Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the role of data and machine learning in enabling flexible clean energy resources through this 51-minute presentation by Utkarsha Agwan from UC Berkeley. Delve into topics such as mitigating climate change, distributed energy resources (DER), local energy markets, flexible loads, and emissions reduction. Learn about the technical challenges, pricing mechanisms, and performance issues in local energy markets, as well as the sources, challenges, and program setup for flexible loads. Discover current approaches to load forecasting and the application of reinforcement learning in local energy markets. Gain insights into the interdisciplinary research being conducted by the DataLearning working group to develop new technologies based on data assimilation and machine learning for clean energy solutions.
Syllabus
Intro
Mitigating climate change
The DER story
The technical challenges
Local energy markets: Pricing
Local energy markets: Performance
Local energy markets: Challenges
Flexible loads: Sources
Flexible loads: Challenges
Flexible loads: Program Setup
Flexible loads: Aggregations
Flexible loads: Assumption
Flexible loads: Current Approach
Flexible loads: Forecasting
Emissions reduction
Local energy markets: RL
Taught by
DataLearning@ICL