Abstract: A microgrid spatial-temporal perception energy management method based on safe deep reinforcement learning includes: transforming an energy management problem of a microgrid (MG) into a constrained Markov decision process (CMDP), where an agent is an energy management agent of the MG; and solving the CMDP by using a safe deep reinforcement learning method, including: 1) building a feature extraction network combining an edge conditioned convolutional (ECC) network and a long short-term memory (LSTM) network to extract spatial and temporal features in a spatial-temporal operating status of the MG; and 2) endowing the agent with abilities to learn policy value and security simultaneously by using an interior-point policy optimization (IPO) algorithm.

Abstract: A stair railing includes at least two vertical posts, at least one horizontal rail and a movable connecting mechanism. The horizontal rail is connected to the vertical post through the movable connecting mechanism, so that the horizontal rail is rotatable in relation to the vertical post. Wherein the movable connecting mechanism includes an insertion part with at least a portion of the insertion part being arc-shaped, and a receiving part that has a receiving space compatible with the insertion part.