Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation
Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation
Journal of Global Optimization
Two improved differential evolution schemes for faster global search
GECCO '05 Proceedings of the 7th annual conference on Genetic and evolutionary computation
Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series)
Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series)
Differential evolution algorithm with strategy adaptation for global numerical optimization
IEEE Transactions on Evolutionary Computation
Differential evolution using a neighborhood-based mutation operator
IEEE Transactions on Evolutionary Computation
JADE: adaptive differential evolution with optional external archive
IEEE Transactions on Evolutionary Computation
IEEE Transactions on Evolutionary Computation
Opposition-Based Differential Evolution
IEEE Transactions on Evolutionary Computation
Accelerating Differential Evolution Using an Adaptive Local Search
IEEE Transactions on Evolutionary Computation
Real-Valued Compact Genetic Algorithms for Embedded Microcontroller Optimization
IEEE Transactions on Evolutionary Computation
Hi-index | 0.00 |
This paper proposes a novel adaptation scheme for Differential Evolution (DE) frameworks. The proposed algorithm, namely Estimation Distribution Differential Evolution (EDDE), is based on a DE structure and employs randomized scale factor ad crossover rate values. These values are sampled from truncated Gaussian probability distribution functions. These probability functions adaptively vary during the optimization process. At the beginning of the optimization the truncated Gaussian functions are characterized by a large standard deviation values and thus are similar to uniform distributions. During the later stages of the evolution, the probability functions progressively adapt to the most promising values attempting to detect the optimal working conditions of the algorithm. The performance offered by the proposed algorithm has been compared with those given by three modern DE based algorithms which represent the state-of-the-art in DE. Numerical results show that the proposed EDDE, despite its simplicity, is competitive with the other algorithms and in many cases displays a very good performance in terms of both final solution detected and convergence speed.