基于EEMD-ACS-SELM的弃风电量组合预测模型

风电已在电力系统中得到了有效利用,因此,弃风电量的准确预测对于电网的安全、经济运行至关重要。文章提出了一种基于集合经验模态分解(EEMD)和t分布自适应变异布谷鸟算法(ACS)优化改进极限学习机(SELM)的弃风电量组合预测方法(EEMD-ACS-SELM)。该方法先采用集合经验模态分解,将原始弃风电量序列分解为一系列不同频率的分量,基于模糊熵理论计算各分量的熵值,并将熵值相似序列重构为新的子序列。然后,将新序列分别建立改进极限学习机预测模型,利用ACS优化算法对SELM算法的输入权值和阈值进行优化。最后,将各序列预测值叠加求和得到原始弃风电量序列的预测值。以新疆某风电场实际运行数据进行算例分析,结果表明,文章所提方法对弃风电量的预测具有较高的精度。

Wind power curtailment combination forecasting model based on EEMD-ACS-SELM

Wind power has demonstrated high-efficiency utilization in electricity system,an accurate forecasting of wind power curtailment is of vital significance in power grid security and economic operation.This paper proposes a novel hybrid forecasting model that includes the ensemble empirical mode decomposition(EEMD),improved extreme learning machine(SELM),and t-distribution adaptive variation cuckoo search algorithm(ACS).Firstly,the EEMD divides the original wind power curtailment sequence into a set of intrinsic mode functions,and the new subsequences can be reconstructed by fuzzy entropy.After that,the input weights and threshold values of SELM prediction model optimized by ACS optimization algorithm is established to predict the new sequence.Finally,the predicted values of each new sequence are summed to obtain the predicted original wind power curtailment sequence.Taking actual data of a Xinjiang wind farm as an example,the results show that the proposed approach has a high accuracy for the prediction of wind power curtailment.