Motamen MohammedAhmed

• Conference paper titled " AI Driven Approach to Power Quality Detection and Classification " on SPIES 2024 - Accepted.
• Journal paper titled " Improved NaS Battery State of Charge and State of Health Estimation: A Novel Integration of Temporal Fusion Transformer, Isolation Forest, and Support Vector Regression " on IEEE Transactions on Industry Applications - Aug 2024.
• Journal paper titled " Bot-MGAT: A Transfer Learning Model Based on Multi-View Graph Attention Networks to Detect Social Bots " on Applied Sciences - Application of Artificial Intelligence on Social Media - Aug 2022.
• Conference paper titled " Real Time Detection of Social Bots on Twitter Using Machine Learning and Apache Kafka " on 2021 5th Cyber Security in Networking Conference (CSNet) - Nov 2021.

1- Power quality assessment methods and approaches on critical sites for DEWA low voltage (LV) network rated at 710 kW including wind, solar, and batteries

• Applied machine learning and deep learning models (decision trees, support vector machines, random forest, XGBoost, artificial neural network, and convolutional neural network) for detection and classification of voltage sag, swell, and interruption using simulated data.
• Built data analytics dashboard for assessing power quality events using real data from power quality analyzers installed in DEWA smart grid station.

2- Exploration and evaluation of micro-PMU for DEWA distribution low voltage (LV) network using simulation data

• Understood micro-PMUs and different network events.
• Preprocessed and analyzed the data to deliver insights to higher management.
• Developed machine learning models for distribution network event detection, localization, and classification using data simulated from benchmark IEEE-34 node feeder with accuracy of over 98%.

3- Smart meter data analytics for DEWA low voltage (LV) network

• Managed the project progress.
• Ensured delivery of project requirements to stakeholders and vendors if they are involved.

4- Full scale implementation for DEWA utility scale battery energy storage

• Analyzed data from battery management system (BMS) for NaS battery rated at 1.2 MW with capacity of 7.2 MWh.
• Developed deep learning temporal fusion transformer model to predict state of charge (SoC) using historical operational battery data.
• Developed machine learning linear regression and XGBoost models for predicting state of health (SoH).

5- Theft detection and mitigation solution for DEWA power distribution assets

• Collaborated with team in writing project proposal and literature review.
• Aggregated and analyzed data for real recorded theft cases (2018-2023) at MV substations.
• Prepared two data analytics reports highlighting insights for business units.
• Conducted site visit to five 11 kV substations for studying impact of theft.
• Prepared set of recommendations to business units on technologies to be utilized.