基于加速遗传算法的舰船电力系统故障恢复

Shipboard Power System Service Restoration Based on the Accelerated Genetic Algorithm

实现舰船电力系统的快速供电恢复是一典型的非线性整数规划问题。根据系统特点,本文给出了一种加速的遗传算法来实现故障恢复。提出了对遗传算法中的个体进行能量熵计算的方法,在算法的退火选择中加入能量熵的选择,以充分地探索解空间,保持种群的多样性。将系统的信息及遗传算法进化过程中的信息应用于对个体的启发式寻优,提高求解速度。舰船电力系统典型故障恢复算例表明,改进算法有效提高了供电恢复的速度及精度,避免了不成熟收敛。

Fast restoration of supply to the unfaulted sections of the shipboard power system (SPS) is a typical nonlinear integer programming problem. According to the characteristics of SPS, this paper presents an accelerated genetic algorithm (GA) to restore service to unfaulted sections of the system. The energy-entropy calculation method of individuals in genetic algorithm (GA) is provided. The energy-entropy selection is added to genetic algorithm annealing selection, which can explore the solution space sufficiently and keep the population diversity. The system information and the evolution information is used to the individuals' heuristic search to accelerate the evolution of GA. Typical SPS fault restoration tests show that the improved GA can improve speed of convergence and precision of restoration and avoid premature convergence.