Stochastic Complexity in Statistical Inquiry Theory
Stochastic Complexity in Statistical Inquiry Theory
Adaptive discretization for probabilistic model building genetic algorithms
Proceedings of the 8th annual conference on Genetic and evolutionary computation
iECGA: integer extended compact genetic algorithm
Proceedings of the 8th annual conference on Genetic and evolutionary computation
Evolutionary programming techniques for economic load dispatch
IEEE Transactions on Evolutionary Computation
Adaptive discretization on multidimensional continuous search spaces
Proceedings of the 10th annual conference on Genetic and evolutionary computation
| Hi-index | 0.00 |
In this paper, we propose a new approach that consists of the extended compact genetic algorithm (ECGA) and split-on-demand (SoD), an adaptive discretization technique, to economic dispatch (ED) problems with nonsmooth cost functions. ECGA is designed for handling problems with decision variables of the discrete type, while the decision variables of ED problems are oftentimes real numbers. Thus, in order to employ ECGA to tackle ED problems, SoD is utilized for discretizing the continuous decision variables and works as the interface between ECGA and the ED problem. Furthermore, ED problems in practice are usually hard for traditional mathematical programming methodologies because of the equality and inequality constraints. Hence, in addition to integrating ECGA and SoD, in this study, we devise a repair operator specifically for making the infeasible solutions to satisfy the equality constraint. To examine the performance and effectiveness, we apply the proposed framework to two different-sized ED problems with nonsmooth cost function considering the valve-point effects. The experimental results are compared to those obtained by various evolutionary algorithms and demonstrate that handling ED problems with the proposed framework is a promising research direction.