11-02, 14:35–15:15 (America/New_York), Winter Garden (Room 5412)
Electricity is unique in that its storage is prohibitively costly; this makes it essential for supply to, at least, meet demand at every second of every day. In times of crisis where demand exceeds its projected amount, system operators need to fall back on different methods to lower demand. One such method is Dynamic Pricing which incentivizes customers to lower their consumption by increasing electricity prices during those times. There are trials that test out this pricing model against a flat rate pricing model. This talk uses mathematics and statistical techniques applied in python to see the impact of dynamic pricing on consumption.
The following is the outline of this talk.
- Introduction I – Problem Space (5 minutes, running total: 5 minutes):
o Introducing the electricity grid and players within that ecosystem at a high-level from generation to transmission to distribution. Some history on the US power grid that has shaped its current state. Concepts introduced: Systems Operators, Demand Response, Dynamic Pricing.
- Introduction II – Dataset (5 minutes, running total: 10 minutes):
o Introducing the dataset, the remainder of the talk is based on. The experiment that was run to gather this dataset. Its shortcomings and basic information about the data such as size, number of participants, duration of experiment, etc.
- Problem Statement (2 minutes: running total: 12 minutes):
o Formulating the question the rest of the talk will be answering. Our goal in this talk is to see if the data captured in this experiment showed whether dynamic pricing was effective in lowering electricity consumption in times of high demand.
- Data Ingestion, Preprocessing, and Exploration (4 minutes, running total: 16 minutes):
o Format and size of data, steps taken to turn it into a format that helps answer the question at hand.
- Method I – Aggregate Linear Regression (7 minutes, running total: 23 minutes):
o Mathematical formulation of the linear model to find the counterfactual consumption.
o Data processing steps.
o Presenting the results, error analysis, interpreting the results.
- Method II – Multiple Linear Regression Model (7 minutes, running total: 30 minutes):
o Mathematical formulation of the model to find the counterfactual consumption.
o Data processing steps.
o Presenting the results, error analysis, interpreting the results.
- Takeaways, conclusion, next steps (5 minutes, running total: 35 minutes):
- Q&A (5 minutes, running total: 40 minutes)
No previous knowledge expected
Saba Nejad is a Data Engineer at Point72 working mostly with alternative data within the energy and industrials sector. She is broadly interested in using mathematics and programming to gain insight from real world data. Prior to joining Point72, she was studying at MIT where she was doing research at the Institute for Data, Systems, and Society. She was previously a Product Manager at Quantopian.