Constrained Multiobjective Optimization Immune Algorithm: Convergence and Application

Authors:
Zhuhong Zhang
Affiliations:
Department of Mathematics, University of Guizhou, Guiyang, Guizhou 550025, P.R. China
Venue:
Computers & Mathematics with Applications
Year:
2006

Citing 5
Cited 2

An evolutionary algorithm with advanced goal and priority specification for multi-objective optimization

Journal of Artificial Intelligence Research
A population and interval constraint propagation algorithm

EMO'03 Proceedings of the 2nd international conference on Evolutionary multi-criterion optimization
Multiobjective programming using uniform design and genetic algorithm

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Evolutionary algorithms with dynamic population size and localexploration for multiobjective optimization

IEEE Transactions on Evolutionary Computation
Handling multiple objectives with particle swarm optimization

IEEE Transactions on Evolutionary Computation

Immune optimization algorithm for constrained nonlinear multiobjective optimization problems

Applied Soft Computing
A class of expected value multi-objective programming problems with random rough coefficients

Mathematical and Computer Modelling: An International Journal

Quantified Score

Hi-index	0.09

Visualization

Abstract

A new optimization technique, multiobjective optimization immune algorithm for constrained nonlinear multiobjective optimization problems is designed based on immune metaphors of humoral immune and Pareto optimality, especially, some interactive metaphors between antigen population and antibody population. It includes four main mechanisms:(1)constraint-handling operation that provides an alternative feasible solution set for rapidly finding Pareto optimal solutions; (2)antibody evolution associated with clonal selection principle and ideas of immune regulation; competition and update of antigens that induces evolution of antibody populations; (3)memory pool used for collecting the best solutions of evolving antibody populations. Convergence is proven through Markov theory as well as demonstrated by the experiment results. Comparative analysis and applications illustrate that it is effective and valuable.