Mobile multihop communication network is an important branch of modern mobile communication system, and is an important technical support for ubiquitous communication. The random movement of the nodes makes the networ...Mobile multihop communication network is an important branch of modern mobile communication system, and is an important technical support for ubiquitous communication. The random movement of the nodes makes the networking be more flexible, but the frequently changing topology will decrease the link duration between nodes significantly, which will increase the packets loss probability and affect the network communication performance. Aiming at the problem of declining link duration caused by nomadic characteristics in mobile multihop communication network, four link duration models for possible moving states are established based on different features in real networking process in this paper, which will provide reliable criterion for the optimal routing selection. Model analysis and simulation results show that the reliable route established by the proposed model will effectively extend the link duration, and can enhance the global stability of the mobile multihop information transmission, so as to provide new option to transmission reliability improvement for the mobile communication network.展开更多
The problem of mobile localization for wireless sensor network has attracted considerable attention in recent years. The localization accuracy will drastically grade in non-line of sight(NLOS) conditions. In this pape...The problem of mobile localization for wireless sensor network has attracted considerable attention in recent years. The localization accuracy will drastically grade in non-line of sight(NLOS) conditions. In this paper, we propose a mobile localization strategy based on Kalman filter. The key technologies for the proposed method are the NLOS identification and mitigation. The proposed method does not need the prior knowledge of the NLOS error and it is independent of the physical measurement ways. Simulation results show that the proposed method owns the higher localization accuracy when compared with other methods.展开更多
According to the existing research, the fault section location and fault location of passive distribution network and active distribution network are reviewed. Among them, fault location of passive distribution networ...According to the existing research, the fault section location and fault location of passive distribution network and active distribution network are reviewed. Among them, fault location of passive distribution network mainly introduces fault segment location based on transient state and steady state quantity and fault location based on transient quantity. The active distribution network mainly introduces the fault segment location based on the current amount and the switching capacity based on the distribution network topology. On this basis, the difficulties of fault location in the distribution network at present are analyzed, and the future development is prospected.展开更多
In this study, the Global Navigation Satellite System （GNSS） network of China is discussed, which can be used to monitor atmospheric precipitable water vapor （PWV）. By the end of 2013, the network had 952 GNSS sit...In this study, the Global Navigation Satellite System （GNSS） network of China is discussed, which can be used to monitor atmospheric precipitable water vapor （PWV）. By the end of 2013, the network had 952 GNSS sites, including 260 belonging to the Crustal Movement Observation Network of China （CMONOC） and 692 belonging to the China Meteorological Administration GNSS network （CMAGN）. Additionally, GNSS observation collecting and data processing procedures are presented and PWV data quality control methods are investigated. PWV levels as determined by GNSS and radiosonde are compared. The results show that GNSS estimates are generally in good agreement with measurements of radio- sondes and water vapor radiometers （WVR）. The PWV retrieved by the national GNSS network is used in weather forecasting, assimilation of data into numerical weather prediction models, the validation of PWV estimates by radiosonde, and plum rain monitoring. The network is also used to monitor the total ionospheric electron content.展开更多
This paper deals with deriving the properties of updated neural network model that is exploited to identify an unknown nonlinear system via the standard gradient learning algorithm. The convergence of this algorithm f...This paper deals with deriving the properties of updated neural network model that is exploited to identify an unknown nonlinear system via the standard gradient learning algorithm. The convergence of this algorithm for online training the three-layer neural networks in stochastic environment is studied. A special case where an unknown nonlinearity can exactly be approximated by some neural network with a nonlinear activation function for its output layer is considered. To analyze the asymptotic behavior of the learning processes, the so-called Lyapunov-like approach is utilized. As the Lyapunov function, the expected value of the square of approximation error depending on network parameters is chosen. Within this approach, sufficient conditions guaranteeing the convergence of learning algorithm with probability 1 are derived. Simulation results are presented to support the theoretical analysis.展开更多
This study proposes a hybrid network model based on data enhancement to address the problem of low accuracy in photovoltaic(PV)power prediction that arises due to insuffi cient data samples for new PV plants.First,a t...This study proposes a hybrid network model based on data enhancement to address the problem of low accuracy in photovoltaic(PV)power prediction that arises due to insuffi cient data samples for new PV plants.First,a time-series gener ative adversarial network(TimeGAN)is used to learn the distri bution law of the original PV data samples and the temporal correlations between their features,and these are then used to generate new samples to enhance the training set.Subsequently,a hybrid network model that fuses bi-directional long-short term memory(BiLSTM)network with attention mechanism(AM)in the framework of deep&cross network(DCN)is con structed to effectively extract deep information from the origi nal features while enhancing the impact of important informa tion on the prediction results.Finally,the hyperparameters in the hybrid network model are optimized using the whale optimi zation algorithm(WOA),which prevents the network model from falling into a local optimum and gives the best prediction results.The simulation results show that after data enhance ment by TimeGAN,the hybrid prediction model proposed in this paper can effectively improve the accuracy of short-term PV power prediction and has wide applicability.展开更多
基金support by the National Natural Science Foundation of China under Grant No.61302074, 61571181Natural Science Foundation of Heilongjiang Province under Grant No.QC2013C061+2 种基金Modern Sensor Technology Research and Innovation Team Foundation of Heilongjiang Province No. 2012TD007Postdoctoral Research Foundation of Heilongjiang Province No. LBH-Q15121Postgraduate Innovation Research Foundation of Heilongjiang University under Grant No. YJSCX2016-019HLJU
文摘Mobile multihop communication network is an important branch of modern mobile communication system, and is an important technical support for ubiquitous communication. The random movement of the nodes makes the networking be more flexible, but the frequently changing topology will decrease the link duration between nodes significantly, which will increase the packets loss probability and affect the network communication performance. Aiming at the problem of declining link duration caused by nomadic characteristics in mobile multihop communication network, four link duration models for possible moving states are established based on different features in real networking process in this paper, which will provide reliable criterion for the optimal routing selection. Model analysis and simulation results show that the reliable route established by the proposed model will effectively extend the link duration, and can enhance the global stability of the mobile multihop information transmission, so as to provide new option to transmission reliability improvement for the mobile communication network.
基金supported by the National Natural Science Foundation of China under Grant No. 61403068, No. 61232016, No. U1405254 and No. 61501100Fundamental Research Funds for the Central Universities of China under Grant No. N130323002 and No. N130323004+3 种基金Natural Science Foundation of Hebei Province under Grant No. F2015501097 and No. F2016501080Scientific Research Fund of Hebei Provincial Education Department under Grant No. Z2014078the PAPD fundNEUQ internal funding under Grant No. XNB201509 and XNB201510
文摘The problem of mobile localization for wireless sensor network has attracted considerable attention in recent years. The localization accuracy will drastically grade in non-line of sight(NLOS) conditions. In this paper, we propose a mobile localization strategy based on Kalman filter. The key technologies for the proposed method are the NLOS identification and mitigation. The proposed method does not need the prior knowledge of the NLOS error and it is independent of the physical measurement ways. Simulation results show that the proposed method owns the higher localization accuracy when compared with other methods.
文摘According to the existing research, the fault section location and fault location of passive distribution network and active distribution network are reviewed. Among them, fault location of passive distribution network mainly introduces fault segment location based on transient state and steady state quantity and fault location based on transient quantity. The active distribution network mainly introduces the fault segment location based on the current amount and the switching capacity based on the distribution network topology. On this basis, the difficulties of fault location in the distribution network at present are analyzed, and the future development is prospected.
基金financially supported by the Special Fund for Meteorological Scientific Research in the Public Interest(GYHY201406012)the National Natural Science Foundation of China(41275114)a construction fund for CMONOC
文摘In this study, the Global Navigation Satellite System （GNSS） network of China is discussed, which can be used to monitor atmospheric precipitable water vapor （PWV）. By the end of 2013, the network had 952 GNSS sites, including 260 belonging to the Crustal Movement Observation Network of China （CMONOC） and 692 belonging to the China Meteorological Administration GNSS network （CMAGN）. Additionally, GNSS observation collecting and data processing procedures are presented and PWV data quality control methods are investigated. PWV levels as determined by GNSS and radiosonde are compared. The results show that GNSS estimates are generally in good agreement with measurements of radio- sondes and water vapor radiometers （WVR）. The PWV retrieved by the national GNSS network is used in weather forecasting, assimilation of data into numerical weather prediction models, the validation of PWV estimates by radiosonde, and plum rain monitoring. The network is also used to monitor the total ionospheric electron content.
文摘This paper deals with deriving the properties of updated neural network model that is exploited to identify an unknown nonlinear system via the standard gradient learning algorithm. The convergence of this algorithm for online training the three-layer neural networks in stochastic environment is studied. A special case where an unknown nonlinearity can exactly be approximated by some neural network with a nonlinear activation function for its output layer is considered. To analyze the asymptotic behavior of the learning processes, the so-called Lyapunov-like approach is utilized. As the Lyapunov function, the expected value of the square of approximation error depending on network parameters is chosen. Within this approach, sufficient conditions guaranteeing the convergence of learning algorithm with probability 1 are derived. Simulation results are presented to support the theoretical analysis.
基金supported by the Regional Innovation and Development Joint Fund of National Natural Science Foundation of China(No.U19A20106)the Science and Technology Major Projects of Anhui Province(No.202203f07020003)the Science and Technology Project of State Grid Corporation of China(No.52120522000F).
文摘This study proposes a hybrid network model based on data enhancement to address the problem of low accuracy in photovoltaic(PV)power prediction that arises due to insuffi cient data samples for new PV plants.First,a time-series gener ative adversarial network(TimeGAN)is used to learn the distri bution law of the original PV data samples and the temporal correlations between their features,and these are then used to generate new samples to enhance the training set.Subsequently,a hybrid network model that fuses bi-directional long-short term memory(BiLSTM)network with attention mechanism(AM)in the framework of deep&cross network(DCN)is con structed to effectively extract deep information from the origi nal features while enhancing the impact of important informa tion on the prediction results.Finally,the hyperparameters in the hybrid network model are optimized using the whale optimi zation algorithm(WOA),which prevents the network model from falling into a local optimum and gives the best prediction results.The simulation results show that after data enhance ment by TimeGAN,the hybrid prediction model proposed in this paper can effectively improve the accuracy of short-term PV power prediction and has wide applicability.
