Control of complex systems with generalized embedding and empirical dynamic modeling

TL;DR

This paper introduces a data-driven, explainable control method for complex nonlinear systems using generalized state space embedding and model predictive control, demonstrated on a large agent-based model.

Contribution

It presents a novel approach combining generalized embedding with model predictive control, applicable to complex systems without extensive model design.

Findings

Successfully controlled a 1200-agent nonlinear system

Demonstrated applicability to various dynamic systems

Provided an explainable alternative to traditional data-driven models

Abstract

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.