In Vehicle-to-infrastructure(V2I)communication networks,mobile users are able to access Internet services,such as video streaming,digital map downloading,database access,online gaming,and even safety services like acc...In Vehicle-to-infrastructure(V2I)communication networks,mobile users are able to access Internet services,such as video streaming,digital map downloading,database access,online gaming,and even safety services like accident alarm,traffic condition broadcast,etc.,through fixed roadside units.However,the dynamics of communication environment and frequent changing topology critically challenge the design of an efficient transport layer protocol,which makes it difficult to guarantee diverse Quality of Service(QoS) requirements for various applications.In this paper,we present a novel transport layer scheme in infrastructure based vehicular networks,and aim to resolve some challenging issues such as source transfer rate adjustment,congestion avoidance,and fairness.By precisely detecting packet losses and identifying various causes of these losses(for example,link disconnection,channel error,packet collision,buffer overflow),the proposed scheme adopts different reacting mechanisms to deal with each of the losses.Moreover,it timely monitors the buffer size of the bottleneck Road-Side Unit(RSU),and dynamically makes transfer rate feedbacks to source nodes to avoid buffer overflow or vacancy.Finally,analysis and simulation results show that the proposed scheme not only successfully reduces packet losses because of buffer overflow and link disconnection but also improves the utilization efficiency of channel resource.展开更多
The congestion control problem in a single node network has been solved by the nonlinearfeedback control method,which has been proven to be effective and robust for different router’s queuesize.However,these control ...The congestion control problem in a single node network has been solved by the nonlinearfeedback control method,which has been proven to be effective and robust for different router’s queuesize.However,these control models are based on the single layer network architecture,and the sendersand receivers are directly connected by one pair of routers.With the network architecture being moreand more complex,it is a serious problem how to cooperate many routers working in the multilayernetwork simultaneously.In this paper,an effective Active Queue Management(AQM)scheme toguarantee the stability by the nonlinear control of imposing some restrictions on AQM parameter inmultilayer network is proposed.The nonlinear control can rely on some heuristics and network trafficcontrollers that appear to be highly correlated with the multilayer network status.The proposedmethod is based on the improved classical Random Early Detection(RED)differential equation and atheorem for network congestion control.The theorem proposed in the paper proved that the stability ofthe fluid model can effectively ensure the convergence of the average rate to its equilibrium pointthrough many routers in multilayer network.Moreover,when the network capacity is larger,theproposed scheme can still approach to the fullest extensibility of utilization and ensure the stability ofthe fluid model.The paper reveals the reasons of congestion control in multilayer network,provides atheorem for avoiding network congestion,and gives simulations to verify the results.展开更多
In this paper, a novel idea for rate allocation combining both vertical coupling and horizontal coupling constraints is proposed, and a unified utility function to balance two paradoxical issues: efficiency and fairne...In this paper, a novel idea for rate allocation combining both vertical coupling and horizontal coupling constraints is proposed, and a unified utility function to balance two paradoxical issues: efficiency and fairness, revenue and cost is elaborated in WCDMA networks. Then, the optimal rate allocation problem is formulated as a network utility maximization(NUM) model based on cross-layer design and end-to-end congestion control, aiming at exploring the impacts of wired networks and the characteristics of radio access networks(RANs) on rate allocation. Furthermore, a distributed algorithm is derived, which can effectively match load states between RANs and wired networks, followed by a detailed illustration of the practical implementations. Numerical results demonstrate a signifi cant performance improvement in the end-to-end throughput.展开更多
Electric load forecasting has been a major area of research in the last decade since the production of accurate short-term forecasts for electricity loads has proven to be a key to success for many of the decision mak...Electric load forecasting has been a major area of research in the last decade since the production of accurate short-term forecasts for electricity loads has proven to be a key to success for many of the decision makers in the energy sector, from power generation to operation of the system. The objective of this research is to analyze the capacity of the MLP （multilayer perceptron neural network） versus SOM （self-organizing map neural network） for short-term load forecasting. The MLP is one of the most commonly used networks. It can be used for classification problems, model construction, series forecasting and discrete control. On the other hand, the SOM is a type of artificial neural network that is trained using unsupervised data to produce a low-dimensional, discretized representation of an input space of training samples in a cell map. Historical data of real global load demand were used for the research. Both neural models provide good prediction results, but the results obtained with the SOM maps are markedly better Also the main advantage of SOM maps is that they reach good results as a network unsupervised. It is much easier to train and interpret the results.展开更多
Based on the neural network technique, this paper proposes a BP neural network model which integrates geological factors which affect top coal caving in a comprehensive index. The index of top coal caving may be used ...Based on the neural network technique, this paper proposes a BP neural network model which integrates geological factors which affect top coal caving in a comprehensive index. The index of top coal caving may be used to forecast the mining cost of working faces, which shows the model’s potential prospect of applications.展开更多
Artificial neural network has unique advantages for massively parallel processing, distributed storage capacity and self-learning ability. The paper mainly constructs neural network identifier and neural network contr...Artificial neural network has unique advantages for massively parallel processing, distributed storage capacity and self-learning ability. The paper mainly constructs neural network identifier and neural network controller for system identification and control on temperature and hmnidity of heating and drying system of materials. And the paper introduces the structure and principles of neural network, and focuses on analyzing learning algorithm, training algorithm and limitation of the most widely applied multi-layer feed-forward neural network （ BP network） , based on which the paper proposes introducing momentum to improve BP network.展开更多
基金ACKNOWLEDGEMENT This work was partially supported by the Na- tional Natural Science Foundation of China under Grant No. 61101121 the Fundamental Research Funds for the Central Universities of China under Grant No. N110404002+2 种基金 the Key Laboratory Project Funds of Shenyang Ligong University under Grant No. 4771004kfs03 the Educational Committee of Liaoning Province Science and Technology Research Projects under Grant No. L2013096 the National Sci- ence and Technology Support Program under Grant No. 2012BAH82F04.
文摘In Vehicle-to-infrastructure(V2I)communication networks,mobile users are able to access Internet services,such as video streaming,digital map downloading,database access,online gaming,and even safety services like accident alarm,traffic condition broadcast,etc.,through fixed roadside units.However,the dynamics of communication environment and frequent changing topology critically challenge the design of an efficient transport layer protocol,which makes it difficult to guarantee diverse Quality of Service(QoS) requirements for various applications.In this paper,we present a novel transport layer scheme in infrastructure based vehicular networks,and aim to resolve some challenging issues such as source transfer rate adjustment,congestion avoidance,and fairness.By precisely detecting packet losses and identifying various causes of these losses(for example,link disconnection,channel error,packet collision,buffer overflow),the proposed scheme adopts different reacting mechanisms to deal with each of the losses.Moreover,it timely monitors the buffer size of the bottleneck Road-Side Unit(RSU),and dynamically makes transfer rate feedbacks to source nodes to avoid buffer overflow or vacancy.Finally,analysis and simulation results show that the proposed scheme not only successfully reduces packet losses because of buffer overflow and link disconnection but also improves the utilization efficiency of channel resource.
基金the National Natural Science Foundation of China(No.60572093)the Specialized Research Fundfor the Doctoral Program of Higher Education(No.20050004016).
文摘The congestion control problem in a single node network has been solved by the nonlinearfeedback control method,which has been proven to be effective and robust for different router’s queuesize.However,these control models are based on the single layer network architecture,and the sendersand receivers are directly connected by one pair of routers.With the network architecture being moreand more complex,it is a serious problem how to cooperate many routers working in the multilayernetwork simultaneously.In this paper,an effective Active Queue Management(AQM)scheme toguarantee the stability by the nonlinear control of imposing some restrictions on AQM parameter inmultilayer network is proposed.The nonlinear control can rely on some heuristics and network trafficcontrollers that appear to be highly correlated with the multilayer network status.The proposedmethod is based on the improved classical Random Early Detection(RED)differential equation and atheorem for network congestion control.The theorem proposed in the paper proved that the stability ofthe fluid model can effectively ensure the convergence of the average rate to its equilibrium pointthrough many routers in multilayer network.Moreover,when the network capacity is larger,theproposed scheme can still approach to the fullest extensibility of utilization and ensure the stability ofthe fluid model.The paper reveals the reasons of congestion control in multilayer network,provides atheorem for avoiding network congestion,and gives simulations to verify the results.
基金supported by National Natural Science Foundation of China (61172079, 61231008, 61201141, 61301176)111 Project (B08038)+1 种基金National S&T Major Project (2010ZX03003001)Shaanxi Province Science and Technology Research and Development Program (2011KJXX-40)
文摘In this paper, a novel idea for rate allocation combining both vertical coupling and horizontal coupling constraints is proposed, and a unified utility function to balance two paradoxical issues: efficiency and fairness, revenue and cost is elaborated in WCDMA networks. Then, the optimal rate allocation problem is formulated as a network utility maximization(NUM) model based on cross-layer design and end-to-end congestion control, aiming at exploring the impacts of wired networks and the characteristics of radio access networks(RANs) on rate allocation. Furthermore, a distributed algorithm is derived, which can effectively match load states between RANs and wired networks, followed by a detailed illustration of the practical implementations. Numerical results demonstrate a signifi cant performance improvement in the end-to-end throughput.
文摘Electric load forecasting has been a major area of research in the last decade since the production of accurate short-term forecasts for electricity loads has proven to be a key to success for many of the decision makers in the energy sector, from power generation to operation of the system. The objective of this research is to analyze the capacity of the MLP （multilayer perceptron neural network） versus SOM （self-organizing map neural network） for short-term load forecasting. The MLP is one of the most commonly used networks. It can be used for classification problems, model construction, series forecasting and discrete control. On the other hand, the SOM is a type of artificial neural network that is trained using unsupervised data to produce a low-dimensional, discretized representation of an input space of training samples in a cell map. Historical data of real global load demand were used for the research. Both neural models provide good prediction results, but the results obtained with the SOM maps are markedly better Also the main advantage of SOM maps is that they reach good results as a network unsupervised. It is much easier to train and interpret the results.
文摘Based on the neural network technique, this paper proposes a BP neural network model which integrates geological factors which affect top coal caving in a comprehensive index. The index of top coal caving may be used to forecast the mining cost of working faces, which shows the model’s potential prospect of applications.
文摘Artificial neural network has unique advantages for massively parallel processing, distributed storage capacity and self-learning ability. The paper mainly constructs neural network identifier and neural network controller for system identification and control on temperature and hmnidity of heating and drying system of materials. And the paper introduces the structure and principles of neural network, and focuses on analyzing learning algorithm, training algorithm and limitation of the most widely applied multi-layer feed-forward neural network （ BP network） , based on which the paper proposes introducing momentum to improve BP network.
