Measurement uncertainties, represented by cyber-attacks and data losses, seriously degrade the quality of power system measurements. Fortunately, the powerful generation ability of the denoising diffusion models can enable more precise measurement generation for power system data recovery. However, the controllable data generation and efficient computing methods of denoising diffusion models for deterministic trajectory still need further investigation. To this end, this paper proposes an improved two-stage denoising diffusion model (TSDM) to identify and reconstruct the measurements with various measurement uncertainties. The first stage of the model comprises a classifier-guided conditional anomaly detection component, while the second stage involves diffusion-based measurement imputation component. Moreover, the proposed TSDM adopts precise means and optimal variances to accelerate the diffusion generation process with subsequence sampling. Extensive numerical case studies demonstrate that the proposed TSDM can accurately recover power system measurements despite strong randomness under renewable energy integration and highly nonlinear dynamics under complex cyber-physical contingencies. Additionally, the proposed TSDM has stronger robustness compared to existing reconstruction networks and exhibits lower computational complexity than general denoising diffusion models.

翻译：测量不确定性（以网络攻击和数据丢失为代表）严重降低了电力系统测量的质量。幸运的是，去噪扩散模型强大的生成能力能够为电力系统数据恢复生成更精确的测量值。然而，可控数据生成和面向确定性轨迹的高效计算方法仍需进一步研究。为此，本文提出一种改进的两阶段去噪扩散模型（TSDM），用于识别并重构存在多种测量不确定性的测量数据。该模型第一阶段包含基于分类器引导的条件异常检测模块，第二阶段则基于扩散的测量插补模块。此外，所提出的TSDM采用精确均值和最优方差，结合子序列采样加速扩散生成过程。大量数值算例表明，尽管可再生能源集成存在强随机性，且复杂信息物理故障具有高度非线性动态，所提出的TSDM仍能准确恢复电力系统测量值。同时，与现有重构网络相比，所提出的TSDM具有更强的鲁棒性，且其计算复杂度低于一般去噪扩散模型。