By optimizing the network topology, this paper proposes a newmethod of queuing theory clustering algorithm based on dynamic programming in a home energy management system（ HEMS）. First, the total cost of the HEMS sy...By optimizing the network topology, this paper proposes a newmethod of queuing theory clustering algorithm based on dynamic programming in a home energy management system（ HEMS）. First, the total cost of the HEMS system is divided into two parts, the gateway installation cost and the data transmission cost. Secondly, through comparing two kinds of different queuing theories, the cost problem of the HEMS is converted into the problem of gateway deployment. Finally, a machine-to-machine（ M2M） gateway configuration scheme is designed to minimize the cost of the system. Simulation results showthat the cost of the HEMS system mainly comes from the installation cost of the gateways when the gateway buffer space is large enough. If the gateway buffer space is limited, the proposed queue algorithm can effectively achieve optimal gateway setting while maintaining the minimal cost of the HEMS at desired levels through marginal analyses and the properties of cost minimization.展开更多
Hybrid Machine Learning (HML) is a kind of advanced algorithm in the field of intelligent information process. It combines the induced learning based-on decision-making tree with the blocking neural network. And it pr...Hybrid Machine Learning (HML) is a kind of advanced algorithm in the field of intelligent information process. It combines the induced learning based-on decision-making tree with the blocking neural network. And it provides a useful intelligent knowledge-based data mining technique. Its core algorithm is ID3 and Field Theory based ART (FTART). The paper introduces the principals of hybrid machine learning firstly, and then applies it into analyzing family apparel expenditures and their influencing factors systematically. Finally, compared with those from the traditional statistic methods, the results from HML is more friendly and easily to be understood. Besides, the forecasting by HML is more correct than by the traditional ways.展开更多
This paper demonstrates how achieving optimal integration between design and energy resources management can be particularly attractive in terms of energy consumption saving （cooling and heating） and lowering greenh...This paper demonstrates how achieving optimal integration between design and energy resources management can be particularly attractive in terms of energy consumption saving （cooling and heating） and lowering greenhouse gas emissions. The building automation system is based on innovative middleware framework which simplifies the modeling of a software for intelligent management of buildings and allows a multistandard and multiprotocol integration of sensors and actuators. The project has the target of underlining the economical opportunities and perspectives concerning the smart system adoption. Estimating the effects of home automation is essential to help its implementation, especially now that energy cost represents a consistent part of the house/building consumptions and will increase in the next few years. The results of the framework application in a residential building proves the validity of the proposed solution.展开更多
The topology of in-home power line communication(PLC) networks varies frequently, which makes traditional routing algorithms failure. To solve this problem, an end-to-end transmission time for remaining path(TTRP) met...The topology of in-home power line communication(PLC) networks varies frequently, which makes traditional routing algorithms failure. To solve this problem, an end-to-end transmission time for remaining path(TTRP) metric-based opportunistic routing(TTRPOR) is proposed. Since a local broadcasting scheme is adopted, the algorithm can find the optimal path for forwarding packets in a dynamic PLC network. The closed-form of the outage probability for a PLC channel is derived to estimate the TTRP. It is proved that the average throughput can achieve maximum as the metric TTRP is utilized to sort candidate forwarding nodes.Numerical results show that the end-to-end throughput of networks with TTRPOR, outperforms that of the network adopting DSR and EXOR, especially for the case of varying-topology in-home PLC networks.展开更多
基金The National Natural Science Foundation of China(No.61471031)the Fundamental Research Funds for the Central Universities(No.2013JBZ01)the Program for New Century Excellent Talents in University of Ministry of Education of China(No.NCET-12-0766)
文摘By optimizing the network topology, this paper proposes a newmethod of queuing theory clustering algorithm based on dynamic programming in a home energy management system（ HEMS）. First, the total cost of the HEMS system is divided into two parts, the gateway installation cost and the data transmission cost. Secondly, through comparing two kinds of different queuing theories, the cost problem of the HEMS is converted into the problem of gateway deployment. Finally, a machine-to-machine（ M2M） gateway configuration scheme is designed to minimize the cost of the system. Simulation results showthat the cost of the HEMS system mainly comes from the installation cost of the gateways when the gateway buffer space is large enough. If the gateway buffer space is limited, the proposed queue algorithm can effectively achieve optimal gateway setting while maintaining the minimal cost of the HEMS at desired levels through marginal analyses and the properties of cost minimization.
文摘Hybrid Machine Learning (HML) is a kind of advanced algorithm in the field of intelligent information process. It combines the induced learning based-on decision-making tree with the blocking neural network. And it provides a useful intelligent knowledge-based data mining technique. Its core algorithm is ID3 and Field Theory based ART (FTART). The paper introduces the principals of hybrid machine learning firstly, and then applies it into analyzing family apparel expenditures and their influencing factors systematically. Finally, compared with those from the traditional statistic methods, the results from HML is more friendly and easily to be understood. Besides, the forecasting by HML is more correct than by the traditional ways.
文摘This paper demonstrates how achieving optimal integration between design and energy resources management can be particularly attractive in terms of energy consumption saving （cooling and heating） and lowering greenhouse gas emissions. The building automation system is based on innovative middleware framework which simplifies the modeling of a software for intelligent management of buildings and allows a multistandard and multiprotocol integration of sensors and actuators. The project has the target of underlining the economical opportunities and perspectives concerning the smart system adoption. Estimating the effects of home automation is essential to help its implementation, especially now that energy cost represents a consistent part of the house/building consumptions and will increase in the next few years. The results of the framework application in a residential building proves the validity of the proposed solution.
基金supported in part by Open Research Fund of National Key Laboratory of Electromagnetic EnvironmentChina Research Institute of Radiowave Propagation (Grant No. 201500013)+3 种基金Open Research Fund of National Mobile Communications Research LaboratoryJiangsu Provincial Science Foundation Project (Grant No. BK20150786)Southeast University (Grant No. 2013D02)National Natural Science Foundation of China (Grants Nos. 61501238, 61271230, 61472190)
文摘The topology of in-home power line communication(PLC) networks varies frequently, which makes traditional routing algorithms failure. To solve this problem, an end-to-end transmission time for remaining path(TTRP) metric-based opportunistic routing(TTRPOR) is proposed. Since a local broadcasting scheme is adopted, the algorithm can find the optimal path for forwarding packets in a dynamic PLC network. The closed-form of the outage probability for a PLC channel is derived to estimate the TTRP. It is proved that the average throughput can achieve maximum as the metric TTRP is utilized to sort candidate forwarding nodes.Numerical results show that the end-to-end throughput of networks with TTRPOR, outperforms that of the network adopting DSR and EXOR, especially for the case of varying-topology in-home PLC networks.
