As the scale of the power system continues to expand,the environment for power operations becomes more and more complex.Existing risk management and control methods for power operations can only set the same risk dete...As the scale of the power system continues to expand,the environment for power operations becomes more and more complex.Existing risk management and control methods for power operations can only set the same risk detection standard and conduct the risk detection for any scenario indiscriminately.Therefore,more reliable and accurate security control methods are urgently needed.In order to improve the accuracy and reliability of the operation risk management and control method,this paper proposes a method for identifying the key links in the whole process of electric power operation based on the spatiotemporal hybrid convolutional neural network.To provide early warning and control of targeted risks,first,the video stream is framed adaptively according to the pixel changes in the video stream.Then,the optimized MobileNet is used to extract the feature map of the video stream,which contains both time-series and static spatial scene information.The feature maps are combined and non-linearly mapped to realize the identification of dynamic operating scenes.Finally,training samples and test samples are produced by using the whole process image of a power company in Xinjiang as a case study,and the proposed algorithm is compared with the unimproved MobileNet.The experimental results demonstrated that the method proposed in this paper can accurately identify the type and start and end time of each operation link in the whole process of electric power operation,and has good real-time performance.The average accuracy of the algorithm can reach 87.8%,and the frame rate is 61 frames/s,which is of great significance for improving the reliability and accuracy of security control methods.展开更多
This study utilizes hot dry rock(HDR)geothermal energy,which is not affected by climate,to address the capacity allocation of photovoltaic(PV)-storage hybrid power systems(HPSs)in frigid plateau regions.The study repl...This study utilizes hot dry rock(HDR)geothermal energy,which is not affected by climate,to address the capacity allocation of photovoltaic(PV)-storage hybrid power systems(HPSs)in frigid plateau regions.The study replaces the conventional electrochemical energy storage system with a stable HDR plant assisted by a flexible thermal storage(TS)plant.An HPS consisting of an HDR plant,a TS plant,and a PV plant is proposed.Game approaches are introduced to establish the game pattern model of the proposed HPS as the players.The annualized income of each player is used as the payoff function.Furthermore,non-cooperative game and cooperative game approaches for capacity allocation are proposed according to the interests of each player in the proposed HPS.Finally,the proposed model and approaches are validated by performing calculations for an HPS in the Gonghe Basin,Qinghai,China as a case study.The results show that in the proposed non-cooperative game approach,the players focus only on the individual payoff and neglect the overall system optimality.The proposed cooperative game approach for capacity allocation improves the flexibility of the HPS as well as the payoff of each game player.Thereby,the HPS can better satisfy the power fluctuation rate requirements of the grid and increase the equivalent firm capacity(EFC)of PV plants,which in turn indirectly guarantees the reliability of grid operation.展开更多
In recent years, integrated electricity-gas systems(IEGSs) have attracted widespread attention. The unifiedscheduling and control of the IEGS depends on high-precisionoperating data. To this end, it is necessary to es...In recent years, integrated electricity-gas systems(IEGSs) have attracted widespread attention. The unifiedscheduling and control of the IEGS depends on high-precisionoperating data. To this end, it is necessary to establish anappropriate state estimation (SE) model for IEGS to filter theraw measured data. Considering that power systems and naturalgas systems have different time scales and sampling periods, thispaper proposes a dynamic state estimation (DSE) method basedon a Kalman filter that can consider the dynamic characteristicsof natural gas pipelines. First, the standardized state transitionequations for the gas system are developed by applying the finitedifference method to the partial differential equations (PDEs) ofthe gas system;then the DSE model for IEGS is formulatedbased on a Kalman filter;also, the measurements from theelectricity system and the gas system with different samplingperiods are fused to ensure the observability of DSE by using theinterpolation method. The IEEE 39-bus electricity system and the18-nodes Belgium gas system are integrated as the test systems.Simulation results verify the proposed method’s accuracy andcalculation efficiency.展开更多
基金This paper is supported by the Science and technology projects of Yunnan Province(Grant No.202202AD080004).
文摘As the scale of the power system continues to expand,the environment for power operations becomes more and more complex.Existing risk management and control methods for power operations can only set the same risk detection standard and conduct the risk detection for any scenario indiscriminately.Therefore,more reliable and accurate security control methods are urgently needed.In order to improve the accuracy and reliability of the operation risk management and control method,this paper proposes a method for identifying the key links in the whole process of electric power operation based on the spatiotemporal hybrid convolutional neural network.To provide early warning and control of targeted risks,first,the video stream is framed adaptively according to the pixel changes in the video stream.Then,the optimized MobileNet is used to extract the feature map of the video stream,which contains both time-series and static spatial scene information.The feature maps are combined and non-linearly mapped to realize the identification of dynamic operating scenes.Finally,training samples and test samples are produced by using the whole process image of a power company in Xinjiang as a case study,and the proposed algorithm is compared with the unimproved MobileNet.The experimental results demonstrated that the method proposed in this paper can accurately identify the type and start and end time of each operation link in the whole process of electric power operation,and has good real-time performance.The average accuracy of the algorithm can reach 87.8%,and the frame rate is 61 frames/s,which is of great significance for improving the reliability and accuracy of security control methods.
基金supported in part by the Joint Fund Project of National Natural Science Foundation of China(No.U1766203)the Key R&D and Transformation Plan of Qinghai Province(No.2021-GX-109)the Basic Research Project of Qinghai Province(No.2020-ZJ-741)。
文摘This study utilizes hot dry rock(HDR)geothermal energy,which is not affected by climate,to address the capacity allocation of photovoltaic(PV)-storage hybrid power systems(HPSs)in frigid plateau regions.The study replaces the conventional electrochemical energy storage system with a stable HDR plant assisted by a flexible thermal storage(TS)plant.An HPS consisting of an HDR plant,a TS plant,and a PV plant is proposed.Game approaches are introduced to establish the game pattern model of the proposed HPS as the players.The annualized income of each player is used as the payoff function.Furthermore,non-cooperative game and cooperative game approaches for capacity allocation are proposed according to the interests of each player in the proposed HPS.Finally,the proposed model and approaches are validated by performing calculations for an HPS in the Gonghe Basin,Qinghai,China as a case study.The results show that in the proposed non-cooperative game approach,the players focus only on the individual payoff and neglect the overall system optimality.The proposed cooperative game approach for capacity allocation improves the flexibility of the HPS as well as the payoff of each game player.Thereby,the HPS can better satisfy the power fluctuation rate requirements of the grid and increase the equivalent firm capacity(EFC)of PV plants,which in turn indirectly guarantees the reliability of grid operation.
基金This work was supported in part by National Natural Science Foundation of China(51777067)and(52077076)in part by funding from the State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources(LAPS2021-18).
文摘In recent years, integrated electricity-gas systems(IEGSs) have attracted widespread attention. The unifiedscheduling and control of the IEGS depends on high-precisionoperating data. To this end, it is necessary to establish anappropriate state estimation (SE) model for IEGS to filter theraw measured data. Considering that power systems and naturalgas systems have different time scales and sampling periods, thispaper proposes a dynamic state estimation (DSE) method basedon a Kalman filter that can consider the dynamic characteristicsof natural gas pipelines. First, the standardized state transitionequations for the gas system are developed by applying the finitedifference method to the partial differential equations (PDEs) ofthe gas system;then the DSE model for IEGS is formulatedbased on a Kalman filter;also, the measurements from theelectricity system and the gas system with different samplingperiods are fused to ensure the observability of DSE by using theinterpolation method. The IEEE 39-bus electricity system and the18-nodes Belgium gas system are integrated as the test systems.Simulation results verify the proposed method’s accuracy andcalculation efficiency.