基于改进鱼群优化支持向量机的短期风电功率预测

发布时间：2018-04-10 06:28

本文选题：人工鱼群算法　切入点：支持向量机　出处：《电测与仪表》2016年03期

【摘要】：针对人工鱼群算法中固定的视野和步长导致算法寻优速度变慢、易陷入局部最优等问题,引入了一个变系数因子来自适应调节人工鱼在聚群、追尾和觅食行为中的视野和步长;此外,为了降低算法后期运算复杂度以获得更多有效的人工鱼,加入一种人工鱼群最大迭代次数淘汰机制。将改进后的人工鱼群算法用来优化支持向量机中的核函数参数和惩罚参数,并应用到风电场短期风电功率预测中。通过实验仿真对比得出改进的人工鱼群优化支持向量机在短期风电功率预测中有较好的效果。
[Abstract]:In order to solve the problem that the fixed visual field and step size in artificial fish swarm algorithm lead to slow optimization speed and local optimization, a variable factor is introduced to adjust the visual field and step size of artificial fish in cluster, rear-end and foraging behavior.In addition, in order to reduce the computational complexity in the later stage of the algorithm to obtain more effective artificial fish, a mechanism of eliminating the maximum iteration number of artificial fish is added.The improved artificial fish swarm algorithm is used to optimize the kernel function parameters and penalty parameters in the support vector machine and is applied to the short-term wind power prediction of the wind farm.The experimental results show that the improved artificial fish swarm optimization support vector machine is effective in short-term wind power prediction.
【作者单位】：上海电机学院电气学院;
【基金】：上海市教委科研创新项目(13YZ140);上海市教委重点学科(J151901) 上海市自然科学然金项目(11ZR1413900)
【分类号】：TM614;TP18

【相似文献】