Engineering Commons^™

Examining The Effectiveness Of Oiled Ballast Water Treatment Processes: Insights Into Hydrocarbon Oxidation Product Formation And Environmental Implications, Maxwell L. Harsha, Danielle E. Verna, Yanila Salas-Ortiz, Eduardo Osborn, Eduardo Turcios Valle, Aleksandar I. Goranov, Patrick G. Hatcher, Ana M. Aguilar-Islas, Patrick L. Tomco, David C. Podgorski

Chemistry & Biochemistry Faculty Publications

Ballast water released from ships into coastal environments has been identified as a mechanism that introduces contaminants of concern into coastal ecosystems. This study investigates the treatment processes employed at a ballast water treatment facility in Valdez, Alaska, that remove hydrocarbons from unsegregated ballast water. Specifically, the aim is to quantify and characterize hydrocarbons of emerging concern, known as dissolved hydrocarbon oxidation products (HOPs) and heavy metals (HMs), throughout the treatment process. Specialized analytical techniques were employed, such as non-volatile dissolved organic carbon analysis, fluorescence spectroscopy, Fourier transform-ion cyclotron resonance-mass spectrometry, and inductively coupled plasma triple quadrupole mass spectrometry. Results …

Ltspice Modeling For Gan-Git Hemt Including Cryogenic Temperature, Md Maksudul Hossain, Yuqi Wei, H. Alan Mantooth

Electrical Engineering Faculty Publications and Presentations

Highly efficient electrically driven avionics have led to a renewed interest in cryogenic propulsion systems with the goal of reducing carbon emission footprint. Although cryogenic converters promise better efficiency and improved power density, the successful design is incumbent upon the appropriate switching device selection and simulation-based analyses prior to initial prototyping. In this work, a datasheet-driven compact model for a gallium nitride (GaN) Gate Injection Transistor (GIT) has been proposed and implemented in LTspice, a versatile, high performance, and free circuit simulator in order to investigate the merit of the chosen device in a power electronic system.

Energy Harvesting For Residential Microgrid Distributed Sensor Systems, Devin C. Whalen

Master’s Theses

Microgrids are localized, independent power grids that can operate while connected to the larger electrical grid. These systems make intelligent decisions regarding power management and use an array of components to monitor power generation, consumption, and environmental conditions. While this technology can save end users money, the complexity of installation and maintenance has limited the adoption of microgrids in residential spaces. To simplify this technology for end users, the next evolution of microgrid components includes sensors that are wireless and ambiently powered.

Even with a microgrid installed, significant energy is wasted in residential spaces. To address this loss, energy harvesting …

The Transformer Modelling For Vftos Calculation - A Comprehensive Review, Mohamed Salah, Ebrahim A. Badran, Mansour H. Abdelrahman

Mansoura Engineering Journal

The transformer is exposed to Very fast transient overvoltages (VFTOs) originated from the switching operations in the gas insulated switchgears (GIS), these overvoltages may damage the transformer insulation and result in catastrophic failures. Consequently, the transformer should be modeled to handle the transient state. In this work, the methods published in the literature to illustrate the VFTOs in GIS are reviewed, and then an overview of the transformer modelling techniques is presented with the contribution and shortcomings of each technique. The determination methods of the parameters required for the modelling of the transformer are also reviewed. In addition, the contributions …

Calculation Of Elastic Constants Of Bulk Metallic Glasses From Indentation Tests, Zhitong Xu, Ming Liu, Fuqian Yang

Chemical and Materials Engineering Faculty Publications

One of the challenges in the applications of instrumented indentation is to simultaneously measure elastic modulus and Poisson’s ratio of homogeneous, isotropic materials. This work proposes empirical equations for simultaneous calculation of elastic modulus and Poisson’s ratio of bulk metallic glasses (BMGs) from the ratio of the short diagonal length to the long diagonal length and the area of the Knoop imprint. The parameters pre- sented in the empirical equations are determined first by Knoop microhardness tests of 24 BMGs, whose elastic moduli and Poisson’s ratios are measured by resonant ultrasound spectroscopy. These empirical equations are further validated by the …

“Zero” Porosity High Loading Nmc622 Positive Electrodes For Li-Ion Batteries, Haidar Y. Alolaywi, Kubra Uzun, Yang-Tse Cheng

Chemical and Materials Engineering Faculty Publications

LiNi0.6 Mn0.2Co0.2 O 2 (NMC622) is a widely used positive electrode material for lithium-ion batteries, including electric vehicles. In this work, we investigated the effects of porosity, ranging from “zero” to the typical 35%, on the electrochemical behavior of high- loading NMC622 electrodes. Although it is well known that the energy density of the electrode increases with increasing areal capacity and decreasing porosity, NMC-positive electrodes with exceedingly low porosity (e.g., near zero) and high loading (e.g., 4 mAh cm−2 ) have not been investigated. Here, we report an intriguing observation that the “zero porosity” NMC electrode can have higher capacity …

Multiple Sclerosis Diagnosis With Deep Learning And Explainable Ai, Nighat Bibi, Jane Courtney, Kathleen M. Curran

Conference papers

Diagnosing multiple sclerosis (MS) presents significant challenges due to its complex clinical presentation and the subjective interpretation of imaging findings. Machine learning (ML) and deep learning (DL) models, despite their potential, often exacerbate these challenges with their opaque decision-making processes, hindering clinical integration. This study addresses these limitations by employing eXplainable Artificial Intelligence (XAI) techniques, specifically integrating Grad-CAM within a Convolutional Neural Network (CNN) framework, EfficientNetB1, for the diagnosis of MS. The primary objective is to enhance the transparency and reliability of MS diagnosis by providing clear visual insights into the model’s decision-making process, while also identifying and mitigating potential …

Enhancing Multiple Sclerosis Diagnosis With Explainable Ai, Nighat Bibi, Jane Courtney, Kathleen M. Curran

Conference papers

Multiple sclerosis (MS) is a complex neurological disorder that requires precise diagnosis for effective treatment. This study aims to enhance MS diagnosis by integrating eXplainable Artificial Intelligence (XAI) techniques into a convolutional neural network (CNN) framework. The proposed model achieves high accuracy and provides visual explanations of its predictions. Using the Gradient-weighted Class Activation Mapping (Grad-CAM) method, it highlights the most important regions in MRI images influencing the model’s decisions, adding transparency and trust to the diagnostic process. The CNN, trained on a dataset of FLAIR MRI images, demonstrates superior performance compared to existing models, with a final accuracy of …

Digitalization Of Railway Transportation Through Ai-Powered Services: Digital Twin Trains, Salih Sarp, Murat Kuzlu, Vukica Jovanovic, Zekeriya Polat, Ozgur Guler

Engineering Technology Faculty Publications

Digitalization is a key concept that transformed the various industries through technologies like Internet of Things (IoT), Artificial Intelligence (AI), and Digital Twin (DT). Although innovations provided by the advancement of digitalization have paved the way for more efficient operations and products for transportation, the rail transportation sector struggles to keep up with the rest of the transportation industry, since trains are designed to last for decades, and the insufficient infrastructure investment leads to multiple railroad derailments across the globe. Therefore, the primary aim is to transform current railway systems into human-centric, adaptable, sustainable and future-proof networks, aligning with Industry …

Nano-Pulse Treatment Overcomes The Immunosuppressive Tumor Microenvironment To Elicit In Situ Vaccination Protection Against Breast Cancer, Anthony Nanajian, Megan Scott, Niculina I. Burcus, Brittney L. Ruedlinger, Edwin A. Oshin, Stephen J. Beebe, Siqi Guo

Bioelectrics Publications

We previously reported that nano-pulse treatment (NPT), a pulsed power technology, resulted in 4T1-luc mammary tumor elimination and a strong in situ vaccination, thereby completely protecting tumor-free animals against a second live tumor challenge. The mechanism whereby NPT mounts effective antitumor immune responses in the 4T1 breast cancer predominantly immunosuppressive tumor microenvironment (TME) remains unanswered. In this study, orthotopic 4T1 mouse breast tumors were treated with NPT (100 ns, 50 kV/cm, 1000 pulses, 3 Hz). Blood, spleen, draining lymph nodes, and tumors were harvested at 4-h, 8-h, 1-day, 3-day, 7-day, and 3-month post-treatment intervals for the analysis of frequencies, death, …

Teaching Analytics Online: A Self-Study Of Professional Practice, Andrew J. Collins, Brandon Butler, James F. Leathrum Jr., Christopher J. Lynch

Engineering Management & Systems Engineering Faculty Publications

As the COVID-19 pandemic caused severe disruption to education enterprises throughout the world, the main response by educational institutions was to move to online learning environments. The purpose of this study was to understand better how instructors could improve online learning for a professional-level week-long short course in a highly technical area (data analytics), which had, pre-COVID, been a hands-on computer, laboratory-based learning experience. The authors used self-study of professional practice to elicit and understand the major issues and concerns of the transition to an online learning environment. Under the guidance of a colleague in teacher education, three course instructors …

Urban Flood Extent Segmentation And Evaluation From Real-World Surveillance Camera Images Using Deep Convolutional Neural Network, Yidi Wang, Yawen Shen, Behrouz Salahshour, Mecit Cetin, Khan Iftekharuddin, Navid Tahvildari, Guoping Huang, Devin K. Harris, Kwame Ampofo, Jonathan L. Goodall

Civil & Environmental Engineering Faculty Publications

This study explores the use of Deep Convolutional Neural Network (DCNN) for semantic segmentation of flood images. Imagery datasets of urban flooding were used to train two DCNN-based models, and camera images were used to test the application of the models with real-world data. Validation results show that both models extracted flood extent with a mean F1-score over 0.9. The factors that affected the performance included still water surface with specular reflection, wet road surface, and low illumination. In testing, reduced visibility during a storm and raindrops on surveillance cameras were major problems that affected the segmentation of flood extent. …

Advanced Nested Coaxial Thin-Film Zno Nanostructures Synthesized By Atomic Layer Deposition For Improved Sensing Performance, Pengtao Lin, Lari S. Zhang, Kai Zhang, Helmut Baumgart

Electrical & Computer Engineering Faculty Publications

We report a new synthesis method for multiple-walled nested thin-film nanostructures by combining hydrothermal growth methods with atomic layer deposition (ALD) thin-film technology and sacrificial films, thereby increasing the surface-to-volume ratio to improve the sensing performance of novel ZnO gas sensors. Single-crystal ZnO nanorods serve as the core of the nanostructure assembly and were synthesized hydrothermally on fine-grained ALD ZnO seed films. Subsequently, the ZnO core nanotubes were coated with alternating sacrificial coaxial 3D wrap-around ALD Al2O3 films and ALD ZnO films. Basically, the center nanorod was coated with an ALD 3D wrap-around Al₂O₃ sacrificial layer to realize a nested …

A Generative Approach For Document Enhancement With Small Unpaired Data, Mohammad Shahab Uddin, Wael Khallouli, Andres Sousa-Poza, Samuel Kovacic, Jiang Li

Engineering Management & Systems Engineering Faculty Publications

Shipbuilding drawings, crafted manually before the digital era, are vital for historical reference and technical insight. However, their digital versions, stored as scanned PDFs, often contain significant noise, making them unsuitable for use in modern CAD software like AutoCAD. Traditional denoising techniques struggle with the diverse and intense noise found in these documents, which also does not adhere to standard noise models. In this paper, we propose an innovative generative approach tailored for document enhancement, particularly focusing on shipbuilding drawings. For a small, unpaired dataset of clean and noisy shipbuilding drawing documents, we first learn to generate the noise in …

Technological Advancements In Brunei’S Local Agriculture And Fisheries Companies: An Exploratory Study Based On Field Observations, Muhammad Firdaus Mujibuddin Syah Mustafa, Navaranjan Namasivayam, Hong Shyang Pei, Fatnin Farhanah Alihan, Amni Sahilah Sahrullamzah, Khairina Umairah Takiyaudin

ASEAN Journal on Science and Technology for Development

This exploratory study, through seven field observations and interviews, investigates the technological advancements transforming Brunei's agricultural landscape in pursuit of local production augmentation and self-sufficiency. It confronts challenges with emerging technologies like aquaponics, hydroponics, fertigation systems, closed-house poultry systems, and UV lighting, which hold promise for enhanced farming practices. The research provides a comprehensive assessment of current practices, including livestock management advancements, underscoring their potential to boost productivity, optimize resource use, and promote sustainable agriculture. Furthermore, it discusses the broader implications for industry standards, job employability, and alignment with Brunei's Vision 2035. The findings contribute invaluable insights, advocating for strategic …

Application Of Three Of Selected Medicinal Plant Extracts In Brunei Darussalam To Improve Shelf Life Of Poultry Product, Hazirah Abd Hamid, Namasivayam Navaranjan, Zohrah Sulaiman, Aida Maryam Binti Hj Basri

ASEAN Journal on Science and Technology for Development

Abstract. Bioactive compounds from plant derived in food application become increasingly in demand due to natural and nutritionally safe products. Due to some issues concerning food safety on the excessive use of synthetic preservatives; the present study aims to investigate the natural alternatives to synthetic antimicrobial food additives. The chicken meat’s shelf life was studied by adopting bio-based antimicrobial agents using three of selected native medicinal plants; P. betle, A. catechu, and A. tricolor, against common foodborne pathogens; E. coli, P. aeruginosa, S. aureus, and Salmonella spp. The overall results revealed that, all study extracts possessed antioxidant properties by DPPH …

Prevalence Of Resistant Escherichia Coli Isolated From Local Meats Sold In Tema Metropolis, Ghana, Frederick Adzitey, Innocent Allan Anachinaba, Charles Addo-Quaye Brown, Nurul Huda, Masmuniri Rambli

ASEAN Journal on Science and Technology for Development

Contamination of meat by Escherichia coli (E. coli) can take its source from the live animal or by cross contamination. The study determined the prevalence of resistance of E. coli isolated from locally produced meats in the Tema Metropolis. Beef (n=200), chicken (n=200) and pork (n=200) were randomly selected and evaluated for the presence of E. coli using the procedure in the Bacteriological Analytical Manual of USA-FDA. The disc diffusion method was used for antibiotic susceptibility test of E. coli (n=55) isolates. Locally produced beef (67%), chicken (41%) and pork (23%) were contaminated by E. coli. Escherichia coli isolates were …

Kinetic Modelling During Soaking Of Dried Long Grain Paddy Mr297, Jhauharotul Muchlisyiyah, Rosnah Shamsudin, Roseliza Kadir Basha, Radhiah Shukri, Syahmeer How, Masmunira Rambli

ASEAN Journal on Science and Technology for Development

This study aimed to assess the soaking behaviour of MR 297 dried paddy under two conditions: room temperature and hot water soaking at 60°C. The experiment involved soaking dried MR297 paddy samples in water for 0.5 to 8 hours at room temperature and 0.5 to 5 hours for soaking at 60°C. The water absorption of MR 297 behaved differently at two different soaking conditions. The kinetic behaviour of the soaking process was also simulated using established 25 predictive models and incorporating 5 novel models presented in this work. The comparison of all prediction models involved using three statistical measures: the …

Assessment Of Novel Plant-Based Fat Efficiency In Comminuted Chicken Meat System, Salma Mohamad Yusop, Shu Jo Lin, Nurkhuzaiah Kamaruzaman, Nurlisa Mohd Azhari

ASEAN Journal on Science and Technology for Development

The composition of fats and oils significantly impacts the flavour, nutrition, and appearance of food. Excessive consumption of saturated fatty acids, primarily found in animal fats, raises the risk of coronary heart disease. To address this, plant-based fats are used as substitutes, with microalgae offering unique nutritional benefits as a fat source. This study evaluates the performance of structured plant-based fats, incorporating microalgae (Aurantiochytrium sp. SW1), as a fat substitute in chicken patties. Four formulations were tested: 0% (control), 5%, 7%, and 10% structured microalgae-based fat. Colour, texture, water-holding capacity, cooking loss, and microstructure in both raw and cooked samples …

Nutritional Quality Of Cultured Giant Freshwater Prawns (Macrobrachium Rosenbergii), Nurul F.M.S. Rizal, Najeebah A. Tashim, Zuhairi Azahari, Aida M. Basri, Tiong H. Lim, Aqilah Junaidi, Suriayati Chuprat, Seno A. Putra, Hanif Fakhrurroja

ASEAN Journal on Science and Technology for Development

Macrobrachium rosenbergii, or the giant freshwater prawn has high market demand due to its exceptional nutritional value for the human diet. Often, most nutritional studies focus on the edible prawn parts, rather than the prawn discarded components. The nutritional evaluation of different prawn parts can provide insights into the nutrient composition and guiding for the development of value-added products. Three groups of prawn samples were collected from 3 different ponds, representing different prawn sizes. The water quality analysis of each pond was also conducted to determine the extent to which it can affect the nutritional composition. The conventional and biochemical …

Pelletizing Of Attapulgite/Carbon Nanocomposite From Used Bleaching Earth For Continuous Treatment Of Wastewater From A Natural Rubber Factory, Lilis Hermida, Joni Agustian, Yin Fong Yeong

ASEAN Journal on Science and Technology for Development

The increase in global natural rubber production has correspondingly elevated the generation of wastewater. To address this, various wastewater treatment methods are being implemented, with continuous adsorption emerging as a promising approach. In this recent study, pelletizing of attapulgite/carbon nanocomposite was conducted to obtain pellet adsorbent for continuous adsorption of wastewater from natural rubber industry. The study aimed to evaluate the characteristics and performance of the pellet adsorbent in wastewater treatment. In the preparation, spent bleaching earth (SBE) with a 200-mesh particle size was calcined to obtain attapulgite/carbon nanocomposite. This nanocomposite was mixed with bentonite clay at a 70:30 (w/w) …

Multilayer Ceramic Capacitor Vibration Source Model Library Development, Yifan Ding, Ming Feng Xue, Jianmin Zhang, Xin Hua, Benjamin Leung, Eric A. Macintosh, Chulsoon Hwang

Electrical and Computer Engineering Faculty Research & Creative Works

When a Multilayer Ceramic Capacitor (MLCC) is Soldered on a Printed Circuit Board (PCB), the Capacitor Deformation Generates a Force on the PCB, Which Serves as a Source to Excite PCB Vibration and Generate Unwanted Acoustic Noise. a MLCC Can Be Used under Any Loading Conditions as Long as the Power Supply Voltage Remains Below its Rated Voltage; Thus, the MLCC Source Mode Can Be Extremely Complicated Because of Different Combinations Including Direct Current Voltage Levels, Alternating Current Noise Amplitudes, and Related Frequencies. When the Power Rail is under Different Loading Conditions, the PCB Vibration Amplitude Can Differ; However, the …

Prompt, Accurate, And Noncontact Material Identification Using A Single Microwave Sensor With Machine Learning Analysis, Chen Zhu, Osamah Alsalman, Jie Huang

Electrical and Computer Engineering Faculty Research & Creative Works

In This Article, a Novel Approach to Microwave Sensors is Proposed and Demonstrated that Allows for Prompt, Accurate, and Noncontact Material Identification Even with Arbitrary Lift-Off Distances between the Sensor and the Material under Test (MUT). a Multilayer Perceptron (MLP) is Trained to Directly Learn the Relation of the Measured Reflection Spectra of a Homemade Open-Ended Coaxial Cable Resonator Probe with Respect to Different MUTs and Then Achieve One-To-One Mapping between a Measured Spectrum and the MUT. as a Proof-Of-Concept Demonstration, the Performance of the MLP Model is Tested using Easily Accessible Materials, Including Wood, Glass, Water, and Metal. Reflection …

Instantaneous Current And Average Power Flow Characterization Of A Dc-Dc-Dc Triple Active Bridge Converter, Jonathan Saelens, Lauryn Morris, Oroghene Oboreh-Snapps, Arnold Fernandes, Praneeth Uddarraju, Sophia A. Strathman, Jonathan W. Kimball

Electrical and Computer Engineering Faculty Research & Creative Works

The Triple Active Bridge (TAB) is a Three-Port Power Converter that Facilitates Bi-Directional Power Flow and Provides Galvanic Isolation, Making It a Subject of Significant Research Attention. This is Attributed to its Diverse Applications in High-Frequency DC-DC Conversion, Electric Vehicles, Renewable Energy Integration, and Micro-Grids. Controlling the System at Run-Time Involves Modification of the Two Phase-Shift Parameters between Respective Bridges. by Analyzing the Fundamental Converter Operating Equations, Future Control Designers Can Use This Framework to Optimize Control Schemes to Mitigate the Under-Determined Nature of the TAB Converter. in This Paper, We Elucidate the Foundational Operational Principles of the TAB and …

Improved Peec Modeling Of Antennas Through Time-Dependent Partial Elements, Fabrizio Loreto, Giuseppe Pettanice, Martin Stumpf, Albert E. Ruehli, Jonas Ekman, Giulio Antonini

Electrical and Computer Engineering Faculty Research & Creative Works

Over the Last Twenty Years, the Evolution of Communications Has Extended the Systems' Operating Frequency Range to the Tens of GHz. in This Framework, Time Domain Integral Equation-Based (TDIE) Methods for Antenna Modeling Have Gained Increasing Interest. among Them, the Partial Elements Equivalent Circuit (PEEC) Method Turns Out to Be Attractive for its Capability to Provide Compact Circuit Models. Similarly to Other Integral Equation-Based Methods, Like the Method of Moments (MoM) in the Time Domain (TD), the PEEC Method Can Suffer from Late-Time Instabilities. This Work Shows that a Rigorous Computation of the Time-Dependent Partial Elements Leads to an Improved …

Addressing Reactive Power Sharing In Parallel Inverter Islanded Microgrid Through Deep Reinforcement Learning, Oroghene Oboreh-Snapps, Sophia A. Strathman, Jonathan Saelens, Arnold Fernandes, Jonathan W. Kimball

Electrical and Computer Engineering Faculty Research & Creative Works

Parallel Inverter Microgrids (MGs) Present a Significant Challenge in the Form of Inverter-Based Distributed Generators (IBDGs) Connected with Varying Line Impedances, Potentially Leading to Substantial Reactive Power-Sharing Errors (RPSE). This Paper Proposes the Fusion of Data-Driven Control into the Conventional Virtual Synchronous Generator in a Bid to Minimize the Sharing Error. First, All State Variables Associated with Each IBDG in the Microgrid Are Sensed and Used as Input Data for a Deep Reinforcement Learning (DRL) Agent. Next, the DRL Agent, motivated by a Unique Reward Function, is Trained to Satisfy Two Objectives: (1) Ensure the Output Voltage of All IBDGs …

Optimal Trajectory Tracking For Uncertain Linear Discrete-Time Systems Using Time-Varying Q-Learning, Maxwell Geiger, Vignesh Narayanan, Sarangapani Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

This Article Introduces a Novel Optimal Trajectory Tracking Control Scheme Designed for Uncertain Linear Discrete-Time (DT) Systems. in Contrast to Traditional Tracking Control Methods, Our Approach Removes the Requirement for the Reference Trajectory to Align with the Generator Dynamics of an Autonomous Dynamical System. Moreover, It Does Not Demand the Complete Desired Trajectory to Be Known in Advance, Whether through the Generator Model or Any Other Means. Instead, Our Approach Can Dynamically Incorporate Segments (Finite Horizons) of Reference Trajectories and Autonomously Learn an Optimal Control Policy to Track Them in Real Time. to Achieve This, We Address the Tracking Problem …

Tilted Fiber Bragg Grating Sensors Based On Time-Domain Measurements With Microwave Photonics, Shiyu Li, Ruimin Jie, Osamah Alsalman, Jie Huang, Chen Zhu

Electrical and Computer Engineering Faculty Research & Creative Works

Tilted fiber Bragg gratings (TFBGs) have garnered substantial research attention and have found widespread applications for sensing a diverse array of physical, chemical, and biological parameters based on optical spectrum measurements. The interrogation of a TFBG sensor typically requires a high-resolution bulky optical spectrum analyzer (OSA) due to the extremely narrow dips caused by the resonance of cladding modes. However, high-resolution OSAs can be costly and have limitations on measuring speed, limiting their practicality. In this paper, a new approach to interrogating TFBG sensors is proposed and experimentally demonstrated based on a microwave photonics technique. Instead of measuring the optical …

Visualization Of Noise Coupling Paths Based On The Reciprocity Theorem, Seungtaek Jeong, Jong Hwa Kwon, Deepak Pai, Jagan Rajagopalan, Chulsoon Hwang

Electrical and Computer Engineering Faculty Research & Creative Works

In this article, visualization of noise coupling paths is proposed and verified. The coupling coefficient (CC) is derived based on the Reciprocity theorem and time-average coupled power, which represents the contribution of each spatial point to the coupled power. The physical meaning of CC is demonstrated by relating the integrations of CC in a volume space occupied by absorbers to the coupled power being suppressed by the absorbers. The proposed method is applied to a practical device and the identified dominant coupling paths are experimentally verified.

Simultaneous Frequency Regulation And Active Power Sharing In Islanded Microgrid Using Deep Reinforcement Learning, Oroghene Oboreh-Snapps, Sophia A. Strathman, Jonathan Saelens, Arnold Fernandes, Lauryn Morris, Praneeth Uddarraju, Jonathan W. Kimball

Electrical and Computer Engineering Faculty Research & Creative Works

This paper presents a novel approach that integrates deep reinforcement learning (DRL) with the conventional virtual synchronous generator (VSG) to address dual objectives of microgrid (MG) control, frequency regulation and precise active power sharing. MGs typically consist of multiple Inverter-Based-Distributed-Generators (IBDGs) connected in parallel through different line impedances. The conventional active power loop (APL) of the VSG encounters significant steady-state frequency errors as load increases/decreases during islanded operation. To mitigate this issue, secondary-level controllers like proportional-integral (PI) control are added to the APL to regulate the frequency of IBDGs. However, PI control compromises power-sharing capabilities when the impedance values of …