A Fitness Landscape View on the Tuning of an Asynchronous Master-Worker EA for Nuclear Reactor Design

TL;DR

This paper applies a fitness landscape analysis to optimize the parameter tuning of a parallel asynchronous evolutionary algorithm for nuclear reactor control, demonstrating potential for improved load-following capabilities in power plants.

Contribution

It introduces a fitness landscape approach to tune evolutionary algorithm parameters specifically for expensive, real-world nuclear reactor optimization problems.

Findings

Fitness landscape features can inform mutation parameter tuning.

Parallel asynchronous EA scales efficiently to thousands of computing units.

Landscape analysis suggests adaptive parameter tuning improves optimization.

Abstract

In the context of the introduction of intermittent renewable energies, we propose to optimize the main variables of the control rods of a nuclear power plant to improve its capability to load-follow. The design problem is a black-box combinatorial optimization problem with expensive evaluation based on a multi-physics simulator. Therefore, we use a parallel asynchronous master-worker Evolutionary Algorithm scaling up to thousand computing units. One main issue is the tuning of the algorithm parameters. A fitness landscape analysis is conducted on this expensive real-world problem to show that it would be possible to tune the mutation parameters according to the low-cost estimation of the fitness landscape features.