Haoran Li

About Me

I am a Visiting Scholar at the Laboratory for Information and Decision Systems (LIDS) at MIT, specializing in smart grids, Machine Learning, Reinforcement Learning, and renewable integration.

I earned a PhD in Electrical, Computer, and Energy Engineering from Arizona State University (ASU), where I also taught and conducted postdoctoral research. My work has been published in IEEE Transactions on Power Systems and IEEE Transactions on Smart Grid, among others, and I have presented at leading conferences such as the NeurIPS, KDD, IEEE ICDM, etc.

You can reach me at haorandd [at] mit.edu.

News

Journals

Low-Dimensional ODE Embedding to Convert Low-Resolution Meters into ‘Virtual’ PMUs

Haoran Li, Zhihao Ma, Yang Weng, Haiwang Zhong, Xiaodong Zheng

IEEE Transactions on Power Systems, 2024, accepted

Distribution Grid Topology and Parameter Estimation Using Deep-Shallow Neural Network with Physical Consistency

Haoran Li, Yang Weng, Vijay Vittal, Erik Blasch

IEEE Transactions on Smart Grid, 2023, accepted

Hd-Deep-EM: Deep Expectation Maximization for Dynamic Hidden State Recovery Using Heterogeneous Data

Zhihao Ma, Haoran Li, Yang Weng, Erik Blasch, Xiaodong Zheng

IEEE Transactions on Power Systems, 2023, accepted

Power System Transfer Learning to Identify Event Types with or without Event Labels

Zhihao Ma, Haoran Li, Yang Weng, Evangelos Farantatos

International Journal of Electrical Power and Energy Systems, 2023, accepted

Structural Tensor Learning for Event Identification with Limited Labels

Haoran Li, Zhihao Ma, Yang Weng, Erik Blasch, Surya Santoso

IEEE Transactions on Power Systems, 2022, accepted

A Transfer Learning Framework for Power System Event Identification

Haoran Li, Zhihao Ma, Yang Weng

IEEE Transactions on Power Systems, 2022, accepted

Distribution Grid Impedance & Topology Estimation with Limited or No Micro-PMUs

Haoran Li, Yang Weng, Yizheng Liao, Brian Keel, Kenneth E. Brown

International Journal of Electrical Power and Energy Systems, 2021, accepted

Conferences

Data Imputation with Uncertainty Using Stochastic Physics-Informed Learning

Lihao Mai, Haoran Li, Yang Weng

IEEE PES General Meeting, 2024, accepted

PIX-GAN: Enhance Physics-Informed Estimation via Generative Adversarial Network

Haoran Li, Yang Weng

IEEE International Conference on Data Mining, 2023, accepted

CoNSoLe: Convex Neural Symbol Learning

Haoran Li, Yang Weng, Hanghang Tong

Advances in Neural Information Processing Systems, 2022, accepted

Domain Adaptation in Physical Systems via Graph Kernel

Haoran Li, Hanghang Tong, Yang Weng

Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022, accepted

Transfer Learning for Event-Type Differentiation on Power Systems

Haoran Li, Zhihao Ma, Yang Weng, Evangelos Farantatos

IEEE International Conference on Smart Grid Synchronized Measurements and Analytics, 2022, accepted

The Powerful Use of AI in the Energy Sector: Intelligent Forecasting

Erik Blasch, Haoran Li, Zhihao Ma, Yang Weng

AAAI FSS-21: Artificial Intelligence in Government and Public Sector, 2021, accepted

Physical Equation Discovery Using Physics-Consistent Neural Network (PCNN) Under Incomplete Observability

Haoran Li, Yang Weng

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2021, accepted

Heterogeneous Transfer Learning on Power Systems: A Merged Multi-modal Gaussian Graphical Model

Haoran Li, Yang Weng, Hanghang Tong

IEEE International Conference on Data Mining, 2020, accepted

An Unsupervised Learning Framework for Event Detection, Type Identification and Localization Using PMUs without Any Historical Labels

Haoran Li, Yang Weng, Evangelos Farantatos, Mahendra Patel

IEEE PES General Meeting, 2019, accepted

A Hybrid Machine Learning Framework for Enhancing PMU-based Event Identification with Limited Labels

Haoran Li, Yang Weng, Evangelos Farantatos, Mahendra Patel

IEEE International Conference on Smart Grid Synchronized Measurements and Analytics, 2019, accepted

Research Projects

• Comprehensive Cybersecurity Technology for Critical Power Infrastructure AI-Based Centralized Defense and Edge Resilience

  Israel-U.S. Binational Industrial Research and Development Foundation (BIRD), 2021−2026

• CAREER: Faithful, Reducible, and Invertible Learning in Distribution System for Power Flow

  National Science Foundation (NSF), 2021−2026

• Artificial Intelligence for Robust Integration of AMI and Synchrophasor Data to Significantly Boost Renewable Penetration

  U.S. Department of Energy (DOE), 2021−2024

• Machine Learning on Topology Identification in the Distribution Grid for 10 Million Customers

  Oncor Electric Delivery Company, 2023−2024

• Sensor Enabled Modeling of Future Distribution Systems with Distributed Energy Resources

  U.S. Department of Energy (DOE), 2019−2023

• Early Outage Identification via Data Mining and Machine Learning for the Synchrophasor Data

  Electric Power Research Institute (EPRI), 2018−2022

• Machine Learning-based Power Flow for Transmission and Distribution Grids with Topology Verification

  Salt River Project (SRP), 2017−2019

Awards and Talks

• Invited Talk, “Geometric Deep Learning for Interpolable and Adaptable Dynamical Modeling”

  Harvard University, Boston, 2024

• Lecture, “Time Series and Dynamically Structured Problems”

  MIT Spring Seminar Series on Machine Learning for Decarbonizing Electric Energy Systems, Boston, 2024

• Lecture, “Introduction: Old problems, new data, new problems: Digitalization, decarbonization, distributed energy systems (3D)”

  MIT Spring Seminar Series on Machine Learning for Decarbonizing Electric Energy Systems, Boston, 2024

• Invited Talk, “Energy System Dynamic Interpolation, Identification, and Symbolization”

  University of Houston, Houston, 2024

• Invited Talk, “Assured Artificial Intelligence for Engineering Systems”

  Southern Methodist University, Dallas, 2024

• Invited Talk, “AI for Energy Systems: New Possibilities”

  MIT Electric Energy System Group, Boston, 2023

• Invited Talk, “Artificial Intelligence (AI) for Robust Integration of AMI and Synchrophasor Data to Significantly Boost Solar Adoption”

  Workshop of the Department of Energy, Boston, 2023

• Finalist, Ph.D. Dissertation Challenge

  IEEE PES Grid Edge Technologies Conference & Exposition, San Diego, 2023

• Invited Talk, “Deep Learning Twin for Optimal DDDAS Monitoring for Cyber-physical Systems”

  Air Force Office of Scientific Research (AFOSR), Arlington, 2022

• Invited Talk, “Assured AI for the Decarbonization Era: Structural Designs on Deep Neural Networks”

  Stanford Smart Grid Seminar, Santa Clara, 2022

• Best Student Award

  Machine Learning of Power System Lab, Arizona State University, 2021, up to $2000

• Student Travel Grant

  IEEE International Conference on Smart Grid Synchronized Measurements and Analytics, Texas, 2019, up to $1,500

• ECEE Travel Grant

  Arizona State University, 2019, up to $1,000

• Student Housing Support

  IEEE Power & Energy Society General Meeting (PESGM), Portland, 2019, up to $800

• Student Award in Machine Learning for Electrical Data

  Tsinghua University, 2018, $2,000

• Invited Talk, “Distribution Grid Topology Identification Using Graphical Models”

  Tsinghua University, 2018

Service

• 2025, Will be a panel session chair, “Harnessing Data-Driven Approaches and Generative AI for Dynamic Modeling, Data Generation, and Control in Distribution Grids”, IEEE Power & Energy Society General Meeting, Austin, Texas.
• 2024, Team member, PES AI Initiative Workplan.
• 2023−present, Reviewer for AI top conference (ICLR, IEEE Big Data), power system top journals (IEEE TPS, TSG, TSE, TEMPR, PES Letter, IET SG, IET RPG, IJEPES, etc.).
• 2024, Program Committee (PC) member, IEEE International Conference on Big Data, Washington DC.
• 2024, Judge of Student Poster Competition at IEEE Power & Energy Society General Meeting (PESGM), Seattle.
• 2023, Co-leader of a group meeting, AI/ML in Energy Systems, in MIT Electric Energy System Group (EESG), Boston.
• 2023, Program Committee (PC) member, IEEE International Conference on Big Data, Sorrento.
• 2023, Panelist, “From Charging Challenges to Becoming Interactive Assets - EVs’ Road Map to Grid Integration”, IEEE Power & Energy Society General Meeting (PESGM), Orlando.
• 2021−2023, Working Group Secretary, Big Data Webinar Working Group, IEEE PES Subcommittee on Big Data & Analytics for Power Systems.