A Methodology for Effective Surrogate Learning in Complex Optimization

TL;DR

This paper introduces the PTME methodology for evaluating deep learning surrogates in complex optimization, focusing on their accuracy and resource efficiency, and demonstrates its application in traffic light network optimization in European cities.

Contribution

It proposes the PTME framework to analyze surrogates combining numerical and physical performance metrics, and applies it to optimize traffic light networks using new metaheuristics.

Findings

PTME effectively evaluates surrogate models' performance and resource consumption.

Surrogate sampling methods and dataset sizes significantly impact efficiency.

Optimized surrogates improve decision-making in urban traffic management.

Abstract

Solving complex problems requires continuous effort in developing theory and practice to cope with larger, more difficult scenarios. Working with surrogates is normal for creating a proxy that realistically models the problem into the computer. Thus, the question of how to best define and characterize such a surrogate model is of the utmost importance. In this paper, we introduce the PTME methodology to study deep learning surrogates by analyzing their Precision, Time, Memory, and Energy consumption. We argue that only a combination of numerical and physical performance can lead to a surrogate that is both a trusted scientific substitute for the real problem and an efficient experimental artifact for scalable studies. Here, we propose different surrogates for a real problem in optimally organizing the network of traffic lights in European cities and perform a PTME study on the surrogates' sampling methods, dataset sizes, and resource consumption. We further use the built surrogates in new optimization metaheuristics for decision-making in real cities. We offer better techniques and conclude that the PTME methodology can be used as a guideline for other applications and solvers.