A Simple Yet Effective Approach to Robust Optimization Over Time

Abstract

Robust optimization over time (ROOT) refers to an optimization problem where its performance is evaluated over a period of future time. Most of the existing algorithms use particle swarm optimization combined with another method which predicts future solutions to the optimization problem. We argue that this approach may perform subpar and suggest instead a method based on a random sampling of the search space. We prove its theoretical guarantees and show that it significantly outperforms the state-of-the-art methods for ROOT.

Differential Evolution in Robust Optimization Over Time Using a Survival Time Approach

“…In the study presented in [18] the authors proposed three random sampling methods to solve ROOT problems, with a better performance against the state-of-the-art algorithms. The methods are described below.…”

“…The problems tackled in this study are based on Moving Peaks Benchmark (MPB) [25] and are configured in a similar way to that used in various specialized literature publications on ROOT, and specifically as used in [18].…”

“…Adam and Yao introduced three methods to address ROOT (Mesh, Optimal in time, and Robust). The authors mentioned that they significantly improves the results obtained for ROOT in the state-of-the-art [18]. Fox, Yang and Caraffini studied different prediction methods in ROOT, including the Linear and Quadratic Regression methods, an Autoregressive model, and Support Vector Regression [19].…”

Robust Optimization Over Time: A Critical Review

“…Next, the best-found position in the promising region c * (t) , which is likely near the summit position, is chosen for deployment. The reason behind choosing the best-found position is that robust solutions usually exist around the summits of the robust promising regions [69,70].…”

“…However, it is important to note that there may be limitations or drawbacks to using EAs in ROOT algorithms, such as high computational costs or difficulty in handling large-scale problems [48,49]. To the best of our knowledge, random sampling [69] is the only non-EA optimization technique used in ROOT methods. However, its effectiveness is limited to low-dimensional problems.…”