System-of-systems Modeling and Optimization: An Integrated Framework for Intermodal Mobility

TL;DR

This paper discusses modeling and optimization techniques for system-of-systems architectures, emphasizing surrogate-based methods like Bayesian optimization to address computational challenges in intermodal mobility systems.

Contribution

It introduces an integrated framework combining modeling and optimization, highlighting surrogate-based approaches to improve efficiency in system-of-systems design.

Findings

Surrogate-based optimization reduces evaluation costs.

Bayesian optimization effectively explores complex architectures.

Physics-based simulations are essential but computationally intensive.

Abstract

For developing innovative systems architectures, modeling and optimization techniques have been central to frame the architecting process and define the optimization and modeling problems. In this context, for system-of-systems the use of efficient dedicated approaches (often physics-based simulations) is highly recommended to reduce the computational complexity of the targeted applications. However, exploring novel architectures using such dedicated approaches might pose challenges for optimization algorithms, including increased evaluation costs and potential failures. To address these challenges, surrogate-based optimization algorithms, such as Bayesian optimization utilizing Gaussian process models have emerged.