@techreport{2006009,
abstract = {Uncertainties in design variables and problem parameters are inevitable and must be considered in an optimization task, if reliable optimal solutions are to be found. Besides the sampling techniques, there exist a number of reliability-based probabilistic optimization techniques for systematically handling such uncertainties. In this paper, first we present a brief review of these classical probabilistic procedures. Thereafter, we discuss different optimization tasks in which these classical reliability-based optimization procedures will, in general, have difficulties in finding true optimal solutions. These probabilistic techniques are borrowed from classical literature and are extended to constitute efficient reliability-based single and multi-objective evolutionary algorithms for solving such difficult problems. Due to the global perspective of evolutionary algorithms, first, we demonstrate the proposed methodology is better able to solve reliability based optimization problems having multiple local-global solutions. Second, we suggest introducing an additional objective of maximizing the reliability index along with optimizing the usual objective function and find a number of Pareto-optimal solutions trading-off between the objective value and corresponding reliability index, thereby allowing the designers to find solutions corresponding to different reliability requirements for a better application. Finally, the concept of single-objective reliability-based optimization is extended to multi-objective optimization of finding a reliable frontier, instead of a single reliable solution. These optimization tasks are illustrated by solving a number of test problems and a well-studied automobile design problem. Results are also compared with a couple of standard classical reliability-based methodologies. This paper demonstrates how classical reliability-based concepts can be used in single and multi-objective evolutionary algorithms to enhance their scope in handling uncertainties, a matter which is common in most real-world problem solving tasks.},
author = {Deb, Kalyanmoy and Padmanabhan, Dhanesh and Gupta, Sulabh and {Kumar Mall}, Abhishek},
title = {{Handling Uncertainties Through Reliability-Based Optimization Using Evolutionary Algorithms}}
}
@article{2006003,
abstract = {The present-day evolutionary multi-objective optimization (EMO) algorithms had a demonstrated history of evolution over the years. The initial EMO methodologies involved additional niching parameters which made them somewhat subjective to the user. Fortunately, soon enough parameter-less EMO methodologies have been suggested thereby making the earlier EMO algorithms unpopular and obsolete. In this paper, we present a functional decomposition of a viable EMO methodology and discuss the critical components which require special attention for making the complete algorithm free from any additional parameter. A critical evaluation of existing EMO methodologies suggest that the elitist non-dominated sorting GA (NSGA-II) is one of EMO algorithms which does not require any additional implicit or explicit parameters other than the standard EA parameters, such as population size, operator probabilities, etc. This parameter-less property of NSGA-II is probably the reason for its popularity to most EMO studies thus far. {\textcopyright} Springer-Verlag Berlin Heidelberg 2007.},
author = {Deb, Kalyanmoy},
doi = {10.1007/978-3-540-69432-8_12},
isbn = {3540694315},
issn = {1860949X},
journal = {Studies in Computational Intelligence},
pages = {241--257},
publisher = {Springer, Berlin, Heidelberg},
title = {{Evolutionary multi-objective optimization without additional parameters}},
url = {https://link.springer.com/chapter/10.1007/978-3-540-69432-8{\_}12},
volume = {54},
year = {2007}
}