When a line failure occurs in a power grid, a load transfer is implemented to reconfigure the network by changingthe states of tie-switches and load demands. Computation speed is one of the major performance indicator...When a line failure occurs in a power grid, a load transfer is implemented to reconfigure the network by changingthe states of tie-switches and load demands. Computation speed is one of the major performance indicators inpower grid load transfer, as a fast load transfer model can greatly reduce the economic loss of post-fault powergrids. In this study, a reinforcement learning method is developed based on a deep deterministic policy gradient.The tedious training process of the reinforcement learning model can be conducted offline, so the model showssatisfactory performance in real-time operation, indicating that it is suitable for fast load transfer. Consideringthat the reinforcement learning model performs poorly in satisfying safety constraints, a safe action-correctionframework is proposed to modify the learning model. In the framework, the action of load shedding is correctedaccording to sensitivity analysis results under a small discrete increment so as to match the constraints of line flowlimits. The results of case studies indicate that the proposed method is practical for fast and safe power grid loadtransfer.展开更多
With the deepening of coalbed methane(CBM)exploration and development,the problem of low gas production has gradually become one of the main factors restricting the development of the CBM industry in China.Reasonable ...With the deepening of coalbed methane(CBM)exploration and development,the problem of low gas production has gradually become one of the main factors restricting the development of the CBM industry in China.Reasonable well pattern deployment can improve the productivity of CBM wells and reduce the cost of production,while the reservoir changes of CBM wells play a important role for well pattern infilling.In this study,the dynamic characteristics of the average reservoir pressure(ARP),permeability,and drainage radius during the development process of CBM wells are systematically analyzed,and predicted the production changes of well groups before and after infilling wells in combination with the characteristics of reservoir changes.The results show that the high gas production wells have a larger pressure drop,long drainage radius,and a large increase in permeability.On the contrary,low gas production wells are characterized by small drainage radius,damaged permeability and difficult to recover.The productivity of infilled horizontal wells is predicted for two well groups with different productivity and reservoir dynamic characteristics.After infilling wells,the production of current wells has increased at different degrees.It is predicted that the average gas production of low gas production well group H1 and middle gas production well group H2 will increase 1.64 and 2.09 times respectively after 3000 days production simulation.In addition,the pressure interference between wells has increased significantly,and the overall gas production of the well group has greatly increased.Infill wells can achieve better development results in areas with superior CBM resources,recoverable reservoir permeability,and small drainage radius during the early production process.The research results provide a reference for the later infill adjustment of CBM well patterns in the study area.展开更多
基金the Incubation Project of State Grid Jiangsu Corporation of China“Construction and Application of Intelligent Load Transferring Platform for Active Distribution Networks”(JF2023031).
文摘When a line failure occurs in a power grid, a load transfer is implemented to reconfigure the network by changingthe states of tie-switches and load demands. Computation speed is one of the major performance indicators inpower grid load transfer, as a fast load transfer model can greatly reduce the economic loss of post-fault powergrids. In this study, a reinforcement learning method is developed based on a deep deterministic policy gradient.The tedious training process of the reinforcement learning model can be conducted offline, so the model showssatisfactory performance in real-time operation, indicating that it is suitable for fast load transfer. Consideringthat the reinforcement learning model performs poorly in satisfying safety constraints, a safe action-correctionframework is proposed to modify the learning model. In the framework, the action of load shedding is correctedaccording to sensitivity analysis results under a small discrete increment so as to match the constraints of line flowlimits. The results of case studies indicate that the proposed method is practical for fast and safe power grid loadtransfer.
基金the National Natural Science Foundation of China(Grant Nos.U1910205 and 41872178)the National Science and Technology Major Project of China(No.2017ZX05064003).
文摘With the deepening of coalbed methane(CBM)exploration and development,the problem of low gas production has gradually become one of the main factors restricting the development of the CBM industry in China.Reasonable well pattern deployment can improve the productivity of CBM wells and reduce the cost of production,while the reservoir changes of CBM wells play a important role for well pattern infilling.In this study,the dynamic characteristics of the average reservoir pressure(ARP),permeability,and drainage radius during the development process of CBM wells are systematically analyzed,and predicted the production changes of well groups before and after infilling wells in combination with the characteristics of reservoir changes.The results show that the high gas production wells have a larger pressure drop,long drainage radius,and a large increase in permeability.On the contrary,low gas production wells are characterized by small drainage radius,damaged permeability and difficult to recover.The productivity of infilled horizontal wells is predicted for two well groups with different productivity and reservoir dynamic characteristics.After infilling wells,the production of current wells has increased at different degrees.It is predicted that the average gas production of low gas production well group H1 and middle gas production well group H2 will increase 1.64 and 2.09 times respectively after 3000 days production simulation.In addition,the pressure interference between wells has increased significantly,and the overall gas production of the well group has greatly increased.Infill wells can achieve better development results in areas with superior CBM resources,recoverable reservoir permeability,and small drainage radius during the early production process.The research results provide a reference for the later infill adjustment of CBM well patterns in the study area.