⚡ Power Systems · 🤖 Machine Learning & Intelligence · 🕸 Networked Dynamical Systems

Nima T. Bazargani, Ph.D.

Bridging physics, data, and networks for resilient energy infrastructures.

Electrical engineer specializing in power systems and AI-driven analytics. I create models, pipelines, and algorithms to enhance grid observability, interpret dynamic behaviors, and support reliable operations under uncertainty. My research integrates graph theory with machine learning to model cyber-physical-economic systems.

Research and Professional Focus

⚡ Power Systems Engineering: real-time analysis of grid behavior, stability assessment and forecasting, and modeling of power system operations under network and market constraints.
🤖 Machine Learning & Intelligence: high-dimensional temporal modeling, deep and adaptive learning methods, and scalable data pipelines for streaming sensor and telemetry data.
🕸 Networked Dynamical Systems: multi-layer representations of physical–cyber–market infrastructures, graph-theoretic flow and sensitivity analysis, and the study of resilience and interdependent system behavior.

about research projects blog cv contact

Semi-Supervised Event Identification for Power Systems

This project introduces a semi-supervised learning framework for classifying disturbance events using high-dimensional PMU data when labels are sparse. Real power-system PMU archives contain thousands of unlabeled snapshots and only a limited number of trusted labeled events. ▣ Problem PMU archives contain very limited labeled data, making supervised training unreliable Grid conditions shift across time, seasons, and topology changes Physics-based features alone cannot fully capture dynamic variability ▣ Approach Combine spectral/modal signatures with learned temporal embeddings Apply self-training, pseudo-label refinement, and consistency constraints Leverage small labeled sets to guide structure in large unlabeled PMU corpora ▣ Validation Strong generalization under low-label regimes Robust identification across multiple utilities and operating conditions Outperforms traditional supervised PMU classifiers in label-scarce settings ▣ Publication arXiv preprint (2024): https://arxiv.org/abs/2309.10095

Source Localization in Linear Dynamical Systems

This project studies the problem of localizing unknown disturbance sources in large linear dynamical systems using limited measurements. The work is motivated by oscillatory events, faults, and cyber-physical anomalies in power grids. ▣ Problem Disturbance inputs propagate through network dynamics Only partial measurements of the system state are available Need to infer where the excitation originated without full model knowledge ▣ Approach Apply subspace system identification to recover reduced-order dynamics Formulate a source localization estimator using Markov parameters Use structured propagation patterns to recover the most probable source ▣ Validation Demonstrated on synthetic linear networks and benchmark system models Accurate localization under noise, limited sensors, and model uncertainty Applicable to oscillation events and cyber-physical anomalies ▣ Publication IEEE CCTA 2023: https://ieeexplore.ieee.org/document/10252510

Event Identification via Modal & Spectral Analysis of PMU Data

This project develops a real-time event identification framework using modal and spectral features extracted from wide-area PMU streams. ▣ Problem PMUs produce extremely high-dimensional, high-rate data Operators need rapid recognition of line trips, generator outages, and oscillations SCADA-level alarms do not capture modal characteristics ▣ Approach Extract modal features (frequency, damping, mode shapes) Build a high-dimensional spectral–temporal representation Apply feature selection (LASSO, MI ranking) Train logistic regression and SVM classifiers ▣ Validation Texas 2000-bus synthetic grid Real utility dataset with ≈500 PMUs Strong accuracy and robustness across conditions ▣ Publication IEEE Transactions on Power Systems (2022): https://ieeexplore.ieee.org/document/9911774

Forced Oscillation Localization via Complex-LASSO

This project develops a Complex-LASSO framework for identifying the sources of forced oscillations (FOs) in wide-area power systems. ▣ Problem Forced oscillations degrade stability and can spread across large systems Source location is often unknown and difficult to estimate PMU measurements are noisy and distributed ▣ Approach Represent unknown FO inputs as sums of sinusoids in the frequency domain Estimate candidate frequencies via empirical spectrum analysis Formulate and solve a complex-valued ℓ₁-regularized least-squares problem Use coordinate descent for efficient optimization ▣ Validation IEEE 68-bus and WECC 179-bus systems Correctly identifies FO locations and amplitudes Scalable to multiple sources and noisy measurements ▣ Publication IEEE PES General Meeting (2022): https://ieeexplore.ieee.org/document/9916993

Event Identification Framework Based on PMU Modal Analysis

A poster contribution demonstrating the use of modal analysis and spectral PMU features for disturbance detection and classification. ▣ Problem Wide-area events leave modal signatures that are not captured by traditional SCADA indicators. ▣ Approach Extract modal dynamics from PMU windows Build feature embeddings for event classification Evaluate temporal stability of modal signatures ▣ Publication IEEE PES General Meeting Poster (2021)

Virtual Synchronous Generator for Frequency Response and Power Damping

This project applies adaptive sliding-mode control to virtual synchronous generators (VSGs) to improve microgrid frequency response and damping. ▣ Problem Converter-dominated microgrids lack physical inertia VSGs emulate synchronous behavior but need robust control Frequency excursions and oscillations persist under disturbances ▣ Approach Design an adaptive sliding-mode VSG controller Enhance frequency response and damping under varying conditions Evaluate robustness against load changes and disturbances ▣ Publication IEEE EPE (2018): https://ieeexplore.ieee.org/document/8559616

Probabilistic Resilience Assessment of Distribution Systems

This project develops a probabilistic resilience assessment framework for distribution and microgrid systems under hurricane-induced disruptions. ▣ Problem Extreme weather events cause widespread outages Need quantitative metrics for expected resilience and restoration feasibility Load and PV generation uncertainty must be included ▣ Approach Define a time-dependent expected resilience metric Use Point Estimate Method (PEM) to propagate uncertainty Compare results against Monte Carlo simulation Apply graph-theoretic restoration feasibility analysis ▣ Validation IEEE 37-node distribution system Comparison of conventional vs. active distribution systems Strong agreement with Monte Carlo, with far lower compute cost ▣ Publication IEEE MELECON (2018): https://ieeexplore.ieee.org/abstract/document/8379107

Resiliency Evaluation Framework for Radial Distribution Grids

This project develops a general resilience evaluation framework for radial distribution feeders exposed to extreme events. ▣ Problem Distribution networks experience structural vulnerabilities during storms and high-impact low-probability events. ▣ Approach Model resilience through topology, damage states, and restoration pathways Use graph metrics to quantify accessibility and load-serving potential ▣ Publication IEEE ICEE (2018): https://ieeexplore.ieee.org/document/8472496

Optimal Sizing of Battery Storage and Wind Penetration

This project applies NSGA-II multi-objective optimization to size battery storage and determine wind penetration levels for optimal microgrid performance. ▣ Problem Microgrid planning requires balancing cost, reliability, renewable penetration, and system constraints. ▣ Approach Formulate a multi-objective optimization problem Use NSGA-II to explore tradeoffs in storage and wind integration Analyze Pareto-front behavior across load and wind scenarios ▣ Publication IEEE ICEE (2017): https://ieeexplore.ieee.org/document/7985180