Identifying extreme events in wholesale energy markets

Project Summary

Modern Energy Group (MEG) finances and operates various distributed energy resources operating in wholesale energy markets, ranging from solar panels to residential smart thermostats. MEG also does financial trading when it identifies arbitrage opportunities in these markets. One of MEG's main operational risks is the very high volatility in wholesale real time (or spot) energy prices. Where stock markets consider a 30% change in price large, energy markets routinely face changes in price on the order of 300%. This high volatility comes from three main "shocks": 1. power demand changes, due to unpredictable weather, industrial patterns, or human consumption; 2. fuel shortages, driven by trade, extraction/exploration, and gathering/transportation economics; 3. electrical transmission outages, driven by operational failure, extreme weather events, and human behavior.

First, this project team will identify what should be considered an "extreme" price shock from 5-10 years of historical data in PJM. Second, the team will work to automatically identify potential causes for the rare events from news articles, public filings, and MEG's own structured data. Third, the team will build reasonable priors for the occurrences of these rare events, and incorporate potential covariance between the events using copulas or similar methods. Finally, the team will create a simple classifier such as logistic regression to predict the likelihood of a price shock on a given day. The model needs to be evaluated with a walk-forward backtest, training on about 3 years of data at a time, and shifting forward the training window in approximately one-month increments, to smooth out potential bias and overfitting in the model. 

Project Lead: Eric Butter, Modern Energy Group

Project Manager: TBD

Themes and Categories
Year
2019
Contact
Paul Bendich
Mathematics
bendich@math.duke.edu

Related Projects

Social and environmental contexts are increasingly recognized as factors that impact health outcomes of patients. This team will have the opportunity to collaborate directly with clinicians and medical data in a real-world setting. They will examine the association between social determinants with risk prediction for hospital admissions, and to assess whether social determinants bias that risk in a systematic way. Applied methods will include machine learning, risk prediction, and assessment of bias. This Data+ project is sponsored by the Forge, Duke's center for actionable data science.

Project Leads: Shelly Rusincovitch, Ricardo Henao, Azalea Kim

Project Manager: TBD

Producing oil and gas in the North Sea, off the coast of the United Kingdom, requires a lease to extract resources from beneath the ocean floor and companies bid for those rights. This team will consult with professionals at ExxonMobil to understand why these leases are acquired and who benefits. This requires historical data on bid history to investigate what leads to an increase in the number of (a) leases acquired and (b) companies participating in auctions. The goal of this team is to create a well-structured dataset based on company bid history from the U.K. Oil and Gas Authority; data which will come from many different file structures and formats (tabular, pdf, etc.). The team will curate these data to create a single, tabular database of U.K. bid history and work programs.

Producing oil and gas in the Gulf of Mexico requires rights to extract these resources from beneath the ocean floor and companies bid into the market for those rights. The top bids are sometimes significantly larger than the next highest bids, but it’s not always clear why this differential exists and some companies seemingly overbid by large margins. This team will consult with professionals at ExxonMobil to curate and analyze historical bid data from the Bureau of Ocean Energy Management that contains information on company bid history, infrastructure, wells, and seismic survey data as well as data from the companies themselves and geopolitical events. The stretch goal of the team will be to see if they can uncover the rationale behind historic bidding patterns. What do the highest bidders know that other bidders to not (if anything)? What characteristics might incentivize overbidding to minimize the risk of losing the right to produce (i.e. ambiguity aversion)?