Hicham Chaoui’s research while affiliated with Texas Tech University and other places

... In particular, as the number of synchronous generators decreases, concerns regarding frequency stability increase owing to the reduction in power system inertia. When a fault occurs in a low-inertia system, the sudden frequency drop and low-frequency nadir can trigger unexpected protection operations and increase the risk of blackouts [6][7][8][9]. Accordingly, transmission system operators (TSOs) worldwide have focused on reorganizing new electricity markets and supplying additional facilities to secure grid reliability owing to the high penetration of IBRs [10][11][12][13][14][15]. ...

Reference:

Estimation of Quantitative Inertia Requirement Based on Effective Inertia Using Historical Operation Data of South Korea Power System

... Among them, Li-ion is widely used in EVs because of its high power density and low cost. However, Li-ion suffers from low overcharge tolerance, and therefore Li-ion requires higher safety protection installed in EVs [6,7]. ...

Reference:

Directional power transfer and data communication using magnetic resonance wireless charging system

... This algorithm makes use of an ANN to optimize the parameters of a fuzzy controller. ANNs are also implemented for improving the droop control performance in [50] by means of a feedforward neural network (FFNN) architecture for islanded and grid-connected modes. In this study, the FFNN algorithm substitutes the conventional virtual impedance control loop by learning the transient inverter's non-linear model characteristic. ...

Reference:

Artificial Intelligence in the Hierarchical Control of AC, DC, and Hybrid AC/DC Microgrids: A Review

... A semi-active HESS involves one storage device connected to the DC Bus via a bi-directional DC-DC converter. An active HESS is defined by the connection of two storage devices through bi-directional DC-DC converters to the DC Bus, as discussed in the literature [21][22][23][24]. ...

Reference:

Energy Management Strategies of PV-Battery/Supercapacitor System for Electric Vehicles

... LSTM [33] is a specialized type of Recurrent Neural Network (RNN) that excels at capturing long-term dependencies in sequential data. Traditional RNNs often face challenges such as gradient vanishing or exploding when processing long time series. ...

Reference:

A Joint Prediction of the State of Health and Remaining Useful Life of Lithium-Ion Batteries Based on Gaussian Process Regression and Long Short-Term Memory

... [30][31][32][33][34] 2 | LITERATURE SURVEY In this literature survey, we delve into a comprehensive analysis of recent research studies focusing on PCM-based TMS techniques. By synthesizing findings from a range of studies references, [35][36][37][38][39][40][41][42][43][44] we aim to provide insights into the diverse approaches and methodologies employed in this field. This examination seeks to elucidate the current state-of-the-art in PCM-based TMS, identify key trends, and highlight areas for further exploration and development. ...

Reference:

Utilizing multilayer perceptron for machine learning diagnosis in phase change material‐based thermal management systems

... However, as the number of optimization goals increases, so do the constraints, which significantly increases the computational burden on the controller. 116 Additionally, these methods require precise mathematical modeling of the system, as inaccuracies in the model can reduce the accuracy of the optimization results. ...

Reference:

A Review on the Powertrains and Energy Management Strategies of Electric Tractors

... Further, the training process aims to minimize this loss function by adjusting the model's weights using optimization algorithms, such as Stochastic gradient descent (SGD) or Adam. These optimization techniques help in minimizing the difference between the predicted and actual stability states, improving the model's ability to accurately classify V/F stability [62][63][64][65][66]. ...

Reference:

A Hierarchical Deep Learning-Based Recurrent Convolutional Neural Network for Robust Voltage and Frequency Operation Management in Microgrids

... While comprehensive, these models often face limitations in predictive accuracy due to issues such as numerical formulations, input data, and parameterizations errors. In contrast, datadriven approaches have gained popularity for their simplicity, speed, and cost-effectiveness (Khaneghah et al. 2023). By analyzing historical data, these models uncover patterns and relationships between predictors and PM 2.5 concentrations, enabling predictions based on temporal sequences of key variables. ...

Reference:

Machine learning and deep learning approaches for PM2.5 prediction: a study on urban air quality in Jaipur, India

... Due to its high energy conversion efficiency, low operating temperature, and environmental friendly by products, PEMFCs are considered potential power generation system for various applications [33]. PEMFCs have garnered significant attention for portable, stationary power generation and transportation applications [28]. However, performance degradation in PEMFCs presents substantial challenges for effective implementation, particularly in applications requiring high reliability, extended lifespans, and low maintenance costs. ...

Reference:

Prediction of PEM fuel cell performance degradation using bidirectional long short-term memory with chimp optimization algorithm