基于ACFOA优化RBF的短期风电功率预测  

Short-term wind power prediction based on the optimization of radial basis function by adaptive chaos fruit fly optimization algorithm

作　　者：崔闪 彭道刚[1] 钱玉良[1] 

机构地区：[1]上海电力学院自动化工程学院,上海200090

出　　处：《可再生能源》2017年第1期80-85,共6页Renewable Energy Resources

基　　金：上海市"科技创新行动计划"社会发展领域项目(16DZ1202500)

摘　　要：为了提高短期风电输出功率预测的准确度,在分析研究基本预测方法的基础上,提出采用一种自适应混沌果蝇算法(ACFOA)优化RBF神经网络的预测方法。该方法中引入自适应混沌对果蝇算法的进化机制进行优化,并利用ACFOA算法改善RBF神经网络结构参数以提高网络的泛化能力,同时对某风电场的历史数据进行验证分析。仿真结果表明,相比于PSO-RBF预测方法,采用提出的预测模型能有效减少较大误差出现的频率,大幅度提高风电输出功率预测的准确度。In order to improve the prediction precisions of short-term output of the wind power,this paper put forward an advanced prediction method, based on the basic prediction methods,optimizing the neural network of radial basis function（RBF） using adaptive chaos fruit fly optimization algorithm（ACFOA）. This optimization method adopted the adaptive chaos to optimize the evolutionary mechanism of the fruit fly algorithm, using ACFOA to improve the structure parameters of RBF neural network to enhance the generalization ability of the network, meanwhile validated and analyzed the historical data of a wind plant. The results of the simulation show the modified prediction model proposed in this paper can effectively reduce the probabilities of occurrence of large error compared with PSO-RBF prediction method and can greatly improve the prediction precisions of output wind power.

关 键 词：风电功率 预测模型 RBF神经网络 ACFOA算法 参数优化 

分 类 号：TK83[动力工程及工程热物理—流体机械及工程] TM614[电气工程—电力系统及自动化]