Journal article 3 views 1 download
The SOS Platform: Designing, Tuning and Statistically Benchmarking Optimisation Algorithms
Mathematics, Volume: 8, Issue: 5, Start page: 785
Swansea University Author: Fabio Caraffini
PDF | Version of Record
Copyright: 2020 by the authors. This is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) licenseDownload (2.37MB)
We present Stochastic Optimisation Software (SOS), a Java platform facilitating the algorithmic design process and the evaluation of metaheuristic optimisation algorithms. SOS reduces the burden of coding miscellaneous methods for dealing with several bothersome and time-demanding tasks such as para...
Check full text
No Tags, Be the first to tag this record!
We present Stochastic Optimisation Software (SOS), a Java platform facilitating the algorithmic design process and the evaluation of metaheuristic optimisation algorithms. SOS reduces the burden of coding miscellaneous methods for dealing with several bothersome and time-demanding tasks such as parameter tuning, implementation of comparison algorithms and testbed problems, collecting and processing data to display results, measuring algorithmic overhead, etc. SOS provides numerous off-the-shelf methods including: (1) customised implementations of statistical tests, such as the Wilcoxon rank-sum test and the Holm–Bonferroni procedure, for comparing the performances of optimisation algorithms and automatically generating result tables in PDF and LATEX formats; (2) the implementation of an original advanced statistical routine for accurately comparing couples of stochastic optimisation algorithms; (3) the implementation of a novel testbed suite for continuous optimisation, derived from the IEEE CEC 2014 benchmark, allowing for controlled activation of the rotation on each testbed function. Moreover, we briefly comment on the current state of the literature in stochastic optimisation and highlight similarities shared by modern metaheuristics inspired by nature. We argue that the vast majority of these algorithms are simply a reformulation of the same methods and that metaheuristics for optimisation should be simply treated as stochastic processes with less emphasis on the inspiring metaphor behind them.
algorithmic design; metaheuristic optimisation; evolutionary computation; swarm intelligence; memetic computing; parameter tuning; fitness trend; Wilcoxon rank-sum; Holm–Bonferroni; benchmark suite
College of Science
This research received no external funding.