Nima Taghipour Bazargani

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


⬇️ Download Full CV (PDF)

🧭 Contents

Professional Profile

I am an electrical engineer specializing in power systems, machine learning, and networked‑system analytics.
My work combines physics‑based modeling with modern data‑driven methods to improve grid monitoring, stability assessment, electricity‑market behavior, and infrastructure resilience.
My experience spans both academic research and industry‑facing engineering, focusing on scalable, real‑time, and operationally relevant solutions for large‑scale electric power systems.

Key technical themes

  • PMU analytics: event identification, oscillation detection, wide‑area monitoring, and synchrophasor‑driven insights.
  • Machine learning: time‑series forecasting, classification, feature extraction, semi‑supervised and continual learning (including MAML) for rare events.
  • Electricity markets: simulation and analytics for SCUC/SCED, congestion studies, price formation, risk analysis, and planning.
  • Resilience & microgrids: battery storage sizing, resiliency metrics, microgrid protection, and restoration planning.
  • Networked infrastructures: multi‑layer graph formulations for power and communication systems; virtual network embedding under uncertainty.

Core expertise

  • Power Systems: wide‑area monitoring using PMUs; power system dynamics, stability, and inertia forecasting; transmission and distribution modeling; planning and operational studies.
  • Machine Learning & Data Science: time‑series forecasting and classification; semi‑supervised learning for rare events; spatio‑temporal feature extraction; reproducible ML pipelines integrating Python and C++ ecosystems.
  • Markets & Optimization: Security‑Constrained Unit Commitment (SCUC) and Economic Dispatch (SCED); scenario‑based congestion and risk analysis; optimization‑informed decision support; integration of external drivers (weather, fuel, outages) into large simulation workflows.

Technical skills

  • Programming & ML: Python (NumPy, pandas, scikit‑learn, PyTorch, TensorFlow/Keras), MATLAB, GAMS, SQL, C++.
  • Analytics & methods: time‑series modeling, optimization, semi‑supervised and incremental learning, modal analysis, dimensionality reduction, data engineering, reproducible pipelines.
  • Cloud & infra: Git/GitHub, Linux, REST APIs, Google Cloud Platform, AWS.
  • Power system tools: PSS®E, PowerWorld, DIgSILENT PowerFactory, PSLF, DSATools, TARA, DAYZER.

Experience

  • Power System Engineer | Electric Power Group (EPG)
    Pasadena, California | Sep 2024 – Jul 2025
    Developed a real-time inertia and system-strength forecasting capability using high-speed synchrophasor (PMU) streams and integrated it into a production C++ analytics platform. Designed a Python-based machine-learning framework interoperable with the existing C++ product stack and applied Model-Agnostic Meta-Learning (MAML) to adapt models to short-term grid shifts while reducing catastrophic forgetting. Crafted physics-informed features for operator-facing situational-awareness tools and championed incremental learning on live PMU streams.

  • Network Model Analyst | CWP Energy
    Montreal, Canada (Remote) | Sep 2023 – Jun 2024
    Conducted large-scale SCUC/SCED simulations for major U.S. markets (MISO, SPP, PJM, ERCOT) to support day-ahead strategy, planning, and risk analysis. Enhanced simulation pipelines by integrating external drivers(e.g., weather, fuel prices, outage schedules) and utilizing cloud compute to scale long-horizon studies for congestion risk and Financial Transmission Right (FTR) analysis. Built scalable Python + Google Cloud workflows for market scenario analysis and produced congestion and price-risk analytics that informed trading and planning decisions.

  • Data Scientist Intern | Drive Powerline (formerly gigElev)
    San Francisco, California (Remote) | May 2022 – Aug 2022
    Designed and deployed REST API pipelines to ingest, clean, and organize electricity market and grid datasets (including CAISO) for downstream analytics. Developed and deployed near-real-time machine-learning models to forecast operational grid metrics, providing improved situational awareness and decision support for internal analytics tools.

  • Graduate Research Associate | Arizona State University
    Tempe, Arizona | Aug 2019 – Sep 2023
    Developed methods for real-time event identification using high-dimensional spatio-temporal PMU measurements. Built a complete event-identification pipeline (event generation via PSS®E Python API, modal-analysis feature extraction, semi-supervised benchmarking, and ML classification) and contributed to PSERC- and NSF-funded projects on oscillation detection, modal feature extraction, and anomaly classification. Applied modal analysis and semi-supervised learning methods to rare events and collaborated on a U.S.–Israel Energy Center initiative that produced an open-source PMU analytics framework — see the arXiv paper for details (arXiv). Research funding included NSF (OAC-1934766), PSERC (S-87) (final report), and a BIRD-sponsored cybersecurity-in-energy program (Energy Center).

  • Guest Researcher | Technical University of Darmstadt (CRC 1053 MAKI)
    Darmstadt, Germany | Oct 2018 – May 2019
    Worked on reliable virtual network embedding for cyber-physical energy systems as part of the Collaborative Research Center 1053 MAKI – Multi-Mechanisms Adaptation for the Future Internet (project page). Formulated the problem as a stochastic mixed-integer optimization for communication networks supporting energy automation and contributed to multi-layer network adaptation mechanisms under uncertainty. Collaborated closely with Prof. Dr. Florian Steinke (homepage).

  • Project Advisor | Niroo Research Institute (NRI)
    Tehran, Iran | Aug 2017 – Jun 2018
    Led resilience-oriented modeling for national power-system infrastructure. Supported the definition, evaluation, and analysis of resilience metrics used in power system planning and developed graph-based restoration and vulnerability assessment modules for infrastructure resilience.

Education & Coursework

Degrees & theses

Degree University / Period Thesis / Focus Advisors
Ph.D., Electrical Engineering Arizona State University (2019–2023) Real-Time Identification of Power System Events Using Phasor Measurement Unit Data Oliver Kosut; Lalitha Sankar
M.Sc., Electrical Engineering (Power Systems) K. N. Toosi University of Technology (2015–2018) Optimal Sizing & Allocation of Battery Energy Storage Systems for Microgrid Resilience S. M. T. Bathaee
B.Sc., Electrical Engineering Shahid Beheshti University (2008–2014) Design & Construction of a Static Frequency Converter for Transformer Testing Mohammad Hossein Aghashabani

Selected Ph.D. coursework (ASU)
Machine Learning for Smart Grid (Yang Weng);
Wide-Area Measurement System Applications (Anamitra Pal);
Random Signal Theory (Gautam Dasarathy);
Linear Algebra & Convex Optimization (Angelia Nedić);
Foundations of Machine Learning (Lalitha Sankar);
Topics in Reinforcement Learning (Dimitri P. Bertsekas);
Power System Stability & Dynamics (Vijay Vittal).

Selected M.Sc. coursework (K. N. Toosi University of Technology)
Power System Dynamics; Power System Reliability; Power System Planning; Advanced Power System Protection; Power System Transients; Flexible AC Transmission Systems (FACTS); Smart Grids.

Selected B.Sc. coursework (Shahid Beheshti University)
Power System Analysis; Power System Operation & Dispatch; Distribution System Planning & Expansion; Power Distribution & Consumption Management; Electrical Machines; Power Electronics.

Projects & Publications

Publications & presentations

• Nima T. Bazargani, Lalitha Sankar, Oliver Kosut — A Semi‑Supervised Approach for Power System Event Identification, arXiv (2024).
• Rajasekhar Anguluri, Nima T. Bazargani, Oliver Kosut, Lalitha Sankar — Source Localization in Linear Dynamical Systems Using Subspace Model Identification, IEEE Conference on Control Technology and Applications (CCTA 2023).
• Nima T. Bazargani, Gautam Dasarathy, Oliver Kosut, Lalitha Sankar — A Machine Learning Framework for Event Identification via Modal Analysis of PMU Data, IEEE Transactions on Power Systems (2022).
• Rajasekhar Anguluri, Nima T. Bazargani, Oliver Kosut, Lalitha Sankar — A Complex‑LASSO Approach for Localizing Forced Oscillations in Power Systems, IEEE Power & Energy Society (PES) General Meeting (2022).
• Additional publications and conference presentations are listed in the PDF CV.

Graduate term projects (M.Sc.)

  • SCUC under AC power flow: Implemented security‑constrained unit commitment with start‑up scheduling under AC power flow constraints.
  • Microgrid protection: Analyzed protection strategies for low‑voltage microgrids using microprocessor‑based protective relays.
  • Resilient microgrid sizing: Developed simulation and optimal sizing of renewable resources on a NASA Ames microgrid testbed.
  • Smart home simulation: Designed a smart home on an IEEE 4‑bus test system with market‑clearing prices and customer incentives.
  • Optimal switch placement: Performed optimal switch placement for reliability improvement and customer interruption cost minimization (Roy Billinton Test System).

Other projects & studies

  • PMU analytics & machine learning: Developed semi-supervised event identification and modal-analysis-based classifiers; built and released an open-source PMU event identification package (PSMLEI) implementing a semi-supervised framework for classifying disturbance events from high-dimensional PMU data under sparse labels (self-training, pseudo-label refinement, and consistency constraints), combining spectral/modal signatures with learned temporal embeddings, and demonstrating robust generalization across low-label regimes and varying operating conditions.
  • System dynamics & oscillations: Worked on complex-LASSO forced oscillation localization and subspace-based source localization; examined dynamical-system identification using spatio-temporal data.
  • Market analysis & resilience: Conducted multi-ISO SCUC/SCED studies, congestion modeling, and probabilistic hurricane resilience assessment; built scenario pipelines for congestion and risk analysis; explored financial transmission right (FTR) strategies.

A more complete list of technical work is available on the Projects page.

Recognition & Acknowledgments

Honors & professional service

  • Ranked 2nd in M.Sc. cohort at K. N. Toosi University of Technology.
  • Ranked 240 out of 30 000+ in the Iran National Graduate Entrance Examination.
  • IEEE Region 8 Paper Contest finalist (Middle East & Europe).
  • Vice‑President, Iranian Student Association (ISA) at Arizona State University.
  • Social Chair, IEEE Power & Energy Society (PES) student chapter committee at Arizona State University.
  • Reviewer for IEEE Transactions on Power Systems, IEEE Power & Energy Society General Meeting, International Journal of Electrical Power & Energy Systems, and the International Power System Conference (PSC).

Academic mentorship & influential faculty

The following faculty members played a significant role in shaping my technical foundation, research interests, and professional direction (listed alphabetically):

Abbreviations

  • PMU — Phasor Measurement Unit
  • WAMS — Wide-Area Monitoring System
  • SCUC — Security-Constrained Unit Commitment
  • SCED — Security-Constrained Economic Dispatch
  • MAML — Model-Agnostic Meta-Learning
  • ISO — Independent System Operator
  • RTO — Regional Transmission Organization
  • FTR — Financial Transmission Right
  • LMP — Locational Marginal Price
  • FACTS — Flexible AC Transmission Systems
  • BESS — Battery Energy Storage System
  • TSO — Transmission System Operator
  • DSO — Distribution System Operator
  • ML — Machine Learning
  • AI — Artificial Intelligence
  • API — Application Programming Interface
  • WAC — Wide-Area Control

about research projects blog cv contact