RAISE LAB - NSFCAREER

CAREER: Machine Learning Based 4D Decomposition and Distributed Optimization

Sponsored by the National Science Foundation (NSF)

This project focuses on advancing power system operation and planning through innovative machine learning and mathematics-based decomposition and distributed algorithms. The research aims to address computational challenges in distributed optimization by developing a groundbreaking four-dimensional decomposition framework optimized using machine learning techniques.

Key objectives include:

Designing scalable asynchronous distributed algorithms that balance efficiency and accuracy.
Leveraging classification and regression methods to reduce computational costs by narrowing the feasible optimization space.
Enhancing algorithm robustness against variations in initial values and objective functions.
Creating advanced information-sharing techniques to improve computational performance.

The developed models and algorithms will be validated on synthetic test systems, setting a foundation for transformative solutions in energy systems and beyond.

Asynchronous Distributed Optimization Algorithm

We developed an asynchronous augmented Lagrangian-based distributed optimization algorithm that leverages prediction-correction techniques and machine learning. This innovative approach enables the efficient and asynchronous solution of computationally heterogeneous subproblems, enhancing scalability and performance.

Student Researchers

Ali Mohammadi
Reza Mahroo
Milad Hasanzadeh
Fouad Hasan
Farnaz Safdarian
Taylor Donnelly

Project Products

F. Hasan, A. Kargarian, “Accelerating L-shaped Two-stage Stochastic SCUC with Learning Integrated Benders Decomposition,” IEEE Transactions on Industrial Informatics, vol. 20, no. 12, pp. 14144 - 14153, 2024.
M. Movahednia, R. Mahroo, A. Kargarian, “Transmission-Distribution Coordination for Enhancing Grid Resiliency Against Flood Hazards,” IEEE Transactions on Power Systems, vol. 39, no. 3, pp. 5272 - 5282, 2024.
R. Mahroo, A. Kargarian, "Learning Infused Quantum-Classical Distributed Optimization Technique for Power Generation Scheduling," IEEE Transactions on Quantum Engineering, vol 4, 2023.
C. Wu, and A. Kargarian, "Computationally Efficient Data-driven Joint Chance Constraints for Power Systems Scheduling," IEEE Transactions on Power Systems, vol 38, no. 3, pp. 2858 - 2867, 2023.
R. Mahroo, A. Kargarian, M. Mehrtash, A. Conejo, "Robust Dynamic TEP with an N-c Security Criterion: A Computationally Efficient Model," IEEE Transactions on Power Systems, vol. 38, no. 1, pp. 912 - 920, 2022.
F. Hasan, A. Kargarian, "Topology-aware Learning Assisted Branch and Ramp Constraints Screening for Dynamic Economic Dispatch," IEEE Transactions on Power Systems, vol. 37, no. 5, pp. 3495 – 3550, 2022.
A. Mohammadi, A. Kargarian, "Learning-aided Asynchronous ADMM for Optimal Power Flow," IEEE Transactions on Power Systems, vol. 37, no. 3, pp. 1671 – 1681, 2022.
F. Safdarian, A. Kargarian, F. Hasan, Multiclass Learning-aided Temporal Decomposition and Distributed Optimization for Power Systems, IEEE Transactions on Power Systems, vol. 36, no. 6, pp. 4941 - 4952, 2021.
A. Mohammadi, A. Kargarian, “Momentum Extrapolation Prediction-Based Asynchronous Distributed Optimization for Power Systems,” Electric Power Systems Research, 2021.
F. Hasan, A. Kargarian, J. Mohammadi, “Hybrid Learning Aided Inactive Constraints Filtering Algorithm to Enhance AC OPF Solution Time,” IEEE Transactions on Industry Applications, vol. 57, no. 2, pp. 1939-9367, 2021.
F. Safdarian, A. Kargarian, “Temporal Decomposition-Based Stochastic Economic Dispatch for Smart Grid Energy Management,” IEEE Transactions on Smart Grid, vol. 11, no. 5, pp. 4544-4554, 2020.
A. Mohammadi, A. Kargarian, “Accelerated and Robust Analytical Target Cascading for Distributed Optimal Power Flow,” IEEE Transactions on Industrial Informatics, vol. 16, no. 12, pp. 7521 – 7531, 2020.
F. Safdarian, A. Mohammadi A. Kargarian, “Temporal Decomposition for Security-Constrained Unit Commitment,” IEEE Transactions on Power Systems, vol. 35, no. 3, pp. 1834-1845, 2020.
F. Safdarian, A. Kargarian, “Time Decomposition Strategy for Security-Constrained Economic Dispatch,” IET Generation, Transmission, Distribution, vol. 13, no. 22, pp. 5129-5138, 2019.
M. Mehrtash, A. Kargarian, A. Mohammadi, “Distributed Optimization-Based Collaborative Security-Constrained Transmission Expiation Planning for Multi-Regional Systems,” IET Generation, Transmission, Distribution, Vol. 13, no. 13, pp.2819-2827, 2019.
R. Mahroo, A. Kargarian, “Hybrid Quantum-Classical Unit Commitment,” IEEE Texas Power and Energy Conference, 2022.
F. Safdarian, A. Mohammadi, A. Kargarian, B. Falahati, “Partitioning Analysis in Temporal Decomposition for Security-Constrained Economic Dispatch,” IEEE Texas Power and Energy Conference, 2020.
F. Hasan, A. Kargarian, A. Mohammadi, "A Survey on Applications of Machine Learning for Optimal Power Flow,” IEEE Texas Power and Energy Conference, 2020.
F. Hasan, A. Kargarian, “Combined Learning and Analytical Model Based Early Warning Algorithm for Real-Time Congestion Management,” IEEE Texas Power and Energy Conference, 2020.
A. Mohammadi, F. Safdarian, A. Kargarian, "Sensitivity of Distributed Optimization Convergence Performance to Reference Bus Location," IEEE PES General Meeting, 2019.
F. Safdarian, L. Lamonte, A. Kargarian, M. Farasat, "Distributed Optimization-Based Hourly Coordination for V2G and G2V," IEEE Texas Power and Energy Conference, College Station, TX, February 2019.
F. Safdarian, O. Ciftci, A. Kargarian, “A Time Decomposition and Coordination Strategy for Power System Multi-Interval Operation,” IEEE PES General Meeting, 2018
A. Mohammadi, M. Mehrtash, A. Kargarian, M. Barati, “Tie-Line Characteristics based Partitioning for Distributed Optimization of Power Systems,” IEEE PES General Meeting, 2018.
M. Mehrtash, A. Mohammadi, A. Kargarian, “Partitioning-based Bus Renumbering Effect on Interior Point-based OPF Solution,” IEEE Texas Power and Energy Conference, 2018.

Google Sites

Report abuse