摘要
为提高光伏预测精度,给电力调度部门提供合理的调度方案,文章首先通过灰色关联度构建待预测日的相似日样本集合,然后通过经验模态分解对光伏出力时间序列进行分解与重构,得到若干个本征模函数分量与一个残差分量,继而对每个分量分别建立预测模型,得到每个分量对应的预测分量并进行叠加,从而得到光伏出力预测值。算例表明,相较于粒子群算法改进的支持向量机算法和人工蜂群算法改进的支持向量机算法,所用萤火虫算法优化的支持向量机算法在对于光伏出力的预测精度上有一定提高。同时也证明经验模态分解能够提升对于非平稳性与随机性较强的序列的预测精度。
In order to improve the accuracy of photovoltaic forecasting and provide a reasonable dispatching scheme for power dispatching department,the grey correlation degree is used to construct the sample set of similar days to be forecasted.The time series of photovoltaic output is decomposed and reconstructed by empirical mode decomposition,and several intrinsic mode function components and one residual component are obtained.The prediction model of each component is established separately,and the corresponding prediction components of each component are obtained and superimposed to obtain the prediction value of photovoltaic output.The example shows that compared with the improved support vector machine algorithm of particle swarm optimization algorithm and the improved support vector machine algorithm of artificial bee colony algorithm,the support vector machine algorithm optimized by the firefly algorithm has a certain improvement in the prediction accuracy of photovoltaic output.It also proves that empirical mode decomposition can improve the prediction accuracy of sequences with strong non-stationarity and randomness.
作者
陆思佳
葛玉林
LU Sijia;GE Yulin(School of Electric Power Engineering,Nanjing Institute of Technology,Nanjing 211167,China)
出处
《黑龙江电力》
CAS
2019年第5期382-386,共5页
Heilongjiang Electric Power
基金
南京工程学院大学生科技创新基金挑战杯支撑项目(项目编号:TZ20190008)
关键词
光伏出力预测
欧式距离
经验模态分解
支持向量机算法
萤火虫算法
photovoltaic output prediction
euclidean distance
empirical mode decomposition
support vector machine algorithm
firefly algorithm
