为求解复杂的不连续、非凸、非线性电力系统的经济负荷分配问题,提出了一种单纯形法(NM)和粒子群算法(PSO)相结合的NM—PSO算法。该算法将单纯形算子嵌入到PSO算法中,把适应值最好的一部分粒子用单纯形法来更新,其余粒子用PSO算法寻优,从而提高PSO算法后期的寻优能力。NM—PSO充分利用PSO算法强大的全局搜索能力和NM快速确定性的局部搜索能力,提高了NM—PSO算法的寻优能力和收敛速度,该算法应用于经济负荷分配问题得到的优化结果好于其他方法。
A hybrid method (NM-PSO), which combines particle swarm optimization (PSO) with Nelder- Mead (NM) simplex method is proposed to solve the discontinuous, nonconvex and nonlinear economic dispatch (ED) problem. Simplex operator is embedied into PSO to improve the search capability of PSO in anaphase. In this method, simplex method is used to update the best part of the whole particles, and others are searched by PSO to look for the best. The hybrid method makes use of the powerful global search capability of PSO and fast local search of NM simplex method. The search efficiency and covergence speed are improved distinctly. Experiments on ED show that the proposed method can get optimal results.