Estimating Force Mix Lower Bounds using a Multi-objective Evolutionary Algorithm

PDF

Authors
  1. Ma, F.
  2. Wesolkowski, S.
Corporate Authors
Defence Research and Development Canada, Centre for Operational Research and Analysis, Ottawa ON (CAN)
Abstract
Nations will always experience conflicting pressures to reduce both (i) the funding of militaries and (ii) the probability that they will not be able to respond to scenarios that may arise. We develop a multiobjective evolutionary algorithm (MOEA) to generate force mix options that trade-off between lower bounds for objective (i) versus objective (ii). A set of military assets or force mix is evaluated against multiple instances of the future, each composed of a mix of stochastically generated realistic scenarios based on historically derived parameters. Scenario success is evaluated by matching each occurrence with a course of action (CoA) whose force element (FE) demands can be met. The lower bound on (i) comes from the assumption that a nation has complete flexibility to engage in scenarios at times that minimize simultaneous demand on FEs. The results are compared with the results from Tyche, a discrete event Simulator, which provides an more realistic, though pessimistic, point estimate of objective (ii). Results confirm the expected relative behavior of both models.
Keywords
force structure;force mix;genetic algorithm;multi-objective evolutionary algorithm
Report Number
DRDC-RDDC-2016-P090 — External Literature
Date of publication
12 Oct 2016
Number of Pages
8
DSTKIM No
CA043223
CANDIS No
804517
Format(s):
Electronic Document(PDF)

Permanent link

Document 1 of 1

Date modified: