Composing Modeling and Simulation with Machine Learning in Julia

TL;DR

This paper introduces JuliaSim, a high-performance environment that integrates machine learning surrogates with traditional modeling in Julia, enabling faster and more efficient simulation and optimization of complex systems.

Contribution

It presents JuliaSim and ModelingToolkit.jl, enabling the composition of trained surrogates with component models for accelerated simulation and design optimization.

Findings

Surrogates achieve less than 4% error in HVAC simulation

Simulation speed is increased by 340 times using CTESN surrogates

Optimization speed is improved by two orders of magnitude

Abstract

In this paper we introduce JuliaSim, a high-performance programming environment designed to blend traditional modeling and simulation with machine learning. JuliaSim can build accelerated surrogates from component-based models, such as those conforming to the FMI standard, using continuous-time echo state networks (CTESN). The foundation of this environment, ModelingToolkit.jl, is an acausal modeling language which can compose the trained surrogates as components within its staged compilation process. As a complementary factor we present the JuliaSim model library, a standard library with differential-algebraic equations and pre-trained surrogates, which can be composed using the modeling system for design, optimization, and control. We demonstrate the effectiveness of the surrogate-accelerated modeling and simulation approach on HVAC dynamics by showing that the CTESN surrogates accurately capture the dynamics of a HVAC cycle at less than 4\% error while accelerating its simulation by 340x. We illustrate the use of surrogate acceleration in the design process via global optimization of simulation parameters using the embedded surrogate, yielding a speedup of two orders of magnitude to find the optimum. We showcase the surrogate deployed in a co-simulation loop, as a drop-in replacement for one of the coupled FMUs, allowing engineers to effectively explore the design space of a coupled system. Together this demonstrates a workflow for automating the integration of machine learning techniques into traditional modeling and simulation processes.