论文部分内容阅读
为了弥补遗传算法易陷入局部解的缺陷,使该算法产生的非劣解更好更均匀地靠近非劣解前沿,并且使多目标调度结果更贴近真实情况,将自组织映射和遗传算法相结合,应用到以发电和供水为目标的水库多目标调度中,并分别与NSGA2算法、主要目标法进行比较分析,验证该算法的合理性与优越性。结果表明,自组织映射遗传算法能在满足约束条件的情况下,使发电供水两目标调度的非劣解更好地向非劣解前沿靠近,给出的实时供水方案更符合实际情况。
In order to make up for the defect that genetic algorithm is easy to fall into local solution, the non-inferior solution generated by the algorithm is better and more uniformly near the non-inferior solution frontier and the multi-objective scheduling result is closer to the real situation. Combining self-organizing map and genetic algorithm , Which is applied to multi-objective reservoir scheduling with power generation and water supply as the target, and compared with the NSGA2 algorithm and the main target method respectively to verify the rationality and superiority of the algorithm. The results show that the self-organizing map-based genetic algorithm can make the non-inferior solutions of the two targets scheduling of generation and supply water to be closer to the non-inferior solution front when the constraints are satisfied, and the given real-time water supply scheme is more in line with the actual situation.