Your Name

Md. Shadman Abid

Nanotechnology Research Center, Sultan Qaboos University, Al-Khoud 123, Muscat, Oman.

Bio

I am currently employed as a research assistant in the Nanotechnology Research Center at Sultan Qaboos University (SQU), where I work on vision-informed multi-modal AI for distribution-network scheduling, AI-driven power-grid path prediction, and deep-learning–based geospatial mapping of electric power grids. I previously worked at SQU’s Sustainable Energy Research Center, where I developed robust optimization and reinforcement learning models for electric-vehicle charging infrastructure and microgrid planning. Earlier, I served as a part-time lecturer in the Department of EEE at Sonargaon University in Dhaka. I also worked as a Power Systems Engineer at NKSoft KEMA Corporation, where I conducted optimal allocation studies of circuit reclosers and load switches across Dhaka’s distribution feeders as part of the DPDC Smart Grid Pilot Project. I completed my B.Sc. in Electrical and Electronic Engineering from the Islamic University of Technology (IUT) in 2022. My research interests include computer vision, deep learning, reinforcement learning, and optimization techniques applied to sustainable energy systems.

Experiences

Lecturer (Part-time), Sonargaon University, Dhaka | August 2022 - June 2024

  • Courses include EEE308: Power System I, EEE410: Power Plant Engineering, EEE401: Control System I, EEE 402: Control System I Laboratory, EEE165: Basics of Electrical Technology, and EE1201: Electrical Engineering Principles.
View Experience View Teaching Experience

Current Projects

Graphical Abstract

Vision-Informed Multi-Modal Multi-Agent Reinforcement Learning for Active Distribution Network Scheduling

  • Introduced the first vision-aware framework for distribution-network scheduling by integrating image-derived soiling features into the cooperative control of solar plants, energy-storage systems, static-var compensators, and flexible water-pumping-station loads.
  • Built a CNN–ViT encoder for real-time generation loss estimation and fused it with grid measurements to enable a perception–control scheduling loop.
  • Implemented the architecture in PyTorch 2.6. The framework was validated using the DeepSolarEye dataset (44K annotated solar images) for soiling regression and applied to the realistic 2289-bus Nizwa grid in Oman, collected from Mazoon Electricity Company (MZEC).
  • Achieved R² = 0.91; reduced operational costs by 7.1%; lowered losses by 19.2%; decreased carbon emissions; and improved renewable-to-load alignment by 15%.
Graphical Abstract

Deep Learning-based Geospatial Mapping Framework for Large-Scale Electric Power Grids

  • Proposed a residual graph-convolutional-network framework capable of predicting geographic locations and connectivity of power-grid infrastructure at reduced computational cost.
  • Implemented the model in PyTorch with Torch Geometric 2.6.1. The study utilized the Mazoon Electricity Company (MZEC) dataset, comprising over 500K poles, 385K service points, and 23K substations across four Omani governorates, as well as the Nigerian transmission grid dataset containing 56K components. All processed datasets were made publicly available via Zenodo.
  • Achieved testing accuracies of 95.88% (Oman) and 92.98% (Nigeria), along with near-perfect regression performance (R² = 0.9993 for Oman, 0.9960 for Nigeria). Training time was reduced by 50% compared to standard GCNs, with convergence achieved in 16–38 epochs versus 48–151 epochs for the baselines.
Graphical Abstract

AI-Driven Power Grid Path Prediction for Large-Scale Distribution Networks

  • Developed the first regression-based framework that formulates path prediction as a spatial-trajectory prediction problem.
  • Developed the model in TensorFlow 2.19.0 with Keras 3.10.0 that fuses sequential UTM coordinates with structured contextual features, including district, governorate, spatial clusters, voltage class, straightness, and cable length.
  • Conducted ablation and SHAP-based explainability analyses. Our results demonstrate that district and governorate embeddings are the dominant contributors, while voltage class, cable length, spatial cluster, and straightness offer negligible predictive value. The framework was validated on a large-scale dataset of 71K overhead conductor segments from the Mazoon Electricity Company (MZEC) grid in Oman.
Graphical Abstract

Neural Architecture Search via Reinforcement Learning for Image-based Solar Panel Soiling Loss Prediction

  • Proposed the first image-only regression framework for predicting soiling-induced power loss in solar panels using a reinforcement learning–driven neural architecture search (NAS) approach.
  • Evaluated the proposed NAS framework through two case studies: regression of soiling-induced power loss and multi-class classification of soiling severity levels.
  • Developed the framework in PyTorch 2.8.0+cu126 and utilized the DeepSolarEye dataset comprising 44K+ annotated solar-panel images for experimental validation.
Graphical Abstract

Robust Deep Learning Model for Spatiotemporal Forecasting of Renewable Energy Sources

  • Developed a spatiotemporal forecasting framework that fuses spatial feature extraction with temporal sequence learning for multi-horizon solar PV and wind power (WP) prediction.
  • Implemented the framework in TensorFlow 2.18.0 with Keras 3.8.0. All processed solar and wind datasets were made publicly available through Zenodo to support open research.
  • Achieved RMSE reductions of 3.8–25.7% for PV and 3.9–18.0% for WP (MAE reductions: 3.8–28.1% for PV and 4.2–32.6% for WP) relative to baselines, with strong robustness under 50% missing or noisy data.
View All Projects View Featured Projects

Featured Publications

R. Ahshan, Md. Shadman Abid, M. Al-Abri

Multi-modal multi-task artificial intelligence model for active distribution network scheduling with multi-agent reinforcement learning
Electric Power Systems Research, Volume 250, 2026, 112091, ISSN 0378-7796,
Publication Type: Journal Article
Publication Image

Md. Shadman Abid, H. J. Apon, S. Hossain, A. Ahmed, R. Ahshan

A novel multi-objective optimization based multi-agent deep reinforcement learning approach for microgrid resources planning
Applied Energy, Volume 353, Part A, 2024, 122029, ISSN 0306-2619
Publication Type: Journal Article
Publication Image

Md. Shadman Abid, R. Ahshan, R. Al-Abri, A. Al-Badi, M. Albadi

Techno-economic and environmental assessment of renewable energy sources, virtual synchronous generators, and electric vehicle charging stations in microgrids
Applied Energy, Volume 353, Part A, 2024, 122028, ISSN 0306-2619
Publication Type: Journal Article
Publication Image

R. Ahshan, Md. Shadman Abid, M. Al-Abri

Geospatial Mapping of Large-Scale Electric Power Grids: A Residual Graph Convolutional Network-Based Approach with Attention Mechanism
Energy and AI, Volume 20, 2025, 100486, ISSN 2666-5468,
Publication Type: Journal Article
Publication Image
View All Publications View Featured Publications