Methods of enhancing the MOO CEM algorithm
AbstractWith the increasing need to solve problems faster and with fewer resources, great emphasisis placed on optimisation. Many real-world problems require addressing more than oneobjective that are in conflict, as well as taking into consideration a number of practical restrictionsor constraints. The multi-objective optimisation using the cross-entropy method (MOOCEM) algorithm is one of many algorithms that addresses the need to solve multi-objectiveproblems effectively, but it has a number of limitations. This paper explores methods ofenhancing the MOO CEM algorithm in order to improve the efficiency and increase the functionalityof the algorithm, allowing for it to be applied to additional classes of problems.Three possible methods of enhancement were identified: using the beta distribution to improvesampling, adding functionality to solve constrained problems and, lastly, implementinga non-dominated sorting algorithm to solve problems with more than two objectives. Thenew algorithms incorporating these enhancements were developed and tested on benchmarkproblems. Subsequently, the results were analysed using standard performance indicatorsand compared to results produced by the original MOO CEM algorithm. The findings of thisstudy indicate that using the beta distribution improves sampling and therefore algorithmefficiency. Methods of handling constraints and solving problems with an increased numberof objectives were implemented successfully. Based on these results, a final algorithmimplementing the enhancements is presented.
Download data is not yet available.
The following license applies:
Attribution CC BY
This license lets others distribute, remix, tweak, and build upon your work, even commercially, as long as they credit you for the original creation.