In this paper,we propose an improved support vector clustering(SVC)algorithm to cluster wind turbines(WTs)in a wind farm(WF).A boundary points(BPs)detecting method based on the grid theory and the connected subdomain(...In this paper,we propose an improved support vector clustering(SVC)algorithm to cluster wind turbines(WTs)in a wind farm(WF).A boundary points(BPs)detecting method based on the grid theory and the connected subdomain(CS)are proposed.Thus the efficiency of SVC is enhanced while maintaining the accuracy of the algorithm.As for the multi-wind condition equivalent of WF,a method to determine the number and capacity of each of the aggregated wind turbines(AWTs)based on historical wind data is proposed.Only wind speed(WS)and wind direction(WD)of the WF are needed to calculate the WSs of each AWT.Results demonstrate that the algorithm proposed in this paper can cluster WTs quickly and accurately.And the dynamic aggregated models of the WFs are suitable for both the single-wind condition and multi-wind condition simulations,with high accuracy being obtained.展开更多
In this article,current research findings of local scour at offshore windfarm monopile foundations are presented.The scour mechanisms and scour depth prediction formulas under different hydrodynamic conditions are sum...In this article,current research findings of local scour at offshore windfarm monopile foundations are presented.The scour mechanisms and scour depth prediction formulas under different hydrodynamic conditions are summarized,including the current-only condition,wave-only condition,combined wave-current condition,and complex dynamic condition.Furthermore,this article analyzes the influencing factors on the basis of classical equations for predicting the equilibrium scour depth under specific conditions.The weakness of existing researches and future prospects are also discussed.It is suggested that future research shall focus on physical experiments under unsteady tidal currents or other complex loadings.The computational fluid dynamics-discrete element method and artificial intelligence technique are suggested being adopted to study the scour at offshore windfarm foundations.展开更多
Advanced sensing,data analysis and communication techniques have led to the emergence and tremendous develop-ment of industrial internet of things(IIoT)in recent years,which raises revolution in condition monitoring a...Advanced sensing,data analysis and communication techniques have led to the emergence and tremendous develop-ment of industrial internet of things(IIoT)in recent years,which raises revolution in condition monitoring and maintenance for electrical assets.An open ecosystem for future IIoT is proposed in this paper and the architecture of the open ecosystem is discussed.An open development environment needs to be established for users to interact with power devices and servers freely via web or mobile applications installed on user terminals,increasing IIoT scalability and flexibility.The core technologies of open ecosystem in future IIoT are discussed,which include comprehensive sensing techniques,wide-area communication tools,Big Data service infrastructure,data analysis algorithms and intelligent maintenance schemes.An application of future IIoT ecosystem in wind farm maintenance is then presented.It is demonstrated that the efficiency and effectiveness of wind farm maintenance can be improved with the support of open ecosystem of future IIoT,providing an innovative insight for electrical assets monitoring and maintenance with high reliability.展开更多
In this paper, a method of stabilizing electric power by a system which is a combination of wind power generation and pumped storage power generation is proposed. The system operates based on the output predicted valu...In this paper, a method of stabilizing electric power by a system which is a combination of wind power generation and pumped storage power generation is proposed. The system operates based on the output predicted value of the windfarm. When the measured windfarm output is larger than the predicted value, the system is pumping up water with surplus power. When the windfarm output is smaller than the predicted value, the system is filling up lack power by hydro generator. Also, since hydro generator works with a start-up delay time, output shortage occurs at this time. To improve output shortage at the time, we estimate the time below the predicted value by a statistical model. As the result, the system succeeded in stabilizing the power and improving the start-up delay time of the hydro generator.展开更多
基金This work has been supported by the projects of the SGCC.
文摘In this paper,we propose an improved support vector clustering(SVC)algorithm to cluster wind turbines(WTs)in a wind farm(WF).A boundary points(BPs)detecting method based on the grid theory and the connected subdomain(CS)are proposed.Thus the efficiency of SVC is enhanced while maintaining the accuracy of the algorithm.As for the multi-wind condition equivalent of WF,a method to determine the number and capacity of each of the aggregated wind turbines(AWTs)based on historical wind data is proposed.Only wind speed(WS)and wind direction(WD)of the WF are needed to calculate the WSs of each AWT.Results demonstrate that the algorithm proposed in this paper can cluster WTs quickly and accurately.And the dynamic aggregated models of the WFs are suitable for both the single-wind condition and multi-wind condition simulations,with high accuracy being obtained.
基金supported by the Major International Joint Research Project P0W3M of the National Natural Science Foundation of China(Grant No.51920105013)the General Project of the National Natural Science Foundation of China(Grant No.52071127).
文摘In this article,current research findings of local scour at offshore windfarm monopile foundations are presented.The scour mechanisms and scour depth prediction formulas under different hydrodynamic conditions are summarized,including the current-only condition,wave-only condition,combined wave-current condition,and complex dynamic condition.Furthermore,this article analyzes the influencing factors on the basis of classical equations for predicting the equilibrium scour depth under specific conditions.The weakness of existing researches and future prospects are also discussed.It is suggested that future research shall focus on physical experiments under unsteady tidal currents or other complex loadings.The computational fluid dynamics-discrete element method and artificial intelligence technique are suggested being adopted to study the scour at offshore windfarm foundations.
基金This work was supported in part by the Beijing Municipal Natural Science Foundation(L161002)and in part by the National Natural Science Foundation of China under Grant 51822705,51777112 and 61703227.
文摘Advanced sensing,data analysis and communication techniques have led to the emergence and tremendous develop-ment of industrial internet of things(IIoT)in recent years,which raises revolution in condition monitoring and maintenance for electrical assets.An open ecosystem for future IIoT is proposed in this paper and the architecture of the open ecosystem is discussed.An open development environment needs to be established for users to interact with power devices and servers freely via web or mobile applications installed on user terminals,increasing IIoT scalability and flexibility.The core technologies of open ecosystem in future IIoT are discussed,which include comprehensive sensing techniques,wide-area communication tools,Big Data service infrastructure,data analysis algorithms and intelligent maintenance schemes.An application of future IIoT ecosystem in wind farm maintenance is then presented.It is demonstrated that the efficiency and effectiveness of wind farm maintenance can be improved with the support of open ecosystem of future IIoT,providing an innovative insight for electrical assets monitoring and maintenance with high reliability.
文摘In this paper, a method of stabilizing electric power by a system which is a combination of wind power generation and pumped storage power generation is proposed. The system operates based on the output predicted value of the windfarm. When the measured windfarm output is larger than the predicted value, the system is pumping up water with surplus power. When the windfarm output is smaller than the predicted value, the system is filling up lack power by hydro generator. Also, since hydro generator works with a start-up delay time, output shortage occurs at this time. To improve output shortage at the time, we estimate the time below the predicted value by a statistical model. As the result, the system succeeded in stabilizing the power and improving the start-up delay time of the hydro generator.
