摘要
随着风力发电在电力系统中的占比逐渐提高,风电功率的波动性和不确定性给电网的稳定运行带来了挑战,因此,风电功率的精准预测对于合理调度电网和保证供电质量具有重要意义。为此,本文提出了一种基于PCA-RSA-ELM风电功率预测模型:首先,使用PCA对原始输入数据进行降维处理,并提取出原始输入数据中的主成分,建立预测模型的训练集;然后,采用RSA算法对ELM模型初始参数进行优化;最后,用训练集训练预测模型,其中误差最小的1组参数组合对应的模型就是最终的PCA-RSA-ELM风电功率预测模型。由实验结果可知,相比于其他模型,本文提出的PCA-RSA-ELM风电功率预测模型预测误差最小,这同时也表明了该预测模型能明显提高风电功率预测的准确性。
With the increasing proportion of wind power in the power system,the fluctuation and uncertainty of wind power bring challenges to the stable operation of the power grid.Therefore,the accurate prediction of wind power is of great significance to the reasonable dispatching of power grid and ensuring the quality of power supply.In order to improve the accuracy of wind power prediction,a wind power prediction model based on PCA-RSA-ELM is proposed in this paper.Firstly,PCA is used to reduce the dimensionality of the original input data,and the principal components in the original input data are extracted to establish the training set of the prediction model.Then,RSA algorithm is used to optimize the initial parameters of ELM model.Finally,the training set is used to train the prediction model,and the model corresponding to the one set of parameter combinations with the smallest error is the final PCA-RSA-ELM wind power prediction model.The experimental results show that compared with other models,the PCA-RSA-ELM wind power prediction model proposed in this paper has the smallest prediction error,indicating that the PCA-RSA-ELM wind power prediction model can significantly improve the accuracy of wind power prediction.
作者
胡经纬
王春雨
HU Jingwei;WANG Chunyu(School of Mechanical and Electrical Engineering,Hefei Vocational and Technical College,Hefei,Anhui 230012,China)
出处
《湖南城市学院学报（自然科学版）》
CAS
2024年第5期64-72,共9页
Journal of Hunan City University:Natural Science
基金
安徽省教育厅高校自然科学研究项目(2023AH052543)
合肥职业技术学院校级科研基金项目(2022Akyjj16)。
关键词
风电功率
预测
优化
准确性
wind power
prediction
optimization
accuracy
