Title :
An Evolutionary Algorithm for Uncertain Optimization Problems
Author :
He, Fangguo ; Shao, Guiming
Abstract :
In order to model uncertain optimization problems, fuzzy expected value programming and chance-constrained programming are formulated. Firstly, the method of fuzzy simulation is used to generate training samples for neural network, and the neural network is embedded into PSO to design a hybrid intelligent algorithm. Then, the death penalty function is adopted to deal with the constraints. Finally, some numerical examples are provided to illustrate the feasibility and effectiveness of the algorithm.
Keywords :
constraint theory; evolutionary computation; fuzzy set theory; learning (artificial intelligence); mathematical programming; neural nets; particle swarm optimisation; chance-constrained programming; death penalty function; evolutionary algorithm; fuzzy expected value programming; fuzzy simulation; hybrid intelligent algorithm; neural network training; particle swarm optimisation; uncertain optimization problems; Chromium; Evolutionary computation; Fuzzy neural networks; Genetic programming; Mathematical programming; Modeling; Neural networks; Particle swarm optimization; Stochastic processes; Uncertainty;
Conference_Titel :
Information Engineering and Computer Science, 2009. ICIECS 2009. International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-4994-1
DOI :
10.1109/ICIECS.2009.5366513
