Curriculum Vitae
My professional journey
A complete detailed PDF of the CV can be found here.
Expertise
- Theories: Mathematical Programming, Machine Learning, and Stochastic Optimization
- Applications: Energy Management, Large-scale Systemsâ Decision-Making
Skillset
- Python (Numpy/Pandas/Matplotlib/Tensorflow/Pyomo/Scikit-learn/Seaborn)
- MATLAB (Simulink/CVX/Optimization Toolbox)
- GAMS/AMPL
- R
- SQL
- Git
- Linux
- PLEXOS
- Commercial Solver APIs (Gurobi/CPLEX/Xpress)
- Microsoft Office Suite (Word/Excel/Powerpoint)
- AutoCAD
- PSCAD
Education
- Ph.D. in Electrical Engineering, Southern Methodist University, 2021
- GPA: 3.87
- Outstanding Graduate Award 2021
- M.S. in Electrical Engineering, Illinois Institute of Technology, 2017
- GPA: 3.81
- B.Eng. in Electrical Engineering, Hunan University, China, 2016
Graduate-level Coursework
- Adaptive Algorithms in Machine Learning (A)
- Data Analytics and Decision Support (A)
- Statistical Pattern Recognition (A)
- Machine Learning in Power Systems (A)
- Stochastic Optimization (A-)
- Applied Optimization for Engineering (A)
- Objective-oriented Programming and Computer Simulation (A)
- Power Market Operation and Economics (A)
- Distribution System Analysis (A)
- Control and Operation of Electric Power Systems (A)
Work Experience
- Senior Optimization Engineer at Ascend Analytics, LLC
- Lead on the software refactoring from GAMS to Python-Xpress API to achieve higher computational performance and more flexible user interface.
- Upgrade and optimize the workflow pipeline between Python and SAS, automating pre-/post-processing within the solution procedure.
- Develop new features in Python-Xpress to satisfy clientsâ needs, involving in tens of unit modules such as battery storage, hydro operation, and multi-energy networks, etc.
- Communicate with clients and help delivering consulting services with high-dimensional customer data.
- Renew key functions of the backend code for PowerSIMMTM and SmartBidderTM, both of which are flagship software at Ascend.
- Postdoctoral Research Fellow at Lawrence Berkeley Lab
- Predict and analyze the solar generation potential in existing building rooftops by deep learning techniques including Graph Neural Nets.
- Implement Python programs for automatic I/O data flow with professional simulation software. Develop GUI and SQL databases for open-source power system optimization software.
- Model and simulate the national power capacity expansion planning and production cost modeling through 2020-2035, considering the power reliability and CO2 emission.
- Draft research proposals for US DOE and California funding agencies, including the California multiobjective power-eco optimization and 2060 carbon neutrality projects.
- Mentor interns and visiting Ph.D., host research calls, and write academic papers.
- Research and Development Fellow at Midcontinent ISO
- Perform timeseries prediction of power generatorsâ startup/shutdown trajectory by employing Gradient Boosting Tree for the offline task and Long-Short-Term Memory network for the online task.
- Design the deterministic MISO real-time look-ahead power supply chain optimization routine and implement in Python with calibration via the MISO production model.
- Query and parse the timeseries data of unitsâ startup and shutdown processes by SQL in the MISO private database, with cleaning and restructuring of original data pairs.
- Induce the improved start/shutdown curves in the stochastic supply chain optimization model on several typical operation days. The daily production cost saving on average is around 8% (million level in dollars).
- Research Intern at National Renewable Energy Laboratory
- Build the multi-timescale optimization framework for short-term market analyses in Python with unique steady-state turbine physical models for renewables.
- Conduct techno-economic assessments of solar panelsâ potentials with built-in energy storage systems in the energy & reserve co-optimization, considering the multi-timescale coordination.
- Debug the simulation software and perform sensitivity analyses with different parameters while adding new and reliable features with validations to better mimic the practical market environment.
- Help designing the interface between the steady-state scheduling in Python and the transient-state dynamics.