energy_data_science
Grad Course, CE 295 – Data Science for Energy
Course Description: Learned the fundamentals of data science methods for the design and operation of energy systems, including mathematical modeling & analysis, state estimation, optimization, machine learning, and optimal control.
File Descriptions:
- hw1.ipynb – battery modeling, analysis, and simulation, utilizing state-space representation and linearization
- hw2.ipynb – state estimation in geothermal heat pump drilling, utilizing a luenberger observer, kalman filter, and extended kalman filter
- hw3.ipynb – optimization of economic dispatch in distribution feeders with renewables, utilizing convex programming and robust constraints.
- hw4.ipynb – time series forecasing of residential electricity power consumption, utilizing average, ARX, and neural network models
- Co-Optimization.ipynb – code for co-optimization of a water heater, HVAC, and solar panels under varying tariff regimes
- final_presentation.pdf – ppt presentation of Co-Optimization.ipynb findings
- final_report.pdf – written report of co-optimization methods and results