Welcome to my personal website. I am a research scientist with a background in control systems, optimization, and machine learning, who is passionate about applied research. In addition to studying and applying algorithms from these fields to solve practical real-world problems, I greatly enjoy teaching both fundamental and advanced concepts in these areas. On this site, you'll find some details of my CV, as well as links to some independent projects.
Prior to earning my PhD at Cal, I developed nonlinear and adaptive control algorithms for unmanned underwater vehicles for the U.S. Navy. During my PhD studies, I developed model-free optimal control techniques for managing renewable energy sources in electric grids. Since joining Lawrence Berkeley National Lab, I've conducted research focusing on the use of optimal control/reinforcement learning techniques for electric grid cybersecurity. Additionally, I have applied time series analysis and machine learning techniques to analyze electric power distribution system phasor data.
Google Scholar
I lead and co-lead several projects at the intersection of control systems/optimization/machine learning and the electric power system. My work has been focused on:
CEE 295 - Data Science for Energy
CEE 191 - Systems Analysis (Introduction to Optimization)
I researched model-free optimal control strategies for managing solar photovoltaic systems. Additionally, I applied semi-supervised learning techniques for inference of properties of electric distribution grids using Phasor Measurement Unit (PMU) data.
I researched ocean-based renewable energy technologies both under development or commercially available and prepared technology readiness level assessments for U.S. Navy shore facility commanders.
I developed and tested control algorithms for unmanned underwater vehicles for the U.S. Navy
I developed model-free optimal control algorithms to manage solar photovoltaic generation systems to optimize the behavior of electric power distribution systems. My advisors were Dave Auslander (Mechanical Engineering) and Duncan Callaway (Energy and Resources Group)
I researched extremum seeking control approaches for peak seeking mobile robot applications. My advisor was Miroslav Krstic.
Elective courses in signal processing, control systems, and robotics. Graduated cum laude.
A collection of small machine learning projects built completley from scratch. I don't use any tools from advanced ML python packages (sklearn, scipy) except for comparison to the from_scratch results.
View ProjectA collection of time series analysis and forecasting techniques from control systems, signal processing, and machine learning.
View ProjectA collection of reinforcement learning problems from OpenAI gym solved with Keras and TensorFlow.
View ProjectExtremum seeking is a nonlinear adaptive control algorithm that is incredibly useful for model-free optimization. This project is a collection of extremum seeking control implementations on python notebooks.
View Project