Multi-Objective Constrained Optimization for Energy Applications via Tree Ensembles

TL;DR

This paper introduces a data-driven tree ensemble method for constrained multi-objective optimization in energy systems, effectively handling complex, heterogeneous variables and unknown dynamics, with demonstrated superior performance in energy-related benchmarks.

Contribution

The paper presents a novel tree ensemble-based approach for constrained multi-objective optimization tailored to complex energy systems with heterogeneous variables and unknown dynamics.

Findings

Outperforms state-of-the-art optimization tools in synthetic benchmarks.

Demonstrates high sampling efficiency and effectiveness in energy applications.

Handles complex constraints and diverse variable types in black-box problems.

Abstract

Energy systems optimization problems are complex due to strongly non-linear system behavior and multiple competing objectives, e.g. economic gain vs. environmental impact. Moreover, a large number of input variables and different variable types, e.g. continuous and categorical, are challenges commonly present in real-world applications. In some cases, proposed optimal solutions need to obey explicit input constraints related to physical properties or safety-critical operating conditions. This paper proposes a novel data-driven strategy using tree ensembles for constrained multi-objective optimization of black-box problems with heterogeneous variable spaces for which underlying system dynamics are either too complex to model or unknown. In an extensive case study comprised of synthetic benchmarks and relevant energy applications we demonstrate the competitive performance and sampling efficiency of the proposed algorithm compared to other state-of-the-art tools, making it a useful all-in-one solution for real-world applications with limited evaluation budgets.