Title: Multiobjective optimisation of stochastic problems using a mixed metaheuristic and regression technique
Authors: Seyed Hamid Reza Pasandideh; Mahsa Mesgaran
Addresses: Department of Industrial Engineering, Faculty of Engineering, Kharazmi University, Tehran, Iran ' Department of Industrial Engineering, Faculty of Engineering, Kharazmi University, Tehran, Iran
Abstract: Many real word decision making problems involve multi response problems which have stochastic nature. In some cases the relationship between input and output variables is unknown and the regression techniques are used to data generation in this paper. The problem is modelled by four multi objective decision making (MODM) approaches and six structures of genetic algorithm (GA) are developed to solve these models. In structure of these genetic algorithms, six pairwise multiple comparisons statistical tests are used to control the random nature of problems. Finally the algorithms are applied to several polynomial examples and compared their performance statistically considering their accuracy and running times. Furthermore the multi attribute decision making method, simple additive weighting (SAW), is used to find the most desirable algorithm.
Keywords: multiobjective stochastic problems; metaheuristics; regression; genetic algorithms; pairwise multiple comparisons; statistical tests; MADM; multiattribute decision making; simple additive weighting; SAW; multiobjective optimisation; modelling.
International Journal of Mathematics in Operational Research, 2016 Vol.8 No.1, pp.96 - 113
Available online: 28 Oct 2015 *Full-text access for editors Access for subscribers Purchase this article Comment on this article