Traditional optimal scheduling methods are limited to accurate physical models and parameter settings, which aredifficult to adapt to the uncertainty of source and load, and there are problems such as the inability to...Traditional optimal scheduling methods are limited to accurate physical models and parameter settings, which aredifficult to adapt to the uncertainty of source and load, and there are problems such as the inability to make dynamicdecisions continuously. This paper proposed a dynamic economic scheduling method for distribution networksbased on deep reinforcement learning. Firstly, the economic scheduling model of the new energy distributionnetwork is established considering the action characteristics of micro-gas turbines, and the dynamic schedulingmodel based on deep reinforcement learning is constructed for the new energy distribution network system with ahigh proportion of new energy, and the Markov decision process of the model is defined. Secondly, Second, for thechanging characteristics of source-load uncertainty, agents are trained interactively with the distributed networkin a data-driven manner. Then, through the proximal policy optimization algorithm, agents adaptively learn thescheduling strategy and realize the dynamic scheduling decision of the new energy distribution network system.Finally, the feasibility and superiority of the proposed method are verified by an improved IEEE 33-node simulationsystem.展开更多
In modern giant buildings,in order to improve energy utilization efficiency, cooling systems have developed from conventional chillers alone to smart energy net which includes chillers,ice storage,ground-source heat p...In modern giant buildings,in order to improve energy utilization efficiency, cooling systems have developed from conventional chillers alone to smart energy net which includes chillers,ice storage,ground-source heat pump,combined cooling heating and power( CCHP) and so on. The reasonable distribution of load is the key to guarantee such system in economical operation.Based on typical multi-type cooling system,economic models of different devices are presented and real-time intelligent economic scheduling with the approach of mixed integer programming is carried out. This algorithm has been applied in a certain building of Shanghai and results of simulation show that it is able to provide guidance on intelligent economic scheduling for multi-type cooling system.展开更多
In this paper,the microgrid economic scheduling mathematical model considering the integration of plug-in hybrid electric vehicles(PHEVs)is presented and the influence of different charging and discharging modes on mi...In this paper,the microgrid economic scheduling mathematical model considering the integration of plug-in hybrid electric vehicles(PHEVs)is presented and the influence of different charging and discharging modes on microgrid economic operation is analyzed.The generic algorithm is used to find an economically optimal solution for the microgrid and PHEV owners.The scheduling of PHEVs and the microgrid are optimized to reduce daily electricity cost and the potential benefits of controlled charging/discharging are explored systematically.Constraints caused by vehicle utilization as well as technical limitations of distributed generation and energy storage system are taken into account.The proposed economic scheduling is evaluated through a simulation by using a typical grid-connected microgrid model.展开更多
基金the State Grid Liaoning Electric Power Supply Co.,Ltd.(Research on Scheduling Decision Technology Based on Interactive Reinforcement Learning for Adapting High Proportion of New Energy,No.2023YF-49).
文摘Traditional optimal scheduling methods are limited to accurate physical models and parameter settings, which aredifficult to adapt to the uncertainty of source and load, and there are problems such as the inability to make dynamicdecisions continuously. This paper proposed a dynamic economic scheduling method for distribution networksbased on deep reinforcement learning. Firstly, the economic scheduling model of the new energy distributionnetwork is established considering the action characteristics of micro-gas turbines, and the dynamic schedulingmodel based on deep reinforcement learning is constructed for the new energy distribution network system with ahigh proportion of new energy, and the Markov decision process of the model is defined. Secondly, Second, for thechanging characteristics of source-load uncertainty, agents are trained interactively with the distributed networkin a data-driven manner. Then, through the proximal policy optimization algorithm, agents adaptively learn thescheduling strategy and realize the dynamic scheduling decision of the new energy distribution network system.Finally, the feasibility and superiority of the proposed method are verified by an improved IEEE 33-node simulationsystem.
基金the Project of Science and Technology Commission of Shanghai Municipality,China(No.12dz1200203)the Chongming Smart Grid National Sci-Tech Support Plan of China(No.2013BAA01B04)
文摘In modern giant buildings,in order to improve energy utilization efficiency, cooling systems have developed from conventional chillers alone to smart energy net which includes chillers,ice storage,ground-source heat pump,combined cooling heating and power( CCHP) and so on. The reasonable distribution of load is the key to guarantee such system in economical operation.Based on typical multi-type cooling system,economic models of different devices are presented and real-time intelligent economic scheduling with the approach of mixed integer programming is carried out. This algorithm has been applied in a certain building of Shanghai and results of simulation show that it is able to provide guidance on intelligent economic scheduling for multi-type cooling system.
基金This work was supported in part by the National Natural Science Foundation of China(No.51477067)in part by the China-UK Joint Project of the National Natural Science Foundation of China(No.51361130150)in part by the Fundamental Research Funds for the Central Universities(No.2014QN219).
文摘In this paper,the microgrid economic scheduling mathematical model considering the integration of plug-in hybrid electric vehicles(PHEVs)is presented and the influence of different charging and discharging modes on microgrid economic operation is analyzed.The generic algorithm is used to find an economically optimal solution for the microgrid and PHEV owners.The scheduling of PHEVs and the microgrid are optimized to reduce daily electricity cost and the potential benefits of controlled charging/discharging are explored systematically.Constraints caused by vehicle utilization as well as technical limitations of distributed generation and energy storage system are taken into account.The proposed economic scheduling is evaluated through a simulation by using a typical grid-connected microgrid model.
