Facility Deployment Decisions through Warp Optimizaton of Regressed Gaussian Processes

TL;DR

This paper introduces a fast, iterative method using Gaussian process regression and dynamic time warping to optimize facility deployment schedules that meet fuel cycle demands efficiently within low-fidelity simulators.

Contribution

It presents a novel optimization approach combining Gaussian process regression with dynamic time warping for rapid deployment schedule determination in fuel cycles.

Findings

Converges within 5-10 iterations to less than 1% demand mismatch.

Applicable to low-fidelity fuel cycle simulators.

Demonstrated on a representative once-through fuel cycle.

Abstract

A method for quickly determining deployment schedules that meet a given fuel cycle demand is presented here. This algorithm is fast enough to perform in situ within low-fidelity fuel cycle simulators. It uses Gaussian process regression models to predict the production curve as a function of time and the number of deployed facilities. Each of these predictions is measured against the demand curve using the dynamic time warping distance. The minimum distance deployment schedule is evaluated in a full fuel cycle simulation, whose generated production curve then informs the model on the next optimization iteration. The method converges within five to ten iterations to a distance that is less than one percent of the total deployable production. A representative once-through fuel cycle is used to demonstrate the methodology for reactor deployment.