摘要
针对非晴天天气类型历史数据量匮乏导致光伏功率预测精度低的问题,提出了一种含有梯度惩罚的改进生成对抗网络(Wasserstein generative adversarial network with gradient penalty,WGAN-GP)和CNN-LSTM-Attention光伏功率短期预测模型。首先,利用K-means++聚类算法将历史光伏数据划分为若干天气类型,使用WGAN-GP生成符合各天气类型数据分布规律的高质量新样本,实现训练集数据增强。其次,结合卷积神经网络(convolutional neural network,CNN)在特征提取上的优势和长短期记忆网络(long short-term memory,LSTM)在时间序列预测上的优势,提升预测模型学习光伏功率与气象数据间长期映射关系的能力。此外,引入注意力机制(Attention)弥补输入序列长时LSTM难以保留关键信息的不足。实验结果表明:基于WGAN-GP对各类型天气样本扩充能有效提高预测精度;与3种经典预测模型相比,所提出的CNN-LSTM-Attention模型具有更高的预测精度。
There is a problem of low accuracy of photovoltaic power prediction due to lack of historical data of non-sunny weather types.Thus a short-term photovoltaic power prediction model based on an Wasserstein generative adversarial network with gradient penalty(WGAN-GP)and CNN-LSTM-Attention is proposed.First,the K-means++clustering algorithm is used to divide the historical photovoltaic data into several weather types,and WGAN-GP is used to generate new high-quality samples that conform to the distribution law of each weather type to enhance the training set data.Second,this paper combines the advantages of both a convolutional neural network(CNN)for feature extraction and of long short-term memory(LSTM)for time series prediction to improve the ability of prediction models to learn the long-term mapping relationship between photovoltaic power and weather data.In addition,the attention mechanism(Attention)is introduced to compensate for the deficiency of LSTM in retaining key information when the input sequence is long.Experimental results show that the prediction accuracy is effectively improved after each type of weather sample expansion based on WGAN-GP.Compared with the three classical prediction models,the proposed CNN-LSTM-Attention model has higher prediction accuracy.
作者
雷柯松
吐松江·卡日
伊力哈木·亚尔买买提
苏宁
吴现
崔传世
LEI Kesong;TUSONGJIANG·Kari;YILIHAMU·Yaermaimaiti;SU Ning;WU Xian;CUI Chuanshi(School of Electrical Engineering,Xinjiang University,Urumqi 830049,China;State Grid Integrated Energy Service Group Co.,Ltd.,Beijing 100053,China)
出处
《电力系统保护与控制》
EI
CSCD
北大核心
2023年第9期108-118,共11页
Power System Protection and Control
基金
国家自然科学基金项目资助(52067021)
新疆维吾尔自治区自然科学基金面上项目资助(2022D01C35)
新疆维吾尔自治区优秀青年科技人才培养项目资助(2019Q012)。
关键词
光伏功率预测
生成对抗网络
卷积神经网络
长短期记忆网络
注意力机制
photovoltaic power prediction
generative adversarial network
convolution neural network
long-short term memory neural network
attention mechanism
