摘要
针对新建光伏发电站原始数据匮乏导致光伏功率预测精度低的问题,提出了一种基于梯度惩罚Wasserstein生成对抗网络(Wasserstein generative adversarial network with gradient penalty,WGAN-GP)和改进长短期记忆网络的光伏功率短期预测模型。首先使用WGAN-GP学习原始真实光伏数据的样本分布规律,然后生成与原始数据相似的高质量新样本,从而实现训练集数据增强;其次,采用纵横交叉算法(crisscross optimization algorithm,CSO)对长短时记忆网络(longshort-termmemory,LSTM)的全连接层参数进行优化,构建LSTM-CSO组合模型对光伏功率进行预测。以澳洲某光伏发电站数据进行仿真建模,实验结果表明:使用数据增强后的样本训练预测模型能够有效提高模型的预测精度,且对原始训练集数据扩充数据量的比例越大,预测模型对于光伏功率预测的精度越高。同时LSTM-CSO相对于LSTM在各个季节类型的不同气象日中均具有更高的预测准确率,以春季测试集为例,LSTM-CSO模型在春季的晴天、多云、雨天下的均方根误差相比于LSTM模型分别降低5.62%、3.44%、10.44%。
Aiming at the problem of low prediction accuracy caused by the lack of original data of new photovoltaic power station,we propose a short-term photovoltaic power prediction method based on Wasserstein generative adversarial network with gradient penalty(WGAN-GP)and improved long-term and short-term memory network.First,WGAN-GP is used to learn the distribution law of original photovoltaic data,then the generator in WGAN-GP generates new samples of high quality similar to the original data,so as to enhance the training set data.Secondly,the crisscross optimization algorithm(CSO)is used to optimize the fully connected layer parameters of the long short-term memory(LSTM)network,and the LSTM-CSO combination model is constructed to predict the photovoltaic power.The simulation model is established with the data of a photovoltaic power station in Australia.The experimental results show that the prediction accuracy of the model can be effectively improved by using the sample training prediction model after data enhancement.The greater the proportion of the original training set data expansion is,the higher the accuracy of the prediction model for photovoltaic power prediction will be.At the same time,LSTM-CSO has higher prediction accuracy than LSTM in different meteorological days of each season type.A spring test set is taken as an example,and results show that the root mean square error of LSTM-CSO model in sunny,cloudy and rainy days in spring is reduced by 5.62%,3.44%and 10.44%respectively compared with LSTM model.
作者
殷豪
张铮
丁伟锋
陈嘉铭
陈黍
孟安波
YIN Hao;ZHANG Zheng;DING Weifeng;CHEN Jiaming;CHEN Shu;MENG Anbo(School of Automation,Guangdong University of Technology,Guangzhou 510006,China)
出处
《高电压技术》
EI
CAS
CSCD
北大核心
2022年第11期4342-4351,共10页
High Voltage Engineering
基金
国家自然科学基金(61876040)。
关键词
光伏功率预测
生成对抗网络
梯度惩罚
长短时记忆
纵横交叉算法
photovoltaic power prediction
generative adversarial network
gradient penalty
long short-term memory
crisscross optimization algorithm
