Brook Abegaz

Dr. Brook Abegaz


Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 April 2022 in IEEE Transactions on Industry Applications
Verified
Journal Article
Closed access
BABrook Abegaz
Brook Abegaz
In this article, a self-driving vehicle controller that optimizes the path a vehicle follows from its initial position to its destination is presented. The methods include clustering-based k-means, hierarchical, Gaussian matrix model, and self-organizing mapping. The real-time parallel implementation of the unsupervised machine learning algorithms could provide fast response times of under one microsecond during the lateral, longitudinal, and angular motion control of the autonomous vehicle. It was observed that a random selection of one of the machine learning methods may not always guarantee the optimality of the position and velocity variables as compared to the desired values. The proposed parallel implementation and optimization of the algorithms could have a significant contribution towards making transportation mobility more reliable and sustainable for future vehicular systems.

1 December 2020 in The Journal of Engineering
Verified
Journal Article
Open access
PDF file
BABrook Abegaz
Brook Abegaz
This study presents the implementation of a new unsupervised machine learning based system called a buck converter controller using unsupervised machine learning (ABCML) to control the operation of a type of switching voltage regulators, commonly called buck converters. The system uses the voltage and current state variables of buck converters to evaluate four switching‐based clustering algorithms, namely a Gaussian mixture model, a self‐organising mapping (SOM), a k ‐means clustering and a hierarchical clustering algorithm. Step response results of the controller implementation with the buck converter show that the SOM controller improves the performance of the voltage regulator system by 99.77% in terms of voltage overshoot and by 63.24% in terms of fall time, whereas the hierarchical clustering algorithm improves the settling time of the output voltage by 3.91%. This finding of optimal machine learning implementation approaches and their comparison could be used to improve the stability and the performance of switching voltage regulation systems which are widely used in electronic systems of today.

22 September 2009 in IEEE Transactions on Power Delivery
Verified
Journal Article
Closed access
ATAdam J. Thomas
Adam J. Thomas
BABrook Abegaz
Brook Abegaz
Sudden changes in the status of an electrical power system involving generation, loading, or fault conditions result in disturbances in the system, which often cause undesired operation. These disturbances propagate through the system in the form of waves in the phase angle of the voltage until they disperse and normal conditions are restored. Electromechanical characteristics of these waves have been modeled in the past through discrete and continuum approaches. In this paper, a simplified method for numerically solving the governing continuum equations is presented. These equations are represented as electromagnetic equations so that software designed for electromagnetics can be used for continuum power systems. The ability to use commercial software leads to several advantages, among them increased flexibility and reduced computational time, as well as avoiding the need to work directly with tensor fields and Gaussian filters. Continuum network equations can be represented as either an electrostatic or magnetostatic problem, while continuum dynamics, such as generator swing equations, can be represented as electric circuits. The proposed model was tested on the highly anisotropic 27-bus New England system and compared with the continuum model of the same system, with comparable results.

4 August 2017 in IEEE Transactions on Power Electronics
Verified
Journal Article
Closed access
BABrook Abegaz
Brook Abegaz
SMSatish M. M. Mahajan
Satish M. M. Mahajan
A major challenge in the stable operation of hybrid power networks is that such systems operate under the influence of perturbations from source fluctuations and from dynamic storage operations. In the current practice, hybrid power networks are operated and controlled by higher-level supervisory control systems using approaches such as droop control logic that may not make use of the accurate network models, full state measurements, and learning mechanisms to deal with the convoluted perturbations on voltage source converters (VSCs). These perturbations could result from natural variations, parameter uncertainties, grid faults, variable loadings, controller settings, and other exogenous disturbances. So far, these perturbations have been considered as lumped terms that do not represent the correlation of perturbations across the network components. In this paper, an integrated, on-chip expert system (EXPSOC) is proposed to compute the correlation between power variables in separate modules, to perform state estimation of power and voltage variables and to improve the tolerance of perturbations in the hybrid networks. Results show the optimality of the approach in controlling dynamic power perturbations and in keeping the stability of the voltage, frequency and power variables at the level of grid connected VSCs.

10 June 2022 in International Transactions on Electrical Energy Systems
Verified
Journal Article
Open access
PDF file
BABrook Abegaz
Brook Abegaz
SZSina Zarrabian
Sina Zarrabian
The state-estimation and optimal control of multigeneration systems are challenging for wide-area systems having numerous distributed automatic voltage regulators (AVR). This paper proposes a modified Q-learning method and algorithm that aim to improve the convergence of the approach and enhance the dynamic response and stability of the terminal voltage of multiple generators in the experimental Western System Coordinating Council (WSCC) and large-scale IEEE 39-bus test systems. The large-scale experimental testbed consists of a six-area, 39-bus system having ten generators that are connected to ten AVRs. The implementation shows promising results in providing stable terminal voltage profiles and other system parameters across a wide range of AVR systems under different test scenarios including N-1 contingency and fault conditions. The approach could provide significant stability improvement for wide-area systems as compared to the implementation of conventional methods such as using standalone AVR and/or power system stabilizers (PSS) for the wide-area control of power systems.

8 December 2021 in The Journal of Engineering
Verified
Journal Article
Open access
PDF file
BABrook Abegaz
Brook Abegaz
In this paper, clustering methods are presented to enhance the stability of automatic voltage regulators using the efficient adjustment of their respective gains. The results show that implementations of some of the clustering algorithms provide better reliability and stability for the feedback‐based voltage regulators as compared to the other methods, namely, a model predictive controller (MPC), a gaussian mixture model (GMM), a self‐organizing mapping (SOM) and hierarchical clustering (HC) methods. Specifically, the K‐Means clustering approach (KM) provided superior stability but a slower rise time of the output voltage of the voltage regulators as compared to the other methods. Furthermore, coordination of the clustering methods is tested for a 10 machine, 39 bus power grid system. The results show that the clustering approach could be applied to improve the efficiency of voltage regulation methods in smart grids and related cyber‐physical systems.