A Novel GAN Architecture Reconstructed Using Bi-LSTM and Style Transfer for PV Temporal Dynamics Simulation

作者：Xueqian Fu, Chunyu Zhang, Xiurong Zhang, Hongbin Sun · 发表于：IEEE Transactions on Sustainable Energy · 年份：2024 · DOI：10.1109/tste.2024.3429781 · 被引用次数：30 · 研究领域：Power Systems and Renewable Energy、Photovoltaic System Optimization Techniques、Solar Radiation and Photovoltaics

The stochastic production simulation of photovoltaic (PV) power is crucial for the analysis of power balance in power planning, annual or monthly operational planning, and long-term transactions in the electricity market, especially in power systems with a high share of PVs. To model the uncertainty and temporal characteristics inherent in PV power, this letter introduces the style transfer and innovatively establishes bi-directional long short-term memory generative adversarial networks (GAN). Simulation results confirm the advantages of the proposed GAN over traditional convolutional neural network-based GANs in simulating the diversity and temporal characteristics of PV power.