Abstract
A new stochastic optimization algorithm referred to by the authors as the 'Mean-Variance Optimization' (MVO) algorithm is presented in this paper. MVO falls into the category of the so-called "population-Based stochastic optimization technique." the uniqueness of the MVO algorithm is based on the strategic transformation used for mutating the offspring based on mean-variance of the n-best dynamic population. the mapping function used transforms the uniformly distributed random variation into a new one characterized by the variance and mean of the n-best population attained so far. the searching space within the algorithm is restricted to the range - zero to one - which does not change after applying the transformation. Therefore, the variables are treated always in this band, but the function evaluation is carried out in the problem range. the performance of MVO algorithm has been demonstrated on standard benchmark optimization functions. It is shown that MVO algorithm finds the near optimal solution and is simple to implement. the features of MVO make it a potentially an attractive algorithm for solving many real-world optimization problems. © 2010 IEEE.
Recommended Citation
I. Erlich et al., "A Mean-Variance Optimization Algorithm," 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010, article no. 5586027, Institute of Electrical and Electronics Engineers, Dec 2010.
The definitive version is available at https://doi.org/10.1109/CEC.2010.5586027
Department(s)
Electrical and Computer Engineering
International Standard Book Number (ISBN)
978-142446910-9
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2024 Institute of Electrical and Electronics Engineers, All rights reserved.
Publication Date
01 Dec 2010
