The attacks on in-vehicle Controller Area Network(CAN)bus messages severely disrupt normal communication between vehicles.Therefore,researches on intrusion detection models for CAN have positive business value for veh...The attacks on in-vehicle Controller Area Network(CAN)bus messages severely disrupt normal communication between vehicles.Therefore,researches on intrusion detection models for CAN have positive business value for vehicle security,and the intrusion detection technology for CAN bus messages can effectively protect the invehicle network from unlawful attacks.Previous machine learning-based models are unable to effectively identify intrusive abnormal messages due to their inherent shortcomings.Hence,to address the shortcomings of the previous machine learning-based intrusion detection technique,we propose a novel method using Attention Mechanism and AutoEncoder for Intrusion Detection(AMAEID).The AMAEID model first converts the raw hexadecimal message data into binary format to obtain better input.Then the AMAEID model encodes and decodes the binary message data using a multi-layer denoising autoencoder model to obtain a hidden feature representation that can represent the potential features behind the message data at a deeper level.Finally,the AMAEID model uses the attention mechanism and the fully connected layer network to infer whether the message is an abnormal message or not.The experimental results with three evaluation metrics on a real in-vehicle CAN bus message dataset outperform some traditional machine learning algorithms,demonstrating the effectiveness of the AMAEID model.展开更多
In this paper,an active network measurement platform is proposed which is a combination of hardware and software.Its innovation lies in the high performance of hardware combined with features that the software is easy...In this paper,an active network measurement platform is proposed which is a combination of hardware and software.Its innovation lies in the high performance of hardware combined with features that the software is easy to program,which retains software flexibility at the same time.By improving the precision of packet timestamp programmable hardware equipment,it provides packet sending control more accurately and supports the microsecond packet interval.We have implemented a model on the NetMagic platform,and done some experiments to analyze the accuracy difference of the user,the kernel and hardware timestamp.展开更多
A stability problem of the linear networked control systems(NCSs) with multisensor having differen data missing rates is investigated in this paper.Each sensor of the multiple sensor-controller communication channels ...A stability problem of the linear networked control systems(NCSs) with multisensor having differen data missing rates is investigated in this paper.Each sensor of the multiple sensor-controller communication channels is assumed to have an individual stochastic data missing rate.The stochastic data missing is described by a Bernoulli binary distribution.Sufficient conditions are given for the closed-loop linear NCS which is exponentially stable in the mean square sense as the existence of random multiple data missing.The stability problem could b disposed by the MATLAB linear matrix inequality(LMI) tool easily.A simulation case is provided to illustrat the validity of the presented LMI approach.展开更多
Based on a media access and control（MAC）protocol,an arrangement of channels and transceivers in optical packet switching dense wavelength division multiplexing（DWDM）networks is proposed in this paper.In order to r...Based on a media access and control（MAC）protocol,an arrangement of channels and transceivers in optical packet switching dense wavelength division multiplexing（DWDM）networks is proposed in this paper.In order to reduce the cost of nodes,fixed transmitters and receivers are used instead of tunable transmitters and receivers.Two fixed transmitters and many fixed receivers are used in each node in the scheme.The average waiting delay of this scheme is analyzed through mathematics and computer simulation.The result shows that the property of the scheme is almost the same as using tunable transmitter and receiver.Furthermore,if the tuning time of tunable transmitters is taken into account,the performance of the tunable transmitter scheme is poor than this scheme at the average waiting delay and throughput of the network.展开更多
This paper considers the output feedback control and stabilization problems for network control systems（NCSs） with packet dropout and input delay, and the TCP（transmission control protocol） case is mainly investig...This paper considers the output feedback control and stabilization problems for network control systems（NCSs） with packet dropout and input delay, and the TCP（transmission control protocol） case is mainly investigated. Specifically, whether the control signal is lost can be acknowledged by the receiver in the NCSs. The main contributions are： 1） For the finite horizon case, the ＂optimal＂output feedback control is derived by using the dynamic programming approach, and it is noted that the separation principle holds for the considered situation; 2） For the infinite horizon case, for the first time, the necessary and sufficient stabilization conditions are derived for NCSs with packet dropout and delay.展开更多
A class of networked control systems is investigated whose communication network is shared with other applications. The design objective for such a system setting is not only the optimization of the control performanc...A class of networked control systems is investigated whose communication network is shared with other applications. The design objective for such a system setting is not only the optimization of the control performance but also the efficient utilization of the communication resources. We observe that at a large time scale the data packet delay in the communication network is roughly varying piecewise constant, which is typically true for data networks like the Internet. Based on this observation, a dynamic data packing scheme is proposed within the recently developed packet-based control framework for networked control systems. As expected this proposed approach achieves a fine balance between the control performance and the communication utilization: the similar control performance can be obtained at dramatically reduced cost of the communication resources. Simulations illustrate the effectiveness of the proposed approach.展开更多
In this paper, the H∞ control problem is investigated for a class of discrete-time switched linear systems with modal persistent dwell-time(MPDT) switching. The redundant channels are considered to use in the data tr...In this paper, the H∞ control problem is investigated for a class of discrete-time switched linear systems with modal persistent dwell-time(MPDT) switching. The redundant channels are considered to use in the data transmission to benefit the capability of overcoming the fragility of networks commonly configured by a single channel in the communication networks subject to random packet losses. In light of a new class of Lyapunov functions, the desired observer-based quasi-time-dependent controllers, which have less conservatism than the time-independent ones, are designed such that the resulting closed-loop system is exponentially mean-square stable with a guaranteed H_∞ disturbance attenuation performance. The MPDT can be minimized while ensuring the existence of such a class of observer-based controllers for a given period of persistence. An example of DC-DC boost converter is provided to verify the effectiveness of theoretical findings.展开更多
This paper addresses a channel scheduling problem for group of dynamically decoupled nonlinear subsystems with actuators connected through digital communication channels and controlled by a centralized controller. Due...This paper addresses a channel scheduling problem for group of dynamically decoupled nonlinear subsystems with actuators connected through digital communication channels and controlled by a centralized controller. Due to the limited communication capacity, only one channel can be activated and hence there is only one pair of sensor and actuator can communicate with the controller at each time instant. In addition, the communication channels are not reliable so Markovian packed dropout is introduced. A predictive control framework is adopted for controller/scheduler co-design to alleviate the performance loss caused by the limited communication capacity. Instead of sending a single control value, the controller sends a sequence of predicted control values to a selected actuator so that there are control input candidates which can be fed to the subsystem when the actuator does not communicate with the controller. A stochastic algorithm is proposed to schedule the usage of the communication medium and sufficient conditions on stochastic stability are given under some mild assumptions.展开更多
基金supported by Chongqing Big Data Engineering Laboratory for Children,Chongqing Electronics Engineering Technology Research Center for Interactive Learning,Project of Science and Technology Research Program of Chongqing Education Commission of China. (No.KJZD-K201801601).
文摘The attacks on in-vehicle Controller Area Network(CAN)bus messages severely disrupt normal communication between vehicles.Therefore,researches on intrusion detection models for CAN have positive business value for vehicle security,and the intrusion detection technology for CAN bus messages can effectively protect the invehicle network from unlawful attacks.Previous machine learning-based models are unable to effectively identify intrusive abnormal messages due to their inherent shortcomings.Hence,to address the shortcomings of the previous machine learning-based intrusion detection technique,we propose a novel method using Attention Mechanism and AutoEncoder for Intrusion Detection(AMAEID).The AMAEID model first converts the raw hexadecimal message data into binary format to obtain better input.Then the AMAEID model encodes and decodes the binary message data using a multi-layer denoising autoencoder model to obtain a hidden feature representation that can represent the potential features behind the message data at a deeper level.Finally,the AMAEID model uses the attention mechanism and the fully connected layer network to infer whether the message is an abnormal message or not.The experimental results with three evaluation metrics on a real in-vehicle CAN bus message dataset outperform some traditional machine learning algorithms,demonstrating the effectiveness of the AMAEID model.
基金Supported by the National High Technology Research and Development Programme of China(No.2007AA01Z416)"New Start" Academic Research Projects of Beijing Union University(No.ZK201204)
文摘In this paper,an active network measurement platform is proposed which is a combination of hardware and software.Its innovation lies in the high performance of hardware combined with features that the software is easy to program,which retains software flexibility at the same time.By improving the precision of packet timestamp programmable hardware equipment,it provides packet sending control more accurately and supports the microsecond packet interval.We have implemented a model on the NetMagic platform,and done some experiments to analyze the accuracy difference of the user,the kernel and hardware timestamp.
基金the National Natural Science Foundation of China(No.U1204515)the Foundation of Young Teachers in Colleges and Universities of Shanghai(No.ZZSDJ12002)the Shanghai Municipal Natural Science Foundation(No.14ZR1417200)
文摘A stability problem of the linear networked control systems(NCSs) with multisensor having differen data missing rates is investigated in this paper.Each sensor of the multiple sensor-controller communication channels is assumed to have an individual stochastic data missing rate.The stochastic data missing is described by a Bernoulli binary distribution.Sufficient conditions are given for the closed-loop linear NCS which is exponentially stable in the mean square sense as the existence of random multiple data missing.The stability problem could b disposed by the MATLAB linear matrix inequality(LMI) tool easily.A simulation case is provided to illustrat the validity of the presented LMI approach.
文摘Based on a media access and control（MAC）protocol,an arrangement of channels and transceivers in optical packet switching dense wavelength division multiplexing（DWDM）networks is proposed in this paper.In order to reduce the cost of nodes,fixed transmitters and receivers are used instead of tunable transmitters and receivers.Two fixed transmitters and many fixed receivers are used in each node in the scheme.The average waiting delay of this scheme is analyzed through mathematics and computer simulation.The result shows that the property of the scheme is almost the same as using tunable transmitter and receiver.Furthermore,if the tuning time of tunable transmitters is taken into account,the performance of the tunable transmitter scheme is poor than this scheme at the average waiting delay and throughput of the network.
基金supported by the National Natural Science Foundation of China under Grant Nos.61120106011,61573221,61633014supported by the program for Outstanding Ph D Candidate of Shandong University
文摘This paper considers the output feedback control and stabilization problems for network control systems（NCSs） with packet dropout and input delay, and the TCP（transmission control protocol） case is mainly investigated. Specifically, whether the control signal is lost can be acknowledged by the receiver in the NCSs. The main contributions are： 1） For the finite horizon case, the ＂optimal＂output feedback control is derived by using the dynamic programming approach, and it is noted that the separation principle holds for the considered situation; 2） For the infinite horizon case, for the first time, the necessary and sufficient stabilization conditions are derived for NCSs with packet dropout and delay.
基金supported by the National Natural Science Foundation of China(Grant Nos.6142230761174061&61304048)+4 种基金the Scientific Research Starting Foundation for the Returned Overseas Chinese Scholars,Ministry of Education of Chinathe National Hi-Tech Research and Development Program of China("863"Project)(Grant No.2014AA06A503)the Youth Innovation Promotion Association,Chinese Academy of Sciences,in part by the Youth Top-Notch Talent Support Programthe 1000-Talent Youth ProgramZhejiang 1000-Talent Program
文摘A class of networked control systems is investigated whose communication network is shared with other applications. The design objective for such a system setting is not only the optimization of the control performance but also the efficient utilization of the communication resources. We observe that at a large time scale the data packet delay in the communication network is roughly varying piecewise constant, which is typically true for data networks like the Internet. Based on this observation, a dynamic data packing scheme is proposed within the recently developed packet-based control framework for networked control systems. As expected this proposed approach achieves a fine balance between the control performance and the communication utilization: the similar control performance can be obtained at dramatically reduced cost of the communication resources. Simulations illustrate the effectiveness of the proposed approach.
基金supported by the National Natural Science Foundation of China(Grant No.61322301)the Natural Science Foundation of Heilongjiang(Grant Nos.F201417&JC2015015)+1 种基金the Fundamental Research Funds for the Central UniversitiesChina(Grant Nos.HIT.BRETIII.201211&HIT.BRETIV.201306)
文摘In this paper, the H∞ control problem is investigated for a class of discrete-time switched linear systems with modal persistent dwell-time(MPDT) switching. The redundant channels are considered to use in the data transmission to benefit the capability of overcoming the fragility of networks commonly configured by a single channel in the communication networks subject to random packet losses. In light of a new class of Lyapunov functions, the desired observer-based quasi-time-dependent controllers, which have less conservatism than the time-independent ones, are designed such that the resulting closed-loop system is exponentially mean-square stable with a guaranteed H_∞ disturbance attenuation performance. The MPDT can be minimized while ensuring the existence of such a class of observer-based controllers for a given period of persistence. An example of DC-DC boost converter is provided to verify the effectiveness of theoretical findings.
基金supported by the Energy Innovation Research Programme of Singapore under Grant No.NRF2013EWT-EIRP004-012Qilu Youth Scholar Discipline Construction Funding from Shandong University+1 种基金the National Natural Science Foundation of China(NSFC)under Grant Nos.61573220,61633014Projects of Major International(Regional)Joint Research Program NSFC under Grant No.61720106011
文摘This paper addresses a channel scheduling problem for group of dynamically decoupled nonlinear subsystems with actuators connected through digital communication channels and controlled by a centralized controller. Due to the limited communication capacity, only one channel can be activated and hence there is only one pair of sensor and actuator can communicate with the controller at each time instant. In addition, the communication channels are not reliable so Markovian packed dropout is introduced. A predictive control framework is adopted for controller/scheduler co-design to alleviate the performance loss caused by the limited communication capacity. Instead of sending a single control value, the controller sends a sequence of predicted control values to a selected actuator so that there are control input candidates which can be fed to the subsystem when the actuator does not communicate with the controller. A stochastic algorithm is proposed to schedule the usage of the communication medium and sufficient conditions on stochastic stability are given under some mild assumptions.
