Hybrid Physical-Data Driven Model for Denoising of Generator State Measurements

The measurement data of power systems are often mixed with a lot of noise due to the interference of the external environment. In order to eliminate the effect of noise, it is significant to denoise the noisy data to obtain the real state measurements. In order to deal with the problem of insufficie...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on instrumentation and measurement Ročník 74; s. 1 - 12
Hlavní autoři: Wang, Huaiyuan, Zhang, Shiping, Liu, Baojin
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Accuracy
Constraints
Data recovery
deep learning (DL)
Differential equations
Generators
Machine learning
Neural networks
Noise
Noise measurement
Noise reduction
Phasor measurement units
physics-informed neural networks (PINNs)
Pollution measurement
Power measurement
power system
Power system stability
stacked denoising autoencoder (SDAE)
Training
ISSN:0018-9456, 1557-9662
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The measurement data of power systems are often mixed with a lot of noise due to the interference of the external environment. In order to eliminate the effect of noise, it is significant to denoise the noisy data to obtain the real state measurements. In order to deal with the problem of insufficient interpretability in existing data-driven denoising methods, a hybrid physical-data driven denoising model (PDDM) based on the stacked denoising autoencoder (SDAE) is proposed. First, the previous knowledge is extracted from the physical model of the generator. Physical constraints are designed based on the inherent relationships between rotor angle, angular frequency, and power. Second, based on SDAE deep-learning (DL) model, physical constraints are embedded into the loss function to guide the training of a neural network. The derivatives of denoised data are leveraged in anticipation of satisfying the differential-algebraic equations. The physical process is directly approximated by the neural network in this method, making the outputs satisfy the physical laws. The reliability and interpretability of the denoising results are improved. Meanwhile, the dependence on datasets is reduced by virtue of the hybrid physical-data driven mode. The robustness is still maintained. Finally, it is verified in the 39-bus New England system and a realistic regional power system. The real noisy data are also taken into account in testing to verify its extensibility. The test results show that the method proposed can achieve a satisfactory effect in both denoising accuracy and generalization capability.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9456
1557-9662
DOI:10.1109/TIM.2025.3545981