)the user’s sojourn time,which is determined by analyzing the AP coverage area;2)neighbor relationship between APs,which is determined by coverage area and signal strength characteristics between neighboring APs.Therefore,candidate APs become the proactive selected ones to update the AP group.Stochastic geometry is used to build system model and performance metrics are analyzed,including AP group coverage probability and average update frequency.Experimental analysis shows that the proposed proactive selection method brings similar coverage probability to traditional handover method,while average update frequency is reduced more than 20%selection criteria.
文摘Vehicular networks are expected to empower auto mated driving and intelligent transportation via vehicle-to-everything(V2X)communications and edge/cloud-assisted computation,and in the meantime Cellular V2X(C-V2X)is gaining wide support from the global industrial ecosystem.The 5G NR-V2X technology is the evolution of LTE-V2X,which is expected to provide ultra-Reliable and Low-Latency Communications(uRLLC)with 1ms latency and 99.999%reliability.Nevertheless,vehicular networks still face great challenges in supporting many emerging time-critical applications,which comprise sensing,communication and computation as closed-loops.
基金Supported by the National Key Research and Development Program of China(No.2022ZD0115503).
文摘Modelling,predicting and analysing driver behaviours are essential to advanced driver assistance systems(ADAS)and the comprehensive understanding of complex driving scenarios.Recently,with the development of deep learning(DL),numerous driver behaviour learning(DBL)methods have been proposed and applied in connected vehicles(CV)and intelligent transportation systems(ITS).This study provides a review of DBL,which mainly focuses on typical applications in CV and ITS.First,a comprehensive review of the state-of-the-art DBL is presented.Next,Given the constantly changing nature of real driving scenarios,most existing learning-based models may suffer from the so-called“catastrophic forgetting,”which refers to their inability to perform well in previously learned scenarios after acquiring new ones.As a solution to the aforementioned issue,this paper presents a framework for continual driver behaviour learning(CDBL)by leveraging continual learning technology.The proposed CDBL framework is demonstrated to outperform existing methods in behaviour prediction through a case study.Finally,future works,potential challenges and emerging trends in this area are highlighted.
基金This work is supported in part by the National Science and Technology Major Projects of China(No.2017ZX03001014)the National Science Fund for Distinguished Young Scholars(No.61425012)the National Science Foundation Project(No.61300183).
文摘Applications of VANETs(Vehicular Ad hoc Networks)have their own requirements and challenges in wireless communication technology.Although regarded as the rst standard for VANETs,IEEE 802.11p is still in the eld-trial stage.Recently,LTE V2X(Long-Term Evolution Vehicular to X)appeared as a systematic V2X solution based on TD-LTE(Time Division Long-Term Evolution)4G.It is regarded as the most powerful competitor to 802.11p.We conduct link level simulations of LTE V2X and DSRC(Dedicated Short-Range Communication)for several di erent types of scenarios.Simulation results show that LTE V2X can achieve the same BLER(Block Error Ratio)with a lower SNR(Signal Noise Ratio)than DSRC.A more reliable link can be guaranteed by LTE V2X,which can achieve the same BLER with lower receiving power than DSRC.The coverage area of LTE V2X is larger than that of DSRC.
基金supported by the National Natural Science Foundation of China (Grant No.60502037)the Specialized Research Fund for the Doctoral Program of Higher Education of China (No.200800131019)+1 种基金Program for New Century Excellent Talents in University (No.NECT-07-0109)the National High Technology Research and Development Program of China (No.2007AA01Z206).
文摘Providing different service priority levels for different kinds of traffic is an important research area in the Internet.As compared with the existing best-effort(BE)service,recent researchers consider devising the belowbest-effort algorithm to realize a low priority service.The aim of below-best-effort service is to use the available bandwidth as much as possible in the premise of not interfering standard best-effort flows.With the best-effort transmission control protocol(TCP)transporting foreground traffic,below-best-effort service can transport background traffic which users do not urgently need to use.In this paper,we review the evolution of below-besteffort service and classify and compare these below-besteffort schemes.We also present some open problems in the research of below-best-effort service and point out the future work.
基金This work is supported by the National Natural Science Foundation of China(Nos.61622101,61571020)Ministry National Key Research and Development Project(No.2016YFE0123100)+1 种基金the National Basic Research Program of China("973"Program)(No.2013CB336700)the open research fund of the State Key Laboratory of Integrated Services Networks(No.ISN18-14),Xidian University.
文摘Vehicular network communication technology is currently attracting a considerable amount of attention.We consider a scenario in which vehicular communication nodes share the same spectrum resources and generate interference with other nodes.Compared with traditional interference-avoiding vehicular communications,this paper aims to increase the number of accessed communication links under the premise of satisfying the required QoS.In our research,communication nodes have opportunities to select relay nodes to both help improve their data transmissions and reduce their transmit power in order to decrease interference with other links while still satisfying their QoS requirements.Based on these objectives,we propose an innovative interference management method that considers link selection,power adaption,and communication mode selection simultaneously to maximize the number of communication links with the lowest power cost.Compared with traditional link-selection and power-adaption interference management schemes,the proposed scheme improves QoS satisfaction with high energy effciency.Simulation results demonstrate both the effciency and the e ectiveness of the proposed scheme.
