In power systems, monitoring, protection, and control are usually model based; an accurate dynamic model for either synchronous generators or power electronic converters is essential. Besides, renewable energies, smart loads, energy storage, and new market behavior add new sources of uncertainty to power systems. Therefore, planning in real-time and developing high-quality models is crucial to adapt to uncertainties. In this thesis, we propose a framework for validating and calibrating power system models using novel methods. At the first step, we developed the nonlinear sensitivity-based method to find the critical parameters. Then, we propose an Approximate Bayesian Computation (ABC) based method which is a simulation-based method. By proposing an adaptive kernel function and a threshold sequence, we reduce the computational complexity of a ABC with a sequential Monte Carlo sampler (ABC-SMC). Using deep learning to improve the estimation accuracy, we overcome the curse of dimensionality in our proposed method. Via event playback, we build the simulations for training our model and using a parallel multi-modal long short-term memory (PM LSTM), we improve the accuracy for the high dimensional cases, but to build a model, we need to have a lot of samples. Our next proposal was a conditional variational autoencoder (CVAE), which has a great performance and requires a much smaller sample for training. The proposed methods are comprehensively evaluated; all results show that the proposed approaches have great performance in time and accuracy. We demonstrate the effectiveness of the proposed models on a synchronous generator with its controllers, a DC-DC buck converter, and a three-port inverter.


If this is your thesis or dissertation, and want to learn how to access it or for more information about readership statistics, contact us at STARS@ucf.edu.

Graduation Date





Batarseh, Issa


Doctor of Philosophy (Ph.D.)


College of Engineering and Computer Science


Electrical and Computer Engineering

Degree Program

Electrical Engineering




CFE0008860; DP0026139



Release Date

December 2022

Length of Campus-only Access

1 year

Access Status

Doctoral Dissertation (Campus-only Access)