Power Plant Model Parameter Calibration Using Conditional Variational Autoencoder

Khazeiynasab, Seyyed Rashid; Zhao, Junbo; Batarseh, Issa; Tan, Bendong

doi:10.1109/tpwrs.2021.3107515

Cited by 16 publications

(8 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It should be noted that the operational costs are chosen based on the NREL ATB file [3] for the year 2050 assuming a capacity factor of 88%, 12%, and 12% for DG8, DG13, and DG30 respectively. More information regarding the power plant parameter identification can be found in [27] [28]. In addition to the cost related parameters, ramp rate limits as well as fixed no-load costs of DGs were considered.…”

Section: Simulation Results and Analysismentioning

confidence: 99%

Hydrogen and Battery Storage Technologies for Low Cost Energy Decarbonization in Distribution Networks

Haggi¹,

Brooker²,

Sun³

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep energy decarbonization cannot be achieved without high penetration of renewables. At higher renewable energy penetrations, the variability and intermittent nature of solar photovoltaic (PV) electricity can cause ramping issues with existing fossil fuel generation, requiring longer term energy storage to increase the reliability of grid operation. A proton exchange membrane electrolyzer can produce H 2 and serves as a utility controllable load. The produced H 2 can then be stored and converted back into electricity, or mixed with natural gas, or used as transportation fuel, or chemical feedstock. This paper considers the perspective of the distribution system operator that operates the distributed energy resources on a standard IEEE 33-node distribution network considering the technical and physical constraints with the goal of minimizing total investment and operation cost. Different case studies, at very high PV penetrations are considered to show the challenges and path to net-zero emission energy production using H 2 energy. Sensitivity of utility PV costs and electrolyzer capital costs on producing H 2 at $1/kg are presented showing that the distribution network could produce 100% renewable electricity and H 2 could be produced at a cost of $1/kg by 2050 with conservative cost estimates and by 2030 with accelerated cost declines.

show abstract

Section: Simulation Results and Analysismentioning

confidence: 99%

Hydrogen and Battery Storage Technologies for Low Cost Energy Decarbonization in Distribution Networks

Haggi¹,

Brooker²,

Sun³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Deep Variational Autoencoder has been used to calibrate hydro generator models [17]. The approach showed very promising results on many parameters (18 parameters) but still needs multiple events to be reliable.…”

Section: Related Workmentioning

confidence: 99%

“…To improve the model calibration efficiency, researchers conducted sensitivity analyses to reduce the problem complexity by eliminating the least impactful parameters by quantifying and comparing the sensitivity of each parameter. The most sensitive parameters have the highest impact on the model while low sensitivity parameters have a small impact on model responses [5], [12], [17], [18], [29]. Our researched power plants included a GENROU (for machine), ESST1A (for exciter), GGOV1 (for governor), and PSS2A (for PSS), with 82 parameters in total.…”

Section: Sensitivity Analysismentioning

confidence: 99%

See 1 more Smart Citation

A Deep Learning-Based Framework for Parameters Calibration of Power Plant Models Using Event Playback Approach

Matar

Elmoudi

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Accurate and reliable calibration of power plant models in the power system is crucial for maintaining grid stability and preventing power outages. This becomes even more crucial as the power grids become more dynamic and stochastic with the ever-increasing penetration of renewable energy sources, mid-size generators, smart loads, and energy storage. Current practice such as staged-test is costly and timeconsuming. Alternatively, recent PMU-based approaches using online measurements without interfering with generators operation have been introduced to provide a scalable and low-cost to meet North American Electric Reliability Corporation (NERC) standards. This research paper proposes a PMU-based framework to validate and calibrate model parameters by a new iterative deep learning approach. The results show that the proposed approach can accurately calibrate power plantmodels from a single disturbance event without the urgent need of prior knowledge of the model's initial parameters. The proposed method has been validated on real-world and simulated scenarios on a relatively large number of calibrated parameters with an average error of 1.43%.

show abstract

“…where C(• ∥ •) is the Kullback-Leibler divergence between two distributions and can not be negative. Now, the ELBO can be optimized via stochastic gradient descent algorithm [19], [20]. IV.…”

Section: A Cvae For Parameter Identificationmentioning

confidence: 99%

WECC Composite Load Model Parameter Identification Using Deep Learning Approach

Khazeiynasab

Zhao

Duan

2022

2022 IEEE Power &Amp; Energy Society General Meeting (PESGM)

View full text Add to dashboard Cite

The increased integration of distributed energy resources (DERs) has significantly changed the load composition. As compared to traditional static or induction motor loads, these inverter-based resources (IBRs) exhibit different behavior. Then, conventional dynamic load modeling with ZIP and induction motors (ZIP + IM) is no longer adequate to address the current load characteristic transitions. Western Electricity Coordinating Council (WECC) has developed the composite load model with distributed generation (CMPLDWG) to accurately represent static load, induction motors, and IBRs. In this paper, we propose a novel deep learning-based method using a conditional variational autoencoder (CVAE) to estimate the CMPLDWG model's posterior distributions. The effectiveness of the proposed method is validated using an IEEE 39-bus test system. The results show that the proposed approach can accurately and efficiently estimate the parameters' posterior distributions.

show abstract

Power Plant Model Parameter Calibration Using Conditional Variational Autoencoder

Cited by 16 publications

References 30 publications

Hydrogen and Battery Storage Technologies for Low Cost Energy Decarbonization in Distribution Networks

Hydrogen and Battery Storage Technologies for Low Cost Energy Decarbonization in Distribution Networks

A Deep Learning-Based Framework for Parameters Calibration of Power Plant Models Using Event Playback Approach

WECC Composite Load Model Parameter Identification Using Deep Learning Approach

Contact Info

Product

Resources

About