摘要
对低频电力数据进行超分辨率重建有助于实现电力系统精准的态势感知与决策分析。现有的超分辨率重建算法存在重建效果不够精确、算法通用性不强等问题。因此,提出了一种基于改进扩散模型的电力数据超分辨率重建技术。扩散模型能够捕捉到数据中细微且复杂的特征,可在低频数据引导下逐步生成高频电力数据。通过将长短期记忆网络与扩散模型相结合,进一步增强了模型对时序数据的挖掘能力,提高了超分辨率重建能力。使用负荷和谐波两种场景下的电力数据进行算例验证,实验表明所提方法能够精准重建高频数据。同时,模型具备良好的泛化性和灵活性,可应用于未经训练的电气参数和建筑数据,也可以重建不同精度的数据。
Super-resolution reconstruction for low-frequency power data is helpful to realize the accurate situation awareness and decision analysis of power systems.The existing super-resolution reconstruction algorithms have problems such as imprecise reconstruction result and weak generality.Therefore,a super-resolution reconstruction technology for power data based on improved diffusion model is proposed.The diffusion model can capture subtle and complex features in the data,and can gradually generate high-frequency power data under the guidance of low-frequency data.By combining the long short-term memory network with the diffusion model,the ability of the model to mine time series data is further enhanced,and the ability of super-resolution reconstruction is improved.The power data in load and harmonic scenarios are used for case verification,and the experiments show that the proposed method can accurately reconstruct high-frequency data.At the same time,the model has good generalization and flexibility,which can be applied to untrained electrical parameters and buildings’data,and can also reconstruct data with different precision.
作者
薛彤丹
王红
齐林海
闫江毓
姜美静
陶顺
XUE Tongdan;WANG Hong;QI Linhai;YAN Jiangyu;JIANG Meijing;TAO Shun(School of Control and Computer Engineering,North China Electric Power University,Beijing 102206,China;School of Electrical and Electronic Engineering,North China Electric Power University,Beijing 102206,China)
出处
《电力系统自动化》
北大核心
2025年第4期214-223,共10页
Automation of Electric Power Systems
基金
国家自然科学基金资助项目(52377101)。
关键词
可再生能源
超分辨率重建
扩散模型
电力数据
高频数据
renewable energy
super-resolution reconstruction
diffusion model
power data
high-frequency data
