A hybrid intelligent messy genetic algorithm for daily generation scheduling in power system

Abstract

Unit commitment (UC) is one of the most important optimization tasks of the daily generation scheduling in power system. However, getting the global optimal solution to meet all the constraints is a comparatively tough problem. The binary coding and stochastic operators in traditional genetic algorithm (GA) are not suitable for solving large-scale UC problem. In this paper, the hybrid intelligent messy genetic algorithm (HIMGA) is proposed to solve the problem due to the characteristics of the daily generation scheduling in power system. The proposed algorithm, using operation status of unit as the genotype and combining heuristic self-adapted intelligent operators, is not only very simple but it also reduces the scale of the UC problems, improves the diversity of evolution population, enhances the searching efficiency and develops the convergence of the algorithm. The simulation results prove the correctness and validity of the proposed method.