基于多学习多目标鸽群优化的动态环境经济调度

Dynamic Economic Emission Dispatch Based on Multiple Learning Multi-objective Pigeon-inspired Optimization

针对电力系统动态环境经济调度(DEED)问题,提出了一种基于多学习策略的多目标鸽群优化(MLMPIO)算法.在多学习策略中,种群个体可以向外部存档集中的多个全局最优位置以及个体的历史最优位置进行学习,进而保持种群的多样性和全局搜索能力,避免陷入早熟收敛.引入了小概率变异扰动机制,进一步增强种群的多样性.为提升算法的运行效率,采用容量自适应变化的外部存档集来存储当前Pareto最优解集.为验证所提算法的性能,将MLMPIO应用于10机组电力系统的DEED问题求解.仿真结果证明了MLMPIO算法解决此类问题的可行性和有效性.

For solving the dynamic economic emission dispatch problem(DEED),a multiple learning based multi-objective pigeon-inspired optimization(MLMPIO)algorithm was proposed in this paper.In the proposed multiple learning strategy,individuals of the population were allowed to learn from multiple global best positions of the external archive,and from the personal historical best positions simultaneously.This learning strategy could enable the preservation of the population’s diversity and global search ability to avoid premature convergence.Meanwhile,small probability mutation was introduced to enhance the swarm diversity further.The external archive with adaptive changing capacity was used to store the current Pareto optimal solutions.The DEED problem of the IEEE 10-generator power system was used to verify the performance of the proposed method.The results demonstrated the feasibility and effectiveness of the proposed method.