Wei Qinglai, Wang Lingxiao, Liu Yu, Polycarpou Marios M
IEEE Trans Neural Netw Learn Syst. 2020 Dec;31(12):5245-5256. doi: 10.1109/TNNLS.2020.2965208. Epub 2020 Nov 30.
In this article, a new deep reinforcement learning (RL) method, called asynchronous advantage actor-critic (A3C) method, is developed to solve the optimal control problem of elevator group control systems (EGCSs). The main contribution of this article is that the optimal control law of EGCSs is designed via a new deep RL method, such that the elevator system sends passengers to the desired destination floors as soon as possible. Deep convolutional and recurrent neural networks, which can update themselves during applications, are designed to dispatch elevators. Then, the structure of the A3C method is developed, and the training phase for the learning optimal law is discussed. Finally, simulation results illustrate that the developed method effectively reduces the average waiting time in a complex building environment. Comparisons with traditional algorithms further verify the effectiveness of the developed method.
在本文中，开发了一种名为异步优势动作评论家（A3C）方法的新型深度强化学习（RL）方法，以解决电梯群控系统（EGCS）的最优控制问题。本文的主要贡献在于，通过一种新型深度强化学习方法设计了EGCS的最优控制律，使得电梯系统能够尽快将乘客送达期望的目的楼层。设计了能够在应用过程中自我更新的深度卷积和循环神经网络来调度电梯。然后，构建了A3C方法的结构，并讨论了学习最优律的训练阶段。最后，仿真结果表明，所开发的方法在复杂建筑环境中有效减少了平均等待时间。与传统算法的比较进一步验证了所开发方法的有效性。
