Due to increasing complexity, uncertainty and data dimensions in power systems, conventional methods often meet bottlenecks when attempting to solve decision and control prob- lems. Therefore, data-driven methods towa...Due to increasing complexity, uncertainty and data dimensions in power systems, conventional methods often meet bottlenecks when attempting to solve decision and control prob- lems. Therefore, data-driven methods toward solving such prob- lems are being extensively studied. Deep reinforcement learning (DRL) is one of these data-driven methods and is regarded as real artificial intelligence (AI). DRL is a combination of deep learning (DL) and reinforcement learning (RL). This field of research has been applied to solve a wide range of complex sequential decision-making problems, including those in power systems. This paper firstly reviews the basic ideas, models, algorithms and techniques of DRL. Applications in power systems such as energy management, demand response, electricity market, operational control, and others are then considered. In addition, recent advances in DRL including the combination of RL with other classical methods, and the prospect and challenges of applications in power systems are also discussed.展开更多
基金This work is supported by National Natural Science Foundation of China under Grant No.61571296the National Key Research and Development Program of China under 2018YFF0214705.
文摘Due to increasing complexity, uncertainty and data dimensions in power systems, conventional methods often meet bottlenecks when attempting to solve decision and control prob- lems. Therefore, data-driven methods toward solving such prob- lems are being extensively studied. Deep reinforcement learning (DRL) is one of these data-driven methods and is regarded as real artificial intelligence (AI). DRL is a combination of deep learning (DL) and reinforcement learning (RL). This field of research has been applied to solve a wide range of complex sequential decision-making problems, including those in power systems. This paper firstly reviews the basic ideas, models, algorithms and techniques of DRL. Applications in power systems such as energy management, demand response, electricity market, operational control, and others are then considered. In addition, recent advances in DRL including the combination of RL with other classical methods, and the prospect and challenges of applications in power systems are also discussed.
