Unsupervised Hybrid Deep Generative Models for Photovoltaic Synthetic Data Generation
Unsupervised Hybrid Deep Generative Models for Photovoltaic Synthetic Data Generation
复制标题
DOI：
10.1109/pesgm46819.2021.9637844
复制
发表时间：
2021-07
期刊：
影响因子：
--
通讯作者：
Dan A. Rosa de Jesús;P. Mandal;T. Senjyu;S. Kamalasadan
中科院分区：
文献类型：
--
作者：
Dan A. Rosa de Jesús;P. Mandal;T. Senjyu;S. Kamalasadan
本文通过探索结合变分自编码器（VAE）和生成对抗网络（GAN）的深度生成模型（DGM），即VAEGAN，为应用于太阳能光伏（PV）合成数据生成问题的深度生成学习领域做出了贡献。我们基于深度学习领域的知识构建了混合深度神经网络（HDNN），在编码层结合卷积层和长短期记忆（LSTM）层，以生成稳健的潜在表示，进而生成高质量的合成光伏数据样本。这些方法的主要优势在于，它使深度生成模型能够更好地进行特征提取，并有效地捕捉数据中的历史趋势。对从实际光伏系统获取的真实数据进行的模拟表明，深度生成模型能够有效地生成一年中多个季节的高质量样本。
This paper contributes to the field of deep generative learning applied to solar photovoltaic (PV) synthetic data generation problems by exploring Deep Generative Model (DGM) that combines Variational Autoencoders (VAE) and Generative Adversarial Networks (GAN), i.e., VAEGAN. We build upon knowledge in the area of deep learning to incorporate our Hybrid Deep Neural Network (HDNN), combining convolutional and Long Short-Term Memory (LSTM) layers at the encoding level for producing robust latent representations and subsequently high-quality synthetic PV data samples. The major advantage of these approaches is that it allows the DGMs to perform better feature extraction as well as to capture the historical trends in data effectively. The simulations on actual data acquired from a real PV system demonstrate the effectiveness of the DGMs to produce high-quality samples for multiple seasons of the year.