[CCoE Notice] Thesis Announcement: Elias Raffoul, "Advanced Forecasting and System Integration Impact Analysis of Renewable Energy and Electric Vehicles on Power Distribution Networks"

[Greenwell, Stephen J]

[Thesis Defense Announcement at the Cullen College of Engineering]
Advanced Forecasting and System Integration Impact Analysis of Renewable Energy and Electric Vehicles on Power Distribution Networks

Elias Raffoul
December 2, 2024; 9:00 AM - 11:00 AM (CST)
Location: Online
Teams: https://urldefense.com/v3/__https://teams.microsoft.com/l/meetup-join/19*3ameeting_NmViZmQ1MjItOTUwMy00NmZmLWJlY2MtMmZkN2ZjZjIxMzhl*40thread.v2/0?context=*7b*22Tid*22*3a*22170bbabd-a2f0-4c90-ad4b-0e8f0f0c4259*22*2c*22Oid*22*3a*2297723938-975b-475c-a245-ac8038e6f996*22*7d__;JSUlJSUlJSUlJSUlJSUl!!LkSTlj0I!De9d2uF6g-EkOSVXY7XwRmcRQ1J2p8dHswPaJScFhTzR46p5MjiPF_WR7AV5Bb5bbPpSc763m5Pfx4Pefs86RKfqSzs$ 
Meeting ID: 220 120 933 087
Passcode: h5rmJJ
Committee Chair:
Xingpeng Li, Ph.D.
Committee Members:
Hao Huang, Ph.D. | Kaushik Rajashekara, Ph.D. | Tianxia Zhao, Ph.D.
Abstract
The rapid evolution of modern power systems, driven by renewable energy integration and transportation electrification, has introduced new challenges in grid reliability, efficiency, and sustainability. This thesis explores advanced modeling techniques to address these challenges, focusing on three interconnected themes: load forecasting, renewable energy integration, and the impact of electric vehicle (EV) adoption on distribution grids.
First, a comparative analysis of machine learning (ML) models, including feedforward neural networks, recurrent neural networks, long short-term memory networks (LSTM), gated recurrent units, and attention temporal graph convolutional networks, is conducted for short-term load forecasting. Using real-world data from Houston's Energy Corridor distribution system, the study identifies the most effective ML models for accurate load prediction, offering insights for optimizing grid operations.
Second, the thesis develops an LSTM-based deep learning framework for net load forecasting in microgrids equipped with solar and wind power. Leveraging typical meteorological year datasets, the model accurately predicts net load dynamics, enabling improved energy management in renewable-based microgrids and addressing the variability inherent in renewable energy sources.
Lastly, the impact of widespread EV charging on power distribution networks is assessed using a detailed simulation of a 240-bus system with 1120 customers. By evaluating ampacity violations, line loading, and voltage stability under various EV penetration scenarios, the research identifies critical grid infrastructure challenges and proposes strategies for grid reinforcement and voltage-level adjustments to ensure reliable operation.
Together, these studies provide a comprehensive framework for advancing power and energy systems through predictive modeling, renewable energy forecasting, and infrastructure planning. By addressing the challenges of grid modernization, this work contributes to the development of resilient, efficient, and sustainable power systems capable of meeting the demands of a decarbonized future.
[Engineered For What's Next]



-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://Bug.EGR.UH.EDU/pipermail/engi-dist/attachments/20241125/c95abce5/attachment-0001.html 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.png
Type: image/png
Size: 28468 bytes
Desc: image001.png
Url : http://Bug.EGR.UH.EDU/pipermail/engi-dist/attachments/20241125/c95abce5/attachment-0002.png 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image002.png
Type: image/png
Size: 5699 bytes
Desc: image002.png
Url : http://Bug.EGR.UH.EDU/pipermail/engi-dist/attachments/20241125/c95abce5/attachment-0003.png