典型文献
Day-ahead scheduling based on reinforcement learning with hybrid action space
文献摘要：
Driven by the improvement of the smart grid, the active distribution network (ADN) has attracted much attention due to its characteristic of active management. By making full use of electricity price signals for optimal scheduling, the total cost of the ADN can be reduced. However, the optimal day-ahead scheduling problem is challenging since the future electri-city price is unknown. Moreover, in ADN, some schedulable vari-ables are continuous while some schedulable variables are dis-crete, which increases the difficulty of determining the optimal scheduling scheme. In this paper, the day-ahead scheduling problem of the ADN is formulated as a Markov decision process (MDP) with continuous-discrete hybrid action space. Then, an algorithm based on multi-agent hybrid reinforcement learning (HRL) is proposed to obtain the optimal scheduling scheme. The proposed algorithm adopts the structure of centralized training and decentralized execution, and different methods are applied to determine the selection policy of continuous scheduling vari-ables and discrete scheduling variables. The simulation experi-ment results demonstrate the effectiveness of the algorithm.
文献关键词：
中图分类号：
作者姓名：
CAO Jingyu;DONG Lu;SUN Changyin
作者机构：
School of Automation, Southeast University, Nanjing 210096, China;School of Cyber Science and Engineering, Southeast University, Nanjing 211189, China
文献出处：
引用格式：
[1]CAO Jingyu;DONG Lu;SUN Changyin-.Day-ahead scheduling based on reinforcement learning with hybrid action space)[J].系统工程与电子技术（英文版）,2022(03):693-705
A类：
schedulable
B类：
Day,ahead,scheduling,reinforcement,learning,hybrid,action,space,Driven,by,improvement,smart,grid,active,distribution,network,ADN,has,attracted,much,attention,due,its,characteristic,management,By,making,full,use,electricity,price,signals,optimal,total,cost,can,be,reduced,However,day,problem,challenging,since,future,unknown,Moreover,some,are,continuous,while,variables,which,increases,difficulty,determining,scheme,In,this,paper,formulated,Markov,decision,process,MDP,discrete,Then,algorithm,multi,agent,HRL,proposed,obtain,adopts,structure,training,decentralized,execution,different,methods,applied,determine,selection,policy,simulation,experi,results,demonstrate,effectiveness
AB值：
0.513473
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
