Beam management,including initial access(IA)and beam tracking,is essential to the millimeter-wave Unmanned Aerial Vehicle(UAV)network.However,the conventional communicationonly and feedback-based schemes suffer a high...Beam management,including initial access(IA)and beam tracking,is essential to the millimeter-wave Unmanned Aerial Vehicle(UAV)network.However,the conventional communicationonly and feedback-based schemes suffer a high delay and low accuracy of beam alignment,since they only enable the receiver to passively“hear”the information of the transmitter from the radio domain.This paper presents a novel sensing-assisted beam management approach,the first solution that fully utilizes the information from the visual domain to improve communication performance.We employ both integrated sensing and communication and computer vision techniques and design an extended Kalman filtering method for beam tracking and prediction.Besides,we also propose a novel dual identity association solution to distinguish multiple UAVs in dynamic environments.Real-world experiments and numerical results show that the proposed solution outperforms the conventional methods in IA delay,association accuracy,tracking error,and communication performance.展开更多
To overcome the problem of existing neighboring access point （AP） discovery methods in WLAN, for example they （PnP） of mul proposed. Us can not provide the accurate neighboring APs information needed for the Plug-...To overcome the problem of existing neighboring access point （AP） discovery methods in WLAN, for example they （PnP） of mul proposed. Us can not provide the accurate neighboring APs information needed for the Plug-and-Play ti-mode APs, three kinds of neighboring AP discovery and information exchange methods are ing these three neighboring AP discovery methods, passive discovery method, active discovery method and station assistant discovery method, the multi-mode AP can discover all neighboring APs and obtain needed information. We further propose two whole process flows, which combine three discovery methods in different manner, to achieve different goals. One process flow is to discover the neighboring AP as fast as possible, called fast discovery process flow. The other is to discover the neighboring AP with minimal interference to neighboring and accuracy of the method is confirmed APs, called the minimal interference process flow. The validity by the simulation.展开更多
Microservices have become popular in enterprises because of their excellent scalability and timely update capabilities.However,while fine-grained modularity and service-orientation decrease the complexity of system de...Microservices have become popular in enterprises because of their excellent scalability and timely update capabilities.However,while fine-grained modularity and service-orientation decrease the complexity of system development,the complexity of system operation and maintenance has been greatly increased,on the contrary.Multiple types of system failures occur frequently,and it is hard to detect and diagnose failures in time.Furthermore,microservices are updated frequently.Existing anomaly detection models depend on offline training and cannot adapt to the frequent updates of microservices.This paper proposes an anomaly detection approach for microservice systems with multi-source data streams.This approach realizes online model construction and online anomaly detection,and is capable of self-updating and self-adapting.Experimental results show that this approach can correctly identify 78.85%of faults of different types.展开更多
Facing the challenges on how to improve spectrum efficiency and how to realize heterogeneous network convergence in future wireless networks,a cognitive radio network(CRN) is proposed as one of the solutions.This has ...Facing the challenges on how to improve spectrum efficiency and how to realize heterogeneous network convergence in future wireless networks,a cognitive radio network(CRN) is proposed as one of the solutions.This has become a major research topic in recent years and it is timely to give an overview of the development of CRN and to summarize key issues and technologies.The fundamental concepts of CRN,including the cognitive cycle model,the network architecture,and the cognitive ability and intelligent decision functions,are introduced in detail based on recent advances.Key issues for each topic,followed with recent research on theory and method,are then classified and the industrialization developments of CRN testbeds based on TD-LTE cellular system and standards are briefly presented.Finally,conclusions are reached on the perspectives and directions of future development.展开更多
Facing the challenges of dynamic adaptation capabilities in the time-varying environment of cognitive wireless networks(CWNs),we introduce reconfiguration capabilities that flexibly and dynamically adapt to changing w...Facing the challenges of dynamic adaptation capabilities in the time-varying environment of cognitive wireless networks(CWNs),we introduce reconfiguration capabilities that flexibly and dynamically adapt to changing wireless environments and service requirements.As an essential characteristic of CWNs,the cognitive reconfiguration can meet user requirements,realize interoperability between heterogeneous networks,make full use of radio resources and adapt to time-varying environments to achieve end-to-end requirements.However,the reconfiguration implementation is still challenging due to the need for complex environment cognition,multi-objective optimization,autonomic decision-making and end-to-end requirement extraction.As an intelligent technology for solving complex issues,we apply adaptive neuro-fuzzy inference system(ANFIS) techniques in this paper to address these challenges in cognitive reconfiguration for self-learning and optimal decision making based on multi-domain cognition results.Moreover,this paper designs a generic ANFIS cognitive reconfiguration system including three functional entities,which are the context management module,multi-domain database and ANFIS optimization module.Finally,numerous results prove the effective performance improvements of the ANFIS based reconfiguration solution in CWN for global end-to-end goals.展开更多
As one of the key characteristics in cognitive wireless networks(CWNs),network environment awareness techniques have received much attention recently.Instead of traditional spectrum sensing technology that suffers fro...As one of the key characteristics in cognitive wireless networks(CWNs),network environment awareness techniques have received much attention recently.Instead of traditional spectrum sensing technology that suffers from problems of miss detection,false alarm,hidden node,and inefficiency,cognitive pilot channel(CPC) technology has been proposed as one of the candidate solutions for an efficient and accurate network information delivery scheme to user equipment(UE).The aim of the CPC technology is to provide the necessary information for the reconfiguration of the UE using the public signaling channel.To ensure the efficient information delivery,the whole geographical area covered by the CPC is divided into square meshes of the same size.Moreover,two typical network information transmission modes for CPC deployment are also proposed:broadcast CPC mode and on-demand CPC mode.To further improve the efficiency of network information delivery,an efficient dynamic mesh grouping scheme has been designed which is based on the fractal theory for the broadcast CPC mode,where adaptive rectangular sized meshes are used to approximately cover the whole area.Compared to the traditional fixed size mesh division strategy,results show that the proposed dynamic mesh grouping scheme significantly reduces the number of meshes by grouping similar meshes together,and the average delay of receiving CPC information on the UE side is therefore reduced.展开更多
基金supported by the Major Research Projects of the National Natural Science Foundation of China(92267202)the National Key Research and Development Project(2020YFA0711303)the BUPT Excellent Ph.D.Students Foundation(CX2022208).
文摘Beam management,including initial access(IA)and beam tracking,is essential to the millimeter-wave Unmanned Aerial Vehicle(UAV)network.However,the conventional communicationonly and feedback-based schemes suffer a high delay and low accuracy of beam alignment,since they only enable the receiver to passively“hear”the information of the transmitter from the radio domain.This paper presents a novel sensing-assisted beam management approach,the first solution that fully utilizes the information from the visual domain to improve communication performance.We employ both integrated sensing and communication and computer vision techniques and design an extended Kalman filtering method for beam tracking and prediction.Besides,we also propose a novel dual identity association solution to distinguish multiple UAVs in dynamic environments.Real-world experiments and numerical results show that the proposed solution outperforms the conventional methods in IA delay,association accuracy,tracking error,and communication performance.
基金NTT-DoCoMo Beijing Communication Labs the National High Technology Research and Development Program of China(No.2006AA01Z276).
文摘To overcome the problem of existing neighboring access point （AP） discovery methods in WLAN, for example they （PnP） of mul proposed. Us can not provide the accurate neighboring APs information needed for the Plug-and-Play ti-mode APs, three kinds of neighboring AP discovery and information exchange methods are ing these three neighboring AP discovery methods, passive discovery method, active discovery method and station assistant discovery method, the multi-mode AP can discover all neighboring APs and obtain needed information. We further propose two whole process flows, which combine three discovery methods in different manner, to achieve different goals. One process flow is to discover the neighboring AP as fast as possible, called fast discovery process flow. The other is to discover the neighboring AP with minimal interference to neighboring and accuracy of the method is confirmed APs, called the minimal interference process flow. The validity by the simulation.
基金supported by ZTE Industry-University-Institute Cooperation Funds under Grant No.HF-CN-202008200001。
文摘Microservices have become popular in enterprises because of their excellent scalability and timely update capabilities.However,while fine-grained modularity and service-orientation decrease the complexity of system development,the complexity of system operation and maintenance has been greatly increased,on the contrary.Multiple types of system failures occur frequently,and it is hard to detect and diagnose failures in time.Furthermore,microservices are updated frequently.Existing anomaly detection models depend on offline training and cannot adapt to the frequent updates of microservices.This paper proposes an anomaly detection approach for microservice systems with multi-source data streams.This approach realizes online model construction and online anomaly detection,and is capable of self-updating and self-adapting.Experimental results show that this approach can correctly identify 78.85%of faults of different types.
基金supported by the National Basic Research Program of China (2009CB320400)the National Natural Science Foundation of China(61121001,60832009)+1 种基金the National Science and Technology Major Project of China (2012ZX03003006)the Program for New Century Excellent Talents in University (NCET-01-0259)
文摘Facing the challenges on how to improve spectrum efficiency and how to realize heterogeneous network convergence in future wireless networks,a cognitive radio network(CRN) is proposed as one of the solutions.This has become a major research topic in recent years and it is timely to give an overview of the development of CRN and to summarize key issues and technologies.The fundamental concepts of CRN,including the cognitive cycle model,the network architecture,and the cognitive ability and intelligent decision functions,are introduced in detail based on recent advances.Key issues for each topic,followed with recent research on theory and method,are then classified and the industrialization developments of CRN testbeds based on TD-LTE cellular system and standards are briefly presented.Finally,conclusions are reached on the perspectives and directions of future development.
基金supported by the National Basic Research Program of China (2009CB320400)the National Natural Science Foundation of China(60832009,61121001)the National Science and Technology Major Project of China (2012ZX03003006)
文摘Facing the challenges of dynamic adaptation capabilities in the time-varying environment of cognitive wireless networks(CWNs),we introduce reconfiguration capabilities that flexibly and dynamically adapt to changing wireless environments and service requirements.As an essential characteristic of CWNs,the cognitive reconfiguration can meet user requirements,realize interoperability between heterogeneous networks,make full use of radio resources and adapt to time-varying environments to achieve end-to-end requirements.However,the reconfiguration implementation is still challenging due to the need for complex environment cognition,multi-objective optimization,autonomic decision-making and end-to-end requirement extraction.As an intelligent technology for solving complex issues,we apply adaptive neuro-fuzzy inference system(ANFIS) techniques in this paper to address these challenges in cognitive reconfiguration for self-learning and optimal decision making based on multi-domain cognition results.Moreover,this paper designs a generic ANFIS cognitive reconfiguration system including three functional entities,which are the context management module,multi-domain database and ANFIS optimization module.Finally,numerous results prove the effective performance improvements of the ANFIS based reconfiguration solution in CWN for global end-to-end goals.
基金supported by the National Basic Research Program of China (2009CB320400)the National Natural Science Foundation of China(60832009,61121001)+1 种基金the Program for New Century Excellent Talents in University (NCET-01-0259)the National Science and Technology Major Project of China (2012ZX03003006)
文摘As one of the key characteristics in cognitive wireless networks(CWNs),network environment awareness techniques have received much attention recently.Instead of traditional spectrum sensing technology that suffers from problems of miss detection,false alarm,hidden node,and inefficiency,cognitive pilot channel(CPC) technology has been proposed as one of the candidate solutions for an efficient and accurate network information delivery scheme to user equipment(UE).The aim of the CPC technology is to provide the necessary information for the reconfiguration of the UE using the public signaling channel.To ensure the efficient information delivery,the whole geographical area covered by the CPC is divided into square meshes of the same size.Moreover,two typical network information transmission modes for CPC deployment are also proposed:broadcast CPC mode and on-demand CPC mode.To further improve the efficiency of network information delivery,an efficient dynamic mesh grouping scheme has been designed which is based on the fractal theory for the broadcast CPC mode,where adaptive rectangular sized meshes are used to approximately cover the whole area.Compared to the traditional fixed size mesh division strategy,results show that the proposed dynamic mesh grouping scheme significantly reduces the number of meshes by grouping similar meshes together,and the average delay of receiving CPC information on the UE side is therefore reduced.
