针对风电场监控和数据采集系统(supervisory control and data acquisition，SCAD A)数据在采集传输过程中常遇到的数据丢失问题，提出一种新的自适应轻量化生成对抗网络插补策略(adaptive transformer slim GAIN，AT-SGAIN)，旨在增强数据完整性。AT-SGAIN通过简化GAIN模型结构，显著提高了计算效率;采用双判别器结构，分别用于真实数据和生成数据的鉴别，保障了速度提升过程中插补精度的维护。算法集成了Transformer(变压器模型)编码器，增强了对风电数据时间序列特征的捕捉能力，并通过自适应双分支注意力机制，精准调整通道和空间注意力权重，提升了网络对局部信息的敏感度。实验结果证明，所提算法在多项对比测试中均显著优于现有经典方法。
A new lightweight generative adversarial network and its application in wind power data interpolation
A lightweight generative adversarial network interpolation strategy based on adaptive transformer slim GAIN(AT-SGAIN)is proposed to address the common problem of data loss in the collection and transmission of supervisory control and data acquisition(SCADA)data in wind farms,aiming to enhance data integrity.AT-SGAIN simplifies the GAIN model structure,significantly improves computational efficiency,and adopts a dual discriminator structure for distinguishing between real data and generated data,ensuring the maintenance of interpolation accuracy during the speed improvement process.This model integrates a Transformer encoder,enhancing the ability to capture time series features of wind power data.Through an adaptive dual branch attention mechanism,it accurately adjusts channel and spatial attention weights,improving the network's sensitivity to local information.The experimental results show that,in multiple comparative tests,the algorithm proposed is significantly better than existing classical methods.
wind power data interpolationSCADA datalightweightTransformeradaptive attention mechanismAT-SGAIN
NETL
NSTL
万方数据
