Model comparison.

Effective control requires knowledge of the process dynamics to guide the system toward desired states. In many control applications this knowledge is expressed mathematically or through data–driven models, however, as complexity grows obtaining a satisfactory mathematical representation is increasingly difficult. Further, many data–driven approaches consist of abstract internal representations that may have no obvious connection to the underlying dynamics and control, or, require extensive model design and training. Here, we remove these constraints by demonstrating model predictive control from generalized state space embedding of the process dynamics providing a data–driven, explainable method for control of nonlinear, complex systems. Generalized embedding and model predictive control are demonstrated on nonlinear dynamics generated by an agent based model of 1200 interacting agents. The method is generally applicable to any type of controller and dynamic system representable in a state space.

高效的控制需要掌握过程动力学知识，以引导系统趋近期望状态。在诸多控制应用场景中，这类知识常以数学形式或数据驱动模型（data-driven model）的形式呈现；然而随着系统复杂度不断提升，获取令人满意的数学表征愈发困难。此外，多数数据驱动方法依赖抽象的内部表征，这类表征要么与底层动力学及控制逻辑缺乏显式关联，要么需要投入大量资源进行模型设计与训练。本文通过基于过程动力学广义状态空间嵌入的模型预测控制（model predictive control），破除了上述限制，提出了一种可用于非线性复杂系统控制的数据驱动、可解释方法。我们基于由1200个交互智能体构成的基于智能体模型（agent-based model）所生成的非线性动力学系统，验证了广义嵌入与模型预测控制方法的有效性。该方法可泛化应用于任意可在状态空间中表征的控制器与动力学系统。