Park Joseph, Sugihara George, Pao Gerald
Scripps Institution of Oceanography, University of California San Diego, La Jolla, CA, United States of America.
Biological Nonlinear Dynamics Data Science Unit, Okinawa Institute of Science and Technology, Onna-son, Okinawa, Japan.
PLoS One. 2024 Aug 1;19(8):e0305408. doi: 10.1371/journal.pone.0305408. eCollection 2024.
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.
有效的控制需要了解过程动态，以引导系统达到期望状态。在许多控制应用中，这种知识通过数学方式或数据驱动模型来表达，然而，随着复杂性的增加，获得令人满意的数学表示变得越来越困难。此外，许多数据驱动方法由抽象的内部表示组成，这些表示可能与潜在动态和控制没有明显联系，或者需要大量的模型设计和训练。在此，我们通过从过程动态的广义状态空间嵌入中演示模型预测控制来消除这些限制，为非线性复杂系统的控制提供一种数据驱动、可解释的方法。在由1200个相互作用代理的基于代理模型生成的非线性动态上演示了广义嵌入和模型预测控制。该方法通常适用于状态空间中可表示的任何类型的控制器和动态系统。
